Fig 1 - available via license: CC BY
Content may be subject to copyright.
The study area, the Korean Peninsula, including North and South Korea. The Shuttle Radar Topography Mission (SRTM) 30m digital elevation map (DEM; downloaded from http://eros.usgs.gov/elevation-products) is used as a background image. https://doi.org/10.1371/journal.pone.0223362.g001
Source publication
In this research, climate classification maps over the Korean Peninsula at 1 km resolution were generated using the satellite-based climatic variables of monthly temperature and precipitation based on machine learning approaches. Random forest (RF), artificial neural networks (ANN), k-nearest neighbor (KNN), logistic regression (LR), and support ve...
Contexts in source publication
Context 1
... and 124.18-131.87˚E longitude (Fig 1). The annual average accumulated precipitation and annual average temperature for the study area is 1113.7 mm/yr and 10.52˚C/yr, respectively, referring to the meteorological data of KMA during 30 years from 1981 to 2010. ...
Context 2
... study area has four distinct seasons, featuring a strong and short rainy season from May to Jun called as "Changma". Mountainous regions constitute 70% of the terrestrial area according to DEM (Fig 1). As the terrain in the Korean Peninsula is complex and rugged, altitudes drastically differ by administrative district and the patches of land cover are relatively small [26]. ...
Context 3
... changing trend from Cfa to Cwa is stronger between the rule-based map (Fig 7B) and the ANN map (Fig 7D) than between the two rule-based maps for the period of 1983-2000 ( Fig 7B) and 2001-2013 (Fig 7C). The difference between Cfa and Cwa is in the second letter; "f" is for fully humid and "w" is for dry winter. ...
Context 4
... shifting of "D" over time might be related to the effect of global warming on the increment of temperature in the Korean Peninsula. Snow climates denoted as "D" are located along the mountainous areas with high elevation (Figs 1 and 7). Although the ANN model in this study was trained using in-situ references of four classes without Dfa, Dfb, and Dwb, the distribution of the cold class (Dwc) is well matched with the high altitude areas of DEM (Fig 1). ...
Context 5
... climates denoted as "D" are located along the mountainous areas with high elevation (Figs 1 and 7). Although the ANN model in this study was trained using in-situ references of four classes without Dfa, Dfb, and Dwb, the distribution of the cold class (Dwc) is well matched with the high altitude areas of DEM (Fig 1). ...
Similar publications
Multidecadal inland surface water dynamics are of increasing interest due to their importance to climate, ecology, and society, yet several key challenges impede long‐term monitoring of inland surface waters globally. This research investigates two novel methods, one addressing subhydroflattened surface estimate uncertainty issues, and a second add...
In this work we have used SRTM 90 and 30m, ASTER 30m and 60 cm Google Earth (GE) based elevation data generated using online tool Terrain Zonum, validation was performed with respect to Survey of India (SOI) toposheet. These results are important for those areas where limited field data are available. It also provides a benchmark for validation of...
Gullies and other forms of erosion have been the greatest environmental problem and catastrophe in most high- and low-income countries. The challenge posed by soil erosion has compromised agricultural productivity, environmental biodiversity and food safety for the world's population. It is important to identify vulnerable areas to soil erosion in...
O mapeamento geomorfológico do Seridó é necessário devido à escassez de produtos dessa natureza, assim como, também, é importante para fins de planejamento e ordenamento territorial, haja vista que a região analisada apresenta cidades em fase de expansão, como, por exemplo, Caicó e Currais Novos. Este trabalho objetivou realizar um mapeamento geomo...
Morphological characteristics of cirques have been studied for decades; however, no repeatable set of metrics has been derived that can consistently identify them. Perhaps more importantly, there is no consensus definition of the form that distinguishes cirques and clusters of cirques from non-cirques. In our approach, we use Shuttle Radar Topograp...
Citations
... Köppen-Geiger climate classification can be found elsewhere (Alvares et al., 2013;Cui et al., 2021a;Park et al., 2019;Peel et al., 2007). ...
