Copyright © 2026 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{199124,
        author = {GK ABANI KUMAR DASH and HEMANGINI DALEI and Dr. Uttam Panda},
        title = {THE FEASIBILITY STUDY OF RAINWATER HARVESTING USING MACHINE LEARNING TECHNIQUE},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {15218-15226},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199124},
        abstract = {This study addresses urban water scarcity by proposing a Long Short-Term Memory (LSTM)-based predictive framework for rainwater harvesting (RWH) that integrates historical rainfall data, roof catchment characteristics, and building water-use patterns to estimate daily demand and harvested yield. The pipeline involves data preprocessing, sequence-based LSTM modelling, and feasibility analysis covering tank sizing, annual offset, and system reliability. Experimental validation on a real-world office dataset achieved high accuracy (R² = 0.9673, MAE = 1.6696 training, 0.1742 testing), with predicted yields aligning closely with observed patterns. Compared to statistical and persistence models, the LSTM approach improved demand forecasting, reduced sizing bias, and provided reliable, cost-effective recommendations for sustainable urban water management.},
        keywords = {Rainwater harvesting, LSTM, water demand forecasting, system reliability, urban water sustainability.},
        month = {April},
        }