Assessing the performance of GIS- based machine learning models with different accuracy measures for determining susceptibility to gully erosion

Using algorithmic game theory to improve supervised machine learning: A novel applicability approach in flood susceptibility mapping

This study was carried out with the aim of applying Condorcet and Borda scoring algorithms based on Game Theory (GT) to determine flood points and Flood Susceptibility Mapping (FSM) based on Machine Learning Algorithms (MLA) including Random Forest (RF), Support Vector Regression (SVR), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) in the Cheshmeh-Kileh watershed, Iran. Therefore, first, FS conditioning factors including Aspect (As), Elevation (El), Euclidean distance (Euc), Forest (F), NDVI, Precipitation (P), Plan Curvature (PlC), Profile Curvature (PrC), Residential (Re), Rangeland (Rl), Slope (Sl), Stream Power Index (SPI), Topographic Position Index (TPI), and Topographic Wetness Index (TWI) were quantified in each Sub-Watershed (SW). Based on this, flood and non-flood points were identified based on both GT algorithms. In the following, MLAs including Random Forest (RF), Support Vector Regression (SVR), Support Vector Machines (SVM), and K-Nearest Neighbors (KNN) were used for the distributional mapping of FS. Finally, based on optimal conjunct approaches, FS maps were presented in the study watershed. Based on the results, among the conjunct algorithms in FS classification, RF-Condorcet and RF-Borda models were selected as the most optimal MLA-GT hybrid models. The upstream SWs were highly susceptible. Also, the effectiveness of NDVI and forest conditioning factors in each classification approach was high. The similarity of SW prioritization based on Condorcet algorithm with RF-Condorcet algorithm was about 86.70%. Meanwhile, the degree of similarity in RF-Borda conjunct algorithm was around 73.33%. These results showed that Condorcet algorithm had an optimal classification compared to Borda scoring algorithm.

Identification of influential weather parameters and seasonal drought prediction in Bangladesh using machine learning algorithm

Droughts pose a severe environmental risk in countries that rely heavily on agriculture, resulting in heightened levels of concern regarding food security and livelihood enhancement. Bangladesh is highly susceptible to environmental hazards, with droughts further exacerbating the precarious situation for its 170 million inhabitants. Therefore, we are endeavouring to highlight the identification of the relative importance of climatic attributes and the estimation of the seasonal intensity and frequency of droughts in Bangladesh. With a period of forty years (1981-2020) of weather data, sophisticated machine learning (ML) methods were employed to classify 35 agroclimatic regions into dry or wet conditions using nine weather parameters, as determined by the Standardized Precipitation Evapotranspiration Index (SPEI). Out of 24 ML algorithms, the four best ML methods, ranger, bagEarth, support vector machine, and random forest (RF) have been identified for the prediction of multi-scale drought indices. The RF classifier and the Boruta algorithms shows that water balance, precipitation, maximum and minimum temperature have a higher influence on drought intensity and occurrence across Bangladesh. The trend of spatio-temporal analysis indicates, drought intensity has decreased over time, but return time has increased. There was significant variation in changing the spatial nature of drought intensity. Spatially, the drought intensity shifted from the northern to central and southern zones of Bangladesh, which had an adverse impact on crop production and the livelihood of rural and urban households. So, this precise study has important implications for the understanding of drought prediction and how to best mitigate its impacts. Additionally, the study emphasizes the need for better collaboration between relevant stakeholders, such as policymakers, researchers, communities, and local actors, to develop effective adaptation strategies and increase monitoring of weather conditions for the meticulous management of droughts in Bangladesh.

Digital exploration of selected heavy metals using Random Forest and a set of environmental covariates at the watershed scale

The current study was established for predicting some selected heavy metals (HMs) including Zn, Mn, Fe, Co, Cr, Ni, and Cu, by applying random forest (RF) and a set of environmental covariates at watershed scale. The objectives were to find out the most effective combination of variables and controlling factors on the variability of HMs in a semiarid watershed in central Iran. One hundred locations were selected in the given watershed in the hypercube manner and soil samples from a surface 0-20 cm depth and concentration of HMs and some soil properties were measured in the laboratory. Three scenarios of input variables were defined for HMs prediction. The results revealed that the first scenario (remote sensing + topographic attributes) explained about 27-34% of the variability in HMs. Inclusion of a thematic map to the scenario I, improved the prediction accuracy for all HMs. Scenario III (remote sensing data+ topographic attributes + soil properties) was the most efficient scenario for prediction of HMs with R² values ranging from 0.32 for Cu to 0.42 for Fe. Similarly, the lowest nRMSE was found for all HMs in scenario III, ranging from 0.271 for Fe to 0.351 for Cu. Among the soil properties, clay content and magnetic susceptibility were the most important variables, and also some remote sensing data (Carbonate index, Soil adjusted vegetation index, Band2, and Band7) and topographic attributes (mainly control soil redistribution along the landscape) were the most efficient variables for estimating HMs. We concluded that the RF model with a combination of remote sensing data, topographic attributes, and assisting of thematic maps such as land use in the studied watershed could reliably predict HMs content.

Optimization of tamoxifen solubility in carbon dioxide supercritical fluid and investigating other molecular targets using advanced artificial intelligence models

Particle size, shape and morphology can be considered as the most significant functional parameters, their effects on increasing the performance of oral solid dosage formulation are indisputable. Supercritical Carbon dioxide fluid (SCCO₂) technology is an effective approach to control the above-mentioned parameters in oral solid dosage formulation. In this study, drug solubility measuring is investigated based on artificial intelligence model using carbon dioxide as a common supercritical solvent, at different pressure and temperature, 120-400 bar, 308-338 K. The results indicate that pressure has a strong effect on drug solubility. In this investigation, Decision Tree (DT), Adaptive Boosted Decision Trees (ADA-DT), and Nu-SVR regression models are used for the first time as a novel model on the available data, which have two inputs, including pressure, X1 = P(bar) and temperature, X2 = T(K). Also, output is Y = solubility. With an R-squared score, DT, ADA-DT, and Nu-SVR showed results of 0.836, 0.921, and 0.813. Also, in terms of MAE, they showed error rates of 4.30E-06, 1.95E-06, and 3.45E-06. Another metric is RMSE, in which DT, ADA-DT, and Nu-SVR showed error rates of 4.96E-06, 2.34E-06, and 5.26E-06, respectively. Due to the analysis outputs, ADA-DT selected as the best and novel model and the find optimal outputs can be shown via vector: (x1 = 309, x2 = 317.39, Y1 = 7.03e-05).

Mapping of groundwater productivity potential with machine learning algorithms: A case study in the provincial capital of Baluchistan, Pakistan

Although groundwater (GW) potential zoning can be beneficial for water management, it is currently lacking in several places around the world, including Pakistan's Quetta Valley. Due to ever increasing population growth and industrial development, GW is being used indiscriminately all over the world. Recognizing the importance of GW potential for sustainable growth, this study used to 16 GW drive factors to evaluate their effectiveness by using six machine learning algorithms (MLA's) that include artificial neural networks (ANN), random forest (RF), support vector machine (SVM), K- Nearest Neighbor (KNN), Naïve Bayes (NB) and Extreme Gradient Boosting (XGBoost). The GW yield data were collected and divided into 70% for training and 30% for validation. The training data of GW yields were integrated into the MLA's along with the GW driver variables and the projected results were checked using the Receiver Operating Characteristic (ROC) curve and the validation data. Out of six ML algorithms, ROC curve showed that the XGBoost, RF and ANN models performed well with 98.3%, 96.8% and 93.5% accuracy respectively. In addition, the accuracy of the models was evaluated using the mean absolute error (MAE), root mean square error (RMSE), F-score and correlation-coefficient. Hydro-chemical data were evaluated, and the water quality index (WQI) was also calculated. The final GW productivity potential (GWPP) maps were created using the MLA's output and WQI as they identify the different classification zones that can be used by the government and other agenciesto locate new GW wells and provide a basis for water management in rocky terrain.

