Erosion Susceptibility Assessment Research Articles

Development of an automated method for flood inundation monitoring, flood hazard, and soil erosion susceptibility assessment using machine learning and AHP–MCE techniques

BackgroundOperational large-scale flood monitoring using publicly available satellite data is possible with the advent of Sentinel-1 microwave data, which enables near-real-time (at 6-day intervals) flood mapping day and night, even in cloudy monsoon seasons. Automated flood inundation area identification in near-real-time involves advanced geospatial data processing platforms, such as Google Earth Engine and robust methodology (Otsu’s algorithm).ObjectivesThe current study employs Sentinel-1 microwave data for flood extent mapping using machine learning (ML) algorithms in Assam State, India. We generated a flood hazard and soil erosion susceptibility map by combining multi-source data on weather conditions and soil and terrain characteristics. Random Forest (RF), Classification and Regression Tool (CART), and Support Vector Machine (SVM) ML algorithms were applied to generate the flood hazard map. Furthermore, we employed the multicriteria evaluation (MCE) analytical hierarchical process (AHP) for soil erosion susceptibility mapping.SummaryThe highest prediction accuracy was observed for the RF model (overall accuracy [OA] > 82%), followed by the SVM (OA > 82%) and CART (OA > 81%). Over 26% of the study area indicated high flood hazard-prone areas, and approximately 60% showed high and severe potential for soil erosion due to flooding. The automated flood mapping platform is an essential resource for emergency responders and decision-makers, as it helps to guide relief activities by identifying suitable regions and appropriate logistic route planning and improving the accuracy and timeliness ofemergency response efforts. Periodic flood inundation maps will help in long-term planning and policymaking, flood management, soil and biodiversity conservation, land degradation, planning sustainable agriculture interventions, crop insurance, and climate resilience studies.

Machine learning models for gully erosion susceptibility assessment in the Tensift catchment, Haouz Plain, Morocco for sustainable development

Gully erosion is a widespread environmental danger, threatening global socio-economic stability and sustainable development. This study comprehensively applied seven machine learning (ML) models including SVM, KNN, RF, XGBoost, ANN, DT, and LR, and evaluated gully erosion susceptibility in the Tensift catchment and predict it within the Haouz plain, Morocco. To ensure the reliability of the findings, the study employed a robust combination of gully erosion inventory, sentinel images, and Digital Surface Model. Eighteen predictors, encompassing topographical, geomorphological, environmental, and hydrological factors, were selected after multicollinearity analyses. The gully erosion susceptibility of the study revealed that approximately 28.18% of the Tensift catchment is at a very high risk of erosion. Furthermore, 15.13% and 31.28% of the catchment are categorized as low and very low respectively. These findings extend to the Haouz plain, where 7.84% of the surface area are very highly risking erosion, while 18.25% and 55.18% are characterized as low and very low risk areas. To gauge the performance of the ML models, an array of metrics including specificity, precision, sensitivity, and accuracy were employed. The study highlights XGBoost and KNN as the most promising models, achieving AUC ROC values of 0.96 and 0.93 in the test phase. The remaining models namely RF (AUC ROC = 0.89), LR (AUC ROC = 0.80), SVM (AUC ROC = 0.81), DT (AUC ROC = 0.86), and ANN (AUC ROC = 0.78), also displayed commendable performance. The novelty of this research is its innovative approach to combat gully erosion through cutting edge ML models, offering practical solutions for watershed conservation, sustainable management, and the prevention of land degradation. These insights are invaluable for addressing the challenges posed by gully erosion within the region, and beyond its geographical boundaries and can be used for defining appropriate mitigation strategies at local to national scale.

