Access to this full-text is provided by MDPI.
Content available from Remote Sensing
This content is subject to copyright.
Citation: Zhang, W.; Peng, L.; Ge, X.;
Yang, L.; Chen, L.; Li, W.
Spatio-Temporal Knowledge
Graph-Based Research on
Agro-Meteorological Disaster
Monitoring. Remote Sens. 2023,15,
4403. https://doi.org/10.3390/
rs15184403
Academic Editors: Adrian Ursu,
Cristian Constantin Stoleriu and
Marian Mierlă
Received: 12 August 2023
Revised: 4 September 2023
Accepted: 6 September 2023
Published: 7 September 2023
Copyright: © 2023 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
remote sensing
Article
Spatio-Temporal Knowledge Graph-Based Research on
Agro-Meteorological Disaster Monitoring
Wenyue Zhang 1,2, Ling Peng 1,2, * , Xingtong Ge 1,2 , Lina Yang 1,2, Luanjie Chen 1,2 and Weichao Li 1
1Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100049, China;
zhangwenyue22@mails.ucas.ac.cn (W.Z.); gexingtong21@mails.ucas.ac.cn (X.G.); yangln@aircas.ac.cn (L.Y.);
chenluanjie20@mails.ucas.ac.cn (L.C.); liweichao@rsai.tech (W.L.)
2College of Resources and Environment (CRE), University of Chinese Academy of Sciences,
Beijing 100049, China
*Correspondence: pengling@aircas.ac.cn
Abstract:
Currently, there is a wealth of data and expert knowledge available on monitoring agro-
meteorological disasters. However, there is still a lack of technical means to organically integrate and
analyze heterogeneous data sources in a collaborative manner. This paper proposes a method for
monitoring agro-meteorological disasters based on a spatio-temporal knowledge graph. It employs
a semantic ontology framework to achieve the organic fusion of multi-source heterogeneous data,
including remote sensing data, meteorological data, farmland data, crop information, etc. And it
formalizes expert knowledge and computational models into knowledge inference rules, thereby
enabling monitoring, early warning, and disaster analysis of agricultural crops within the observed
area. The experimental area for this research is the wheat planting region in three counties in Henan
Province. The method is tested using simulation monitoring, early warning, and impact calculation
of the past two occurrences of dry hot wind disasters. The experimental results demonstrate that
the proposed method can provide more specific and accurate warning information and post-disaster
analysis results compared to raw records. The statistical results of NDVI decline also validate the
correlation between the severity of wheat damage caused by dry hot winds and the intensity and
duration of their occurrences. Regarding remote sensing data, this paper proposes a method that
directly incorporates remote sensing data into spatio-temporal knowledge inference calculations. By
integrating remote sensing data into the regular monitoring process, the advantages of remote sensing
data granted by continuous observation are utilized. This approach represents a beneficial attempt
to organically integrate remote sensing and meteorological data for monitoring, early warning, and
evaluation analysis of agro-meteorological disasters.
Keywords:
multi-source heterogeneous data; expert knowledge formalization; spatio-temporal
knowledge inference; early warning; remote sensing disaster monitoring
1. Introduction
Agro-meteorological disasters refer to unfavorable weather conditions or abnormal
climate events that significantly reduce crop yields or even stop crop growth during the
agricultural growing process [
1
]. These disasters have a severe impact on agricultural
production and the economy. With global climate change, agro-meteorological disasters
are showing an increasing trend. Therefore, conducting research on agro-meteorological
disaster monitoring is of great practical significance in reducing agricultural losses caused
by meteorological disasters. For the monitoring task, on one hand, it is important to timely
and accurately transmit information on potential disastrous weather to relevant personnel
for early warning purposes and provide them with emergency defense measures. On the
other hand, it is necessary to monitor the affected area, severity, and other aspects after
the disaster.
Remote Sens. 2023,15, 4403. https://doi.org/10.3390/rs15184403 https://www.mdpi.com/journal/remotesensing
Remote Sens. 2023,15, 4403 2 of 18
Monitoring and early warning of agro-meteorological disasters is a highly complex
task. Firstly, agro-meteorological disasters encompass various types, each having different
impacts on crops and requiring different monitoring indicators and thresholds. Secondly,
even for the same type of meteorological disaster, different crops may have varying levels
of tolerance, and therefore the required meteorological indicators for monitoring may differ
as well. For example, the meteorological indicators for dry hot wind during the flowering
and fruiting period of mango in Panzhihua City include daily maximum temperature,
daily average relative humidity, daily minimum relative humidity, and daily maximum
wind speed [
2
]. In contrast, the meteorological indicators for dry hot wind in the winter
wheat region of northern China include daily maximum temperature, relative humidity
at 14:00, and wind speed at 14:00 [
3
]. Extensive research has been conducted on agro-
meteorological disaster monitoring and early warning, resulting in rich theoretical and
practical achievements. Several monitoring and early warning platforms have been devel-
oped. For instance, Lou et al. [
4
] established an agro-meteorological disaster monitoring
and early warning system based on automatic weather stations, radar, satellites, numerical
forecasts, and short message technology, which enables the timely transmission of disaster
warnings and mitigation information to anyone, anywhere, at any time, improving the
effectiveness of disaster prevention and mitigation. Mo et al. [
5
] utilized remote sensing
data, meteorological ground observations, and basic geographic information data to assess
drought and flood disasters in rice production, developing a monitoring and early warning
system for major agro-meteorological disasters in Guangxi, enabling rapid production
of disaster monitoring, early warnings, and evaluation products for different crops. Sun
et al. [
6
] integrated the defense requirements of four major protected agriculture facilities
and developed a facility agriculture agro-meteorological disaster monitoring and early
warning system and intelligent decision push service system for cucumber production,
utilizing data mining from the internet and expert knowledge-based decision-making tech-
nology. Xiao et al. [
7
] developed a Zhejiang Province agro-meteorological service platform
that integrates meteorological monitoring and forecasting grid data, agro-meteorological
index data, and geographic and administrative information data, consisting of six subsys-
tems, including an agro-meteorological disaster monitoring and early warning system and
an agro-meteorological observation and monitoring system. However, some platforms
primarily focus on pre-disaster monitoring and early warning and do not consider post-
disaster monitoring and evaluation. Additionally, although some platforms incorporate
remote sensing data, they only utilize it for land use and land cover classification and
crop distribution mapping, failing to fully leverage the advantages of low-cost and easily
accessible remote sensing data for continuous monitoring of crop growth conditions and
disaster impacts.
In fact, there have been several studies on using remote sensing data to construct
relevant indices for disaster monitoring and assessment. Li et al. [
8
] found that the NDVI
(Normalized Difference Vegetation Index) and RVI (Ratio Vegetation Index) are more
sensitive than the ARVI (Atmospherically Resistant Vegetation Index) in detecting the
severity of hot dry wind disasters, making them suitable for the large-scale monitoring of
such disasters. Zhong et al. [
9
] utilized multi-temporal NDVI changes to assess frost damage
in sugarcane. Therefore, the data involved in agro-meteorological disaster monitoring
tasks include remote sensing data, meteorology data, farmland data, crop data, etc. The
expertise required includes knowledge of disaster warning, computational models for
disaster assessment and analysis, and so on. By organically integrating these disaster data
and expert knowledge in a spatio-temporal knowledge graph, it is possible to achieve
coordinated management, analysis, and calculation of data and knowledge, leveraging the
semantic attributes and logical reasoning capabilities of knowledge graphs.