A possible shift in climate zones in Southeast Asia (SEA) for different shared socioeconomic pathways (SSPs) is evaluated in this study. The ability of 19 Coupled Model Intercomparison Project (CMIP6) global climate models (GCMs) in reconstructing the Köppen-Geiger climate zones in SEA, estimated using reanalysis data (ERA5) for the period 1979-2014, was analysed using five categorical evaluation metrics. The best-performing models were selected to prepare an ensemble to project possible shifts in climate zones for different SSP scenarios in the future. Besides, future projections in climate variables were evaluated to assess the driving factor of climate shifts in the future. The results showed that three CMIP6 GCMs, EC-Earth3-Veg-LR, CMCC-ESM2 and CanESM5, had a higher skill in classifying the observed climate of SEA. Selected GCMs showed climate shifting in 3.4 to 12.6% of the total area of SEA for different SSPs. The highest geographical shift in climate was projected in the north, from dry winter and hot summer (Cwa) to tropical with dry winter (Aw), followed by Aw to tropical monsoon (Am) in the north and south, and tropical without dry season (Af) to Am in the middle and southwest of SEA. An increase in minimum temperature was the key to climate shifting from Cwa to Aw in the north, while increased rainfall was a reason for Aw to Am transition in the north and south. Overall, climatic shifting was higher for high emission scenarios. The maps of future climate zones generated in this study can help to identify the hotspots of ecologically vulnerable areas in SEA due to climate change.
... The RF algorithm, which is fast and load resistant, was introduced by Brierman in 2001 and is a community learning algorithm that collects the decisions of several independent multivariate trees. [8] The LR algorithm is employed to reveal the unique effect of one or more independent variables on the result. Due to its ability to predict the outcome and to reveal the unique effect of each data on the result, it is preferred in medical research. ...
Introduction: In the skeletal system, the most dimorphic bones employed for postmortem gender prediction include the bones in the pelvic skeleton. Bone measurements are usually conducted with cadaver bones. Computed tomography (CT) is an increasingly popular method due to its ease of use, reconstruction opportunities, and lower impact of age bias and provides a modern data source. Even when parameters obtained with different or same bones are missing, machine learning (ML) algorithms allow the use of statistical methods to predict gender. This study was carried out in order to obtain high accuracy in estimating gender with the pelvis skeleton by integrating ML algorithms, which are used extensively in the field of engineering, in the field of health. Material and Methods: In the present study, pelvic CT images of 300 healthy individuals (150 females, 150 males) between the ages of 25 and 50 (the mean female age = 40, the mean male age = 37) were transformed into orthogonal images, and landmarks were placed on promontory, iliac crest, sacroiliac joint, anterior superior iliac spine, anterior inferior iliac spine, terminal line, obturator foramen, greater trochanter, lesser trochanter, femoral head, femoral neck, body of femur, ischial tuberosity, acetabulum, and pubic symphysis, and coordinates of these regions were obtained. Four groups were formed based on various angle and length combinations obtained from these coordinates. These four groups were analyzed with ML algorithms such as Logistic Regression, Linear Discriminant Analysis (LDA), Random Forest, Extra Trees Classifier, and ADA Boost Classifier. Results: In the analysis, it was determined that the highest accuracy was 0.96 (sensitivity 0.95, specificity 0.97, Matthew's Correlation Coefficient 0.93) with LDA. Discussion and Conclusion: The use of length and angle measurements obtained from the pelvis showed that the LDA model was effective in estimating gender.
... Fovell and Fovell [32] regionalized the climate in the United States by clustering 344 climate divisions of the National Climatic Data Center (NCDC) dataset. Marston and Ellis [33] and Park et al. [34] applied cluster analysis to gridded climate data to regionalize the climates of the United States and the Korean peninsula, respectively. Hoffman et al. [35] used cluster analysis of the outputs of a general circulation model (GCM) to identify climate regimes and compare different simulation scenarios. ...
Climate zone classification promotes our understanding of the climate and provides a framework for analyzing a range of environmental and socioeconomic data and phenomena. The Köppen–Geiger classification system is the most widely used climate classification scheme. In this study, we compared the climate zones objectively defined using data-driven methods with Köppen–Geiger rule-based classification. Cluster analysis was used to objectively delineate the world’s climatic regions. We applied three clustering algorithms—k-means, ISODATA, and unsupervised random forest classification—to a dataset comprising 10 climatic variables and elevation; we then compared the obtained results with those from the Köppen–Geiger classification system. Results from both the systems were similar for some climatic regions, especially extreme temperature ones such as the tropics, deserts, and polar regions. Data-driven classification identified novel climatic regions that the Köppen–Geiger classification could not. Refinements to the Köppen–Geiger classification, such as precipitation-based subdivisions to existing Köppen–Geiger climate classes like tropical rainforest (Af) and warm summer continental (Dfb), have been suggested based on clustering results. Climatic regions objectively defined by data-driven methods can further the current understanding of climate divisions. On the other hand, rule-based systems, such as the Köppen–Geiger classification, have an advantage in characterizing individual climates. In conclusion, these two approaches can complement each other to form a more objective climate classification system, wherein finer details can be provided by data-driven classification and supported by the intuitive structure of rule-based classification.