Forecasting the Risk Factor of Frontier Markets: A Novel Stacking Ensemble of Neural Network Approach

Forecasting the risk factor of the financial frontier markets has always been a very challenging task. Unlike an emerging market, a frontier market has a missing parameter named “volatility”, which indicates the market’s risk and as a result of the absence of this missing parameter and the lack of proper prediction, it has almost become difficult for direct customers to invest money in frontier markets. However, the noises, seasonality, random spikes and trends of the time-series datasets make it even more complicated to predict stock prices with high accuracy. In this work, we have developed a novel stacking ensemble of the neural network model that performs best on multiple data patterns. We have compared our model’s performance with the performance results obtained by using some traditional machine learning ensemble models such as Random Forest, AdaBoost, Gradient Boosting Machine and Stacking Ensemble, along with some traditional deep learning models such as Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term (BiLSTM). We have calculated the missing parameter named “volatility” using stock price (Close price) for 20 different companies of the frontier market and then made predictions using the aforementioned machine learning ensemble models, deep learning models and our proposed stacking ensemble of the neural network model. The statistical evaluation metrics RMSE and MAE have been used to evaluate the performance of the models. It has been found that our proposed stacking ensemble neural network model outperforms all other traditional machine learning and deep learning models which have been used for comparison in this paper. The lowest RMSE and MAE values we have received using our proposed model are 0.3626 and 0.3682 percent, respectively, and the highest RMSE and MAE values are 2.5696 and 2.444 percent, respectively. The traditional ensemble learning models give the highest RMSE and MAE error rate of 20.4852 and 20.4260 percent, while the deep learning models give 15.2332 and 15.1668 percent, respectively, which clearly states that our proposed model provides a very low error value compared with the traditional models.

Identification of Soil Properties Associated with the Incidence of Banana Wilt Using Supervised Methods

Over the last few decades, a growing incidence of Banana Wilt (BW) has been detected in the banana-producing areas of the central zone of Venezuela. This disease is thought to be caused by a fungal−bacterial complex, coupled with the influence of specific soil properties. However, until now, there was no consensus on the soil characteristics associated with a high incidence of BW. The objective of this study was to identify the soil properties potentially associated with BW incidence, using supervised methods. The soil samples associated with banana plant lots in Venezuela, showing low (n = 29) and high (n = 49) incidence of BW, were collected during two consecutive years (2016 and 2017). On those soils, sixteen soil variables, including the percentage of sand, silt and clay, pH, electrical conductivity, organic matter, available contents of K, Na, Mg, Ca, Mn, Fe, Zn, Cu, S and P, were determined. The Wilcoxon test identified the occurrence of significant differences in the soil variables between the two groups of BW incidence. In addition, Orthogonal Least Squares Discriminant Analysis (OPLS-DA) and the Random Forest (RF) algorithm was applied to find soil variables capable of distinguishing banana lots showing high or low BW incidence. The OPLS-DA model showed a proper fitting of the data (R2Y: 0.61, p value < 0.01), and exhibited good predictive power (Q2: 0.50, p value < 0.01). The analysis of the Receiver Operating Characteristics (ROC) curves by RF revealed that the combination of Zn, Fe, Ca, K, Mn and Clay was able to accurately differentiate 84.1% of the banana lots with a sensitivity of 89.80% and a specificity of 72.40%. So far, this is the first study that identifies these six soil variables as possible new indicators associated with BW incidence in soils of lacustrine origin in Venezuela.

Hybrid Machine Learning Approach for Gully Erosion Mapping Susceptibility at a Watershed Scale

Gully erosion is a serious threat to the state of ecosystems all around the world. As a result, safeguarding the soil for our own benefit and from our own actions is a must for guaranteeing the long-term viability of a variety of ecosystem services. As a result, developing gully erosion susceptibility maps (GESM) is both suggested and necessary. In this study, we compared the effectiveness of three hybrid machine learning (ML) algorithms with the bivariate statistical index frequency ratio (FR), named random forest-frequency ratio (RF-FR), support vector machine-frequency ratio (SVM-FR), and naïve Bayes-frequency ratio (NB-FR), in mapping gully erosion in the GHISS watershed in the northern part of Morocco. The models were implemented based on the inventory mapping of a total number of 178 gully erosion points randomly divided into 2 groups (70% of points were used for training the models and 30% of points were used for the validation process), and 12 conditioning variables (i.e., elevation, slope, aspect, plane curvature, topographic moisture index (TWI), stream power index (SPI), precipitation, distance to road, distance to stream, drainage density, land use, and lithology). Using the equal interval reclassification method, the spatial distribution of gully erosion was categorized into five different classes, including very high, high, moderate, low, and very low. Our results showed that the very high susceptibility classes derived using RF-FR, SVM-FR, and NB-FR models covered 25.98%, 22.62%, and 27.10% of the total area, respectively. The area under the receiver (AUC) operating characteristic curve, precision, and accuracy were employed to evaluate the performance of these models. Based on the receiver operating characteristic (ROC), the results showed that the RF-FR achieved the best performance (AUC = 0.91), followed by SVM-FR (AUC = 0.87), and then NB-FR (AUC = 0.82), respectively. Our contribution, in line with the Sustainable Development Goals (SDGs), plays a crucial role for understanding and identifying the issue of “where and why” gully erosion occurs, and hence it can serve as a first pathway to reducing gully erosion in this particular area.

Mapping Gully Erosion Variability and Susceptibility Using Remote Sensing, Multivariate Statistical Analysis, and Machine Learning in South Mato Grosso, Brazil

In Brazil, the development of gullies constitutes widespread land degradation, especially in the state of South Mato Grosso, where fighting against this degradation has become a priority for policy makers. However, the environmental and anthropogenic factors that promote gully development are multiple, interact, and present a complexity that can vary by locality, making their prediction difficult. In this framework, a database was constructed for the Rio Ivinhema basin in the southern part of the state, including 400 georeferenced gullies and 13 geo-environmental descriptors. Multivariate statistical analysis was performed using principal component analysis (PCA) to identify the processes controlling the variability in gully development. Susceptibility maps were created through four machine learning models: multivariate discriminant analysis (MDA), logistic regression (LR), classification and regression tree (CART), and random forest (RF). The predictive performance of the models was analyzed by five evaluation indices: accuracy (ACC), sensitivity (SST), specificity (SPF), precision (PRC), and Receiver Operating Characteristic curve (ROC curve). The results show the existence of two major processes controlling gully erosion. The first is the surface runoff process, which is related to conditions of slightly higher relief and higher rainfall. The second also reflects high surface runoff conditions, but rather related to high drainage density and downslope, close to the river network. Human activity represented by peri-urban areas, construction of small earthen dams, and extensive rotational farming contribute significantly to gully formation. The four machine learning models yielded fairly similar results and validated susceptibility maps (ROC curve > 0.8). However, we noted a better performance of the random forest (RF) model (86% and 89.8% for training and test, respectively, with an ROC curve value of 0.931). The evaluation of the contribution of the parameters shows that susceptibility to gully erosion is not governed primarily by a single factor, but rather by the interconnection between different factors, mainly elevation, geology, precipitation, and land use.