Gully Erosion Susceptibility Assessment Using Different Machine Learning Algorithms: A Case Study of Shazand Watershed in Iran

Gully Erosion Susceptibility Assessment Using Different Machine Learning Algorithms: A Case Study of Shazand Watershed in Iran

Soil erosion susceptibility assessment of Swat River sub-watersheds using the morphometry-based compound factor approach and GIS

Soil erosion susceptibility assessment of Swat River sub-watersheds using the morphometry-based compound factor approach and GIS

Random Forest–based gully erosion susceptibility assessment across different agro-ecologies of the Upper Blue Nile basin, Ethiopia

Several environmental factors are known to influence the spatial distribution and susceptibility of gully erosion, yet the relative importance and interaction of these factors remain little understood in Ethiopia. In this study, we integrated detailed field investigations with high-resolution remote sensing products to assess gully erosion susceptibility and identify its controlling factors using Random Forest (RF) model in six representative watersheds across contrasting (highland, midland, and lowland) agro-ecological environments in the Upper Blue Nile basin of Ethiopia. Data for 20 controlling factors were extracted from datasets at eight different pixel resolutions ranging from 0.5 to 30 m in a geographic information system environment. About 70 % and 30 % of the dataset in each watershed were randomly selected for model training and validation purposes, respectively. Multicollinearity and correlation analyses were performed to identify variables with collinearity problems and explain their statistical relationships among the other variables. RF predicted gully erosion susceptibility and the relative importance of the controlling factors. The model showed outstanding performance when the finest-resolution datasets were used. Elevation, height above nearest drainage, runoff curve number-II, distance from streams, drainage density, soil type, and land use/land cover were found to be the most important factors controlling the spatial distribution of gullies in all six watersheds, irrespective of the watershed treatment conditions and agro-ecological settings. Thus, the most susceptible land to gully erosion was low-lying grazing and cultivated lands with sensitive soil of high runoff-generation capacity located within short horizontal and vertical distances from drainage networks. Therefore, basin- and watershed-scale gully management strategies should give priority to these areas. The identification of the runoff curve number-II, a hydrologic parameter for predicting direct runoff from excess rainfall, as one of the most important factors controlling gully erosion was a novel finding which will be useful for developing improved process-based gully erosion models.

Soil water erosion susceptibility assessment using deep learning algorithms

Accurate assessment of soil water erosion (SWE) susceptibility is critical for reducing land degradation and soil loss, and for mitigating the negative impacts of erosion on ecosystem services, water quality, flooding and infrastructure. Deep learning algorithms have been gaining attention in geoscience due to their high performance and flexibility. However, an understanding of the potential for these algorithms to provide fast, cheap, and accurate predictions of soil erosion susceptibility is lacking. This study provides the first quantification of this potential. Spatial predictions of susceptibility are made using three deep learning algorithms – Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) and Long-Short Term Memory (LSTM) – for an Iranian catchment that has historically experienced severe water erosion. Through a comparison of their predictive performance and an analysis of the driving geo-environmental factors, the results reveal: (1) elevation was the most effective variable on SWE susceptibility; (2) all three developed models had good prediction performance, with RNN being marginally the most superior; (3) maps of SWE susceptibility revealed that almost 40 % of the catchment was highly or very highly susceptible to SWE and 20 % moderately susceptible, indicating the critical need for soil erosion control in this catchment. Through these algorithms, the soil erosion susceptibility of catchments can potentially be predicted accurately and with ease using readily available data. Thus, the results reveal that these models have great potential for use in data poor catchments, such as the one studied here, especially in developing nations where technical modeling skills and understanding of the erosion processes occurring in the catchment may be lacking.

Gully erosion susceptibility assessment based on machine learning-A case study of watersheds in Tuquan County in the black soil region of Northeast China

Owing to its unique topographic and climatic conditions, agricultural production, and anthropogenic grazing, severe gully erosion has developed in the watersheds of Tuquan County located in the black soil region of Northeast China. Using three machine learning models to assess gully erosion susceptibility in this region, the main purpose of this study was to determine the important factors affecting the occurrence of gully erosion from 25 geo-environmental factors and select the model with the best prediction performance. Field data collection was conducted for 823 gullies. 12,496 pixels corresponding to 823 gullies and 12,496 pixels without gully erosion were randomly selected to form the model calculation database. According to the principle of multiple screening, this study selected 25 geo-environmental factors affecting the occurrence of gully erosion. Two factors, coarse sand content and fine sand content, were excluded by multi-collinearity analysis and using random forest (RF), convolution neural network (CNN), and transformer models, combining the 10-fold cross-validation and related validation metrics to assess the susceptibility of gully erosion in Tuquan County’s small watersheds. The results show that the convergence index (CI), topographical wetness index (TWI), terrain ruggedness index (TRI), and distance from the river based on the RF model are important factors affecting the occurrence of gully erosion. The transformer model (mean AUC of training = 95.338 %, mean AUC of validation = 95.342 %) was superior to the RF (mean AUC of training = 99.997 %, mean AUC of validation = 92.518 %) and CNN (mean AUC of training = 86.995 %, mean AUC of validation = 84.647 %) models in predicting performance. To ensure that the management and decision-making departments take reasonable and effective measures to prevent gully erosion in the study area, the gully erosion susceptibility maps produced using the three machine learning models were beneficial.

