Evaluation of Different Machine Learning Models for Predicting Soil Erosion in Tropical Sloping Lands of Northeast Vietnam
Open Access
- 2 April 2021
- journal article
- research article
- Published by Hindawi Limited in Applied and Environmental Soil Science
- Vol. 2021, 1-14
- https://doi.org/10.1155/2021/6665485
Abstract
Soil erosion induced by rainfall under prevailing conditions is a prominent problem to farmers in tropical sloping lands of Northeast Vietnam. This study evaluates possibility of predicting erosion status by machine learning models, including fuzzy k-nearest neighbor (FKNN), artificial neural network (ANN), support vector machine (SVM), least squares support vector machine (LSSVM), and relevance vector machine (RVM). Model evaluation employed a historical dataset consisting of ten explanatory variables and soil erosion featured four different land use managements on hillslopes in Northwest Vietnam. All 236 data samples representing soil erosion/nonerosion events were randomly prepared (80 for training and 20 for testing) to assess the robustness of the five models. This subsampling process was repeatedly carried out by 30 rounds to eliminate the issue of randomness in data selection. Classification accuracy rate (CAR) and area under receiver operating characteristic (AUC) were used to evaluate performance of the five models. Significant difference between different algorithms was verified by the Wilcoxon test. Results of the study showed that RVM model achieves the best outcomes in both training (CAR=92.22 and AUC=0.98) and testing phases (CAR=91.94 and AUC=0.97). Four other learning algorithms also demonstrated good performance as indicated by their CAR values surpassing 80 and AUC values greater than 0.9. Hence, these results strongly confirm the efficacy of applying machine learning models for soil erosion prediction.Keywords
Funding Information
- National Foundation for Science and Technology Development (105.08-2017.302)
This publication has 64 references indexed in Scilit:
- An insight into classification with imbalanced data: Empirical results and current trends on using data intrinsic characteristicsInformation Sciences, 2013
- Redistribution of carbon and nitrogen through irrigation in intensively cultivated tropical mountainous watershedsBiogeochemistry, 2011
- WEPP and ANN models for simulating soil loss and runoff in a semi-arid Mediterranean regionEnvironmental Monitoring and Assessment, 2010
- Artificial Neural Network estimation of soil erosion and nutrient concentrations in runoff from land application areasComputers and Electronics in Agriculture, 2008
- Evaluation of suspended load changes using AnnAGNPS and SWAT semi-empirical erosion modelsCATENA, 2008
- A review of erosion and sediment transport modelsEnvironmental Modelling & Software, 2003
- Artificial neural networks of soil erosion and runoff prediction at the plot scaleCATENA, 2003
- Factors affecting soil erosion hazards and conservation needs for tropical steeplandsSoil Technology, 1997
- Using monthly precipitation data to estimate the R-factor in the revised USLEJournal of Hydrology, 1994
- Training feedforward networks with the Marquardt algorithmIEEE Transactions on Neural Networks, 1994