Interpretation of Bayesian-optimized deep learning models for enhancing soil erosion susceptibility prediction and management: a case study of Eastern India

References

• Abdo HG. 2021. Estimating water erosion using RUSLE, GIS and remote sensing in Wadi-Qandeel river basin, Lattakia, Syria. ProcIndian Natl Sci Acad. 87(3):514–523. doi: 10.1007/s43538-021-00047-0.
   Web of Science ®Google Scholar
• Abdo H, Salloum J. 2017. Mapping the soil loss in Marqya basin: Syria using RUSLE model in GIS and RS techniques. Environ Earth Sci. 76(3):114. doi: 10.1007/s12665-017-6424-0.
   Web of Science ®Google Scholar
• Ahmed IA, Talukdar S, Baig MRI, Ramana GV, Rahman A, Shahfahad. 2024. Quantifying soil erosion and influential factors in Guwahati’s urban watershed using statistical analysis, machine and deep learning. Remote Sens Appl: Soc Environ. 33:101088. doi: 10.1016/j.rsase.2023.101088.
   Google Scholar
• Ahmed IA, Talukdar S, Islam ARMT, Rihan M, Malafaia G, Bera S, Ramana GV, Rahman A. 2023a. Contribution and behavioral assessment of physical and anthropogenic factors for soil erosion using integrated deep learning and game theory. J Clean Prod. 416:137689. doi: 10.1016/j.jclepro.2023.137689.
   Web of Science ®Google Scholar
• Ahmed IA, Talukdar S, Naikoo MW, Parvez A, Pal S, Ahmed S, Rahman A, Islam ARMdT, Mosavi AH, Shahfahad, et al. 2023b. A new framework to identify most suitable priority areas for soil-water conservation using coupling mechanism in Guwahati urban watershed, India, with future insight. J Clean Prod 382:135363. doi: 10.1016/j.jclepro.2022.135363.
   Web of Science ®Google Scholar
• Al-Najjar D, Al-Najjar H, Al-Rousan N, Assous HF. 2022. Developing machine learning techniques to investigate the impact of air quality indices on tadawul exchange index. Complexity. 2022(1):1–12. doi: 10.1155/2022/4079524.
   Google Scholar
• Arabameri A, Tiefenbacher JP, Blaschke T, Pradhan B, Tien Bui D. 2020. Morphometric analysis for soil erosion susceptibility mapping using novel gis-based ensemble model. Remote Sens. 12(5):874. doi: 10.3390/rs12050874.
   Google Scholar
• Aslam B, Maqsoom A, Alaloul WS, Musarat MA, Jabbar T, Zafar A. 2021. Soil erosion susceptibility mapping using a GIS-based multi-criteria decision approach: case of district Chitral, Pakistan. Ain Shams Eng J. 12(2):1637–1649. doi: 10.1016/j.asej.2020.09.015.
   Web of Science ®Google Scholar
• Bag R, Mondal I, Dehbozorgi M, et al. 2022. Modelling and mapping of soil erosion susceptibility using machine learning in a tropical hot sub-humid environment. J Clean Prod. 364:132428.
   Web of Science ®Google Scholar
• Bag R, Mondal I, Dehbozorgi M, Bank SP, Das DN, Bandyopadhyay J, Pham QB, Fadhil Al-Quraishi AM, Nguyen XC. 2022. Modelling and mapping of soil erosion susceptibility using machine learning in a tropical hot sub-humid environment. J Cleaner Prod. 364:132428. doi: 10.1016/j.jclepro.2022.132428.
   Web of Science ®Google Scholar
• Barakat A, Rafai M, Mosaid H, Islam MS, Saeed S. 2023. Mapping of water-induced soil erosion using machine learning models: a case study of Oum Er Rbia Basin (Morocco). Earth Syst Environ. 7(1):151–170., doi: 10.1007/s41748-022-00317-x.
   Google Scholar
• Bhattacharya RK, Das Chatterjee N, Das K. 2021. Land use and land cover change and its resultant erosion susceptible level: an appraisal using RUSLE and logistic regression in a tropical plateau basin of West Bengal, India. Environ Dev Sustain. 23(2):1411–1446. doi: 10.1007/s10668-020-00628-x.
