Abstract :

Accurate Prediction Of Groundwater Levels Is Crucial For Sustainable Water Resource Management, Especially In Regions Facing Water Scarcity. Traditional Statistical And Machine Learning Models Often Struggle To Capture The Complex Spatial-temporal Dependencies Inherent In Groundwater Systems. This Study Proposes A Hybrid Approach Combining Random Forest (RF) And Deep Convolutional Neural Networks (DCNN) To Enhance Groundwater Level Prediction Accuracy. The Random Forest Algorithm Is Utilized To Select The Most Significant Hydro-meteorological Features And Reduce Dimensionality, While The DCNN Effectively Captures Non-linear And Spatialtemporal Patterns From The Processed Data. The Hybrid Model Is Trained And Validated Using Historical Groundwater Observations, Rainfall, Temperature, And Other Relevant Environmental Parameters. Experimental Results Demonstrate That The Proposed RF-DCNN Model Outperforms Conventional Models In Terms Of Prediction Accuracy, Robustness, And Generalization Capability. This Approach Provides A Reliable Tool For Water Resource Planners And Policymakers To Anticipate Groundwater Fluctuations And Make Informed Decisions For Sustainable Water Management.

Published:

28-10-2025

Issue:

Vol. 25 No. 10 (2025)

Page Nos:

169-174

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite