Resumen

HABIBI, Vahid; AHMADI, Hassan; JAFFARI, Mohammad  y  MOEINI, Abolfazl. Prediction of land degradation by Machine Learning Methods: A Case study from Sharifabad Watershed, Central Iran. Earth Sci. Res. J. [online]. 2021, vol.25, n.3, pp.353-362.  Epub 02-Jun-2022. ISSN 1794-6190.  https://doi.org/10.15446/esrj.v25n3.75821.

To monitor and predict the Groundwater levels in Sharifabad watershed, Central province, Iran three models of Partial Least Square Regression (PLSR), Artificial Neural Networks (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) have been used. In all models, 70% of the data was used for training, while 30% of data were employed for testing and validation. Monthly rainfall, topographic wetness index (TWI index), the distance from the river, Geographic location was the inputs and the level of groundwater was the output of each method. It is observed that ANN has the highest efficiency, which agrees with other findings. The results of ANN have been used in preparation of groundwater distribution map. According to the potential desertification map and groundwater level index, the potential of desertification had become severe since 2002 and was at a rate of 60% of land area, which, due to incorrect land management in 2016, increased to almost 98% of the land surface in the study area. Using ANN, it is predicted that 100% of the area was severely degraded for 2025. In addition to the target variable, latitude and longitude play important roles in ordinary Krigging and decreased the total error of two combined models.

Palabras clave : Land degradation; Machine Learning; Groundwater level; Partial Least Square Regression (PLSR); Artificial Neural Networks (ANN); Adaptive Neuro-Fuzzy Inference System (ANFIS).

        · resumen en Español     · texto en Inglés     · Inglés ( pdf )