An improved multi-criteria decision analysis approach for watershed soil erosion susceptibility assessment

Soil erosion within watersheds is a common phenomenon worldwide, and many scientific efforts have been made to address this problem. The Revised Universal Soil Loss Equation (RUSLE) model has been widely employed in soil erosion estimation. However, several studies have highlighted its limitations and the need to account for some key aspects of soil erosion which are not considered in the model. This study explores the potential of utilizing locally dominant soil erosion driving factors alongside the RUSLE model for soil erosion susceptibility assessment within the OIO watershed. Landsat 8 OLI image for the year 2020, DEM, soil data, Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS) datasets coupled with field observed datasets were employed to derive these factors. They include soil loss, sediment yield, sediment transport index, and runoff. Numerical rankings that represent the level of contribution of each factor and their attributes to soil erosion within the watershed were generated using the Fuzzy Analytical Hierarchy Process (FAHP). Each factor was reclassified according to these rankings and overlaid using the GIS-based weighted overlay technique to model soil erosion within the OIO watershed. Finally, we employed a statistical combination of the modelled soil erosion map and Hydrological Response Unit (HRU) to assess erosion susceptibility within the watershed. Initial results from the study highlighted the variabilities in annual soil loss (min: < 6.0 t ha−1 yr−1, max: ≥ 58.0 t ha−1 yr−1, mean: 13.55 t ha−1 yr−1) and identified areas with high predispositions to soil loss within the OIO watershed. The annual sediment yield of the entire OIO watershed ranged between ≤ 14.04 to 715.10 t ha−1yr−1 with an annual average of 14.88 t ha−1yr−1. In addition, the sediment transport index and runoff volume for the OIO watershed range between 0.00–69.07 and 0.00–70.00 mm, respectively. Five erosion susceptibility levels were delineated: very slight, slight, moderate, severe, and severe. They occupied 65.00%, 24.43%, 7.69%, 2.63%, and 0.23% of the watershed, respectively. Accuracy assessment conducted using the Receiver Operating Curve (ROC) showed that the soil erosion susceptibility map has an AUC value of 0.86, indicating acceptable results. Our methodological approach improves the RUSLE model, especially regarding preliminary soil susceptibility assessment for watershed development under typical data-scarce conditions.

Erosion susceptibility assessment using fuzzy logic and multi-influencing factors combination approach

Erosion susceptibility assessment using fuzzy logic and multi-influencing factors combination approach

Gully Erosion Susceptibility Assessment in the Kondoran Watershed Using Machine Learning Algorithms and the Boruta Feature Selection

Gully erosion susceptibility mapping is an essential land management tool to reduce soil erosion damages. This study investigates gully susceptibility based on multiple diagnostic analysis, support vector machine and random forest algorithms, and also a combination of these models, namely the ensemble model. Thus, a gully susceptibility map in the Kondoran watershed of Iran was generated by applying these models on the occurrence and non-occurrence points (as the target variable) and several predictors (slope, aspect, elevation, topographic wetness index, drainage density, plan curvature, distance to streams, lithology, soil texture and land use). The Boruta algorithm was used to select the most effective variables in modeling gully erosion susceptibility. The area under the receiver operating characteristic curve (AUC), the receiver operating characteristics, and true skill statistics (TSS) were used to assess the model performance. The results indicated that the ensemble model had the best performance (AUC = 0.982, TSS = 0.93) compared to the others. The most effective factors in gully erosion susceptibility mapping of the study region were topological, anthropogenic, and geological. The methodology and variables of this study can be used in other regions to control and mitigate the gully erosion phenomenon by applying biophilic and regenerative techniques at the locations of the most influential factors.