A knowledge graph is a data organization form that represents entities, concepts, and
their semantic relationships through a directed graph. Essentially, it is a type of semantic
network wherein nodes represent entities or concepts and edges represent the attributes
of entities/concepts or the semantic relationships between them [
10
]. Various knowledge
Remote Sens. 2023,15, 4403 3 of 18
graphs have been developed in the field of agriculture. Qi et al. [
11
] proposed a method
for constructing a Chinese meteorology and agriculture knowledge graph based on semi-
structured data. Liu et al. [
12
] described the application of crop disease and pest knowledge
graphs in expert systems, search engines, and knowledge-based question-answering sys-
tems. Chen et al. [
13
] summarized the applications of multimodal knowledge graphs in
agriculture, focusing on intelligent question answering, disease and pest recognition, and
agricultural product recommendation research. Wang et al. [
14
] proposed a knowledge
graph construction framework for the entire sweet cherry industry chain and utilized
knowledge graph fusion and mining of relevant data to provide knowledge services for
the development of the sweet cherry industry. Some studies have also applied knowledge
graphs in the field of disaster research. Wang et al. [
15
] analyzed 2890 Chinese litera-
ture resources on disaster risk research in the Chinese Knowledge Resource Integrated
Database from 2000 to 2017, constructing a knowledge structure graph of disaster risk re-
search, including hotspots, co-occurrence matrices of keywords, core authors, and research
institutions. Ge et al. [
16
,
17
] utilized spatio-temporal knowledge graphs for predicting
natural disasters such as wildfires and landslides, achieving high accuracy. Chen et al. [
18
]
improved the prediction of landslide disasters in areas with scarce sample data using
spatio-temporal semantic reasoning. Spatio-temporal knowledge graphs have inherent
advantages in organizing and managing heterogeneous spatio-temporal data, making them
well suited to address the challenges faced in agro-meteorological disaster monitoring and
early warning. However, no relevant research has been found in this specific area.
This paper introduces a semantic ontology framework and constructs a spatio-temporal
knowledge graph for agro-meteorological disaster monitoring. It aims to organize and
manage heterogeneous spatio-temporal data sources such as farmland data, crop infor-
mation, meteorological data, remote sensing data, and so on. The system converts expert
knowledge and calculation models into inference rules and utilizes the spatio-temporal
knowledge graph to enable pre-disaster monitoring and warning as well as post-disaster
impact analysis driven by data and knowledge collaboration.
The academic contributions of this paper include the following:
(1)
This paper constructs an agro-meteorological disaster monitoring spatio-temporal
knowledge graph, facilitating the fusion of multi-source data and knowledge for
pre-disaster monitoring and warning, as well as post-disaster impact analysis.
(2)
Compared to coarse-grained monitoring at the provincial or county levels, this paper
achieves finer-scale monitoring at the level of farmland patches using remote sensing
techniques, with warning information sent to specific farmland managers.
(3)
This paper realizes the integration of remote sensing data into knowledge inference
and calculation processes.
2. Materials and Methods
2.1. Study Area
Henan Province is a major agricultural province in China and the largest wheat-
producing region in the country. Dry hot winds, as a typical meteorological disaster, are
one of the major agro-meteorological hazards in the northern wheat-growing areas of
China. Dry hot winds can be categorized into three types: the high-temperature and low-
humidity type, the withering type after rain, and the drought type [
19
]. The meteorological
indicators of dry hot winds vary in different regions. The meteorological indicators of
the high-temperature and low-humidity type of dry hot winds in the northern winter
wheat-growing areas are shown in Table 1[3].
In this study, two instances of dry hot wind disasters that occurred in Yanjin County,
Qi County (under the jurisdiction of Hebi City), and Wuyang County in May 2013 and May
2019 were selected for simulation calculations based on the collected dry hot wind warning
records. The relevant warning records are shown in Table 2.
Remote Sens. 2023,15, 4403 4 of 18
Table 1.
The meteorological indicators for dry hot wind days in the winter wheat region of northern
China.
Severity Levels of Dry Hot
Wind Days
Daily Maximum
Temperature_◦C
Relative Humidity at
14:00_% Wind Speed at 14:00_m/s
severe dry hot wind day ≥35 ≤25 ≥3
moderate dry hot wind day ≥32 ≤30 ≥2
mild dry hot wind day ≥30 ≤30 ≥2
Table 2. Dry hot wind early warning records.
Region Dry Hot Wind Early Warning Records.
Henan Province From 11 May to 13, 2013, Henan Province issued a red warning signal
for three consecutive days due to the occurrence of dry hot wind [20].
Hebi City
On 22 May 2019, at 8:05 am, an orange warning signal for dry hot wind
was issued, and it was expected that dry hot wind would occur in the
urban area on the same day [21].
Yanjin County
On 22 May 2019, at 20:13, an orange warning signal for dry hot wind
was issued again, and it was expected that dry hot wind would occur
the next day [22].
Wuyang County
On 22 May 2019, at 07:39, an orange warning signal for dry hot wind
was issued, and it was expected that dry hot wind would occur within
the next 24 h [21].
2.2. Data Source
The historical meteorological data used in this study were obtained from the European
Space Agency [
23
], with a spatial resolution of 1 km and a temporal resolution of hourly
data. The European Space Agency meteorological data use Coordinated Universal Time
(UTC). Four meteorological elements were used in this study, namely 2 m temperature, 2 m
dew point temperature, wind speed u-component, and wind speed v-component.
The remote sensing satellite data used in this study were collected from the Moderate-
resolution Imaging Spectroradiometer (MODIS), which is operated by the Terra and Aqua
satellites and provides medium-resolution imaging spectrometer data. One MODIS image
with the row–column number “h27v05” covers the entire Henan Province. Among them,
MOD09GA [
24
] is the daily land surface reflectance product provided by the Terra satellite,
which includes seven bands of land surface reflectance with a spatial resolution of 500
m. The spectral characteristics of green vegetation mainly include strong absorption in
the red band and strong reflection in the near-infrared band. Various vegetation indices,
mainly those based on the combination of red and near-infrared channels, can enhance
vegetation information and reflect the growth status of plants. Commonly used vegetation
indices such as the NDVI and EVI can respond to primary damage caused by a reduction
in functional leaf chlorophyll and can be used to quantitatively assess the disaster situation
of crops [
8
]. In this study, the NDVI was calculated using the red band (sur_refl_b01_1)
and near-infrared band (sur_refl_b02_1) of MOD09GA, and the calculation formula is as
follows:
NDVI =NI R −R
NIR +R(1)
where NIR represents the near-infrared band reflectance and Rrepresents the red band
reflectance.
The distribution of wheat planting in Henan in 2013 was derived from the “1 km Plant-
ing Distribution Dataset of the Three Major Grain Crops in China (2000–2019)” published
by the National Ecological Science Data Center. The temporal resolution is annual, and
the spatial resolution is 1 km. This dataset is extracted based on the Leaf Area Index (LAI)
product from the Global Land Surface Characteristics Parameters (GLASS) product [
25
].
Remote Sens. 2023,15, 4403 5 of 18
The GLASS product is a long-term, high-precision global land surface remote sensing
product derived through the inversion of multi-source remote sensing data and ground
measurement data [26].
2.3. Spatio-Temporal Knowledge Graph Construction
The Web Ontology Language (OWL) was chosen as the semantic expression language
for constructing the spatio-temporal knowledge graph. The construction of the spatio-
temporal knowledge graph primarily involved domain knowledge collection, ontology
construction, knowledge extraction, knowledge fusion, formalization of inference rules,
and triple storage. The research framework of this paper is illustrated in Figure 1.
Remote Sens. 2023, 15, x FOR PEER REVIEW 5 of 18
The distribution of wheat planting in Henan in 2013 was derived from the “1 km
Planting Distribution Dataset of the Three Major Grain Crops in China (2000–2019)” pub-
lished by the National Ecological Science Data Center. The temporal resolution is annual,
and the spatial resolution is 1 km. This dataset is extracted based on the Leaf Area Index
(LAI) product from the Global Land Surface Characteristics Parameters (GLASS) product
[25]. The GLASS product is a long-term, high-precision global land surface remote sensing
product derived through the inversion of multi-source remote sensing data and ground
measurement data [26].
2.3. Spatio-Temporal Knowledge Graph Construction
The Web Ontology Language (OWL) was chosen as the semantic expression language
for constructing the spatio-temporal knowledge graph. The construction of the spatio-
temporal knowledge graph primarily involved domain knowledge collection, ontology
construction, knowledge extraction, knowledge fusion, formalization of inference rules,
and triple storage. The research framework of this paper is illustrated in Figure 1.