Assessment of agricultural prospects in relation to land use change and population pressure on a spatiotemporal framework

The urbanisation process moves quickly in emerging nations like India and Bangladesh, transforming natural landscapes into unsustainable landscapes. Consequently, growing development has had a significant impact on agricultural land as a natural environment. Moreover, there is a scarcity of research on fragmentation probability modelling in the extant literature. Thus, by combining random forest (RF) and bagging with the datasets which are multi-temporal in a GIS framework, the probability of fragmentation of LULC at Jangipur subdivision in India and Bangladesh can be modelled. Parallelepiped, Mohalnobis distance, support vector machines (SVM), spectral angle mapper (SAM), and artificial neural networks (ANN) classifiers were used for LULC classification, where SVM (Kappa coefficient: 0.87) surpassed other classifiers. The LULC maps for 1990, 2000, 2010, and 2020 were created using the best classifier (SVM). During this time, the built-up area grew from 23.769 to 158.125 km². Then, using an ANN-based cellular automata model, the future LULC map for 2030 was predicted (CA-ANN). In 2030, the built-up area would be 201.58 km². Then the matrices of class and landscape were taken out of the LULC maps utilising FRAGSTAT software and included the patch number (NP), largest patch index (LPI), edge density (ED), contagion index (percentage) (CONTAG), perimeter and area (P/A), aggregation index (AI), landscape percentage (PLAND), the area of class (CA), patch density (PD), edge in total (TE), total core area (TCA), and largest shape index (LSI). The validation results revealed that bagging (0.915 = AUC) and RF (0.874 = AUC) are capable of assessing fragmentation probability, with the bagging model having the greatest precision level of the two. Almost 20% of the total LULC was in a high and very high zone of fragmentation vulnerability, necessitating the use of direct measures to safeguard it. As a result, adequate LULC management is required.

How far spatial resolution affects the ensemble machine learning based flood susceptibility prediction in data sparse region

Although the effect of digital elevation model (DEM) and its spatial resolution on flood simulation modeling has been well studied, the effect of coarse and finer resolution image and DEM data on machine learning ensemble flood susceptibility prediction has not been investigated, particularly in data sparse conditions. The present work was, therefore, to investigate the performance of the resolution effects, such as coarse (Landsat and SRTM) and high (Sentinel-2 and ALOS PALSAR) resolution data on the flood susceptible models. Another motive of this study was to construct very high precision and robust flood susceptible models using standalone and ensemble machine learning algorithms. In the present study, fifteen flood conditioning parameters were generated from both coarse and high resolution datasets. Then, the ANN-multilayer perceptron (MLP), random forest (RF), bagging (B)-MLP, B-gaussian processes (B-GP) and B-SMOreg algorithms were used to integrate the flood conditioning parameters for generating the flood susceptible models. Furthermore, the influence of flood conditioning parameters on the modelling of flood susceptibility was investigated by proposing an ROC based sensitivity analysis. The validation of flood susceptibility models is also another challenge. In the present study, we proposed an index of flood vulnerability model to validate flood susceptibility models along with conventional statistical techniques, such as the ROC curve. Results showed that the coarse resolution based flood susceptibility MLP model has appeared as the best model (area under curve: 0.94) and it has predicted 11.65 % of the area as very high flood susceptible zones (FSz), followed by RF, B-MLP, B-GP, and B-SMOreg. Similarly, the high resolution based flood susceptibility model using MLP has predicted 19.34 % of areas as very high flood susceptible zones, followed by RF (14.32 %),B-MLP (14.88 %), B-GP, and B-SMOreg. On the other hand, ROC based sensitivity analysis showed that elevation influences flood susceptibility largely for coarse and high resolution based models, followed by drainage densityand flow accumulation. In addition, the accuracy assessment using the IFV model revealed that the MLP model outperformed all other models in the case of a high resolution imageThe coarser resolution image's performance level is acceptable but quite low. So, the study recommended the use of high resolution images for developing a machine learning algorithm based flood susceptibility model. As the study has clearly identified the areas of higher flood susceptibility and the dominant influencing factors for flooding, this could be used as a good database for flood management.

Spatial modeling of gully head erosion on the Loess Plateau using a certainty factor and random forest model

Gully head erosion significantly contributes to land degradation, and affects gully dynamics on the Loess Plateau of China. Modeling with a gully head erosion susceptibility map (GHEM) is an essential step toward appropriate mitigation measures. This study evaluates the effectiveness of two varieties of advanced data mining techniques-a bivariate statistical model (certainty factor (CF)) and a machine learning model (random forest (RF)) for the accurate mapping of gully head erosion susceptibility taking the Dongzhi Loess Tableland of China as an example at a regional scale. A database comprising 11 geographic and environmental parameters was extracted with 415 spatially distributed gully heads, of which 70% (291) were selected for model training and 30% (124) were used for validation. An accuracy evaluation using the area under the curve (AUC) value revealed that the CF model was 84.1% accurate, while the AUC value of the RF model map was 88.8% accurate. According to the RF method used to assess the relative significance of predictor variables, the most significant factors influencing the spatial distribution of the GHEM were the slope angle, slope aspect, topographic wetness index, and slope length. The GHEM can ultimately aid in decision making with respect to soil planning and management and sustainable development of the study area, which can be applied to other similar loess regions.

Machine learning algorithm-based risk assessment of riparian wetlands in Padma River Basin of Northwest Bangladesh

Wetland risk assessment is a global concern especially in developing countries like Bangladesh. The present study explored the spatiotemporal dynamics of wetlands, prediction of wetland risk assessment. The wetland risk assessment was predicted based on ten selected parameters, such as fragmentation probability, distance to road, and settlement. We used M5P, random forest (RF), reduced error pruning tree (REPTree), and support vector machine (SVM) machine learning techniques for wetland risk assessment. The results showed that wetland areas at present are declining less than one-third of those in 1988 due to the construction of the dam at Farakka, which is situated at the upstream of the Padma River. The distance to the river and built-up area are the two most contributing drivers influencing the wetland risk assessment based on information gain ratio (InGR). The prediction results of machine learning models showed 64.48% of area by M5P, 61.75% of area by RF, 62.18% of area by REPTree, and 55.74% of area by SVM have been predicted as the high and very high-risk zones. The results of accuracy assessment showed that the RF outperformed than other models (area under curve: 0.83), followed by the SVM, M5P, and REPTree. Degradation of wetlands explored in this study demonstrated the negative effects on biodiversity. Therefore, to conserve and protect the wetlands, continuous monitoring of wetlands using high resolution satellite images, feeding with the ecological flow, confining built up area and agricultural expansion towards wetlands, and new wetland creation is essential for wetland management.

A Study on Prediction Model of Gully Volume Based on Morphological Features in the JINSHA Dry-Hot Valley Region of Southwest China

Gully erosion is well-developed in the Jinsha dry-hot valley region, which has caused serious soil losses. Gully volume is regarded as an effective indicator that can reflect the development intensity of gully erosion, and the evolutionary processes of gullies can be predicted based on the dynamic variation in gully volume. Establishing an effective prediction model of gully volume is essential to determine gully volume accurately and conveniently. Therefore, in this work, an empirical prediction model of gully volume was constructed and verified based on detailed morphological features acquired by elaborate field investigations and measurements in 134 gullies. The results showed the mean value of gully length, width, depth, cross-section area, volume, and vertical gradient decreased with the weakness of the activity degree of the gully, although the decrease in processes of these parameters had some differences. Moreover, a series of empirical prediction models of gully volume was constructed, and gully length was demonstrated to be a better predictor than other morphological features. Lastly, the effectiveness test showed the model of V = aL^b was the most effective in predicting gully volume among the different models established in this study. Our results provide a useful approach to predict gully volume in dry-hot valley regions.

