Fig 8 - uploaded by He Yin
Content may be subject to copyright.
Source publication
Land use maps describe the spatial distribution of natural resources, cultural landscapes, and human settlements, serving as an important planning tool for decision makers. In the Sahel area, such information is valuable for risk management and mitigation in challenging sectors like food security, flood control, and urban planning. Due to its unifo...
Context in source publication
Context 1
... on the Classifier Ensemble (CE) map (Fig. 8), the area estimates for different land use classes in the study region are 873 km 2 bare soil (22.3 ± 3.2%), 82 km 2 rice (2.1 ± 0.6%), 162 km 2 , built-up (4.1 ± 0.9%), 184 km 2 , dense vegetation (4.7 ± 1.3%), 564 km 2 , cropland (14.4 ± 2.3%), 170 km 2 rocky (4.3 ± 0.6%), 1845 km 2 sparse vegetation (47.1 ± 3.6%), and 36 km 2 water ...
Similar publications
The effort to increase agricultural productivity continues to receive interest in Africa as low productivity levels, poverty and food insecurity remain or even increase. This study used the Färe-Primont Index to estimate agricultural total factor productivity growth for 49 African countries. Panel data consisting of 833 observations for the period...
Citations
... Land use is defined as the purpose for which humans exploit the land cover such as for agriculture, settlement, etc. (Lambin et al., 2006;Mishra et al., 2014), while land cover is defined as the biophysical components that cover the earth's land surface and can be observed directly such as forest, building, water, etc (Linh, 2013, Phiri and Morgenroth, 2017. As the major components of the natural environment, LULC information has become an important input to a wide range of studies and applications such as in urban planning, natural resource, and environmental monitoring, land use policy development, and even to understanding of the global climate evolution (Foley et al., 2005, Li et al., 2020, Schulz et al., 2021. Hence, it is the prime spatial information that should be archived regularly. ...
... In the absence of field data prior to 2017, a fixed pixel approach was used to obtain robust accuracy assessments of the mapping products across the whole time series. This method is established in terrestrial time series validation as limited validation data in time series analysis is common [73][74][75] . First, a selection of known seagrass and non-seagrass areas from modern validation data were identified and their boundaries were tracked and delineated manually through time. ...
The areal extent of seagrass meadows is in rapid global decline, yet they provide highly valuable societal benefits. However, their conservation is hindered by data gaps on current and historic spatial extents. Here, we outline an approach for national-scale seagrass mapping and monitoring using an open-source platform (Google Earth Engine) and freely available satellite data (Landsat, Sentinel-2) that can be readily applied in other countries globally. Specifically, we map contemporary (2021) and historical (2000–2021; n = 10 maps) shallow water seagrass extent across the Maldives. We found contemporary Maldivian seagrass extent was ~ 105 km² (overall accuracy = 82.04%) and, notably, that seagrass area increased threefold between 2000 and 2021 (linear model, + 4.6 km² year⁻¹, r² = 0.93, p < 0.001). There was a strongly significant association between seagrass and anthropogenic activity (p < 0.001) that we hypothesize to be driven by nutrient loading and/or altered sediment dynamics (from large scale land reclamation), which would represent a beneficial anthropogenic influence on Maldivian seagrass meadows. National-scale tropical seagrass expansion is unique against the backdrop of global seagrass decline and we therefore highlight the Maldives as a rare global seagrass ‘bright spot’ highly worthy of increased attention across scientific, commercial, and conservation policy contexts.
... Using Sentinel-2 satellite images, land monitoring applications can be performed, including identifying crop types and tree species, detecting water bodies, and mapping built-up areas (Schulz et al., 2021). Recent research has used Sentinel-2 data with an improved spatial and spectral resolution to map the vegetation characteristics of African savannahs (Anchang et al., 2020). ...
... In remote sensing science, integrating satellite data from different sensors is a common practice (Shafeian et al., 2021;Vizzari, 2022). Sentinel-2 and Sentinel-1 data have frequently been merged to enhance the precision of land cover change classification (Borges et al., 2020;Schulz et al., 2021;Urban et al., 2021;Vizzari, 2022). In this study, Sentinel-1 integration was motivated by the fact that the sensor is unaffected by clouds, making it simple to monitor the extent of non-native species at any given time (Borges et al., 2020;Zhou et al., 2020). ...
