Performance Assessment of Machine Learning Techniques for Gully Erosion Mapping in South-East Nigeria

Soil erosion is a serious environmental hazard affecting southeast Nigeria. The rate of erosion has continued to increase with devastating impact and has led to land degradation (gullies). To assess the socio-economic and environmental implications of gully erosion and to develop management plans to deal with them, quantitative and qualitative data on soil erosion rates at regional scales are needed. Hence, this study aimed at investigating the spatial and temporal variations of gully erosion impacted areas of South East Nigeria using machine learning techniques to develop a suitable approach for accurately modelling gully erosion impact in South East, Nigeria. Its objectives are to: acquire, process, and perform object-based gully mapping analysis with Kompsat-3 imagery of South East Nigeria, Nigeria using three machine learning algorithms (Linear discriminant analysis, Support Vector Machine, and Artificial Neural Network); compare the performance of the three selected machine learning algorithms using statistical techniques and determine the best suited for gully mapping within the study area; determine the pattern and trend of Gully Erosion in South East, Nigeria between 2010 and 2020, using the best-suited machine learning algorithm; and predict the future gully development pattern for the next 10 years. The methodology involved the acquisition and use of KOMPSAT-3 imagery, identification of gully erosion impacted areas, and topographic maps. Image preprocessing, development of classification scheme, object-based image analysis, trend analysis, and pattern of gully development and expansion. Accuracy assessment and gully development prediction to 2030 as data analysis. The results showed consistent identification of eight class features, including waterbody, dense vegetation, agricultural land, bare ground, built-up area, sand, savannah, and gully erosion. The performance evaluation of the three techniques revealed promising outcomes. LDA achieved an accuracy of 0.759, while SVM demonstrated a higher accuracy of 0.853 and balanced sensitivity and specificity. ANN showed good performance with an accuracy of 0.790. Based on its superior accuracy and balanced performance, SVM was selected for mapping the spatial trend of gully erosion in the study area.