Figure 1. Overall research framework.
2.3.1. Ontology Construction
During ontology construction, we first designed an overall conceptual framework, as
shown in Figure 2. The ontology is divided into semantic ontology, spatial ontology, tem-
poral ontology, and rule objects.
Figure 1. Overall research framework.
2.3.1. Ontology Construction
During ontology construction, we first designed an overall conceptual framework,
as shown in Figure 2. The ontology is divided into semantic ontology, spatial ontology,
temporal ontology, and rule objects.
The semantic ontology includes geographic entities such as farmland patches, crops,
farmland managers, remote sensing data, disaster reports, etc. The main entities, entity
properties, and relationships between entities are shown in Figure 3. Entity properties are
divided into object properties and data properties. The domain specifies the definition
domain of the property, and the range specifies the value domain of the property. In
particular, the spatio-temporal knowledge graph does not directly store the actual remote
sensing image data. Instead, it semantically models their key characteristics, such as spatial
resolution, temporal resolution, sensor type, and acquisition path. During analysis and
computation, based on the computation requirements, the corresponding remote sensing
Remote Sens. 2023,15, 4403 6 of 18
image entities were inferred and computed based on semantic features such as spatial
resolution, temporal resolution, sensor type, and acquisition path.
Remote Sens. 2023, 15, x FOR PEER REVIEW 6 of 18
Figure 2. Agro-meteorological disaster monitoring ontology model.
The semantic ontology includes geographic entities such as farmland patches, crops,
farmland managers, remote sensing data, disaster reports, etc. The main entities, entity
properties, and relationships between entities are shown in Figure 3. Entity properties are
divided into object properties and data properties. The domain specifies the definition
domain of the property, and the range specifies the value domain of the property. In par-
ticular, the spatio-temporal knowledge graph does not directly store the actual remote
sensing image data. Instead, it semantically models their key characteristics, such as spa-
tial resolution, temporal resolution, sensor type, and acquisition path. During analysis
and computation, based on the computation requirements, the corresponding remote
sensing image entities were inferred and computed based on semantic features such as
spatial resolution, temporal resolution, sensor type, and acquisition path.
Figure 3. The main entities, entity properties, and relationships among entities in a semantic ontol-
ogy.
The semantic ontology also includes meteorological grids, specifically Level1Hour-
lyMeteorologicalGrid (referred to as Level1Grid) for hourly data, Level2DailyMeteorolog-
icalGrid (referred to as Level2Grid) for daily data, and Level3PeriodMeteorologicalGrid
(referred to as Level3Grid) for data within a specific time period. Among them,
Level1Grid is further divided into various meteorological indicators. The properties of
Figure 2. Agro-meteorological disaster monitoring ontology model.
Remote Sens. 2023, 15, x FOR PEER REVIEW 6 of 18
Figure 2. Agro-meteorological disaster monitoring ontology model.
The semantic ontology includes geographic entities such as farmland patches, crops,
farmland managers, remote sensing data, disaster reports, etc. The main entities, entity
properties, and relationships between entities are shown in Figure 3. Entity properties are
divided into object properties and data properties. The domain specifies the definition
domain of the property, and the range specifies the value domain of the property. In par-
ticular, the spatio-temporal knowledge graph does not directly store the actual remote
sensing image data. Instead, it semantically models their key characteristics, such as spa-
tial resolution, temporal resolution, sensor type, and acquisition path. During analysis
and computation, based on the computation requirements, the corresponding remote
sensing image entities were inferred and computed based on semantic features such as
spatial resolution, temporal resolution, sensor type, and acquisition path.
Figure 3. The main entities, entity properties, and relationships among entities in a semantic ontol-
ogy.
The semantic ontology also includes meteorological grids, specifically Level1Hour-
lyMeteorologicalGrid (referred to as Level1Grid) for hourly data, Level2DailyMeteorolog-
icalGrid (referred to as Level2Grid) for daily data, and Level3PeriodMeteorologicalGrid
(referred to as Level3Grid) for data within a specific time period. Among them,
Level1Grid is further divided into various meteorological indicators. The properties of
Figure 3.
The main entities, entity properties, and relationships among entities in a semantic ontology.
The semantic ontology also includes meteorological grids, specifically Level1Hourly
MeteorologicalGrid (referred to as Level1Grid) for hourly data, Level2DailyMeteorologicalGrid
(referred to as Level2Grid) for daily data, and Level3PeriodMeteorologicalGrid (referred to
as Level3Grid) for data within a specific time period. Among them, Level1Grid is further
divided into various meteorological indicators. The properties of different meteorological
grids are shown in Table 3. The relationships between meteorological grids and other
entities will be introduced in Section 2.3.4.
Remote Sens. 2023,15, 4403 7 of 18
Table 3. Meteorological grid entity and properties.
Entity Types Entity Properties Data Properties Meanings
Level1HourlyTemperatureGrid T_C xsd: double Temperature_◦C
Level1HourlyDewPointTemperatureGrid
DPT_C xsd: double Dew point temperature_◦C
Level1HourlyRelativeHumidityGrid RH_PCT xsd: double Relative humidity_%
Level1HourlyWindSpeedGrid WS_MPS xsd: double Wind speed_m/s
Level2DailyMeteorologicalGrid
D_MAX_T_C xsd: double Daily maximum temperature_◦C
14_RH_PCT xsd: double Relative humidity at 14:00_%
14_WS_MPS xsd: double Wind speed at 14:00_m/s
grid2DryHotWind xsd: string
Severity levels of dry hot winds:
“false”, “mild”, “moderate”,
“severe”
Level3PeriodMeteorologicalGrid
grid3DryHotWind xsd: double Is there an occurrence of dry hot
winds?
dryHotWindStartDate xsd: DateTime Start date of dry hot winds
dryHotWindFinishDate xsd: DateTime Finish date of dry hot winds
severeDryHotWindDate xsd: string Dates of severe dry hot winds
moderateDryHotWindDate
xsd: string Dates of moderate dry hot winds
mildDryHotWindDate xsd: string Dates of mild dry hot winds
The spatial ontology adopts the GeoSPARQL [
27
] spatial semantic representation
specification, whose structure is shown in Figure 4. The GeoSPARQL ontology is based on
the feature model of the Open Geospatial Consortium (OGC) and includes a class called
geo: SpatialObject, which has two main subclasses, geo: Feature and geo: Geometry. For
example, a farmland patch is a geo: Feature, which is a conceptual entity, and it also has a
geo: Geometry to describe its spatial extent.
Remote Sens. 2023, 15, x FOR PEER REVIEW 7 of 18
different meteorological grids are shown in Table 3. The relationships between meteoro-
logical grids and other entities will be introduced in Section 2.3.4.
Table 3. Meteorological grid entity and properties.
Entity Types Entity Properties Data Properties Meanings
Level1HourlyTemperatureGrid T_C xsd: double Temperature_°C
Level1HourlyDewPointTemperatureGrid DPT_C xsd: double
Dew point tempera-
ture_°C
Level1HourlyRelativeHumidityGrid RH_PCT xsd: double Relative humidity_%
Level1HourlyWindSpeedGrid WS_MPS xsd: double Wind speed_m/s
Level2DailyMeteorologicalGrid
D_MAX_T_C xsd: double
Daily maximum tempera-
ture_°C
14_RH_PCT xsd: double
Relative humidity at
14:00_%
14_WS_MPS xsd: double
Wind speed at 14:00_m/s
grid2DryHotWind xsd: string
Severity levels of dry hot
winds: “false”, “mild”,
“moderate”, “severe”
Level3PeriodMeteorologicalGrid
grid3DryHotWind xsd: double
Is there an occurrence of
dry hot winds?
dryHotWindStartDate xsd: DateTime Start date of dry hot winds
dryHotWindFinishDate xsd: DateTime
Finish date of dry hot
winds
severeDryHotWindDate xsd: string
Dates of severe dry hot
winds
moderateDryHotWindDate xsd: string
Dates of moderate dry hot
winds
mildDryHotWindDate xsd: string
Dates of mild dry hot
winds
The spatial ontology adopts the GeoSPARQL [27] spatial semantic representation
specification, whose structure is shown in Figure 4. The GeoSPARQL ontology is based
on the feature model of the Open Geospatial Consortium (OGC) and includes a class
called geo: SpatialObject, which has two main subclasses, geo: Feature and geo: Geometry.
