Head-cut gully erosion susceptibility mapping in semi-arid region using machine learning methods: insight from the high atlas, Morocco

Gully erosion has been identified in recent decades as a global threat to people and property. This problem also affects the socioeconomic stability of societies and therefore limits their sustainable development, as it impacts a nonrenewable resource on a human scale, namely, soil. The focus of this study is to evaluate the prediction performance of four machine learning (ML) models: Logistic Regression (LR), classification and regression tree (CART), Linear Discriminate Analysis (LDA), and the k-Nearest Neighbors (kNN), which are novel approaches in gully erosion modeling research, particularly in semi-arid regions with a mountainous character. 204 samples of erosion areas and 204 samples of non-erosion areas were collected through field surveys and high-resolution satellite images, and 17 significant factors were considered. 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. kNN is the ideal model for this study. The value of the AUC from ROC considering the testing datasets of KNN is 0.93; the remaining models are associated to ideal AUC and are similar to kNN in terms of values. The AUC values from ROC of GLM, LDA, and CART for testing datasets are 0.90, 0.91, and 0.84, respectively. The value of accuracy considering the validation datasets of LDA, CART, KNN, and GLM are 0.85, 0.82, 0.89, 0.84 respectively. The values of Kappa of LDA, CART, and GLM for testing datasets are 0.70, 0.65, and 0.68, respectively. ML models, in particular KNN, GLM, and LDA, have achieved outstanding results in terms of creating soil erosion susceptibility maps. The maps created with the most reliable models could be a useful tool for sustainable management, watershed conservation and prevention of soil and water losses.

[1]  M. Fnais,et al.  Assessment of Soil Suitability Using Machine Learning in Arid and Semi-Arid Regions , 2023, Agronomy.

[2]  S. Pal,et al.  Evaluation of climate change impacts on future gully erosion using deep learning and soft computational approaches , 2022 .

[3]  S. Oliveira,et al.  Landslide susceptibility assessment in the rocky coast subsystem of Essaouira, Morocco , 2022, Natural Hazards and Earth System Sciences.

[4]  S. Pal,et al.  Hydrogeochemical characterization based water resources vulnerability assessment in India's first Ramsar site of Chilka lake. , 2022, Marine pollution bulletin.

[5]  R. Moussadek,et al.  Soil water erosion assessment in Morocco through modeling and fingerprinting applications: A review , 2022, Heliyon.

[6]  Sk Ajim Ali,et al.  Hybrid Machine Learning Approach for Gully Erosion Mapping Susceptibility at a Watershed Scale , 2022, ISPRS Int. J. Geo Inf..

[7]  Mourad Jadoud,et al.  A comparative study of different machine learning methods coupled with GIS for landslide susceptibility assessment: a case study of N’fis basin, Marrakesh High Atlas (Morocco) , 2022, Arabian Journal of Geosciences.

[8]  V. Vallès,et al.  Mapping Gully Erosion Variability and Susceptibility Using Remote Sensing, Multivariate Statistical Analysis, and Machine Learning in South Mato Grosso, Brazil , 2022, Geosciences.

[9]  S. Pal,et al.  A novel hybrid of meta-optimization approach for flash flood-susceptibility assessment in a monsoon-dominated watershed, Eastern India , 2022, Environmental Earth Sciences.

[10]  M. Khazaei,et al.  DEM Resolution Effects on Machine Learning Performance for Flood Probability Mapping , 2021, Journal of Hydro-environment Research.

[11]  Asish Saha,et al.  Evaluation of different DEMs for gully erosion susceptibility mapping using in-situ field measurement and validation , 2021, Ecol. Informatics.

[12]  Richard M. Cruse,et al.  Gully Erosion Susceptibility Mapping in Highly Complex Terrain Using Machine Learning Models , 2021, ISPRS Int. J. Geo Inf..

[13]  B. Pradhan,et al.  Spatial Prediction of Groundwater Potentiality in Large Semi-Arid and Karstic Mountainous Region Using Machine Learning Models , 2021, Water.

[14]  A. Arabameri,et al.  Chemical weathering and gully erosion causing land degradation in a complex river basin of Eastern India: an integrated field, analytical and artificial intelligence approach , 2021, Natural Hazards.

[15]  L. Bouchaou,et al.  Mapping soil erosion–prone sites through GIS and remote sensing for the Tifnout Askaoun watershed, southern Morocco , 2021, Arabian Journal of Geosciences.