Uncertainties Analysis of Collapse Susceptibility Prediction Based on Remote Sensing and GIS: Influences of Different Data-Based Models and Connections between Collapses and Environmental Factors

To study the uncertainties of a collapse susceptibility prediction (CSP) under the coupled conditions of different data-based models and different connection methods between collapses and environmental factors, An’yuan County in China with 108 collapses is used as the study case, and 11 environmental factors are acquired by data analysis of Landsat TM 8 and high-resolution aerial images, using a hydrological and topographical spatial analysis of Digital Elevation Modeling in ArcGIS 10.2 software. Accordingly, 20 coupled conditions are proposed for CSP with five different connection methods (Probability Statistics (PSs), Frequency Ratio (FR), Information Value (IV), Index of Entropy (IOE) and Weight of Evidence (WOE)) and four data-based models (Analytic Hierarchy Process (AHP), Multiple Linear Regression (MLR), C5.0 Decision Tree (C5.0 DT) and Random Forest (RF)). Finally, the CSP uncertainties are assessed using the area under receiver operation curve (AUC), mean value, standard deviation and significance test, respectively. Results show that: (1) the WOE-based models have the highest AUC accuracy, lowest mean values and average rank, and a relatively large standard deviation; the mean values and average rank of all the FR-, IV- and IOE-based models are relatively large with low standard deviations; meanwhile, the AUC accuracies of FR-, IV- and IOE-based models are consistent but higher than those of the PS-based model. Hence, the WOE exhibits a greater spatial correlation performance than the other four methods. (2) Among all the data-based models, the RF model has the highest AUC accuracy, lowest mean value and mean rank, and a relatively large standard deviation. The CSP performance of the RF model is followed by the C5.0 DT, MLR and AHP models, respectively. (3) Under the coupled conditions, the WOE-RF model has the highest AUC accuracy, a relatively low mean value and average rank, and a high standard deviation. The PS-AHP model is opposite to the WOE-RF model. (4) In addition, the coupled models show slightly better CSP performances than those of the single data-based models not considering connect methods. The CSP performance of the other models falls somewhere in between. It is concluded that the WOE-RF is the most appropriate coupled condition for CSP than the other models.

A Review on Assessing and Mapping Soil Erosion Hazard Using Geo-Informatics Technology for Farming System Management

Soil erosion is a severe threat to food production systems globally. Food production in farming systems decreases with increasing soil erosion hazards. This review article focuses on geo-informatics applications for identifying, assessing and predicting erosion hazards for sustainable farming system development. Several researchers have used a variety of quantitative and qualitative methods with erosion models, integrating geo-informatics techniques for spatial interpretations to address soil erosion and land degradation issues. The review identified different geo-informatics methods of erosion hazard assessment and highlighted some research gaps that can provide a basis to develop appropriate novel methodologies for future studies. It was found that rainfall variation and land-use changes significantly contribute to soil erosion hazards. There is a need for more research on the spatial and temporal pattern of water erosion with rainfall variation, innovative techniques and strategies for landscape evaluation to improve the environmental conditions in a sustainable manner. Examining water erosion and predicting erosion hazards for future climate scenarios could also be approached with emerging algorithms in geo-informatics and spatiotemporal analysis at higher spatial resolutions. Further, geo-informatics can be applied with real-time data for continuous monitoring and evaluation of erosion hazards to risk reduction and prevent the damages in farming systems.

Assessing, mapping, and optimizing the locations of sediment control check dams construction

Check dams are considered to be one of the most effective measures for conservation of the soil and water resources. However, identifying the most suitable sites for the installation of check dams remain quite demanding. This research investigates and compares five machine learning algorithms (MLAs) - boosted regression trees (BRT), multivariate adaptive regression spline (MARS), mixture discriminant analysis (MDA), random forest (RF), and support vector machine (SVM) - for generating check-dam site-suitability maps (CDSSMs) and assessing them in Firuzkuh County, Iran. First, the locations of 475 existing check dams were monitored, registered, and divided into calibration (70%) and testing datasets (30%) for training and validation of the models. Fourteen check-dam conditioning factors (CDCFs) were selected and checked for multicollinearity. The relative importance of the CDCFs assessed using the elastic net (ENET) algorithm. Results demonstrated that distance from river (DFR) and drainage density (DD) to be the most significant factors for mapping the suitable sites for the erection of check dams. This research revealed that all of five MLAs had excellent accuracy for predicting the check-dam site-suitability with high AUC values: RF (0.966), SVM (0.878), MARS (0.878), MDA (0.844), and BRT (0.843). The most accurate model (RF) showed that 16.95%, 35.55%, 31.08%, and 16.42% of study area comes under low, moderate, high, and very high suitability classes. The outcome achieved by this research will be helpful to sustainability planners and managers in constructing check dams at suitable sites for better conservation of soil and water resources.

A Novel Model Integrating Deep Learning for Land Use/Cover Change Reconstruction: A Case Study of Zhenlai County, Northeast China

In recent decades, land use/cover change (LUCC) due to urbanization, deforestation, and desertification has dramatically increased, which changes the global landscape and increases the pressure on the environment. LUCC not only accelerates global warming but also causes widespread and irreversible loss of biodiversity. Therefore, LUCC reconstruction has important scientific and practical value for studying environmental and ecological changes. The commonly used LUCC reconstruction models can no longer meet the growing demand for uniform and high-resolution LUCC reconstructions. In view of this circumstance, a deep learning-integrated LUCC reconstruction model (DLURM) was developed in this study. Zhenlai County of Jilin Province (1986–2013) was taken as an example to verify the proposed DLURM. The average accuracy of the DLURM reached 92.87% (compared with the results of manual interpretation). Compared with the results of traditional models, the DLURM had significantly better accuracy and robustness. In addition, the simulation results generated by the DLURM could match the actual land use (LU) map better than those generated by other models.

Novel Ensemble of Multivariate Adaptive Regression Spline with Spatial Logistic Regression and Boosted Regression Tree for Gully Erosion Susceptibility

The extreme form of land degradation through different forms of erosion is one of the major problems in sub-tropical monsoon dominated region. The formation and development of gullies is the dominant form or active process of erosion in this region. So, identification of erosion prone regions is necessary for escaping this type of situation and maintaining the correspondence between different spheres of the environment. The major goal of this study is to evaluate the gully erosion susceptibility in the rugged topography of the Hinglo River Basin of eastern India, which ultimately contributes to sustainable land management practices. Due to the nature of data instability, the weakness of the classifier andthe ability to handle data, the accuracy of a single method is not very high. Thus, in this study, a novel resampling algorithm was considered to increase the robustness of the classifier and its accuracy. Gully erosion susceptibility maps have been prepared using boosted regression trees (BRT), multivariate adaptive regression spline (MARS) and spatial logistic regression (SLR) with proposed resampling techniques. The re-sampling algorithm was able to increase the efficiency of all predicted models by improving the nature of the classifier. Each variable in the gully inventory map was randomly allocated with 5-fold cross validation, 10-fold cross validation, bootstrap and optimism bootstrap, while each consisted of 30% of the database. The ensemble model was tested using 70% and validated with the other 30% using the K-fold cross validation (CV) method to evaluate the influence of the random selection of training and validation database. Here, all resampling methods are associated with higher accuracy, but SLR bootstrap optimism is more optimal than any other methods according to its robust nature. The AUC values of BRT optimism bootstrap, MARS optimism bootstrap and SLR optimism bootstrap are 87.40%, 90.40% and 90.60%, respectively. According to the SLR optimism bootstrap, the 107,771 km2 (27.51%) area of this region is associated with a very high to high susceptible to gully erosion. This potential developmental area of the gully was found primarily in the Hinglo River Basin, where lateral exposure was mainly observed with scarce vegetation. The outcome of this work can help policy-makers to implement remedial measures to minimize the damage caused by erosion of the gully.