... The spatial analysis was considered to be essential in the selection without the experimental design including the replication of the family. Spatial analysis is also considered to be useful in the progeny trials [23,27,29], in particular, under high environmental heterogeneity, for example in mountainous sites in Korea [59]. ...
Background
Larix kaempferi is one of the major timber species in Northeast Asia. Demand for the reforestation of the species is rising in South Korea due to an increase in large timber production and utilization. However, progeny trials for the species have not been explored, making it challenging to foster advanced generations of tree improvement. In the present study, genetic testing and selection for diameter growth were conducted using pedigree reconstruction and phenotypic spatial distribution analysis in a plantation of L. kaempferi . The aim of the present study was to select the superior larch individuals using the pedigree reconstruction and phenotypic spatial distribution to substitute progeny trials. The plantation of seed orchard crops was established in 1990 and one-hundred and eighty-eight trees were selected as the study material. Genetic variation was investigated first to validate its adequacy as breeding material. Genetic testing was carried out using a model considering pedigree information and spatial autoregression of the phenotypes.
Results
The expected heterozygosity of the mother trees and offspring were 0.672 and 0.681 presenting the corresponding level of genetic variation between two groups. The pedigree reconstruction using maternity analysis assigned one to six progenies to ninety-two candidate mothers. The accuracy of genetic testing was exceedingly increased with the animal model considering AR1 ⊗ AR1 structure compared to the animal model only. The estimated genetic variance of the former was 9.086 whereas that of the latter was 4.9E-5 for DBH. The predicted breeding values of the offspring for DBH were ranged from -5.937 cm to 5.655 cm and the estimated heritability of diameter growth was 0.344.
Conclusions
The genetic testing approach based on pedigree reconstruction and phenotypic spatial distribution analysis was considered a useful analytical scheme that could replace or supplement progeny trials.
... The modeling of the present B with RF manages to represent the existing complexity in the climatic limits of each B [36,49]. One way to improve the model is by using the assemblies of various machine learning models, as presented by Bax et al. [19]. ...
The biodiversity present in Peru will be affected by climatic and anthropogenic changes; therefore, understanding these changes will help generate biodiversity conservation policies. This study analyzes the potential distributions of biomes (B) in Peru under the effects of climate change. The evaluation was carried out using the random forest (RF) method, six bioclimatic variables, and digital topography for the classification of current B in Peru. Subsequently, the calibrated RF model was assimilated to three downscaled regional climate models to project future B distributions for the 2035–2065 horizon. We evaluated possible changes in extension and elevation as well as most susceptible B. Our projections show that future scenarios agreed that 82% of current B coverage will remain stable. Approximately 6% of the study area will change its current conditions to conditions of higher humidity; 4.5% will maintain a stable physiognomy, but with an increase in humidity; and finally, 6% will experience a decrease in humidity but maintain its appearance. Additionally, glaciers and swamps are indicated as the most vulnerable B, with probable losses greater than 50% of their current area. These results demonstrate the need to generate public policies for the adaptation and mitigation of climate effects on B at a national scale.
... SVR is a regression version of the support vector machine (SVM) that aims to find an optimal hyperplane to fit the data and predict an unknown pixel. SVR/SVM performs well in modeling small samples and has been widely used in remote sensing [54], [85], [88]- [90]. SVR generally transforms training data from the original feature space into a higher dimension to find an optimum hyperplane [91]. ...