... The study demonstrated that the RF ML algorithm is suitable for complex and heterogeneous landscapes, as it effectively captures the spatial patterns and spectral information in the data (Fu et al., 2017). The study by Schulz et al. (2021) also utilized RF to classify different LULC classes using Sentinel-2 satellite imagery, achieving a high classification accuracy. Combining separate data sets enables the use of bands from various electromagnetic spectrum regions (Nuthammachot & Stratoulias, 2019). ...
Imphal Valley, situated in Manipur, India, stands as an intermontane valley of great ecological significance, notably hosting Loktak Lake. This research delves into the Land Use Land Cover Change (LULCC) within the Imphal Valley from 2016 to 2021 and assesses their impact on air quality across distinct land cover types. We used Sentinel‐1 & 2 data, ALOS PALSAR Digital Elevation Model, and applied Random Forest (RF), a machine learning algorithm for effective land use and land cover (LULC) mapping. Additionally, Sentinel‐5P data was utilized to monitor air quality parameters (CO, HCHO, NO2, SO2, Aerosol Index) spanning 2019 to 2021. The overall accuracies for the LULC maps employing a k (k = 3) fold approach for accuracy assessment varied between 88% and 92%, with corresponding Kappa coefficient ranging from 0.85 to 0.90. Noteworthy trends emerged from our analysis, revealing an increase in settlements and horticulture farms and a decline in forested areas and phumdis (floating biomass). Our findings highlight a mean concentration of CO ranging between 0.045 mol/m² and 0.055 mol/m² in different land cover types during February and March (2019–2021). Furthermore, we observed maximum mean HCHO, NO2, SO2, and aerosol index concentrations in March. Pollution levels surged during forest fires and shifting agriculture seasons, while aerosol levels declined during the lockdown period. This integrated approach emphasized on the comprehensive analysis of the dynamic interplay between LULCC and air quality in the Imphal Valley. This intricate relationship between LULC changes and air quality dynamics in the Imphal Valley, contribute to our understanding of the environmental dynamics in this ecologically vital region.
... In this study, the classification performance of RF and SVM algorithms was evaluated. These algorithms demonstrate less sensitivity to the choice of input features [18] and are equally reliable [106][107][108]. The maps in (Figure 5), obtained through RF and SVM methods with different features combinations, were quite similar, except for differences in accuracies. ...
Generating orchards spatial distribution maps within a heterogeneous landscape is challenging and requires fine spatial and temporal resolution images. This study examines the effectiveness of Sentinel-1 (S1) and Sentinel-2 (S2) satellite data of relatively high spatial and temporal resolutions for discriminating major orchards in the Khairpur district of the Sindh province, Pakistan using machine learning methods such as random forest (RF) and a support vector machine. A Multicollinearity test (MCT) was performed among the multi-temporal S1 and S2 variables to remove those with high correlations. Six different feature combination schemes were tested, with the fusion of multi-temporal S1 and S2 (scheme-6) outperforming all other combination schemes. The spectral separability between orchards pairs was assessed using Jeffries-Matusita (JM) distance, revealing that orchard pairs were completely separable in the multi-temporal fusion of both sensors, especially the indistinguishable pair of dates-mango. The performance difference between RF and SVM was not significant, SVM showed a slightly higher accuracy, except for scheme-4 where RF performed better. This study concludes that multi-temporal fusion of S1 and S2 data, coupled with robust ML methods, offers a reliable approach for orchard classification. Prospectively, these findings will be helpful for orchard monitoring , improvement of yield estimation and precision based agricultural practices.
... To effectively identify the willow and non-willow classes, the GEE cloud computing platform was used to provide image collections, preprocess, extract features, classify, and check the accuracy of produced maps [48]. This stage entailed a number of procedures, including image collecting and filtering, cloud-cover masking, calculation of spectral indices, extraction of spectral-temporal information, and classification [49,50]. For image classification and the training samples, a nonparametric random forest (RF) classifier was used. ...