Soil Erosion Susceptibility Mapping in Kozetopraghi Catchment, Iran: A Mixed Approach Using Rainfall Simulator and Data Mining Techniques

Soil erosion determines landforms, soil formation and distribution, soil fertility, and land degradation processes. In arid and semiarid ecosystems, soil erosion is a key process to understand, foresee, and prevent desertification. Addressing soil erosion throughout watersheds scales requires basic information to develop soil erosion control strategies and to reduce land degradation. To assess and remediate the non-sustainable soil erosion rates, restoration programs benefit from the knowledge of the spatial distribution of the soil losses to develop maps of soil erosion. This study presents Support Vector Machine (SVM), Random Forest (RF), and adaptive boosting (AdaBoost) data mining models to map soil erosion susceptibility in Kozetopraghi watershed, Iran. A soil erosion inventory map was prepared from field rainfall simulation experiments on 174 randomly selected points along the Kozetopraghi watershed. In previous studies, this map has been prepared using indirect methods such as the Universal Soil Loss Equation to assess soil erosion. Direct field measurements for mapping soil erosion susceptibility have so far not been carried out in our study site in the past. The soil erosion rate data generated by simulated rainfall in 1 m2 plots at rainfall rate of 40 mmh−1 was used to develop the soil erosion map. Of the available data, 70% and 30% were randomly classified to calibrate and validate the models, respectively. As a result, the RF model with the highest area under the curve (AUC) value in a receiver operating characteristics (ROC) curve (0.91), and the lowest mean square error (MSE) value (0.09), has the most concordance and spatial differentiation. Sensitivity analysis by Jackknife and IncNodePurity methods indicates that the slope angle is the most important factor within the soil erosion susceptibility map. The RF susceptibility map showed that the areas located in the center and near the watershed outlet have the most susceptibility to soil erosion. This information can be used to support the development of sustainable restoration plans with more accuracy. Our methodology has been evaluated and can be also applied in other regions.

Seismic Vulnerability Assessment and Mapping of Gyeongju, South Korea Using Frequency Ratio, Decision Tree, and Random Forest

The main purpose of this study was to compare the prediction accuracies of various seismic vulnerability assessment and mapping methods. We applied the frequency ratio (FR), decision tree (DT), and random forest (RF) methods to seismic data for Gyeongju, South Korea. A magnitude 5.8 earthquake occurred in Gyeongju on 12 September 2016. Buildings damaged during the earthquake were used as dependent variables, and 18 sub-indicators related to seismic vulnerability were used as independent variables. Seismic data were used to construct a model for each method, and the models’ results and prediction accuracies were validated using receiver operating characteristic (ROC) curves. The success rates of the FR, DT, and RF models were 0.661, 0.899, and 1.000, and their prediction rates were 0.655, 0.851, and 0.949, respectively. The importance of each indicator was determined, and the peak ground acceleration (PGA) and distance to epicenter were found to have the greatest impact on seismic vulnerability in the DT and RF models. The constructed models were applied to all buildings in Gyeongju to derive prediction values, which were then normalized to between 0 and 1, and then divided into five classes at equal intervals to create seismic vulnerability maps. An analysis of the class distribution of building damage in each of the 23 administrative districts showed that district 15 (Wolseong) was the most vulnerable area and districts 2 (Gangdong), 18 (Yangbuk), and 23 (Yangnam) were the safest areas.

Soil Management Effects on Soil Water Erosion and Runoff in Central Syria—A Comparative Evaluation of General Linear Model and Random Forest Regression

The Mediterranean part of Syria is affected by soil water erosion due to poor land management. Within this context, the main aim of this research was to track soil erosion and runoff after each rainy storm between September 2013 and April 2014 (rainy season), on two slopes with different gradients (4.7%; 10.3%), under three soil cover types (SCTs): bare soil (BS), metal sieve cover (MC), and strip cropping (SC), in Central Syria. Two statistical multivariate models, the general linear model (GLM), and the random forest regression (RFR) were applied to reveal the importance of SCTs. Our results reveal that higher erosion rate, as well as runoff, were recorded in BS followed by MC, and SC. Accordingly, soil cover had a significant effect (p < 0.001) on soil erosion, and no significant difference was detected between MC and SC. Different combinations of slopes and soil cover had no effect on erosion, at least in this experiment. RFR performed better than GLM in predictions. GLM’s median of mean absolute error was 21% worse than RFR. Nonetheless, 25 repetitions of 2-fold cross-validation ensured the highest available prediction accuracy for RFR. In conclusion, we revealed that runoff, rain intensity and soil cover were the most important factors in erosion.

Novel Machine Learning Approaches for Modelling the Gully Erosion Susceptibility

The extreme form of land degradation caused by the formation of gullies is a major challenge for the sustainability of land resources. This problem is more vulnerable in the arid and semi-arid environment and associated damage to agriculture and allied economic activities. Appropriate modeling of such erosion is therefore needed with optimum accuracy for estimating vulnerable regions and taking appropriate initiatives. The Golestan Dam has faced an acute problem of gully erosion over the last decade and has adversely affected society. Here, the artificial neural network (ANN), general linear model (GLM), maximum entropy (MaxEnt), and support vector machine (SVM) machine learning algorithm with 90/10, 80/20, 70/30, 60/40, and 50/50 random partitioning of training and validation samples was selected purposively for estimating the gully erosion susceptibility. The main objective of this work was to predict the susceptible zone with the maximum possible accuracy. For this purpose, random partitioning approaches were implemented. For this purpose, 20 gully erosion conditioning factors were considered for predicting the susceptible areas by considering the multi-collinearity test. The variance inflation factor (VIF) and tolerance (TOL) limit were considered for multi-collinearity assessment for reducing the error of the models and increase the efficiency of the outcome. The ANN with 50/50 random partitioning of the sample is the most optimal model in this analysis. The area under curve (AUC) values of receiver operating characteristics (ROC) in ANN (50/50) for the training and validation data are 0.918 and 0.868, respectively. The importance of the causative factors was estimated with the help of the Jackknife test, which reveals that the most important factor is the topography position index (TPI). Apart from this, the prioritization of all predicted models was estimated taking into account the training and validation data set, which should help future researchers to select models from this perspective. This type of outcome should help planners and local stakeholders to implement appropriate land and water conservation measures.

GIS-Based Machine Learning Algorithms for Gully Erosion Susceptibility Mapping in a Semi-Arid Region of Iran

In the present study, gully erosion susceptibility was evaluated for the area of the Robat Turk Watershed in Iran. The assessment of gully erosion susceptibility was performed using four state-of-the-art data mining techniques: random forest (RF), credal decision trees (CDTree), kernel logistic regression (KLR), and best-first decision tree (BFTree). To the best of our knowledge, the KLR and CDTree algorithms have been rarely applied to gully erosion modeling. In the first step, from the 242 gully erosion locations that were identified, 70% (170 gullies) were selected as the training dataset, and the other 30% (72 gullies) were considered for the result validation process. In the next step, twelve gully erosion conditioning factors, including topographic, geomorphological, environmental, and hydrologic factors, were selected to estimate gully erosion susceptibility. The area under the ROC curve (AUC) was used to estimate the performance of the models. The results revealed that the RF model had the best performance (AUC = 0.893), followed by the KLR (AUC = 0.825), the CDTree (AUC = 0.808), and the BFTree (AUC = 0.789) models. Overall, the RF model performed significantly better than the others, which may support the application of this method to a transferable susceptibility model in other areas. Therefore, we suggest using the RF, KLR, and CDT models for gully erosion susceptibility mapping in other prone areas to assess their reproducibility.

