The prediction of soil moisture constants (SMCs), including field capacity (FC), permanent wilting point (PWP) and available water content (AWC), is essential for efficient irrigation scheduling and water management in the coastal regions of Bangladesh affected by salinity, flooding and waterlogging. However, the comparative evaluation of machine learning (ML) models for predicting SMCs in these complex coastal soils remains limited. Therefore, this study evaluated five ML models to predict SMCs using soil physicochemical parameters (pH; electrical conductivity; organic matter; bulk density; and sand, silt and clay fractions). The observed ranges were 6.5%–38.4%, 1.3%–15.5% and 5.1%–26.0% for FC, PWP and AWC, respectively. Among the applied models, the multilayer perceptron (MLP) achieved the best predictive performance, with
R
2
values of 0.926, 0.911 and 0.906 for FC, PWP and AWC, respectively, whereas MLR showed the weakest performance, with corresponding
R
2
values of 0.804, 0.761 and 0.738. Compared with the other models, MLP improved
R
2
by 3%–23% and reduced RMSE by 13%–40% across FC, PWP and AWC. Using input combination‐5 (IC‐5), the MLP explained more than 89% of the variability and achieved up to 98% prediction accuracy, highlighting its strong potential for predicting SMCs in coastal soils to support agricultural productivity.
M. S. Islam, Mohammad Ismail, J. Basak et al.· Irrigation and Drainage· 0 citations
The availability of groundwater resources varies spatially due to hydrogeological, geomorphological, and environmental factors, representing a significant threat to agricultural sustainability in the drought-prone Barind Tract of Bangladesh. This study aimed to identify groundwater potential zones (GWPZ) in Naogaon district using an integrated approach combining remote sensing (RS), geographic information system (GIS), and the analytic hierarchy process (AHP). Eleven thematic layers including geology, lineament density, topographic wetness index (TWI), drainage density, rainfall, land use and land cover (LULC), soil type, slope, curvature, distance from rivers (DFR), and elevation were weighted and integrated using weighted overlay analysis. Multicollinearity assessment indicated no significant multicollinearity among the parameters, and sensitivity analysis identified lineament density, geology, and drainage density as the most influential factors. The resulting GWPZ map classified the district into very low (9.07%), low (23.36%), moderate (27.81%), high (26.10%), and very high (13.66%) potential zones, with high and very high zones concentrated in the central and eastern parts and low potential zones in the northwestern and southwestern regions. Model validation using the ROC curve yielded an AUC of 0.821, indicating very good predictive performance. The GWPZ map can support groundwater management by identifying suitable locations for new wells, prioritizing artificial recharge sites, and guiding sustainable irrigation planning in the Barind Tract.
M. G. A. Yeamin, Mohammad Ismail, J. Basak et al.· Discover Geoscience· 0 citations