For example, a farmland patch is a geo: Feature, which is a conceptual entity, and it also
has a geo: Geometry to describe its spatial extent.
Figure 4. Illustration of the GeoSPARQL Spatial Ontology structure.
Figure 4. Illustration of the GeoSPARQL Spatial Ontology structure.
The temporal ontology adopts the SWRL Temporal Ontology (SWRLTO) model [
28
],
whose structure is shown in Figure 5. Objects that require the association of temporal
semantic information are abstracted as “spatio-temporal entities”. Instances of “spatio-
temporal entities” serve as subjects in typical triples of this model and are associated with
instances of the “valid time” object as objects through the predicate temporal: hasValidTime.
The “valid time” object can be further divided into two subclasses: temporal: ValidInstant
and temporal: ValidPeriod, which are used to represent the semantics of specific instants
and time periods, respectively.
Remote Sens. 2023,15, 4403 8 of 18
Remote Sens. 2023, 15, x FOR PEER REVIEW 8 of 18
The temporal ontology adopts the SWRL Temporal Ontology (SWRLTO) model [28],
whose structure is shown in Figure 5. Objects that require the association of temporal se-
mantic information are abstracted as “spatio-temporal entities”. Instances of “spatio-tem-
poral entities” serve as subjects in typical triples of this model and are associated with
instances of the “valid time” object as objects through the predicate temporal: hasValid-
Time. The “valid time” object can be further divided into two subclasses: temporal: Va-
lidInstant and temporal: ValidPeriod, which are used to represent the semantics of specific
instants and time periods, respectively.
Figure 5. Illustration of the SWRL Temporal Ontology structure.
2.3.2. Knowledge Extraction
In this paper, both the farmland data and the meteorological data go through several
steps, including clipping, coordinate system standardization, scaling and rounding, and
conversion to GeoJSON format (as shown in Figure 6). However, only the farmland data
are further converted into triples because these data are updated only based on the crop
growth cycle, which can span several months, half a year, or a year. But the meteorological
data are updated frequently, and the proportion of abnormal data that can cause disasters
is relatively small compared to normal data. Therefore, including all meteorological data
in the database would result in a significant and meaningless storage burden. We identi-
fied abnormal data based on the meteorological indicators and their thresholds that con-
stitute agro-meteorological disasters (e.g., the meteorological indicators and their thresh-
olds for dry hot winds as shown in Table 1).
Figure 6. Data preprocessing workflow.
For other data, we first organized them into a CSV table, as shown in Table 4, and
then extracted triplets from them.
Figure 5. Illustration of the SWRL Temporal Ontology structure.
2.3.2. Knowledge Extraction
In this paper, both the farmland data and the meteorological data go through several
steps, including clipping, coordinate system standardization, scaling and rounding, and
conversion to GeoJSON format (as shown in Figure 6). However, only the farmland data
are further converted into triples because these data are updated only based on the crop
growth cycle, which can span several months, half a year, or a year. But the meteorological
data are updated frequently, and the proportion of abnormal data that can cause disasters
is relatively small compared to normal data. Therefore, including all meteorological data in
the database would result in a significant and meaningless storage burden. We identified
abnormal data based on the meteorological indicators and their thresholds that constitute
agro-meteorological disasters (e.g., the meteorological indicators and their thresholds for
dry hot winds as shown in Table 1).
Remote Sens. 2023, 15, x FOR PEER REVIEW 8 of 18
The temporal ontology adopts the SWRL Temporal Ontology (SWRLTO) model [28],
whose structure is shown in Figure 5. Objects that require the association of temporal se-
mantic information are abstracted as “spatio-temporal entities”. Instances of “spatio-tem-
poral entities” serve as subjects in typical triples of this model and are associated with
instances of the “valid time” object as objects through the predicate temporal: hasValid-
Time. The “valid time” object can be further divided into two subclasses: temporal: Va-
lidInstant and temporal: ValidPeriod, which are used to represent the semantics of specific
instants and time periods, respectively.
Figure 5. Illustration of the SWRL Temporal Ontology structure.
2.3.2. Knowledge Extraction
In this paper, both the farmland data and the meteorological data go through several
steps, including clipping, coordinate system standardization, scaling and rounding, and
conversion to GeoJSON format (as shown in Figure 6). However, only the farmland data
are further converted into triples because these data are updated only based on the crop
growth cycle, which can span several months, half a year, or a year. But the meteorological
data are updated frequently, and the proportion of abnormal data that can cause disasters
is relatively small compared to normal data. Therefore, including all meteorological data
in the database would result in a significant and meaningless storage burden. We identi-
fied abnormal data based on the meteorological indicators and their thresholds that con-
stitute agro-meteorological disasters (e.g., the meteorological indicators and their thresh-
olds for dry hot winds as shown in Table 1).
Figure 6. Data preprocessing workflow.
For other data, we first organized them into a CSV table, as shown in Table 4, and
then extracted triplets from them.
Figure 6. Data preprocessing workflow.
For other data, we first organized them into a CSV table, as shown in Table 4, and then
extracted triplets from them.
Table 4. Example of a CSV table.
Subject Predicate Object Subject Type Object Type
Dry Hot Wind affectCrop Wheat Agro-meteorological disaster Crop
2.3.3. Knowledge Fusion
For geospatial entities with spatio-temporal attributes such as agricultural land plots
and meteorological grids, in addition to the properties specified in Figure 3, additional
multiscale geocoding index information is required. We calculated the geocoding based
Remote Sens. 2023,15, 4403 9 of 18
on the Web Mercator projection grid partitioning method (as shown in Figure 7) and
indexed the geospatial entities in the spatio-temporal knowledge graph as follows: <Subject:
Geospatial Entity Predicate: hasTileCode Object: Tile Code>.
Remote Sens. 2023, 15, x FOR PEER REVIEW 9 of 18
Table 4. Example of a CSV table.
Subject Predicate Object Subject Type Object Type
Dry Hot Wind affectCrop Wheat Agro-meteorological disaster Crop
2.3.3. Knowledge Fusion
For geospatial entities with spatio-temporal aributes such as agricultural land plots
and meteorological grids, in addition to the properties specified in Figure 3, additional
multiscale geocoding index information is required. We calculated the geocoding based
on the Web Mercator projection grid partitioning method (as shown in Figure 7) and in-
dexed the geospatial entities in the spatio-temporal knowledge graph as follows: <Subject:
Geospatial Entity Predicate: hasTileCode Object: Tile Code>.
The grid partitioning level is generally in the range of 0–26. A geospatial entity has a
series of tile codes at different scales, represented as strings. For example,
“z14_x13335_y6860” indicates that the Mercator projection grid has been partitioned with
a spatial x-coordinate of 13,335, a y-coordinate of 6860, and a grid code level of 14. Differ-
ent types of geospatial entities insert multiscale tile codes during the construction of the
knowledge graph. The matching based on the tile codes associated with feature entities
supports multiscale spatial queries of spatio-temporal feature entities.
Figure 7. Web Mercator projection grid subdivision method.