Assessment of the outbreak risk, mapping and infection behavior of COVID-19: Application of the autoregressive integrated-moving average (ARIMA) and polynomial models

Infectious disease outbreaks pose a significant threat to human health worldwide. The outbreak of pandemic coronavirus disease 2019 (COVID-19) has caused a global health emergency. Thus, identification of regions with high risk for COVID-19 outbreak and analyzing the behaviour of the infection is a major priority of the governmental organizations and epidemiologists worldwide. The aims of the present study were to analyze the risk factors of coronavirus outbreak for identifying the areas having high risk of infection and to evaluate the behaviour of infection in Fars Province, Iran. A geographic information system (GIS)-based machine learning algorithm (MLA), support vector machine (SVM), was used for the assessment of the outbreak risk of COVID-19 in Fars Province, Iran whereas the daily observations of infected cases were tested in the-polynomial and the autoregressive integrated moving average (ARIMA) models to examine the patterns of virus infestation in the province and in Iran. The results of the disease outbreak in Iran were compared with the data for Iran and the world. Sixteen effective factors were selected for spatial modelling of outbreak risk. The validation outcome reveals that SVM achieved an AUC value of 0.786 (March 20), 0.799 (March 29), and 86.6 (April 10) that displays a good prediction of outbreak risk change detection. The results of the third-degree polynomial and ARIMA models in the province revealed an increasing trend with an evidence of turning, demonstrating extensive quarantines has been effective. The general trends of virus infestation in Iran and Fars Province were similar, although a more volatile growth of the infected cases is expected in the province. The results of this study might assist better programming COVID-19 disease prevention and control and gaining sorts of predictive capability would have wide-ranging benefits.

Susceptibility Mapping of Soil Water Erosion Using Machine Learning Models

Soil erosion is a serious threat to sustainable agriculture, food production, and environmental security. The advancement of accurate models for soil erosion susceptibility and hazard assessment is of utmost importance for enhancing mitigation policies and laws. This paper proposes novel machine learning (ML) models for the susceptibility mapping of the water erosion of soil. The weighted subspace random forest (WSRF), Gaussian process with a radial basis function kernel (Gaussprradial), and naive Bayes (NB) ML methods were used in the prediction of the soil erosion susceptibility. Data included 227 samples of erosion and non-erosion locations through field surveys to advance models of the spatial distribution using predictive factors. In this study, 19 effective factors of soil erosion were considered. The critical factors were selected using simulated annealing feature selection (SAFS). The critical factors included aspect, curvature, slope length, flow accumulation, rainfall erosivity factor, distance from the stream, drainage density, fault density, normalized difference vegetation index (NDVI), hydrologic soil group, soil texture, and lithology. The dataset cells of samples (70% for training and 30% for testing) were randomly prepared to assess the robustness of the different models. The functional relevance between soil erosion and effective factors was computed using the ML models. The ML models were evaluated using different metrics, including accuracy, the kappa coefficient, and the probability of detection (POD). The accuracies of the WSRF, Gaussprradial, and NB methods were 0.91, 0.88, and 0.85, respectively, for the testing data; 0.82, 0.76, and 0.71, respectively, for the kappa coefficient; and 0.94, 0.94, and 0.94, respectively, for POD. However, the ML models, especially the WSRF, had an acceptable performance regarding producing soil erosion susceptibility maps. Maps produced with the most robust models can be a useful tool for sustainable management, watershed conservation, and the reduction of soil and water loss.

Using machine learning algorithms to map the groundwater recharge potential zones

Groundwater recharge is indispensable for the sustainable management of freshwater resources, especially in the arid regions. Here we address some of the important aspects of groundwater recharge through machine learning algorithms (MLAs). Three MLAs including, SVM, MARS, and RF were validated for higher prediction accuracies in generating groundwater recharge potential maps (GRPMs). Accordingly, soil permeability samples were prepared and are arbitrarily grouped into training (70%) and validation (30%) samples. The GRPMs are generated using sixteen effective factors, such as elevation (denoted using a digital elevation model; DEM), aspect, slope angle, TWI (topographic wetness index), fault density, MRVBF (multiresolution index of valley bottom flatness), rainfall, lithology, land use, drainage density, distance from rivers, distance from faults, annual ETP (evapo-transpiration), minimum temperature, maximum temperature, and rainfall 24-hr. Subsequently, the VI (variables importance) is assessed based on the LASSO algorithm. The GRPMs of three MLAs were validated using the ROC-AUC (receiver operating characteristic-area under curve) and various techniques including true positive rate (TPR), false positive rate (FPR), F-measures, fallout, sensitivity, specificity, true skill statistics (TSS), and corrected classified instances (CCI). Based on the validation, the RF algorithm performed better (AUC = 0.987) than the SVM (AUC = 0.963) and the MARS algorithm (AUC = 0.962). Furthermore, the accuracy of these MLAs are included in excellent class, based on the ROC curve threshold. Our case study shows that the GRPMs are potential guidelines for decision-makers in drafting policies related to the sustainable management of the groundwater resources.

Capability and robustness of novel hybridized models used for drought hazard modeling in southeast Queensland, Australia

Widespread detrimental and long-lasting droughts are having catastrophic impacts around the globe. Researchers, organizations, and policy makers need to work together to obtain precise information, enabling timely and accurate decision making to mitigate drought impacts. In this study, a spatial modeling approach based on an adaptive neuro-fuzzy inference system (ANFIS) and several metaheuristic optimizations (ANFIS-BA, ANFIS-GA, ANFIS-ICA, ANFIS-PSO) was developed to predict the spatial occurrence of drought in a region in southeastern Queensland, Australia. In this approach, data describing the distribution of eight drought-contributing factors were prepared for input into the models to serve as independent variables. Relative departures of rainfall (RDR) and relative departures of soil moisture (RDSM) were analyzed to identify locations where drought conditions have occurred. The set of locations in the study area identified as having experienced drought conditions was randomly divided into two groups, 70% were used for training and 30% for validation. The models employed these data to generate maps that predict the locations that would be expected to experience drought. The prediction accuracy of the model-produced drought maps was scrutinized with two evaluation metrics: area under the receiver operating characteristic curve (AUC) and root mean square error (RMSE). The results demonstrate that the hybridized models (ANFIS-BA (AUC_mean = 83.7%, RMSE_mean = 0.236), ANFIS-GA (AUC_mean = 81.62%, RMSE_mean = 0.247), ANFIS-ICA (AUC_mean = 82.12%, RMSE_mean = 0.247), and ANFIS-PSO (AUC_mean = 81.42%, RMSE_mean = 0.255)) yield better predictive performance than the standalone ANFIS model (AUC_mean = 71.8%, RMSE_mean = 0.344). Furthermore, sensitivity analyses indicated that plant-available water capacity, the percentage of soil comprised of sand, and mean annual precipitation were the most important predictors of drought hazard. The versatility of the new approach for spatial drought modeling and the capacity of ANFIS model hybridization to improve model performance suggests great potential to assist decision makers in their formulations of drought risk, recovery, and response management, and in the development of contingency plans.