   Web of Science ®Google Scholar
• Biswas T, Pal SC, Saha A, Ruidas D, Islam ARMT, Shit M. 2023. Hydro-chemical assessment of groundwater pollutant and corresponding health risk in the Ganges delta, Indo-Bangladesh region. J Cleaner Prod. 382:135229. doi: 10.1016/j.jclepro.2022.135229.
   Web of Science ®Google Scholar
• Blake WH, Rabinovich A, Wynants M, Kelly C, Nasseri M, Ngondya I, Patrick A, Mtei K, Munishi L, Boeckx P, et al. 2018. Soil erosion in East Africa: an interdisciplinary approach to realising pastoral land management change. Environ Res Lett. 13(12):124014. doi: 10.1088/1748-9326/aaea8b.
   Web of Science ®Google Scholar
• Chakrabortty R, Pal SC. 2023. Modeling soil erosion susceptibility using GIS-based different machine learning algorithms in monsoon dominated diversified landscape in India. Model Earth Syst Environ. 9(2):2927–2942. doi: 10.1007/s40808-022-01681-3.
   Web of Science ®Google Scholar
• Chakrabortty R, Pal SC, Arabameri A, Ngo PTT, Chowdhuri I, Roy P, Malik S, Das B. 2022. Water-induced erosion potentiality and vulnerability assessment in Kangsabati river basin, eastern India. Environ Dev Sustain. 24(3):3518–3557. doi: 10.1007/s10668-021-01576-w.
   Web of Science ®Google Scholar
• Chakrabortty R, Pal SC, Sahana M, et al. 2020. Soil erosion potential hotspot zone identification using machine learning and statistical approaches in eastern India. Netherlands: Springer.
   Google Scholar
• Chakrabortty R, Pradhan B, Mondal P, Pal SC. 2020. The use of RUSLE and GCMs to predict potential soil erosion associated with climate change in a monsoon-dominated region of eastern India. Arab J Geosci. 13(20):1073. doi: 10.1007/s12517-020-06033-y.
   Web of Science ®Google Scholar
• Cheng Z, Lu D, Li G, et al. 2018. A random forest-based approach to map soil erosion risk distribution in Hickory Plantations in western Zhejiang Province, China. Remote Sens. 10:1899.
   Google Scholar
• Esmali Ouri A, Golshan M, Janizadeh S, Cerdà A, Melesse AM. 2020. Soil erosion susceptibility mapping in Kozetopraghi catchment, Iran: a mixed approach using rainfall simulator and data mining techniques. Land. 9(10):368. doi: 10.3390/land9100368.
   Web of Science ®Google Scholar
• FAO. 2019. Soil erosion–the greatest challenge for sustainable soil management. Rome: FAO. 100 pp.
   Google Scholar
• Feng DC, Wang WJ, Mangalathu S, Taciroglu E. 2021. Interpretable XGBoost-SHAP machine-learning model for shear strength prediction of squat RC walls. J Struct Eng. 147(11):04021173. doi: 10.1061/(ASCE)ST.1943-541X.0003115.
   Web of Science ®Google Scholar
• Flanagan DC, Ascough JC, Nearing MA, Laflen JM. 2001. The water erosion prediction project (WEPP) model. In: Harmon RS, Doe WW, editors. Landscape erosion and evolution modeling. Boston, MA: Springer. doi: 10.1007/978-1-4615-0575-4_7.
   Google Scholar
• Gayen A, Haque SM, Saha S. 2020. Modeling of gully erosion based on random forest using GIS and R. In: Shit P, Pourghasemi H, Bhunia G, editors. Gully erosion studies from India and surrounding regions. Advances in science, technology & innovation. Cham: Springer. doi: 10.1007/978-3-030-23243-6_3.
   Google Scholar
• Gholami H, Mohammadifar A, Golzari S, Song Y, Pradhan B., 2023. Interpretability of simple RNN and GRU deep learning models used to map land susceptibility to gully erosion. Sci Total Environ. 904:166960. doi: 10.1016/j.scitotenv.2023.166960.
   PubMed Web of Science ®Google Scholar
• Ghosal K, Das Bhattacharya S. 2020. A review of RUSLE model. J Indian Soc Remote Sens. 48(4):689–707. doi: 10.1007/s12524-019-01097-0.
   Web of Science ®Google Scholar
• Ghosh A, Maiti R. 2021. Soil erosion susceptibility assessment using logistic regression, decision tree and random forest: study on the Mayurakshi river basin of Eastern India. Environ Earth Sci. 80(8):1–16. doi: 10.1007/s12665-021-09631-5.