[16]  Hamid Reza Pourghasemi,et al.  Landslide susceptibility mapping using machine learning algorithms and comparison of their performance at Abha Basin, Asir Region, Saudi Arabia , 2021, Geoscience Frontiers.

[17]  Kwanele Phinzi,et al.  Mapping Permanent Gullies in an Agricultural Area Using Satellite Images: Efficacy of Machine Learning Algorithms , 2021, Agronomy.

[18]  M. Meliho,et al.  A Methodological Comparison of Three Models for Gully Erosion Susceptibility Mapping in the Rural Municipality of El Faid (Morocco) , 2021, Sustainability.

[19]  Biswajeet Pradhan,et al.  Robustness analysis of machine learning classifiers in predicting spatial gully erosion susceptibility with altered training samples , 2021, Geomatics, Natural Hazards and Risk.

[20]  Hamid Reza Pourghasemi,et al.  Soil erosion assessment using RUSLE model and its validation by FR probability model , 2020, Geocarto International.

[21]  Biswajeet Pradhan,et al.  Comparison of machine learning models for gully erosion susceptibility mapping , 2020, Geoscience Frontiers.

[22]  Tarig A. Ali,et al.  Flash Flood Susceptibility Modeling and Magnitude Index Using Machine Learning and Geohydrological Models: A Modified Hybrid Approach , 2020, Remote. Sens..

[23]  Wei Chen,et al.  GIS-Based Machine Learning Algorithms for Gully Erosion Susceptibility Mapping in a Semi-Arid Region of Iran , 2020, Remote. Sens..

[24]  Hamid Reza Pourghasemi,et al.  A machine learning framework for multi-hazards modeling and mapping in a mountainous area , 2020, Scientific Reports.

[25]  Geoffrey I. Webb,et al.  A Bayesian-inspired, deep learning, semi-supervised domain adaptation technique for land cover mapping , 2020, ArXiv.

[26]  M. Meliho,et al.  Spatial assessment of soil erosion risk by integrating remote sensing and GIS techniques: a case of Tensift watershed in Morocco , 2020, Environmental Earth Sciences.

[27]  Yuei-An Liou,et al.  Land-Use Land-Cover Classification by Machine Learning Classifiers for Satellite Observations - A Review , 2020, Remote. Sens..

[28]  Mary Ann Piette,et al.  Building thermal load prediction through shallow machine learning and deep learning , 2020, Applied Energy.

[29]  Nadhir Al-Ansari,et al.  Shallow Landslide Susceptibility Mapping: A Comparison between Logistic Model Tree, Logistic Regression, Naïve Bayes Tree, Artificial Neural Network, and Support Vector Machine Algorithms , 2020, International journal of environmental research and public health.

[30]  Wei Chen,et al.  GIS-Based Gully Erosion Susceptibility Mapping: A Comparison of Computational Ensemble Data Mining Models , 2020, Applied Sciences.

[31]  Thomas Blaschke,et al.  Machine Learning-Based Gully Erosion Susceptibility Mapping: A Case Study of Eastern India , 2020, Sensors.

[32]  Thomas Blaschke,et al.  Landslide Susceptibility Evaluation and Management Using Different Machine Learning Methods in The Gallicash River Watershed, Iran , 2020, Remote. Sens..

[33]  Nadhir Al-Ansari,et al.  Flood Detection and Susceptibility Mapping Using Sentinel-1 Remote Sensing Data and a Machine Learning Approach: Hybrid Intelligence of Bagging Ensemble Based on K-Nearest Neighbor Classifier , 2020, Remote. Sens..

[34]  Biswajeet Pradhan,et al.  Comparative assessment using boosted regression trees, binary logistic regression, frequency ratio and numerical risk factor for gully erosion susceptibility modelling , 2019 .

[35]  Donatello Telesca,et al.  Machine learning models accurately predict ozone exposure during wildfire events. , 2019, Environmental pollution.

[36]  Seyed Amir Naghibi,et al.  A Comparative Assessment of Random Forest and k-Nearest Neighbor Classifiers for Gully Erosion Susceptibility Mapping , 2019, Water.

[37]  H. Pourghasemi,et al.  Gully erosion susceptibility assessment and management of hazard-prone areas in India using different machine learning algorithms. , 2019, The Science of the total environment.

[38]  Biswajeet Pradhan,et al.  A Novel Ensemble Artificial Intelligence Approach for Gully Erosion Mapping in a Semi-Arid Watershed (Iran) , 2019, Sensors.