The goal of this study was to estimate the areas under willow cultivation by farmers, as well as their growth and health status. Due to the extremely small patch size of land cover types in the study area, Sentinel-2 data were used to conduct supervised classification based on the random forest machine learning technique, and a large training dataset was produced from PlanetScope satellite imagery. The results of image classification using Google Earth Engine indicated that the Sentinel data were suitable for identifying willow-cultivated areas. It was found that these areas declined from 875.32 ha in 2017 to 288.41 ha in 2022. The analysis of the growth and health conditions of willow-cultivated plots also revealed that the temporal variations in the NDVI in these plots decreased significantly in 2022 as compared to previous years (p < 0.05). An in-depth analysis revealed a significant positive correlation between NDVI, precipitation, and temperature. It was found that the most efficient components explaining the process of browning the vegetation in the planted willow plots were the increasing temperature and decreasing precipitation. This research may be used to document the national and global monitoring efforts for climate change adaptation.
... For the algorithm's robustness, the transferability assessment of a model is perilous. The robustness of the model helps to generalize, model consistency, and efficacy [8]. Basheer et al. (2022) [38] suggested several robust classification methods and quality datasets for LULC mapping, e.g., SVM, RF, CART, ArcGIS Pro, and Google Earth Engine to map LULC using Landsat TM, Sentinel-2, and PlanetScope datasets. ...
... The result showed that the SVM algorithm and the PlanetScope data outperformed other datasets and algorithms. The study also showed that the fusion and ensemble of ML algorithms improved classification accuracy over a single ML algorithm [8,34]. ...
Land use and land cover (LULC) classification plays a significant role in the analysis of climate change, evidence-based policies, and urban and regional planning. For example, updated and detailed information on land use in urban areas is highly needed to monitor and evaluate urban development plans. Machine learning (ML) algorithms, and particularly ensemble ML models support transferability and efficiency in mapping land uses. Generalization, model consistency, and efficiency are essential requirements for implementing such algorithms. The transfer-ensemble learning approach is increasingly used due to its efficiency. However, it is rarely investigated for mapping complex urban LULC in Global South cities, such as India. The main objective of this study is to assess the performance of machine and ensemble-transfer learning algorithms to map the LULC of two metropolitan cities of India using Landsat 5 TM, 2011, and DMSP-OLS nightlight, 2013. This study used classical ML algorithms, such as Support Vector Machine-Radial Basis Function (SVM-RBF), SVM-Linear, and Random Forest (RF). A total of 480 samples were collected to classify six LULC types. The samples were split into training and validation sets with a 65:35 ratio for the training, parameter tuning, and validation of the ML algorithms. The result shows that RF has the highest accuracy (94.43%) of individual models, as compared to SVM-RBF (85.07%) and SVM-Linear (91.99%). Overall, the ensemble model-4 produces the highest accuracy (94.84%) compared to other ensemble models for the Kolkata metropolitan area. In transfer learning, the pre-trained ensemble model-4 achieved the highest accuracy (80.75%) compared to other pre-trained ensemble models for Delhi. This study provides innovative guidelines for selecting a robust ML algorithm to map urban LULC at the metropolitan scale to support urban sustainability.
... Irrespective of the PBIA and OBIA, the highest accuracies were consistently achieved with the RF. Similar results have been observed in other studies, such as Mao et al. (2020) and Schulz et al. (2021), where RF outperformed other ML models. This study aimed to classify two classes, forest and nonforest, which exhibited a wide range of spectral signature variations and mixed pixels due to the inclusion of various tree species with differing density and age within the forest class, as well as different land use and land cover types such as cropland, bare land, water bodies, and artificial lands within the non-forest class. ...