Soil erosion susceptibility assessment using logistic regression, decision tree and random forest: study on the Mayurakshi river basin of Eastern India

Soil erosion is one of the major environmental hazards causing severe land degradation in the sub-tropical monsoon dominated Mayurakshi river basin (MRB) of Eastern India. Hence, this study aims to delineate the areas with severe soil erosion probability (SEP) using logistic regression (LR), decision tree (DT), and Random forest (RF). A soil erosion inventory map was prepared using 150 rill and gully erosion prone sites, out of which 70% sample points were randomly chosen for modelling and remaining 30% sites were used for model validation. Alongside, 12 conditioning factors including elevation, curvature, aspect, runoff, TWI, slope, geology, stream frequency, rainfall erosivity, NDVI, LS-factor, and LULC were selected as spatial data base for model building. Multicollinearity among conditioning factors were performed using tolerance (TOL) and variance inflation factor (VIF). The analysis concludes that the possibility of soil erosion is very high in the undulating western parts of Mayurakshi river basin as compared to other sectors. The validation results obtained from ROC curve and kappa statistics is showing that DT and RF reached a higher prediction accuracy than LR model.

The application of an expert knowledge‐driven approach for assessing gully erosion susceptibility in the subtropical Nigerian savannah

This study assessed gully erosion susceptibility in Southern Gombe State, Nigeria. The objectives of the study were to: (1) prepare gully inventory of Southern Gombe State, (2) apply the Analytical Hierarchy Process to assess the contribution of gully erosion predisposing factors, and (3) produce a gully erosion susceptibility map of Southern Gombe State. Based on geomorphological study involving interpretation of Google Earth images and field surveys, 127 gullies were identified and 13 gully erosion predisposing factors assumed to influence gully erosion susceptibility were selected. Identified gullies were randomly split into training (89 or 70 per cent) and validation (38 or 30 per cent) datasets. The contribution of each gully erosion predisposing factor was obtained using the Analytical Hierarchy Process. The results indicated that slope (0.130), stream density (0.121), and distance from stream (0.121) play crucial roles in gully erosion susceptibility. By overlaying the gully erosion susceptibility factor maps, a gully erosion susceptibility map was created. A natural break method was then used to classify gully erosion areas into relatively safe (6.04 km2), less susceptible (3332.46 km2), moderately susceptible (1811.49 km2), highly susceptible (1146.35 km2), and extremely susceptible (1726.77 km2) categories. Field verification confirmed that the map accurately classified 92.11 per cent of the validation datasets, signifying the Analytical Hierarchy Process as a reliable method for gully erosion susceptibility assessment. The created gully erosion susceptibility map can assist land planners to identify critical gully erosion areas where prevention and mitigation actions should be implemented.

Implementation of Artificial Intelligence Based Ensemble Models for Gully Erosion Susceptibility Assessment

The Rarh Bengal region in West Bengal, particularly the eastern fringe area of the Chotanagpur plateau, is highly prone to water-induced gully erosion. In this study, we analyzed the spatial patterns of a potential gully erosion in the Gandheswari watershed. This area is highly affected by monsoon rainfall and ongoing land-use changes. This combination causes intensive gully erosion and land degradation. Therefore, we developed gully erosion susceptibility maps (GESMs) using the machine learning (ML) algorithms boosted regression tree (BRT), Bayesian additive regression tree (BART), support vector regression (SVR), and the ensemble of the SVR-Bee algorithm. The gully erosion inventory maps are based on a total of 178 gully head-cutting points, taken as the dependent factor, and gully erosion conditioning factors, which serve as the independent factors. We validated the ML model results using the area under the curve (AUC), accuracy (ACC), true skill statistic (TSS), and Kappa coefficient index. The AUC result of the BRT, BART, SVR, and SVR-Bee models are 0.895, 0.902, 0.927, and 0.960, respectively, which show very good GESM accuracies. The ensemble model provides more accurate prediction results than any single ML model used in this study.