2.3.4. Monitoring Reasoning Engine
The reasoning engine designed in this paper consists of a series of spatio-temporal
semantic reasoning rules, represented as RuleObject. Each rule is composed of an event
object (TriggerObject, abbreviated as Tr) and an action object (ActionObject, abbreviated
as Ac), represented as RuleObject = (Tr, Ac). Tr represents the event object included in
RuleObject, Ac represents the action object included in RuleObject, and RuleObject repre-
sents the inference result. In this paper, the event TriggerObject is defined as a triplet,
represented as TriggerObject = (O, T, S), where O represents the set of geospatial entities
included in the event object, and T and S represent the intersection of this geospatial entity
set in the temporal and spatial dimensions, respectively. A spatio-temporal co-occurrence
scenario with a set of geospatial entities can be described as an event object, which serves
as the definition of the condition for applying a reasoning rule. When the condition is
satisfied, the reasoning engine triggers the execution of the action object to obtain the in-
ference result. The concepts of event (or action) objects are further divided into independ-
ent events (or actions) and event (or action) combinations, which together constitute the
Figure 7. Web Mercator projection grid subdivision method.
The grid partitioning level is generally in the range of 0–26. A geospatial entity has a se-
ries of tile codes at different scales, represented as strings. For example, “z14_x13335_y6860”
indicates that the Mercator projection grid has been partitioned with a spatial x-coordinate
of 13,335, a y-coordinate of 6860, and a grid code level of 14. Different types of geospatial
entities insert multiscale tile codes during the construction of the knowledge graph. The
matching based on the tile codes associated with feature entities supports multiscale spatial
queries of spatio-temporal feature entities.
2.3.4. Monitoring Reasoning Engine
The reasoning engine designed in this paper consists of a series of spatio-temporal
semantic reasoning rules, represented as RuleObject. Each rule is composed of an event
object (TriggerObject, abbreviated as Tr) and an action object (ActionObject, abbreviated
as Ac), represented as RuleObject = (Tr, Ac). Tr represents the event object included
in RuleObject, Ac represents the action object included in RuleObject, and RuleObject
represents the inference result. In this paper, the event TriggerObject is defined as a triplet,
represented as TriggerObject = (O, T, S), where O represents the set of geospatial entities
included in the event object, and T and S represent the intersection of this geospatial entity
set in the temporal and spatial dimensions, respectively. A spatio-temporal co-occurrence
scenario with a set of geospatial entities can be described as an event object, which serves as
the definition of the condition for applying a reasoning rule. When the condition is satisfied,
the reasoning engine triggers the execution of the action object to obtain the inference result.
The concepts of event (or action) objects are further divided into independent events
(or actions) and event (or action) combinations, which together constitute the concept of
knowledge inference rules [
16
]. The formalization of the reasoning rules designed in this
paper is shown in Figure 8.
Remote Sens. 2023,15, 4403 10 of 18
Remote Sens. 2023, 15, x FOR PEER REVIEW 10 of 18
concept of knowledge inference rules [16]. The formalization of the reasoning rules de-
signed in this paper is shown in Figure 8.
Figure 8. Formalization of inference rules.
The principle of the reasoning engine executing “GiveEarlyWarning” is as follows:
After obtaining meteorological data, the reasoning engine integrates it into Level1Grid,
Level2Grid, and Level3Grid sequentially. Then, based on certain criteria for agro-meteor-
ological disasters, it filters out abnormal meteorological grids. If there are abnormal me-
teorological grids, it calculates the spatio-temporal intersection between the abnormal
grids and the farmland patches affected by this type of disaster. If the result is not empty,
it indicates that certain farmland patches are at risk for this type of meteorological disas-
ter. An early warning is issued for these farmland patches, providing the spatial extent,
land management personnel, start and end dates of the disaster, severity level of the dis-
aster, and recommended defense measures. After the meteorological data are updated,
the above steps are repeated. If there are changes in the disaster information, the warning
information is updated accordingly.
The principle of the reasoning engine executing “CalculateNDVIDifference” is as fol-
lows: After a disaster occurs, the reasoning engine obtains pre- and post-disaster remote
sensing data and calculates the NDVI decline matrix within the farmland patches. It then
returns the average and maximum values to the knowledge graph for storage, which are
used to record the actual extent of the affected farmland patches.
The overall reasoning flow is shown in Figure 9, where the left half corresponds to
the “GiveEarlyWarning” content mentioned above and the right half corresponds to the
“CalculateNDVIDifference” content mentioned above. Green lines represent the infor-
mation to be retrieved from the knowledge graph, and yellow lines represent the infor-
mation to be added to the knowledge graph.
Figure 8. Formalization of inference rules.
The principle of the reasoning engine executing “GiveEarlyWarning” is as follows: After
obtaining meteorological data, the reasoning engine integrates it into Level1Grid, Level2Grid,
and Level3Grid sequentially. Then, based on certain criteria for agro-meteorological disasters,
it filters out abnormal meteorological grids. If there are abnormal meteorological grids, it
calculates the spatio-temporal intersection between the abnormal grids and the farmland
patches affected by this type of disaster. If the result is not empty, it indicates that certain
farmland patches are at risk for this type of meteorological disaster. An early warning is
issued for these farmland patches, providing the spatial extent, land management personnel,
start and end dates of the disaster, severity level of the disaster, and recommended defense
measures. After the meteorological data are updated, the above steps are repeated. If there
are changes in the disaster information, the warning information is updated accordingly.
The principle of the reasoning engine executing “CalculateNDVIDifference” is as
follows: After a disaster occurs, the reasoning engine obtains pre- and post-disaster remote
sensing data and calculates the NDVI decline matrix within the farmland patches. It then
returns the average and maximum values to the knowledge graph for storage, which are
used to record the actual extent of the affected farmland patches.
The overall reasoning flow is shown in Figure 9, where the left half corresponds to the
“GiveEarlyWarning” content mentioned above and the right half corresponds to the “Cal-
culateNDVIDifference” content mentioned above. Green lines represent the information to
be retrieved from the knowledge graph, and yellow lines represent the information to be
added to the knowledge graph.
2.3.5. Knowledge Storage
The factual triplets and rule triplets formed from the above steps were stored and
visualized using the GraphDB database in this study. Specifically, meteorological data are
only placed outside the graph database and serve as the event triggering reasoning in the
knowledge graph.
Remote Sens. 2023,15, 4403 11 of 18
Remote Sens. 2023, 15, x FOR PEER REVIEW 11 of 18
Figure 9. Inference process in the inference engine.
2.3.5. Knowledge Storage
The factual triplets and rule triplets formed from the above steps were stored and
visualized using the GraphDB database in this study. Specifically, meteorological data are
only placed outside the graph database and serve as the event triggering reasoning in the
knowledge graph.
3. Results
This study selected meteorological and remote sensing data from before and after the
two disasters mentioned in Table 2 to monitor and assess the impact of dry hot wind dis-
asters.
3.1. Spatio-Temporal Knowledge Graph
In this study, a pixel was considered as a farmland patch. The information of farm-
land patches in the spatio-temporal knowledge graph is shown in Figure 10, including
three types of information: basic information such as farmland management personnel,
crop types, etc.; spatial information including TileCode, GridElement, etc.; and temporal
information including the validity period of the farmland patch, specifically StartTime,
FinishTime, etc.
Figure 9. Inference process in the inference engine.
3. Results
This study selected meteorological and remote sensing data from before and after
the two disasters mentioned in Table 2to monitor and assess the impact of dry hot wind
disasters.
3.1. Spatio-Temporal Knowledge Graph
In this study, a pixel was considered as a farmland patch. The information of farm-
land patches in the spatio-temporal knowledge graph is shown in Figure 10, including
three types of information: basic information such as farmland management personnel,
crop types, etc.; spatial information including TileCode, GridElement, etc.; and temporal
information including the validity period of the farmland patch, specifically StartTime,
FinishTime, etc.
The WKT coordinates are as follows: “<http://www.opengis.net/def/crs/OGC/1.
3/CRS84, accessed on 7 August 2023>Polygon((113.50125068990748 33.43262540390898,
113.51269774769881 33.431067613189725, 113.51488054906483 33.43924015718123, 113.5034322060161
33.44079809188075, 113.50125068990748 33.43262540390898))”.This indicates that the farm-
land patch is composed of this series of points in the WGS1984 coordinate system.