[39]  Wei Chen,et al.  Gully headcut susceptibility modeling using functional trees, naïve Bayes tree, and random forest models , 2019, Geoderma.

[40]  H. Pourghasemi,et al.  Assessment of the importance of gully erosion effective factors using Boruta algorithm and its spatial modeling and mapping using three machine learning algorithms , 2019, Geoderma.

[41]  Saro Lee,et al.  Modelling gully-erosion susceptibility in a semi-arid region, Iran: Investigation of applicability of certainty factor and maximum entropy models. , 2019, The Science of the total environment.

[42]  B. Pradhan,et al.  Gully erosion zonation mapping using integrated geographically weighted regression with certainty factor and random forest models in GIS. , 2019, Journal of environmental management.

[43]  H. Pourghasemi,et al.  Assessing the performance of GIS- based machine learning models with different accuracy measures for determining susceptibility to gully erosion. , 2019, The Science of the total environment.

[44]  H. Pourghasemi,et al.  Gully Erosion Modeling Using GIS-Based Data Mining Techniques in Northern Iran: A Comparison Between Boosted Regression Tree and Multivariate Adaptive Regression Spline , 2018, Advances in Natural and Technological Hazards Research.

[45]  S.M. Mohidul Islam,et al.  Soil Classification Using Machine Learning Methods and Crop Suggestion Based on Soil Series , 2018, 2018 21st International Conference of Computer and Information Technology (ICCIT).

[46]  B. Pradhan,et al.  Spatial modelling of gully erosion using evidential belief function, logistic regression, and a new ensemble of evidential belief function–logistic regression algorithm , 2018, Land Degradation & Development.

[47]  H. Pourghasemi,et al.  GIS-based gully erosion susceptibility mapping: a comparison among three data-driven models and AHP knowledge-based technique , 2018, Environmental Earth Sciences.

[48]  Wei Chen,et al.  GIS-based groundwater potential analysis using novel ensemble weights-of-evidence with logistic regression and functional tree models. , 2018, The Science of the total environment.

[49]  Binh Thai Pham,et al.  Prediction of shear strength of soft soil using machine learning methods , 2018, CATENA.

[50]  Sunil Saha,et al.  Assessment of land suitability for the paddy cultivation using analytical hierarchical process (AHP): a study on Hinglo river basin, Eastern India , 2018, Modeling Earth Systems and Environment.

[51]  Hamid Reza Pourghasemi,et al.  Spatial modelling of gully erosion in Mazandaran Province, northern Iran , 2018 .

[52]  H. Pourghasemi,et al.  Performance assessment of individual and ensemble data-mining techniques for gully erosion modeling. , 2017, The Science of the total environment.

[53]  Hamid Reza Pourghasemi,et al.  Evaluation of different machine learning models for predicting and mapping the susceptibility of gully erosion , 2017 .

[54]  Wei Chen,et al.  Landslide spatial modeling: Introducing new ensembles of ANN, MaxEnt, and SVM machine learning techniques , 2017 .

[55]  Sunil Saha,et al.  Application of weights-of-evidence (WoE) and evidential belief function (EBF) models for the delineation of soil erosion vulnerable zones: a study on Pathro river basin, Jharkhand, India , 2017, Modeling Earth Systems and Environment.

[56]  Meliho Modeste,et al.  Cartographie Des Risques De L’erosion Hydrique Par L’equation Universelle Revisee Des Pertes En Sols, La Teledetection Et Les Sig Dans Le Bassin Versant De L’ourika (Haut Atlas, Maroc) , 2016 .

[57]  Wei Chen,et al.  Application of frequency ratio, weights of evidence and evidential belief function models in landslide susceptibility mapping , 2016 .

[58]  H. Pourghasemi,et al.  Gully erosion susceptibility mapping: the role of GIS-based bivariate statistical models and their comparison , 2016, Natural Hazards.

[59]  H. Pourghasemi,et al.  Flood susceptibility mapping using frequency ratio and weights-of-evidence models in the Golastan Province, Iran , 2016 .

[60]  Claudia Notarnicola,et al.  Review of Machine Learning Approaches for Biomass and Soil Moisture Retrievals from Remote Sensing Data , 2015, Remote. Sens..

[61]  A. Cheggour,et al.  Land use and climate change effects on soil erosion in a semi-arid mountainous watershed (High Atlas, Morocco) , 2015 .