Integration of artificial intelligence with meta classifiers for the gully erosion susceptibility assessment in Hinglo river basin, Eastern India

The main aim of this study is to evaluate the gully erosion susceptibility coupling the artificial intelligence and machine learning ensemble approaches. In the present study, the multilayer perceptron neural network (MLP) was used as the base classifier and the hybrid ensemble machine learning methods i.e. Bagging and Dagging were used as the functional classifiers. The Hinglo river basin, an important tributary of the Ajay River was selected as the study area, consists with the parts of Chhotonagpur plateau and Rarh lateritic region. The study area is facing the gully erosion problems which are interrupted the growth of the agriculture. The gully erosion susceptibility maps (GESMs), prepared by MLP, MLP-Bagging and MLP-Dagging were classified into four classes such as low, moderate, high and very high susceptibility classes with the help of natural break method (NBM) in GIS environment. The very high susceptibility class covered 19.41% (MLP), 13.52% (MLP-Bagging) and 15.30% (MLP-Dagging) areas of the basin. For the evaluation and comparison of the models, receiver operating characteristics (ROC), accuracy, mean absolute error (MAE) and root mean square error (RMSE) were applied. Overall, all the gully erosion susceptibility models were performed as excellent. Integration of hybrid ensemble models with MLP has increase the accuracy of the MLP models. Among these models MLP-Dagging has achieved the highest accuracy in compare to the other models. The importance of the selected factors in the present study was assessed by the Relief-F method. The results show that the soil type factor has the highest predictive performance. Sensitivity analysis also showed soil type as most important factor. The gully erosion susceptibility maps (GESMs) are considered as the efficient tool which could be used to take the necessary steps for mitigating and controlling the soil erosion problem and sustainable environmental management and development.

Multivariate Logistic Regression Model for Soil Erosion Susceptibility Assessment under Static and Dynamic Causative Factors

Multivariate Logistic Regression Model for Soil Erosion Susceptibility Assessment under Static and Dynamic Causative Factors

Gully erosion susceptibility assessment and management of hazard-prone areas in India using different machine learning algorithms

Gully erosion is one of the most effective drivers of sediment removal and runoff from highland areas to valley floors and stable channels, where continued off-site effects of water erosion occur. Gully initiation and development is a natural process that greatly impacts natural resources, agricultural activities, and environmental quality as it promotes land and water degradation, ecosystem disruption, and intensification of hazards. In this research, an attempt is made to produce gully erosion susceptibility maps for the management of hazard-prone areas in the Pathro River Basin of India using four well-known machine learning models, namely, multivariate additive regression splines (MARS), flexible discriminant analysis (FDA), random forest (RF), and support vector machine (SVM). To support this effort, observations from 174 gully erosion sites were made using field surveys. Of the 174 observations, 70% were randomly split into a training data set to build susceptibility models and the remaining 30% were used to validate the newly built models. Twelve gully erosion conditioning factors were assessed to find the areas most susceptible to gully erosion. The predisposing factors were slope gradient, altitude, plan curvature, slope aspect, land use, slope length (LS), topographical wetness index (TWI), drainage density, soil type, distance from the river, distance from the lineament, and distance from the road. Finally, the results from the four applied models were validated with the help of ROC (Receiver Operating Characteristics) curves. The AUC value for the RF model was calculated to be 96.2%, whereas for those for the FDA, MARS, and SVM models were 84.2%, 91.4%, and 88.3%, respectively. The AUC results indicated that the random forest model had the highest prediction accuracy, followed by the MARS, SVM, and FDA models. However, it could be concluded that all the machine learning models performed well according to their prediction accuracy. The produced GESMs can be very useful for land managers and policy makers as they can be used to initiate remedial measures and erosion hazard mitigation in prioritized areas.

Soil Erosion Susceptibility Assessment for Prioritization of Hilly Areas of a Watershed in the Arunachal Himalayas in Northeast India Based on Weighted Sum Analysis Method on Morphometric Parameters

In the present study, soil erosion susceptibility analysis has been carried out in the Dikrong watershed, predominantly located in the Arunachal Himalayas, applying the Weighted Sum Analysis (WSA) technique on some important morphometric parameters. Based on this approach, prioritization of the sub-watersheds has been determined by assigning weightages, derived from the correlation matrix, to the respective parameters and, accordingly, the sub-watersheds have been categorized into three priority levels viz., high, moderate, and low to very low. It has been ascertained that sub-watersheds Niorch, Chimpu, and Pang are high susceptible zones requiring urgent and efficient planning and management for better conservation.

