Search

Understanding annual extraction volumes and fluctuations in groundwater depth is essential in water resource management. This study applied various machine learning methods to predict the spatial variability of groundwater depletion (GWD) in an alluvial aquifer located along the southern coasts of the Caspian Sea (Mazandaran Plain). Initially, mean GWD values were measured from 250 piezometric wells across the plain. Subsequently, the factors controlling GWD were identified and provided. These factors encompass natural elements, including precipitation, evaporation, topography, groundwater depth, aquifer transmissivity, and proximity to water bodies. They also include anthropogenic factors such as extraction rates and proximity to industrial centres. Three machine learning models – Random Forest (RF), Deep Learning (DL), and Extreme Gradient Boosting (EGB) – were employed to model GWD using consistent training and test data. In this context, GWD was used as the output, and its controlling factors were incorporated as input variables. Correlation coefficients between GWD and its controlling factors revealed that the transmissivity of aquifer formations (R = 0.81), groundwater withdrawal within well radii (R = 0.69), and groundwater depth (R = 0.6) were the most significant factors. All three models demonstrated high efficacy during the training and testing stages. However, during testing, EGB offered the highest performance in modelling GWD due to extraction (R2 = 0.8, NSE = 0.82). The verified model was then used to predict annual drawdown or extraction across the plain. The predicted results were visually represented as an annual GWD or extraction map within a GIS framework. A comparison between observed GWD values in piezometric wells and the predicted values confirmed the robust performance of the proposed methodology (R2 = 0.8). This methodology can be employed effectively to predict spatial changes in GWD or annual extraction in other plains. [ABSTRACT FROM AUTHOR]

Soil erosion and sediment transport measurement is a time-consuming and difficult step yet important part of hydrological studies. Hence, use of models has become commonplace in estimating soil erosion and sediment transport. In this study, we used an artificial neural network (ANN) to simulate soil erosion rates. A geographic information system (GIS) was used as a pre-processor and post-processor tool to present the spatial variation of the soil erosion rate. The ANN was trained, optimized and verified using data from the Kasilian watershed located in the northern part of Iran. Field plots were used to estimate soil erosion values on the hillslopes. A Multi Layer Perceptron (MLP) network was adopted, where the soil erosion rate was the output variable and the rainfall intensity and amount, air and soil temperature, soil moisture, vegetation cover and slope were the inputs. After the training process, the network was tested. According to the test results, the ANN can estimate soil erosion with an acceptable level (coefficient of determination = 0.94, mean squared error = 0.04). The verified network and its inputs were used to estimate soil erosion rates on the hillslopes. Finally, a soil erosion rate map was generated based on the results of the verified network and GIS capabilities. The results confirm the high potential when coupling an ANN and a GIS in soil erosion estimation and mapping on the hillslopes. [ABSTRACT FROM AUTHOR]