In this study, a new deep learning method was developed to estimate the spatiotemporal properties of the hourly aerosol optical depth (AOD) because existing physical models are limited in their abilities to separate the reflectance between aerosols and the underlying surface over land, accurately and effectively. By incorporating geostationary ocean color imagery (GOCI), multispectral bands were applied to train data-driven models to estimate the high-spatiotemporal-resolution AOD over Northeast Asia. Physical model and traditional machine learning (ML) models (the random forest (RF) and support vector regression (SVR) models) were compared with the deep neural network (DNN) model to evaluate its accuracy, implementing hold-out validation and k-fold cross-validation approaches. In the statistical results of the hold-out validation, the DNN model showed the higher accuracy (root mean square error (RMSE) = 0.112, mean bias error (MBE) = 0.007, and correlation coefficient (R) = 0.863) relative to the traditional SVR (RMSE = 0.123, MBE = -0.010, and R = 0.833) and RF (RMSE = 0.125, MBE = 0.004, and R = 0.825) models. The DNN model also exhibited the best performance for most statistical metrics among the traditional SVR, RF, and selected physical models (except for the correlation coefficients and index of agreement) in the spatial and temporal cross-validation analyses. Although the DNN model was trained using the match-up dataset between the top of atmosphere (TOA) reflectance from GOCI multispectral bands and AErosol RObotic NETwork measurements, it showed high spatial and temporal generalization performance owing to its deeper and more complicated network structure. Hourly GOCI AOD data obtained using a deep learning approach with high accuracy are expected to be useful for the quantification of aerosol contents and monitoring of diurnal variations in the AOD.
... The spatial analysis was considered to be essential in the selection without the experimental design including the replication of the family. Spatial analysis is also considered to be useful in the progeny trials [23,27,29], in particular, under high environmental heterogeneity, for example in mountainous sites in Korea [59]. ...
Background: Larix kaempferi is one of the major timber species in Northeast Asia. Demand for the reforestation of the species is rising in South Korea due to an increase in large timber production and utilization. However, progeny trials for the species have not been explored, making it challenging to foster advanced generations of tree improvement. In the present study, genetic testing and selection for diameter growth were conducted using pedigree reconstruction and phenotypic spatial distribution analysis in a plantation of L. kaempferi. The aim of the present study was to select the superior larch individuals using the pedigree reconstruction and phenotypic spatial distribution to substitute progeny trials. The plantation of seed orchard crops was established in 1990 and one-hundred and eighty-eight trees were selected as the study material. Genetic variation was investigated first to validate its adequacy as breeding material. Genetic testing was carried out using a model considering pedigree information and spatial autoregression of the phenotypes. The major environmental effects on growth were assessed to understand the site characteristics where the breeding materials were located.
Results: The expected heterozygosity of the mother trees and offspring were 0.672 and 0.681 presenting the corresponding level of genetic variation between two groups. The pedigree reconstruction using maternity analysis assigned one to six progenies to ninety-two candidate mothers. The accuracy of genetic testing was exceedingly increased with the animal model considering AR1⊗AR1 structure compared to the animal model only. The estimated genetic variance of the former was 9.086 whereas that of the latter was 4.9E-5. The predicted breeding values of the offspring were ranged from -5.937 to 5.655 and the estimated heritability of diameter growth was 0.344. Shifts in the effects of the factors were detected using geographically weighted regression analysis, which provided information on the post-sectioning of the plantation.
Conclusions: The genetic testing approach based on pedigree reconstruction and phenotypic spatial distribution analysis was considered a useful analytical scheme that could replace or supplement progeny trials. Subdivision of the plantation as blocks of the progeny testing was accomplished a posteriori based on the changes of the environmental effects.
... EAR-surface relative humidity (RHns), a ratio of existing humidity to the potential capacity of saturation vapor pressures under various air temperature (Ta) [1], directly influences terrestrial ecosystems. RHns has been used as a crucial factor for a range of terrestrial and atmospheric research fields, including climatic modeling [2], meteorological factor estimations [3], aerosol estimation [4], energy balance modeling [5]- [7], drought monitoring [8], [9], vegetation productivity estimations [9], leaf wetness estimations [11], [12], climatic zone classifications [13], [14], and heat index calculations [15]. RHns data are generally obtained using radiosonde [16] and automated surface observing systems (ASOS), which are point-based, and thus spatially discontinuous. ...
Near-surface relative humidity (RHns) is an essential meteorological parameter for water, carbon, and climate studies. However, spatially continuous RHns estimation is difficult due to the spatial discontinuity of in-situ observations and the cloud contamination of satellite-based data. This study proposed machine learning-based models to estimate spatially continuous daily RHns at 1 km resolution over Japan and South Korea under all sky conditions and examined the spatiotemporal patterns of RHns. All sky estimation of RHns using machine learning has been rarely conducted, and it can be an alternative to the currently available RHns data mostly from numerical models, which have relatively low spatial resolution. We combined two schemes for clear sky conditions (scheme A, which uses satellite and reanalysis data) and cloudy sky conditions (scheme B, which uses reanalysis data solely). The relatively small numbers of data in extremely low and high RHns conditions (i.e., < 30% or >70%, respectively) were augmented by applying an oversampling method to avoid biased training. The machine learning models based on random forest and XGBoost were trained and validated using 94 in-situ observation sites from meteorological administrations of both countries from 2012 to 2017. The results showed that XGBoost produced slightly better performance than random forest, and the spatially continuous RHns model combined based on XGBoost yielded the coefficient of determination of 0.72 and a root mean square error of 10.61%. Spatiotemporal patterns of the estimated RHns agreed with in-situ observations reflecting the effect of topography on RHns.