Multitemporal Analysis of Gully Erosion in Olive Groves by Means of Digital Elevation Models Obtained with Aerial Photogrammetric and LiDAR Data

Gully erosion is one of the main processes of soil degradation, representing 50%–90% of total erosion at basin scales. Thus, its precise characterization has received growing attention in recent years. Geomatics techniques, mainly photogrammetry and LiDAR, can support the quantitative analysis of gully development. This paper deals with the application of these techniques using aerial photographs and airborne LiDAR data available from public database servers to identify and quantify gully erosion through a long period (1980–2016) in an area of 7.5 km2 in olive groves. Several historical flights (1980, 1996, 2001, 2005, 2009, 2011, 2013 and 2016) were aligned in a common coordinate reference system with the LiDAR point cloud, and then, digital surface models (DSMs) and orthophotographs were obtained. Next, the analysis of the DSM of differences (DoDs) allowed the identification of gullies, the calculation of the affected areas as well as the estimation of height differences and volumes between models. These analyses result in an average depletion of 0.50 m and volume loss of 85000 m3 in the gully area, with some periods (2009–2011 and 2011–2013) showing rates of 10,000–20,000 m3/year (20–40 t/ha*year). The manual edition of DSMs in order to obtain digital elevation models (DTMs) in a detailed sector has facilitated an analysis of the influence of this operation on the erosion calculations, finding that it is not significant except in gully areas with a very steep shape.

Comparative assessment of the flash-flood potential within small mountain catchments using bivariate statistics and their novel hybrid integration with machine learning models

The present study is carried out in the context of the continuous increase, worldwide, of the number of flash-floods phenomena. Also, there is an evident increase of the size of the damages caused by these hazards. Bâsca Chiojdului River Basin is one of the most affected areas in Romania by flash-flood phenomena. Therefore, Flash-Flood Potential Index (FFPI) was defined and calculated across the Bâsca Chiojdului river basin by using one bivariate statistical method (Statistical Index) and its novel ensemble with the following machine learning models: Logistic Regression, Classification and Regression Trees, Multilayer Perceptron, Random Forest and Support Vector Machine and Decision Tree CART. In a first stage, the areas with torrentiality were digitized based on orthophotomaps and field observations. These regions, together with an equal number of non-torrential pixels, were further divided into training surfaces (70%) and validating surfaces (30%). The next step of the analysis consisted of the selection of flash-flood conditioning factors based on the multicollinearity investigation and predictive ability estimation through Information Gain method. Eight factors, from a total of ten flash-floods predictors, were selected in order to be included in the FFPI calculation process. By applying the models represented by Statistical Index and its ensemble with the machine learning algorithms, the weight of each conditioning factor and of each factor class/category in the FFPI equations was established. Once the weight values were derived, the FFPI values across the Bâsca Chiojdului river basin were calculated by overlaying the flash-flood predictors in GIS environment. According to the results obtained, the central part of Bâsca Chiojdului river basin has the highest susceptibility to flash-flood phenomena. Thus, around 30% of the study site has high and very high values of FFPI. The results validation was carried out by applying the Prediction Rate and Success Rate. The methods revealed the fact that the Multilayer Perceptron - Statistical Index (MLP-SI) ensemble has the highest efficiency among the 3 methods.

GIS-Based Gully Erosion Susceptibility Mapping: A Comparison of Computational Ensemble Data Mining Models

Gully erosion destroys agricultural and domestic grazing land in many countries, especially those with arid and semi-arid climates and easily eroded rocks and soils. It also generates large amounts of sediment that can adversely impact downstream river channels. The main objective of this research is to accurately detect and predict areas prone to gully erosion. In this paper, we couple hybrid models of a commonly used base classifier (reduced pruning error tree, REPTree) with AdaBoost (AB), bagging (Bag), and random subspace (RS) algorithms to create gully erosion susceptibility maps for a sub-basin of the Shoor River watershed in northwestern Iran. We compare the performance of these models in terms of their ability to predict gully erosion and discuss their potential use in other arid and semi-arid areas. Our database comprises 242 gully erosion locations, which we randomly divided into training and testing sets with a ratio of 70/30. Based on expert knowledge and analysis of aerial photographs and satellite images, we selected 12 conditioning factors for gully erosion. We used multi-collinearity statistical techniques in the modeling process, and checked model performance using statistical indexes including precision, recall, F-measure, Matthew correlation coefficient (MCC), receiver operatic characteristic curve (ROC), precision–recall graph (PRC), Kappa, root mean square error (RMSE), relative absolute error (PRSE), mean absolute error (MAE), and relative absolute error (RAE). Results show that rainfall, elevation, and river density are the most important factors for gully erosion susceptibility mapping in the study area. All three hybrid models that we tested significantly enhanced and improved the predictive power of REPTree (AUC=0.800), but the RS-REPTree (AUC= 0.860) ensemble model outperformed the Bag-REPTree (AUC= 0.841) and the AB-REPTree (AUC= 0.805) models. We suggest that decision makers, planners, and environmental engineers employ the RS-REPTree hybrid model to better manage gully erosion-prone areas in Iran.

Identifying the Contributions of Multi-Source Data for Winter Wheat Yield Prediction in China

Wheat is a leading cereal grain throughout the world. Timely and reliable wheat yield prediction at a large scale is essential for the agricultural supply chain and global food security, especially in China as an important wheat producing and consuming country. The conventional approach using either climate or satellite data or both to build empirical and crop models has prevailed for decades. However, to what extent climate and satellite data can improve yield prediction is still unknown. In addition, socio-economic (SC) factors may also improve crop yield prediction, but their contributions need in-depth investigation, especially in regions with good irrigation conditions, sufficient fertilization, and pesticide application. Here, we performed the first attempt to predict wheat yield across China from 2001 to 2015 at the county-level by integrating multi-source data, including monthly climate data, satellite data (i.e., Vegetation indices (VIs)), and SC factors. The results show that incorporating all the datasets by using three machine learning methods (Ridge Regression (RR), Random Forest (RF), and Light Gradient Boosting (LightGBM)) can achieve the best performance in yield prediction (R2: 0.68~0.75), with the most individual contributions from climate (~0.53), followed by VIs (~0.45), and SC factors (~0.30). In addition, the combinations of VIs and climate data can capture inter-annual yield variability more effectively than other combinations (e.g., combinations of climate and SC, and combinations of VIs and SC), while combining SC with climate data can better capture spatial yield variability than others. Climate data can provide extra and unique information across the entire growing season, while the peak stage of VIs (Mar.~Apr.) do so. Furthermore, incorporating spatial information and soil proprieties into the benchmark models can improve wheat yield prediction by 0.06 and 0.12, respectively. The optimal wheat prediction can be achieved with approximately a two-month leading time before maturity. Our study develops timely and robust methods for winter wheat yield prediction at a large scale in China, which can be applied to other crops and regions.

Object-Based Mapping of Gullies Using Optical Images: A Case Study in the Black Soil Region, Northeast of China

Gully erosion is a widespread natural hazard. Gully mapping is critical to erosion monitoring and the control of degraded areas. The analysis of high-resolution remote sensing images (HRI) and terrain data mixed with developed object-based methods and field verification has been certified as a good solution for automatic gully mapping. Considering the availability of data, we used only open-source optical images (Google Earth images) to identify gully erosion through image feature modeling based on OBIA (Object-Based Image Analysis) in this paper. A two-end extrusion method using the optimal machine learning algorithm (Light Gradient Boosting Machine (LightGBM)) and eCognition software was applied for the automatic extraction of gullies at a regional scale in the black soil region of Northeast China. Due to the characteristics of optical images and the design of the method, unmanaged gullies and gullies harnessed in non-forest areas were the objects of extraction. Moderate success was achieved in the absence of terrain data. According to independent validation, the true overestimation ranged from 20% to 30% and was mainly caused by land use types with high erosion risks, such as bare land and farm lanes being falsely classified as gullies. An underestimation of less than 40% was adjacent to the correctly extracted gullied areas. The results of extraction in regions with geographical object categories of a low complexity were usually more satisfactory. The overall performance demonstrates that the present method is feasible for gully mapping at a regional scale, with high automation, low cost, and acceptable accuracy.

