Soil erosion potential hotspot zone identification using machine learning and statistical approaches in eastern India
- PDF / 6,526,579 Bytes
- 36 Pages / 439.37 x 666.142 pts Page_size
- 40 Downloads / 158 Views
Soil erosion potential hotspot zone identification using machine learning and statistical approaches in eastern India Rabin Chakrabortty1 · Subodh Chandra Pal1 · Mehebub Sahana2 · Ayan Mondal3 · Jie Dou4,5 · Binh Thai Pham6 · Ali P. Yunus7 Received: 7 January 2020 / Accepted: 27 July 2020 © Springer Nature B.V. 2020
Abstract Land degradation is very severe in the subtropical monsoon-dominated region due to the uncertainty of rainfall in the long term, and most of the rainfall occurs with high intensity and kinetic energy over short time periods. So, keeping this scenario in view, the main objective of this work is to identify areas vulnerable to soil erosion and propose the most suitable model for soil erosion susceptibility in subtropical environment. The implementation of machine learning and artificial intelligence techniques with a GIS environment for determining erosion susceptibility is highly acceptable in terms of optimal accuracy. The point-specific values of different elements from random sampling were considered for this study. Sensitivity analysis of the predicted models (i.e., analytical neural network, geographically weighted regression and GWR–ANN ensemble) was performed using the maximum causative factors and related primary field observations. The area under curve of receiver operating system reveals precision with 87.13, 89.57 and 91.64 for GWR, ANN and ensemble GWR–ANN, respectively. The ensemble GWR–ANN is more optimal than the GWR, ANN for determining water-induced soil erosion susceptibility. The process of soil erosion is not a unidirectional process, so the multidimensional impacts from the conditioning factors have to be determined precisely by considering the maximum possible factors as well as selecting optimal models for specific regions. Keywords Land degradation · Soil erosion · Random sampling · Ensemble GWR–ANN · Unidirectional process
1 Introduction Water-induced soil erosion in the tropical and subtropical regions is one of the major issues of global importance in terms of the depletion of fertile soil and its transformation into barren and unproductive land. The subtropical region dominated by the monsoon climate has unique features in terms of seasonal temperature fluctuation and the associated rainfall occurrence. * Subodh Chandra Pal [email protected] Extended author information available on the last page of the article
13
Vol.:(0123456789)
Natural Hazards
The monsoon season is correlated with a more important rainfall event frequency that has both direct and indirect effects on the depletion of soil. The short-term soil erosion and its consequences cannot be accurately defined, but the effect of soil erosion can be clearly observed in the long term (Parveen et al. 2012). We can see from the records that soil erosion can destroy a whole civilization and its associated means of living (Boardman and Favis-mortlock 1998). The subtropical area is highly populated and most of the people are dependent on systems of rainfed agricultural production. But this area was fac
Data Loading...