Soil Erosion Susceptibility Assessment of the Lower Himachal Himalayan Watershed

Assessment of erosion status of a watershed is an essential prerequisite for integrated watershed management. It not only assists in chalking out suitable soil and water conservation measures to arrest erosion and conserve water but also helps in devising best management practices to enhance biomass production in watersheds. Keeping this in view, the present study has been undertaken by involving geospatial-statistical techniques to determine the critical and priority areas for soil and water conservation in Suketi watershed of the lower Himachal Himalayan region. A novel weighted sum analysis technique was used for ranking each of hydrological unit by obtaining the weightages from various morphometric parameters. This technique offers dynamic, effective and sustainable approach over traditional prioritization methods in which significance of each parameter were considered equally. Considering this approach, sub-watersheds were delineated into low, medium and high priority zones. The results illustrate that about 52 % of sub-watersheds of Suketi watershed are in moderate to high erosion and runoff susceptible zones. Therefore, these potential areas can be considered for preferential soil and water conservation planning. The results obtained from the study will be useful for various stakeholders such as agriculturists, water resource managers, conservation measures planners and decision policy makers for better management practices and decision making. The geospatial-statistical technique can be used for effective estimation of erosion status of watersheds leading to watershed prioritization for taking up soil and water conservation measures in watershed systems. Finally, this technique can be very useful in remote, rugged and inaccessible watersheds with absence of soil erosion and runoff monitoring.

Soil erosion susceptibility assessment through geo-statistical multivariate approach in Panchkula district of Haryana, India

The aim of the present study is to map and evaluate the soil erosion susceptibility in Panchkula district of Haryana. Based on field survey and information analysis, 12 factors such as rainfall, vegetation cover, soil type, geomorphology, slope angle, stream power, slope length, topographical curvature, drainage density, topographical wetness, land use/land cover, and slope aspect have been identified as soil erosion stimulating factors. Different thematic layers of these parameters using remote sensing data and geographical information system (GIS) have been generated and subsequently integrated with the weighted index overlay (WIO) method for the identification and delineation of soil erosion prone areas. The weight of each thematic layer corresponding to the susceptibility level has been determined through the rank sum method technique. The obtained results reveal that about 32% area of the district is prone to high and very high erosion which spreads in north-western parts. In order to test the reliability of the adopted model for soil erosion susceptibility, validation procedures have been executed. Soil erosion susceptibility assessment commenced by means of geo-statistical multivariate approach may be very useful for planning erosion control measures, which is a prerequisite for integrated soil and water resources management in the district.

Gully erosion susceptibility mapping: the role of GIS-based bivariate statistical models and their comparison

Gully erosion is a key issue in natural resource management that often has severe environmental, economic, and social consequences. The objective of the present study is to assess the capability of weights-of-evidence (WofE) and frequency ratio (FR) models for spatial prediction of gully erosion susceptibility and characterizing susceptibility conditions at Chavar region, Ilam province, Iran. At first, a gully erosion inventory map is prepared, using multiple field surveys. In total, of the 63 gullies which have been identified, 44 (70 %) cases are randomly algorithm selected to build gully susceptibility models, while the remaining 19 (30 %) cases are used to validate the models. The effectiveness of gully erosion susceptibility assessment via GIS-based models depends on appropriate selection of the conditioning factors which play an important role in gully erosion. Learning vector quantization (LVQ), one of the supervised neural network methods, is employed in order to estimate variable importance. In this research, the selected conditioning factors are: lithology, land use, distance from river, soil texture, slope degree, slope aspect, plan curvature, topographic wetness index, drainage density, and altitude. Finally, validation of the gully dataset which has not been utilized during the spatial modeling process is applied to validate the gully susceptibility maps. The receiver operating characteristic curves for each gully susceptibility map (i.e., produced by WofE and FR) are drawn, and the areas under the curves (AUC) are calculated. The results show that the gully erosion susceptibility map produced by the frequency ratio model (AUC = 78.11 %) functions well in prediction compared with the WofE model (AUC = 70.07 %). Furthermore, LVQ results reveal that distance from river, drainage density, and land use are the most effective factors.