3.2. Pre-Disaster Monitoring Results
Since meteorological forecast data are constantly updated, the reasoning engine, upon
detecting that a farmland patch will be affected by dry hot wind starting from a certain
day, adds a DisasterReport entity node to the farmland patch node, recording its start and
end dates, severity level, and other relevant information. Subsequently, with the updated
meteorological forecast data, the attributes of this DisasterReport entity node will also be
continuously updated until the disaster is over. This process forms a historical archive of
the warning results. When the farmland patch is detected to be affected by a disaster again,
a new DisasterReport entity node will be added to the corresponding node.
This paper illustrates the above principle using the example of the dry hot wind
disaster that occurred in Qi County in May 2013. We assumed the meteorological forecast
data have a cycle of 7 days with updates occurring once daily in the following experiment.
On 5 May, meteorological forecast data from 6 May to 12 May were obtained. It
was detected that a certain farmland patch would experience a dry hot wind from the
11th to the 12th, with a moderate severity on the 11th and a severe severity on the 12th.
Remote Sens. 2023,15, 4403 12 of 18
Consequently, a meteorological disaster warning was issued for this farmland patch, and a
DryHotWindReport node was added.
Remote Sens. 2023, 15, x FOR PEER REVIEW 12 of 18
Figure 10. Example of farmland patches in a spatio-temporal knowledge graph.
The WKT coordinates are as follows: “<hp://www.open-
gis.net/def/crs/OGC/1.3/CRS84, accessed on 7 August 2023>Polygon((113.50125068990748
33.43262540390898, 113.51269774769881 33.431067613189725, 113.51488054906483
33.43924015718123, 113.5034322060161 33.44079809188075, 113.50125068990748
33.43262540390898))”.This indicates that the farmland patch is composed of this series of
points in the WGS1984 coordinate system.
3.2. Pre-Disaster Monitoring Results
Since meteorological forecast data are constantly updated, the reasoning engine,
upon detecting that a farmland patch will be affected by dry hot wind starting from a
certain day, adds a DisasterReport entity node to the farmland patch node, recording its
start and end dates, severity level, and other relevant information. Subsequently, with the
updated meteorological forecast data, the aributes of this DisasterReport entity node will
also be continuously updated until the disaster is over. This process forms a historical
archive of the warning results. When the farmland patch is detected to be affected by a
disaster again, a new DisasterReport entity node will be added to the corresponding node.
This paper illustrates the above principle using the example of the dry hot wind dis-
aster that occurred in Qi County in May 2013. We assumed the meteorological forecast
data have a cycle of 7 days with updates occurring once daily in the following experiment.
On 5 May, meteorological forecast data from 6 May to 12 May were obtained. It was
detected that a certain farmland patch would experience a dry hot wind from the 11th to
the 12th, with a moderate severity on the 11th and a severe severity on the 12th. Conse-
quently, a meteorological disaster warning was issued for this farmland patch, and a Dry-
HotWindReport node was added.
On 6 May, meteorological forecast data from 7 May to 13 May were obtained. It was
detected that the same farmland patch would experience a dry hot wind from the 11th to
the 13th, with a moderate severity on the 11th and 13th, and a severe severity on the 12th.
Therefore, another meteorological disaster warning was issued for this farmland patch,
and the aributes of the DryHotWindReport node were modified accordingly, as shown
in Figure 11.
Figure 10. Example of farmland patches in a spatio-temporal knowledge graph.
On 6 May, meteorological forecast data from 7 May to 13 May were obtained. It was
detected that the same farmland patch would experience a dry hot wind from the 11th to
the 13th, with a moderate severity on the 11th and 13th, and a severe severity on the 12th.
Therefore, another meteorological disaster warning was issued for this farmland patch,
and the attributes of the DryHotWindReport node were modified accordingly, as shown
in Figure 11.
Remote Sens. 2023, 15, x FOR PEER REVIEW 13 of 18
Figure 11. Adding a DisasterReport instance to a farmland patch instance.
Similarly, the warning information was promptly updated with the updates of mete-
orological forecast data.
The warning results for Qi County, Yanjin County, and Wuyang County are shown
in Tables 5 and 6.
Table 5. Monitoring and early warning results for dry hot wind in 2013, shown as number of farm-
land patches of different severity levels.
Region 1 Mild,
1 Moderate 3 Moderate 4 Moderate 1 Moderate,
1 Severe
2 Moderate,
1 Severe
3 Moderate,
1 Severe
1 Moderate,
2 Severe
Qi County 148 86
Yanjin County 240 358 4
Wuyang County 49 168 249 20
Table 6. Monitoring and early warning results for dry hot wind in 2019, shown as number of farm-
land patches of different severity levels.
Region 1 Mild, 1 Moderate, 1 Severe 2 Moderate, 1 Severe
Qi County 25 237
Yanjin County 517
Wuyang County 271 295
The warning messages are shown in Figure 12. In the dry hot wind warning results,
the information provided includes the location of the farmland patch, disaster situation,
measures for preventing dry hot wind, and farmland management personnel.
Figure 11. Adding a DisasterReport instance to a farmland patch instance.
Remote Sens. 2023,15, 4403 13 of 18
Similarly, the warning information was promptly updated with the updates of meteo-
rological forecast data.
The warning results for Qi County, Yanjin County, and Wuyang County are shown in
Tables 5and 6.
Table 5.
Monitoring and early warning results for dry hot wind in 2013, shown as number of farmland
patches of different severity levels.
Region 1 Mild,
1 Moderate 3 Moderate 4 Moderate 1 Moderate,
1 Severe
2 Moderate,
1 Severe
3 Moderate,
1 Severe
1 Moderate,
2 Severe
Qi County 148 86
Yanjin County 240 358 4
Wuyang County 49 168 249 20
Table 6.
Monitoring and early warning results for dry hot wind in 2019, shown as number of farmland
patches of different severity levels.
Region 1 Mild, 1 Moderate, 1 Severe 2 Moderate, 1 Severe
Qi County 25 237
Yanjin County 517
Wuyang County 271 295
The warning messages are shown in Figure 12. In the dry hot wind warning results,
the information provided includes the location of the farmland patch, disaster situation,
measures for preventing dry hot wind, and farmland management personnel.
Remote Sens. 2023, 15, x FOR PEER REVIEW 14 of 18
Figure 12. Example of agro-meteorological disaster monitoring and early warning instance.
3.3. Post-Disaster Monitoring Results
For each farmland patch, the reasoning engine obtains remote sensing data from the
day before and the day after the disaster. It further calculates the NDVI to determine the
actual extent of damage. The average decrease in the NDVI on farmland patches with
different degrees of damage in each county is shown in Tables 7 and 8. The decrease in the
NDVI is also used as an aribute for the corresponding disaster report entity node of the
affected farmland patch.
Table 7. Average NDVI decrease in differently affected farmland patches in 2013.
Region 1 Mild,
1 Moderate 3 Moderate 4 Moderate 1 Moderate,
1 Severe
2 Moderate,
1 Severe
3 Moderate,
1 Severe
1 Moderate,
2 Severe
Qi County 0.04 0.36
Yanjin County 0.05 0.35 0.36
Wuyang County 0.01 0.08 0.12 0.17
Table 8. Average NDVI decrease in differently affected farmland patches in 2019.
Region 1 Mild, 1 Moderate, 1 Severe 2 Moderate, 1 Severe
Qi County 0.08 0.12
Yanj in Co unt y 0.2
Wuyang County 0.27 0.31
The two tables above also confirm the correlation between the severity of damage to
wheat caused by dry hot wind and the intensity and duration of a dry hot wind occurrence
[29]. Therefore, in situations where resources and manpower are limited, priority should
be given to implementing disaster risk reduction measures in agricultural areas that are
more severely affected by disasters.
Figure 12. Example of agro-meteorological disaster monitoring and early warning instance.
