Ground Water Modelling

S. VIVEKANANDHA REDDY1, Ms. Priyanka (GUIDE) 2 B. MANJULA 3, V. RAJA SEKHAR4 , RISHI RAJ 5

1 Dept. of CSE, Siddhartha Institute of Technology and Sciences,  21tq1a6746@siddhartha.co.in

2 Dept. of CSE, Siddhartha Institute of Technology and Sciences, Jalagapriyanka.cse@siddhartha.co.in

3 Dept. of CSE, Siddhartha Institute of Technology and Sciences, 21tq1a6713@siddhartha.co.in

4 Dept. of CSE, Siddhartha Institute of Technology and Sciences, 22tq5a6703@siddhartha.co.in

5Dept. of CSE, Siddhartha Institute of Technology and Sciences, 21tq1a6738@siddhartha.co.in

Abstract -This study presents a groundwater level prediction model developed using a Deep Convolutional Neural Network (DCNN) to support sustainable water resource management. Historical hydro-meteorological data including irrigation, rainfall, temperature, and evaporation were utilized from a dataset comprising 168 records. The data was divided into 80% for training and 20% for testing. A six-layer DCNN was designed and implemented using TensorFlow to capture complex, non-linear relationships within the data. The model's performance was benchmarked against the Random Forest algorithm, which achieved 20% accuracy, while the DCNN demonstrated significantly better predictive capability with 95% accuracy. The results affirm the potential of deep learning in modeling environmental data, even with relatively small datasets, and offer a promising direction for improving the accuracy of groundwater level forecasting for real-world applications..

Key Words:  groundwater prediction, deep learning, DCNN, hydro-meteorological data, TensorFlow, environmental modeling