   Web of Science ®Google Scholar
• Iban MC, Bilgilioglu SS. 2023. Snow avalanche susceptibility mapping using novel tree-based machine learning algorithms (XGBoost, NGBoost, and LightGBM) with eXplainable Artificial Intelligence (XAI) approach. Stoch Environ Res Risk Assess. 37(6):2243–2270. doi: 10.1007/s00477-023-02392-6.
   Web of Science ®Google Scholar
• Igwe CA, Mbagwu JSC. 1999. Application of SLEMSA and USLE erosion models for potential erosion hazard mapping in South-Eastern Nigeria. Int Agrophysics. 13:41–48.
   Google Scholar
• Jaydhar AK, Pal SC, Saha A, Islam ARMT, Ruidas D. 2022. Hydrogeochemical evaluation and corresponding health risk from elevated arsenic and fluoride contamination in recurrent coastal multi-aquifers of eastern India. J Cleaner Prod. 369:133150. doi: 10.1016/j.jclepro.2022.133150.
   Web of Science ®Google Scholar
• Kebede YS, Endalamaw NT, Sinshaw BG, Atinkut HB. 2021. Modeling soil erosion using RUSLE and GIS at watershed level in the upper beles, Ethiopia. Environ Challenges. 2:100009. doi: 10.1016/j.envc.2020.100009.
   Google Scholar
• Khosravi K, Rezaie F, Cooper JR, Kalantari Z, Abolfathi S, Hatamiafkoueieh J., 2023. Soil water erosion susceptibility assessment using deep learning algorithms. J Hydrol. 618:129229. doi: 10.1016/j.jhydrol.2023.129229.
   Web of Science ®Google Scholar
• Kulimushi LC, Bigabwa Bashagaluke J, Prasad P, Heri-Kazi AB, Lal Kushwaha N, Masroor M, Choudhari P, Elbeltagi A, Sajjad H, Mohammed S, et al. 2023. Soil erosion susceptibility mapping using ensemble machine learning models: a case study of upper Congo river sub-basin. Catena. 222:106858. doi: 10.1016/j.catena.2022.106858.
   Web of Science ®Google Scholar
• Li L, Wang Y, Liu C. 2014. Effects of land use changes on soil erosion in a fast developing area. Int J Environ Sci Technol. 11:1549–1562.
   Web of Science ®Google Scholar
• Mallik S, Das S, Chakraborty A, Mishra U, Talukdar S, Bera S, Ramana GV. 2023. Prediction of non-carcinogenic health risk using Hybrid Monte Carlo-machine learning approach. Human and Ecol Risk Assess: An Int J. 29(3–4):777–800. doi: 10.1080/10807039.2023.2188417.
   Web of Science ®Google Scholar
• Mohammed S, Abdo HG, Szabo S, Pham QB, Holb IJ, Linh NTT, Anh DT, Alsafadi K, Mokhtar A, Kbibo I, et al. 2020a. Estimating human impacts on soil erosion considering different hillslope inclinations and land uses in the coastal region of Syria. Water. 12(10):2786. doi: 10.3390/w12102786.
   Web of Science ®Google Scholar
• Mohammed S, Alsafadi K, Talukdar S, Kiwan S, Hennawi S, Alshihabi O, Sharaf M, Harsanyie E. 2020b. Estimation of soil erosion risk in southern part of Syria by using RUSLE integrating geo informatics approach. Remote Sens Appl: Soc Environ. 20:100375. doi: 10.1016/j.rsase.2020.100375.
   Google Scholar
• Morgan P. 1984. The thermal structure and thermal evolution of the continental lithosphere. Phys Chem Earth. 15:107–193. doi: 10.1016/0079-1946(84)90006-5.
   Google Scholar
• Morgan RPC. 2001. A simple approach to soil loss prediction: a revised Morgan–Morgan–Finney model. Catena. 44(4):305–322. doi: 10.1016/S0341-8162(00)00171-5.
   Web of Science ®Google Scholar
• Morgan RPC, Duzant JH. 2008. Modified MMF (Morgan–Morgan–Finney) model for evaluating effects of crops and vegetation cover on soil erosion. Earth Surf Process Landforms J Br Geomorphol Res Gr. 33:90–106.