Mesoscale Mapping of Sediment Source Hotspots for Dam Sediment Management in Data-Sparse Semi-Arid Catchments

Land degradation and water availability in semi-arid regions are interdependent challenges for management that are influenced by climatic and anthropogenic changes. Erosion and high sediment loads in rivers cause reservoir siltation and decrease storage capacity, which pose risk on water security for citizens, agriculture, and industry. In regions where resources for management are limited, identifying spatial-temporal variability of sediment sources is crucial to decrease siltation. Despite widespread availability of rigorous methods, approaches simplifying spatial and temporal variability of erosion are often inappropriately applied to very data sparse semi-arid regions. In this work, we review existing approaches for mapping erosional hotspots, and provide an example of spatial-temporal mapping approach in two case study regions. The barriers limiting data availability and their effects on erosion mapping methods, their validation, and resulting prioritization of leverage management areas are discussed.

Spatial Modeling of Snow Avalanche Using Machine Learning Models and Geo-Environmental Factors: Comparison of Effectiveness in Two Mountain Regions

Although snow avalanches are among the most destructive natural disasters, and result in losses of life and economic damages in mountainous regions, far too little attention has been paid to the prediction of the snow avalanche hazard using advanced machine learning (ML) models. In this study, the applicability and efficiency of four ML models: support vector machine (SVM), random forest (RF), naïve Bayes (NB) and generalized additive model (GAM), for snow avalanche hazard mapping, were evaluated. Fourteen geomorphometric, topographic and hydrologic factors were selected as predictor variables in the modeling. This study was conducted in the Darvan and Zarrinehroud watersheds of Iran. The goodness-of-fit and predictive performance of the models was evaluated using two statistical measures: the area under the receiver operating characteristic curve (AUROC) and the true skill statistic (TSS). Finally, an ensemble model was developed based upon the results of the individual models. Results show that, among individual models, RF was best, performing well in both the Darvan (AUROC = 0.964, TSS = 0.862) and Zarrinehroud (AUROC = 0.956, TSS = 0.881) watersheds. The accuracy of the ensemble model was slightly better than all individual models for generating the snow avalanche hazard map, as validation analyses showed an AUROC = 0.966 and a TSS = 0.865 in the Darvan watershed, and an AUROC value of 0.958 and a TSS value of 0.877 for the Zarrinehroud watershed. The results indicate that slope length, lithology and relative slope position (RSP) are the most important factors controlling snow avalanche distribution. The methodology developed in this study can improve risk-based decision making, increases the credibility and reliability of snow avalanche hazard predictions and can provide critical information for hazard managers.

Novel ensembles of COPRAS multi-criteria decision-making with logistic regression, boosted regression tree, and random forest for spatial prediction of gully erosion susceptibility

Gully erosion is considered as a severe environmental problem in many areas of the world which causes huge damages to agricultural lands and infrastructures (i.e. roads, buildings, and bridges); however, gully erosion modeling and prediction with high accuracy are still difficult due to the complex interactions of various factors. The objective of this research was to develop and introduce three new ensemble models, which were based on Complex Proportional Assessment of Alternatives (COPRAS), Logistic Regression (LR), Boosted Regression Tree (BRT), Random Forest (RF), and Frequency Ratio (FR) for spatial prediction of gully erosion with a case study at the Najafabad watershed (Iran). For this purpose, a total of 290 head-cut of gullies and 17 conditioning factors were collected and used to establish a geospatial database. Subsequently, FR was used to determine the spatial relationship between the conditioning factors and the head-cut of gullies, whereas RF, BRT, and LR were used to quantify the relative importance of these factors. In the next step, three ensemble gully erosion models, named COPRAS-FR-RF, COPRAS-FR-BRT, and COPRAS-FR-LR were developed and verified. The Success Rate Curve (SRC), and the Prediction Rate Curve (PRC) and their areas under the curves (AUC) were used to check the performance of the three proposed models. The result showed that Soil group, geomorphology, and drainage density factors played the key role on the occurrence of the gully erosion. All the three models have very high degree-of-fit and the prediction performance, the COPRAS-FR-RF model (AUC-SRC = 0.974 and AUC-PRC = 0.929), the COPRAS-FR-BRT model (AUC-SRC = 0.973 and AUC-PRC = 0.928), and the COPRAS-FR-LR model (AUC-SRC = 0.972 and AUC-PRC = 0.926); therefore, it is concluded that they are efficient and new powerful tools which could be used for predicting gully erosion in prone-areas.

Performance Evaluation of the GIS-Based Data-Mining Techniques Decision Tree, Random Forest, and Rotation Forest for Landslide Susceptibility Modeling

This study analyzed and compared landslide susceptibility models using decision tree (DT), random forest (RF), and rotation forest (RoF) algorithms at Woomyeon Mountain, South Korea. Out of a total of 145 landslide locations, 102 locations (70%) were used for model training, and the remaining 43 locations (30%) were used for validation. Fourteen landslide conditioning factors were identified, and the contributions of each factor were evaluated using the RRelief-F algorithm with a 10-fold cross-validation approach. Three factors, timber diameter, age, and density had no contribution to landslide occurrence. Landslide susceptibility maps (LSMs) were produced using DT, RF, and RoF models with the 11 remaining landslide conditioning factors: altitude, slope, aspect, profile curvature, plan curvature, topographic position index, elevation-relief ratio, slope length and slope steepness, topographic wetness index, stream power index, and timber type. The performances of the LSMs were assessed and compared based on sensitivity, specificity, precision, accuracy, kappa index, and receiver operating characteristic curves. The results showed that the ensemble learning methods outperformed the single classifier (DT) and that the RoF model had the highest prediction capability compared to the DT and RF models. The results of this study may be helpful in managing areas vulnerable to landslides and establishing mitigation strategies.

A Comparative Assessment of Random Forest and k-Nearest Neighbor Classifiers for Gully Erosion Susceptibility Mapping

This research was conducted to determine which areas in the Robat Turk watershed in Iran are sensitive to gully erosion, and to define the relationship between gully erosion and geo-environmental factors by two data mining techniques, namely, Random Forest (RF) and k-Nearest Neighbors (KNN). First, 242 gully locations we determined in field surveys and mapped in ArcGIS software. Then, twelve gully-related conditioning factors were selected. Our results showed that, for both the RF and KNN models, altitude, distance to roads, and distance from the river had the highest influence upon gully erosion sensitivity. We assessed the gully erosion susceptibility maps using the Receiver Operating Characteristic (ROC) curve. Validation results showed that the RF and KNN models had Area Under the Curve (AUC) 87.4 and 80.9%, respectively. As a result, the RF method has better performance compared with the KNN method for mapping gully erosion susceptibility. Rainfall, altitude, and distance from a river were identified as the most important factors affecting gully erosion in this area. The methodology used in this research is transferable to other regions to determine which areas are prone to gully erosion and to explicitly delineate high-risk zones within these areas.