Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{184548,
        author = {Sagar Shandilya and K. Venkata Rao},
        title = {Groundwater Level Prediction Using a Hybrid LSTM–Prophet Model},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {4},
        pages = {1824-1832},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=184548},
        abstract = {Although groundwater is crucial for residential, agricultural and industrial use but the water security is now under tremendous risk owing to over-extraction, climate change and changes in land use. Traditional groundwater level prediction methods, such as manual monitoring and empirical models, struggle with automation, scaling and capturing complex non-linear interaction between the influencing factors.  To solve these problems, this research proposes a prediction framework based on machine learning (ML) that increases efficiency, accuracy and adaptability.  The system integrates a range of information, including historical groundwater levels, rainfall, temperature, soil characteristics, land use and also handles missing data using imputation techniques. Long Short-Term Memory (LSTM) networks and Prophet are the examples of advanced ML models that are used to predict outcomes and capture complex patterns far better than the conventional statistical models. The robustness of the model is further improved by incorporating feature engineering and cross-validation. This suggested ML-driven solution performs better as it is automated, scalable across contexts and accurate in prediction.These ML-based solutions address the shortcomings of the pre-existing methods and offers a pragmatic sustainable groundwater management. Thereby, aiding in better planning for water resources as well as the environmental preservation.},
        keywords = {Groundwater Storage (GWS), Machine Learning (ML), LSTM (Long-Short Term Memory), Prophet, Soil Moisture, Terrestrial Water Storage (TWS), GRACE/GRACE-OF},
        month = {September},
        }