   Web of Science ®Google Scholar
• Morgan RPC, Quinton JN, Smith RE, et al. 1998. The European Soil Erosion Model (EUROSEM): a dynamic approach for predicting sediment transport from fields and small catchments. Earth Surf Process Landforms J Br Geomorphol Gr. 23:527–544.
   Web of Science ®Google Scholar
• Mosavi A, Golshan M, Janizadeh S, et al. 2022. Ensemble models of GLM, FDA, MARS, and RF for flood and erosion susceptibility mapping: a priority assessment of sub-basins. Geocarto Int. 37:2541–2560.
   Web of Science ®Google Scholar
• Mosavi A, Sajedi-Hosseini F, Choubin B, Taromideh F, Rahi G, Dineva AA. 2020. Susceptibility mapping of soil water erosion using machine learning models. Water. 12(7):1995. doi: 10.3390/w12071995.
   Web of Science ®Google Scholar
• Mustafa MRU, Sholagberu AT, Yusof KW, Hashim AM, Khan MWA, Shahbaz M., 2018. SVM-based geospatial prediction of soil erosion under static and dynamic conditioning factors. MATEC Web Conf. 203:04004. doi: 10.1051/matecconf/201820304004.
   Google Scholar
• Nasidi NM, Wayayok A, Abdullah AF, Kassim MSM. 2020. Vulnerability of potential soil erosion and risk assessment at hilly farms using InSAR technology. Alger J Eng Technol. 3:1–8.
   Google Scholar
• Negese A, Fekadu E, Getnet H. 2021. Potential soil loss estimation and erosion-prone area prioritization using RUSLE, GIS, and remote sensing in Chereti Watershed, Northeastern Ethiopia. Air Soil Water Res. 14:117862212098581. doi: 10.1177/1178622120985814.
   Web of Science ®Google Scholar
• Pal S. 2015. Identification of soil erosion vulnerable areas in Chandrabhaga river basin: a multi-criteria decision approach. Model Earth Syst Environ. 2(1):1–11. doi: 10.1007/s40808-015-0052-z.
   Google Scholar
• Pal SC, Ruidas D, Saha A, Islam ARMT, Chowdhuri I. 2022. Application of novel data-mining technique based nitrate concentration susceptibility prediction approach for coastal aquifers in India. J Cleaner Prod. 346:131205. doi: 10.1016/j.jclepro.2022.131205.
   Web of Science ®Google Scholar
• Phinzi K, Ngetar NS, Ebhuoma O. 2021. Soil erosion risk assessment in the Umzintlava catchment (T32E), Eastern Cape, South Africa, using RUSLE and random forest algorithm. South African Geographical Journal. 103(2):139–162. doi: 10.1080/03736245.2020.1716838.
   Web of Science ®Google Scholar
• Prasanth Kadiyala S, Woo WL. 2021. Flood prediction and analysis on the relevance of features using explainable artificial intelligence. In 2021 2nd Artificial Intelligence and Complex Systems Conference. p. 1–6. doi: 10.1145/3516529.3516530.
   Google Scholar
• Renard KG, Foster GR, Weesies GA, Porter JP. 1991. RUSLE, revised universal soil loss equation. J Soil Water Conserv. 46(1):30–33.
   Web of Science ®Google Scholar
• Rose CW, Coughlan KJ, Fentie B. 1998. Griffith University Erosion System Template (GUEST). In Modelling soil erosion by water. p. 399–412, Springer Berlin Heidelberg.
   Google Scholar
• Ruidas D, Pal SC, Saha A, Chowdhuri I, Shit M. 2022. Hydrogeochemical characterization based water resources vulnerability assessment in India’s first Ramsar site of Chilka lake. Mar Pollut Bull. 184:114107. doi: 10.1016/j.marpolbul.2022.114107.
   PubMed Web of Science ®Google Scholar
• Ruidas D, Pal SC, Towfiqul Islam ARM, Saha A. 2023. Hydrogeochemical evaluation of groundwater aquifers and associated health hazard risk mapping using ensemble data driven model in a water scares plateau region of eastern India. Expo Health. 15(1):113–131. doi: 10.1007/s12403-022-00480-6.
   Web of Science ®Google Scholar
• Sadhasivam N, Bhardwaj A, Pourghasemi HR, Kamaraj NP. 2020. Morphometric attributes-based soil erosion susceptibility mapping in Dnyanganga watershed of India using individual and ensemble models. Environ Earth Sci. 79(14):1–28. doi: 10.1007/s12665-020-09102-3.
