Se observó que el modelo ANN es el de mayor eficiencia, y que es acorde con otros hallazgos. La pluviosidad mensual, el índice topográfico de humedad (TWI index), la distancia al río y la ubicación geográfica fueron los datos ingresados, mientras que el índice de agua subterránea es el resultado de cada método. El 70 % de la información fue utilizada para probar los tres modelos, mientras que el 30 % se empleo en la evaluación y validación. Keywords: Land degradation Machine Learning Groundwater level Partial Least Square Regression (PLSR) Artificial Neural Networks (ANN) Adaptive Neuro-Fuzzy Inference System (ANFIS)Ĭon el fin de monitorear y predecir los niveles de agua subterránea en la cuenca Sharifabad, provincia Central de Irán, se utilizaron los modelos Regresión de mínimos cuadrados parciales (PLSR, del inglés Partial Least Square Regression), Redes neuronales artificiales (ANN, Artificial Neural Networks), y Sistema de inferencia de neurodifusión adaptativo (ANFIS, Adaptive Neuro-Fuzzy Inference System). In addition to the target variable, latitude and longitude play important roles in ordinary Krigging and decreased the total error of two combined models. Using ANN, it is predicted that 100% of the area was severely degraded for 2025. 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.
The results of ANN have been used in preparation of groundwater distribution map. It is observed that ANN has the highest efficiency, which agrees with other findings. 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. In all models, 70% of the data was used for training, while 30% of data were employed for testing and validation.
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.
0 kommentar(er)