Despite utilizing various remote sensing datasets, precise tree-cutting detection remains challenging due to
spatial and spectral resolution constraints in satellite imagery, complex landscapes, data integration issues, and
the need for accurate multi-temporal reference datasets. This study investigates the utilization of PlanetScope
(PS) satellite images, along with pixel-based (PBIA) and object-based (OBIA) image analysis, for accurate
mapping of forest cover and detection of tree cuttings. Detailed multi-temporal reference datasets were collected
based on airborne laser scanning (ALS)-derived canopy height models (CHM) and very high-resolution (VHR)
aerial orthomosaics. Reference datasets were used to train three machine learning (ML) models: random forest
(RF), support vector machine (SVM), and feed-forward neural network (Nnet) in two forest districts located in
Western and Northern Poland. The study also assessed the generalization capabilities of the best model in both
local and temporal contexts. Regarding forest cover mapping, the OBIA RF classifier outperformed all other
models with an overall accuracy (OA) of 99.27 % and Kappa of 98.18 %, while the PBIA SVM model showed the
lowest (OA = 97.18 %, Kappa = 94.35 %). The testing of the model’s generalization confirmed the performance
of the OBIA RF model, with the Dice Coefficient ranging from 95.86 % to 96.74 %. The methodology’s effectiveness in tree-cutting detection was demonstrated, with the detection rate ranging from 96.20 % to 99.39 % for
the total number of cuttings, and from 99.45 % to 99.86 % for the total volume. In conclusion, the integration of
PS satellite images, spectral-textural features, and generalized ML models proves to be effective for tree-cutting
detection.
... Também imagens provenientes do sensor MODIS (Moderate Resolution Imaging Spectroradiometer) disponibilizadas ao nível global e anualmente de 2000 a 2020, com resolução espacial de 250, 500 e 1000m, têm sido usadas para detectar alterações no uso do solo (Friedl et al., 2010). Mais recentemente, regista-se um aumento na utilização de imagens dos programas Sentinel-2 e Sentinel-1 devido à sua alta resolução (10m), escala global e de acesso gratuito (Campos-Taberner et al., 2020;Phiri et al., 2020;Schulz et al., 2021). ...
At the center of global initiatives, various approaches are being discussed and realigned to achieve global objectives for production and food security for the present and future generations. However, agricultural systems, which are the main biogeophysical source for ensuring nutritional benefits and global food security, undergo changes over time. In the coming decades, these systems will face complex challenges, for example, associated with changes in food consumption patterns, climate change, land abandonment and/or intensification of land use. The ability of these systems to support global food security will be determined by their efficiency, sustainability, and equity. The integration of geospatial approaches to geographical research offers a practical opportunity to model agricultural systems, which, in turn, can contribute to obtain new data that assist in decision-making processes, anticipating future changes, and projecting long-term robust strategies to manage imminent challenges. This article presents a reflection on the development and integration of spatial analysis, geospatial data, and simulation models in the field of agricultural systems, highlighting and exemplifying different modeling techniques and geospatial technologies to support current and future research needs.
... However, the implementation of successful conservation strategies and forest when employing conventional machine learning algorithms for forest cover mapping-such as random forests (RF) [19] support vector machines (SVM) [20], and classification and regression trees (CART) [21]-the performance of individual classifications can differ based on the RS data, classification scheme, and scene settings [22]. In light of this variability, a new array of techniques has emerged within the RS field that merges different individual classifiers to generate an ensemble map [23,24]. ...
The conservation and management of forest areas require knowledge about their extent and attributes on multiple scales. The combination of multiple classifiers has been proposed as an attractive classification approach for improved accuracy and robustness that can efficiently exploit the complementary nature of diverse remote sensing data and the merits of individual classifiers. The aim of this study was to develop and evaluate multiple classifier systems (MCSs) within a cloud-based computing environment for multi-scale forest mapping in Northeastern Greece using passive and active remote sensing data. Five individual machine learning base classifiers were used for class discrimination across the three different hierarchy levels, and five ensemble approaches were used for combining them. In the case of the binary classification scheme in the upper level of the hierarchy for separating woody vegetation (forest and shrubs) from other land, the overall accuracy (OA) slightly increased with the use of the MCS approach, reaching 94%. At the lower hierarchical levels, when using the support vector machine (SVM) base classifier, OA reached 84.13% and 74.89% for forest type and species mapping, respectively, slightly outperforming the MCS approach. Yet, two MCS approaches demonstrated robust performance in terms of per-class accuracy, presenting the highest average F1 score across all classification experiments, indicating balanced misclassification errors across all classes. Since the competence of individual classifiers is dependent on individual scene settings and data characteristics, we suggest that the adoption of MCS systems in efficient computing environments (i.e., cloud) could alleviate the need for algorithm benchmarking for Earth’s surface cover mapping.