   Web of Science ®Google Scholar
• Saha S, Gayen A, Pourghasemi H, Tiefenbacher J. 2019. Identification of soil erosion-susceptible areas using fuzzy logic and analytical hierarchy process modeling in an agricultural watershed of Burdwan district, India. Environ Earth Sci. 78(23):649. doi: 10.1007/s12665-019-8658-5.
   PubMed Web of Science ®Google Scholar
• Saha S, Sarkar R, Thapa G, Roy J. 2021. Modeling gully erosion susceptibility in Phuentsholing, Bhutan using deep learning and basic machine learning algorithms. Environ Earth Sci. 80(8):1–21. doi: 10.1007/s12665-021-09599-2.
   Web of Science ®Google Scholar
• Sarkar T, Mishra M. 2018. Soil erosion susceptibility mapping with the application of logistic regression and artificial neural network. J Geovisualization Spat Anal. 2(1):8. doi: 10.1007/s41651-018-0015-9.
   Google Scholar
• Shao K, Youssef K, Moon S, Bouchard L. 2019. Explainable AI landslide susceptibility modeling by superposable neural networks. In: AGU Fall Meeting Abstracts; p. EP43D–E2390.
   Google Scholar
• Silburn DM, Loch RJ. 1989. Evaluation of the CREAMS model. I. Sensitivity analysis of the soil erosion sedimentation component for aggregated clay soils. Soil Res. 27:545–561.
   Web of Science ®Google Scholar
• Sinshaw BG, Belete AM, Tefera AK, Dessie AB, Bizuneh BB, Alem HT, Atanaw SB, Eshete DG, Wubetu TG, Atinkut HB, et al. 2021. Prioritization of potential soil erosion susceptibility region using fuzzy logic and analytical hierarchy process, upper Blue Nile Basin, Ethiopia. Water-Energy Nexus. 4:10–24. doi: 10.1016/j.wen.2021.01.001.
   Google Scholar
• Talukdar S, Ahmed S, Naikoo MW, Rahman A, Mallik S, Ningthoujam S, Bera S, Ramana GV, Shahfahad. 2023. Predicting lake water quality index with sensitivity-uncertainty analysis using deep learning algorithms. J Cleaner Production. 406:136885. doi: 10.1016/j.jclepro.2023.136885.
   Web of Science ®Google Scholar
• Vogel H-J, Bartke S, Daedlow K, Helming K, Kögel-Knabner I, Lang B, Rabot E, Russell D, Stößel B, Weller U, et al. 2018. A systemic approach for modeling soil functions. SOIL. 4(1):83–92. doi: 10.5194/soil-4-83-2018.
   Web of Science ®Google Scholar
• Wan A, Dunlap L, Ho D, et al. 2020. NBDT: neural-backed decision trees. arXiv Prepr arXiv200400221.
   Google Scholar
• Youssef K, Shao K, Moon S, Bouchard L-S. 2022. XAI model for accurate and interpretable landslide susceptibility. arXiv Prepr arXiv220106837.
   Google Scholar
• Yunkai L, Yingjie T, Zhiyun O, Lingyan W, Tingwu X, Peiling Y, Huanxun Z. 2010. Analysis of soil erosion characteristics in small watersheds with particle swarm optimization, support vector machine, and artificial neuronal networks. Environ Earth Sci. 60(7):1559–1568. doi: 10.1007/s12665-009-0292-1.
   Web of Science ®Google Scholar
• Zhao Y, Gao G, Ding G, Wang L, Chen Y, Zhao Y, Yu M, Zhang Y., 2022. Assessing the influencing factors of soil susceptibility to wind erosion: A wind tunnel experiment with a machine learning and model-agnostic interpretation approach. Catena. 215:106324. doi: 10.1016/j.catena.2022.106324.
   Web of Science ®Google Scholar
• Zhou X, Wen H, Li Z, Zhang H, Zhang W. 2022. An interpretable model for the susceptibility of rainfall-induced shallow landslides based on SHAP and XGBoost. Geocarto Int. 37(26):13419–13450. doi: 10.1080/10106049.2022.2076928.
   Web of Science ®Google Scholar
• Ziadat FM, Zdruli P, Christiansen S, et al. 2022. An overview of land degradation and sustainable land management in the near East and North Africa. Sustain Agric Res. 11:11–24.
   Google Scholar