Remote Sens. 2023,15, 4403 14 of 18
3.3. Post-Disaster Monitoring Results
For each farmland patch, the reasoning engine obtains remote sensing data from the
day before and the day after the disaster. It further calculates the NDVI to determine the
actual extent of damage. The average decrease in the NDVI on farmland patches with
different degrees of damage in each county is shown in Tables 7and 8. The decrease in the
NDVI is also used as an attribute for the corresponding disaster report entity node of the
affected farmland patch.
Table 7. Average NDVI decrease in differently affected farmland patches in 2013.
Region 1 Mild,
1 Moderate 3 Moderate 4 Moderate 1 Moderate,
1 Severe
2 Moderate,
1 Severe
3 Moderate,
1 Severe
1 Moderate,
2 Severe
Qi County 0.04 0.36
Yanjin County 0.05 0.35 0.36
Wuyang County 0.01 0.08 0.12 0.17
Table 8. Average NDVI decrease in differently affected farmland patches in 2019.
Region 1 Mild, 1 Moderate, 1 Severe 2 Moderate, 1 Severe
Qi County 0.08 0.12
Yanjin County 0.2
Wuyang County 0.27 0.31
The two tables above also confirm the correlation between the severity of damage to
wheat caused by dry hot wind and the intensity and duration of a dry hot wind occur-
rence [
29
]. Therefore, in situations where resources and manpower are limited, priority
should be given to implementing disaster risk reduction measures in agricultural areas that
are more severely affected by disasters.
3.4. Query Results
After the above steps, the disaster information at the farmland patch level is also added
to the knowledge graph, resulting in a continuously updated agro-meteorological disaster
database. Various queries can be performed using the SPARQL Protocol and RDF Query
Language (SPARQL) [30] query statements. Figure 13 shows three example questions.
The query results are as follows: “3”, “1322 km
2
”, and “Wuyang County”. This implies
that based on the existing information in the database, there are three counties in Henan
Province that have experienced dry hot wind. The farmland area affected by dry hot wind
in 2013 was 1322 square kilometers, and Wuyang County was the county most affected by
dry hot wind in 2019.
Remote Sens. 2023,15, 4403 15 of 18
Remote Sens. 2023, 15, x FOR PEER REVIEW 15 of 18
3.4. Query Results
After the above steps, the disaster information at the farmland patch level is also
added to the knowledge graph, resulting in a continuously updated agro-meteorological
disaster database. Various queries can be performed using the SPARQL Protocol and RDF
Query Language (SPARQL) [30] query statements. Figure 13 shows three example ques-
tions.
Figure 13. Examples of SPARQL query statement.
The query results are as follows: “3”, “1322 km
2
”, and “Wuyang County”. This im-
plies that based on the existing information in the database, there are three counties in
Henan Province that have experienced dry hot wind. The farmland area affected by dry
hot wind in 2013 was 1322 square kilometers, and Wuyang County was the county most
affected by dry hot wind in 2019.
4. Discussion
This paper proposes a technical method based on a spatio-temporal knowledge
graph for the integrated organization and management of remote sensing data, meteoro-
logical data, farmland data, crop information, expert knowledge, and computational mod-
els. The knowledge graph starts reasoning spontaneously from the input meteorological
data, sequentially discovering dry hot wind occurrences, calculating pre- and post-disas-
ter NDVI decline values, and supplementing the knowledge graph with the disaster in-
formation. For two dry hot wind disasters, the knowledge graph constructed in this study
provided more specific and accurate disaster information through reasoning. Therefore,
Figure 13. Examples of SPARQL query statement.
4. Discussion
This paper proposes a technical method based on a spatio-temporal knowledge graph
for the integrated organization and management of remote sensing data, meteorological
data, farmland data, crop information, expert knowledge, and computational models.
The knowledge graph starts reasoning spontaneously from the input meteorological data,
sequentially discovering dry hot wind occurrences, calculating pre- and post-disaster NDVI
decline values, and supplementing the knowledge graph with the disaster information.
For two dry hot wind disasters, the knowledge graph constructed in this study provided
more specific and accurate disaster information through reasoning. Therefore, for tasks
such as detecting dry hot wind disasters and using remote sensing to assess meteorological
disasters, the proposed method in this paper is a valuable technique worth exploring.
However, there are still some limitations in this research. Firstly, the spatial resolution
of the wheat distribution data [
25
] used in this paper is relatively low, and the pixels
cannot accurately represent actual farmland patches. Therefore, in practical applications,
remote sensing intelligent interpretation should be used to obtain higher-resolution crop
distribution data. If ground survey data can be obtained, the farmland patches can be
further integrated into actual land management units (such as farms or plantations), so that
warning information can be accurately communicated to the farmland managers.
Secondly, the historical meteorological data used in this paper also have a low spatial
resolution. Improving the spatial resolution of these meteorological data would be more
beneficial in providing more accurate warning results at the plot level.
Thirdly, for the NDVI difference matrix before and after disasters within the farmland
patches, the paper only includes statistical measures such as the average value. If more
domain knowledge, such as the relationship between NDVI decline and actual damage
Remote Sens. 2023,15, 4403 16 of 18
indicators (such as yield), can be obtained, it would be possible to provide indicators that
are easier for farmland management personnel to understand and use after obtaining the
NDVI decline values.
Lastly, in this research, remote sensing images are only used for monitoring calcula-
tions after predicting the occurrence of dry hot wind based on meteorological data. This
results in the accuracy of warnings relying mainly on meteorological data. Objectively, con-
tinuous monitoring of crop growth using remote sensing images can automatically detect
disasters based on their changes, forming a coupling relationship between meteorological
data warning and remote sensing data monitoring to a greater extent.
5. Conclusions
In the field of remote sensing, the aim of Earth spatial information services is to deliver
the right data/information/knowledge at the right time to the right person in the right
place [
31
]. In the context of agro-meteorological disaster monitoring tasks, this paper
proposes an effective method:
(1) This paper constructs a spatio-temporal knowledge graph for agro-meteorological disas-
ter monitoring, integrating multiple heterogeneous data sources such as meteorological
data, remote sensing data, farmland data, and agricultural knowledge. This enables the
integration and intelligent analysis of pre-disaster meteorological disaster monitoring
and post-disaster impact analysis driven by data and knowledge cooperation.
(2)
This paper uses remote sensing techniques to refine the granularity of meteorolog-
ical disaster monitoring and warning to the farmland patch level, providing a new
approach for fine-grained agricultural management.
(3)
This paper incorporates MODIS remote sensing image data directly into knowledge
reasoning and computation. MODIS remote sensing data are involved in the daily
monitoring process, making full use of the advantages of long-term continuous
observation of crop remote sensing data. It explores the synergistic development path
of the participation of remote sensing in spatio-temporal knowledge computation
and reasoning.
(4)
The knowledge graph is supplemented with the results of monitoring, early warning,
and evaluation analysis in each iteration as disaster information, achieving automatic
iterative updating of the knowledge graph. Over the long term, it naturally becomes
an agro-meteorological disaster database.
Based on the spatio-temporal knowledge graph and reasoning process for agro-
meteorological disaster monitoring and warning constructed in this paper, further research
can be carried out as follows:
(1)
Regarding historical data, although dry hot wind meteorological disasters occur fre-
quently, have a wide impact range, affect multiple crops, and cause significant losses,
detailed and comprehensive statistical data have not yet been formed. In line with
the research method proposed in this paper, historical dry hot wind meteorological
disaster data could be extracted from national-level historical meteorological data over
the past few years, forming a historical dry hot wind disaster database. Using this
database, the spatial-temporal patterns of dry hot wind disasters and the relationship
between meteorological conditions and NDVI differences can be explored.
(2)
Looking towards the future, once issues such as real-time acquisition of meteorologi-
cal and remote sensing data are resolved, the method proposed in this paper can be
directly applied to agro-meteorological disaster monitoring tasks. Additionally, since
the warning in this paper relies on meteorological data, the accuracy of meteorological
forecast data directly impacts the effectiveness of agro-meteorological disaster warn-
ings. By incorporating the “spatio-temporal patterns of dry hot wind meteorological
disasters” mentioned in point (1) as an auxiliary for monitoring and warning, the
accuracy of warnings can be improved.
