Comparative Study of Wavelet–ANN and Wavelet– ARIMA Models for Groundwater Level Forecasting

Rashmi Tukaram Naik

doi:10.71097/IJSAT.v16.i4.9944

Comparative Study of Wavelet–ANN and Wavelet– ARIMA Models for Groundwater Level Forecasting

Author(s)	Ms. Rashmi Tukaram Naik
Country	India
Abstract	Groundwater is one of the most critical natural resources for sustaining life, agriculture, and economic activity, particularly in regions with high seasonal variability in rainfall and surface water availability. Accurate prediction of groundwater levels (GWL) is essential for effective water resource management, drought preparedness, and flood risk mitigation. This study presents a comparative analysis of two hybrid modelling approaches—Wavelet Transform combined with Artificial Neural Networks (WT+ANN) and Wavelet Transform combined with AutoRegressive Integrated Moving Average (WT+ARIMA)—for forecasting GWL in Britona, Goa. The Wavelet Transform was applied to decompose the original GWL series into approximation and detail components, effectively separating low-frequency trends from high-frequency fluctuations. For the WT+ANN model, these components were used as inputs to a feedforward neural network to capture complex nonlinear relationships. In the WT+ARIMA model, the approximation component was modelled with ARIMA while detail components were reconstructed to enhance short-term prediction accuracy. Performance was evaluated using the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), the coefficient of determination (R²), and the correlation between the observed and predicted series. Results show that WT+ANN achieved very high R² and correlation values, making it particularly suited for flood forecasting and rapid decisionmaking during extreme events. Conversely, WT+ARIMA consistently produced very low RMSE and MAE, indicating superior accuracy for long-term water policy planning and sustainable management. These findings demonstrate that the choice between WT+ANN and WT+ARIMA should be guided by the intended application—whether immediate risk response or strategic resource planning.
Keywords	Groundwater level prediction, Wavelet Transform, ARIMA, Artificial Neural Networks, Hybrid models, RMSE, R², flood forecasting, policy planning
Field	Mathematics > Statistics
Published In	Volume 16, Issue 4, October-December 2025
Published On	2025-12-25
DOI	https://doi.org/10.71097/IJSAT.v16.i4.9944
Short DOI	https://doi.org/hbgzf5

View / Download PDF File

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 16 Isu 3 Cover Page Vol 16 Isu 2 Cover Page Vol 16 Isu 1

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Comparative Study of Wavelet–ANN and Wavelet– ARIMA Models for Groundwater Level Forecasting

Share this