[62]  S. Abd-Elmabod,et al.  Evaluating Soil Threats Under Climate Change Scenarios in the Andalusia Region, Southern Spain , 2015 .

[63]  Jung Hyun Lee,et al.  A novel ensemble bivariate statistical evidential belief function with knowledge-based analytical hierarchy process and multivariate statistical logistic regression for landslide susceptibility mapping , 2014 .

[64]  I. Marzolff,et al.  Soil erosion in gully catchments affected by land-levelling measures in the Souss Basin, Morocco, analysed by rainfall simulation and UAV remote sensing data , 2014 .

[65]  Michael Märker,et al.  A GIS-based approach for gully erosion susceptibility modelling: a test in Sicily, Italy , 2013, Environmental Earth Sciences.

[66]  J. Poesen,et al.  Gully head retreat rates in the semi-arid highlands of Northern Ethiopia , 2012 .

[67]  Paolo Magliulo,et al.  Assessing the susceptibility to water-induced soil erosion using a geomorphological, bivariate statistics-based approach , 2012, Environmental Earth Sciences.

[68]  Chuluong Choi,et al.  Soil erosion risk in Korean watersheds, assessed using the revised universal soil loss equation , 2011 .

[69]  M. Conforti,et al.  Geomorphology and GIS analysis for mapping gully erosion susceptibility in the Turbolo stream catchment (Northern Calabria, Italy) , 2011 .

[70]  Tian Yingjie,et al.  Analysis of soil erosion characteristics in small watersheds with particle swarm optimization, support vector machine, and artificial neuronal networks , 2010 .

[71]  S. Schnabel,et al.  Gully erosion, land use and topographical thresholds during the last 60 years in a small rangeland catchment in SW Spain , 2009 .

[72]  J. L. Ternan,et al.  Dealing with soil variability: some insights from land degradation research in central Spain , 2002 .

[73]  J. Poesen,et al.  The European Soil Erosion Model (EUROSEM): A dynamic approach for predicting sediment transport from fields and small catchments. , 1998 .

[74]  G. F. Hall,et al.  Soil degradation: I. Basic processes , 1989 .

[75]  I. Moore,et al.  Physical basis of the length-slope factor in the universal soil loss equation , 1986 .

[76]  E. Heady,et al.  Measurement of sediment control impacts on agriculture , 1978 .

[77]  M. Stone Cross‐Validatory Choice and Assessment of Statistical Predictions , 1976 .

[78]  Forest Baskett,et al.  An Algorithm for Finding Nearest Neighbors , 1975, IEEE Transactions on Computers.

[79]  Thomas Blaschke,et al.  Landslide Mapping Using Two Main Deep-Learning Convolution Neural Network Streams Combined by the Dempster–Shafer Model , 2021, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[80]  Subodh Chandra Pal,et al.  Development of Different Machine Learning Ensemble Classifier for Gully Erosion Susceptibility in Gandheswari Watershed of West Bengal, India , 2020 .

[81]  Asish Saha,et al.  Understanding the Morphology and Development of a Rill-Gully: An Empirical Study of Khoai Badland, West Bengal, India , 2019 .

[82]  Saeid Janizadeh,et al.  Landslide Susceptibility Survey Using Modeling Methods , 2019, Spatial Modeling in GIS and R for Earth and Environmental Sciences.

[83]  A. Barakat,et al.  Remote sensing and GIS techniques for prediction of land use land cover change effects on soil erosion in the high basin of the Oum Er Rbia River (Morocco) , 2019, Remote Sensing Applications: Society and Environment.

[84]  H. Pourghasemi,et al.  Spatial Modeling of Gully Erosion , 2019, Spatial Modeling in GIS and R for Earth and Environmental Sciences.

[85]  G. Woltjer,et al.  SOIL DEGRADATION , 2011 .

[86]  E. Rotigliano,et al.  Gully erosion susceptibility assessment by means of GIS-based logistic regression: A case of Sicily (Italy) , 2014 .

[87]  A. Murwira,et al.  Potential of weight of evidence modelling for gully erosion hazard assessment in Mbire District – Zimbabwe , 2014 .

[88]  S. Daba An investigation of the physical and socioeconomic determinants of soil erosion in the Hararghe Highlands, eastern Ethiopia , 2003 .

[89]  H. J. Smith Application of Empirical Soil Loss Models in southern Africa: a review , 1999 .

[90]  É. Roose Adaptation des méthodes de conservation des sols aux conditions écologiques et socio-économiques de l'Afrique de l'Ouest , 1977 .