Remote Sens. 2023,15, 4403 17 of 18
Author Contributions:
Conceptualization, W.Z., L.P., X.G. and L.Y.; methodology, W.Z. and W.L.;
validation, W.Z. and W.L.; resources, W.Z.; data curation, W.Z.; writing—original draft preparation,
W.Z.; writing—review and editing, W.Z., L.P., X.G., L.Y. and L.C.; funding acquisition, L.P. All authors
have read and agreed to the published version of the manuscript.
Funding:
This research was supported by the National Key Research and Development Program of
China (2022YFD2001102).
Data Availability Statement: Data sharing not applicable.
Conflicts of Interest: The authors declare no conflict of interest.
References
1. Cheng, C. Climate and Agriculture in China; China Meteorological Press: Beijing, China, 1991.
2.
National Public Service Platform for Standards Information. Available online: https://std.samr.gov.cn/db/search/
stdDBDetailed?id=F42D1753A8CC5CAAE05397BE0A0A115E (accessed on 7 August 2023).
3.
China Meteorological Administration. Available online: https://www.cma.gov.cn/2011xzt/20120816/20130625/2013062506/201
307/t20130701_218101.html (accessed on 7 August 2023).
4.
Lou, W.; Zhu, X.; Zhou, S.; Xue, G.; Cai, J.; Ji, Z. Monitoring and early warning system for agro-ecological and agriculture
meteorological disaster in Shaoxing City. Trans. CSAE 2007,23, 182–186. [CrossRef]
5.
Mo, J.; Zhong, S.; Chen, Y.; Kuang, Z.; He, Y.; Li, L. Development and application of monitoring and early warning system for
main agro-meteorological disasters in Guangxi Province. J. Nat. Disasters 2013,22, 150–157. [CrossRef]
6.
Sun, Z.; Wang, Y.; Zhang, L.; Guo, W. Design and realization of intelligent service system for monitoring and warning of
meteorological disasters in facility agriculture in North China. Trans. CSAE 2018,34, 149–156. [CrossRef]
7.
Xiao, J.; Yao, Y.; Jin, Z.; Li, R.; Yuan, D.; Zhang, H.; Wang, Z. Design and implementation of agro-meteorological service platform
based on WebGIS. Meteorol. Environ. Sci. 2017,40, 132–139. [CrossRef]
8.
Li, Y.; Wei, Y.; Liu, R.; Fang, W.; Cheng, L. Remote sensing monitoring of a dry hot wind disaster in Wheat-Growing Area of
Henan Province. Chin. J. Agrometeorol. 2014,35, 593–599. [CrossRef]
9.
Zhong, S.; Chen, Y.; Liu, J.; Sun, M.; Ding, M.; Kuang, Z. Monitoring and Evaluation Method on Sugarcane Frost Injury Using
Multi-sources Remote Sensing Images. Sci. Technol. Eng. 2018,18, 189–193. [CrossRef]
10.
Lu, F.; Zhu, Y.; Zhang, X. Spatio-temporal knowledge graph: Advances and perspectives. J. Geo-Inf. Sci.
2023
,25, 1091–1105.
[CrossRef]
11.
Qi, C.; Song, Q.; Zhang, P.; Yuan, H. Cn-MAKG: China Meteorology and Agriculture Knowledge Graph Construction Based
on Semi-structured Data. In Proceedings of the 2018 IEEE/ACIS 17th International Conference on Computer and Information
Science (ICIS), Singapore, 6–8 June 2018; pp. 692–696. [CrossRef]
12.
Liu, X.; Bai, X.; Wang, L.; Ren, B.; Lu, S.; Li, L. Review and Trend Analysis of Knowledge Graphs for Crop Pest and Diseases. IEEE
Access 2019,7, 62251–62264. [CrossRef]
13.
Chen, J.; Xu, X.; Zhang, Y.; Zhou, Y.; Wang, H.; Tan, C. Research Progress of Multimodal Knowledge Graph in Agriculture.
J. Agric. Big Data 2022,4, 126–134. [CrossRef]
14.
Wang, D.; Zhou, F.; Li, Y.; Liu, W.; Wang, J.; Zhang, Q.; Cui, D. Study on the construction of knowledge map of sweet cherry
industry in China. China Fruits 2023,1, 104–108. [CrossRef]
15.
Wang, P.; Liu, T.; Du, P.; Yang, G. Analysis on mapping knowledge domain of disaster risk research in China from 2000 to 2017.
J. Nat. Disasters 2019,28, 169–177. [CrossRef]
16.
Ge, X.; Yang, Y.; Chen, J.; Li, W.; Huang, Z.; Zhang, W.; Peng, L. Disaster Prediction Knowledge Graph Based on Multi-Source
Spatio-Temporal Information. Remote Sens. 2022,14, 1214. [CrossRef]
17.
Ge, X.; Yang, Y.; Peng, L.; Chen, L.; Li, W.; Zhang, W.; Chen, J. Spatio-Temporal Knowledge Graph Based Forest Fire Prediction
with Multi Source Heterogeneous Data. Remote Sens. 2022,14, 3496. [CrossRef]
18.
Chen, L.; Ge, X.; Yang, L.; Li, W.; Peng, L. An Improved Multi-Source Data-Driven Landslide Prediction Method Based on
Spatio-Temporal Knowledge Graph. Remote Sens. 2023,15, 2126. [CrossRef]
19.
Huo, Z.; Shang, Y.; Wu, D.; Wu, L.; Fan, Y.; Wang, P.; Yang, J.; Wang, C. Review on Disaster of Hot Dry Wind for Wheat in China.
J. Appl. Meteorol. Sci. 2019,30, 129–141.
20.
Central Government Portal Website. Available online: https://www.gov.cn/jrzg/2013-05/13/content_2401555.htm (accessed on
7 August 2023).
21. Dahebao Website. Available online: http://www.dahebao.cn/news/1409136?cid=1409136 (accessed on 7 August 2023).
22. Xinxin Travel Weather Forecast. Available online: https://tianqi.cncn.com/yanjin/news-550549 (accessed on 7 August 2023).
23.
Copernicus Climate Change Service (C3S) Climate Data Store (CDS). Available online: https://cds.climate.copernicus.eu/
cdsapp#!/dataset/reanalysis-era5-land?tab=form (accessed on 7 August 2023).
24.
US Government Computer. Available online: https://e4ftl01.cr.usgs.gov/MOLT/MOD09GA.061/ (accessed on 7 August 2023).
25.
Luo, Y.; Zhang, Z.; Li, Z.; Chen, Y.; Zhang, L.; Cao, J.; Tao, F. Identifying the spatio-temporal changes of annual harvesting areas
for three staple crops in China by integrating multi-data sources. Environ. Res. Lett. 2020,15, 074003. [CrossRef]
Remote Sens. 2023,15, 4403 18 of 18
26.
National Earth System Science Data Center. Available online: http://www.geodata.cn/thematicView/GLASS.html?guid2=52092
346086099 (accessed on 7 August 2023).
27. GeoSPARQL. Available online: http://www.geosparql.org/ (accessed on 25 February 2022).
28.
O’Connor, M.J.; Das, A.K. A method for representing and querying temporal information in owl. In Proceedings of the
International Joint Conference on Biomedical Engineering Systems and Technologies, Valencia, Spain, 20–23 January 2010;
pp. 97–110.
29. Shi, D. Introduction of Meteorological Support for Winter Wheat Production; China Meteorological Press: Beijing, China, 1994.
30.
SPARQL-Semantic Web Standards. Available online: https://www.w3.org/2001/sw/wiki/SPARQL (accessed on 7 August 2023).
31. Li, D. Towards Geo-spatial Information Science in Big Data Era. Acta Geod. Et Cartogr. Sin. 2016,45, 379–384. [CrossRef]
Disclaimer/Publisher’s Note:
The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.
Available via license: CC BY 4.0
Content may be subject to copyright.