... A supervised classification with Mahalanobis distance was used to classify climate regions in China based on the data collected from 172 stations between 1984 and 2013 [34]. One study reported delineation of high resolution climate regions in Korean peninsula using the ANN, random forest, k-nearest neighbor, logistic regression, and SVM supervised learnings [35]. Both unsupervised and supervised learnings were adopted to delineate homogeneous climatic regions in Pakistan. ...
This study extracted 16 climatic data variables including annual temperature, freeze thaw, precipitation, and snowfall conditions from the Long-term Pavement Performance (LTPP) program database to evaluate the climatic regionalization for pavement infrastructure. The effect and significance of climate change were firstly evaluated using time as the only predictor and t-test. It was found that both the temperature and humidity increased in most States. Around one third of the 800 weather stations record variation of freeze and precipitation classifications and a few of them show significant change of classifications over time based on the results of logistic regression analyses. Three unsupervised machine learning including Principle Component Analysis (PCA), factor analysis and cluster analysis were conducted to identify the main component and common factors for climatic variables, and then to classify datasets into different groups. Then, two supervised machine learning methods including Fisher’s discriminant analysis and Artificial Neural Networks (ANN) were adopted to predict the climatic regions based on climatic data. Results of PCA and factor analysis show that temperature and humidity are the first two principle components and common factors, accounting for 71.6% of the variance. The 4-means clusters include wet no freeze, dry no freeze, dry freeze and snow freeze. The best k-mean clustering suggested 9 clusters with more temperature clusters. Both the Fisher’s linear discriminant analysis and ANN can effectively predict climatic regions with multiple climatic variables. ANN performs better with higher R square and low misclassification rate, especially for those with more layers and nodes.
... Moreover, extreme temperature and uncharacteristic rainfall patterns would not allow the species to prosper for long periods of dry spells (Fig. 1). These trends were observed worldwide, where temporal shifting of climate was examined over the period from 1950 to 2013 (Park et al. 2019). Importantly, a species distribution model (SDM) study was conducted by incorporating climate change scenarios into the ecological restoration decisionmaking in southern California scrub and shrubland habitats for 44 focal plant taxa. ...
Salvadora oleoides is a keystone and economically important species in the desert biome of the Indian subcontinent. However, species decline has been observed during field surveys (2016–2019) conducted in the Indian states of Punjab, Haryana, Rajasthan and Gujarat. For species distribution mapping, geospatial data of 683 trees were recorded, out of which 70.28% were used for training and the rest to validate the MaxEnt model. The statistically significant AUC value ranged from 0.92 ± 0.02 (LGM) to 0.93 ± 0.01 (RCP 2.6_70) with an average of 0.92 ± 0.00. The bioclimatic variables, namely precipitation of warmest quarter (Bio 18), annual precipitation (Bio 12), altitude (Alt), precipitation of wettest month (Bio 13), precipitation of coldest quarter (Bio 19) and maximum temperature of warmest month (Bio 5), contributed significantly for predicting the species distribution, which ranged from 60.3% (Last Glacial Maximum, LGM) to 85.5% (Current) with an average of 75.82%. For the climate change scenario (2050s and 2070s), a sharp decline in the species distribution area was observed for all RCPs (when compared with the current estimate of 8638.01 km2), which ranged from 2102.90 (RCP 2.6_70) to 5494.23 km2 (RCP 8.5_70). The model output revealed that the distribution is in accordance with the Köppen-Geiger climate classification system and the geological map of northwestern India. In relation to the geological variables, distribution of S. oleoides occurrence is conditioned to the presence of calcium-rich bedrock, which is used as a mechanism of compensation for the high salinity of desert soils. Overall, the study provides an eco-geo-distribution map and the potential use of MaxEnt in prediction modelling of the species. Furthermore, the research led to insights for suitable conservation and management plans for S. oleoides in arid zones of south Asian sub-continental climatic conditions.
