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{174090,
        author = {Vanshita Sonule and V.N.Mahawadiwar and Aditya Sapate and Ajay Pipare},
        title = {SPI-Based Drought Forecasting in Maharashtra Using LSTM: A Decadal Analysis (2014-2024)},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {10},
        pages = {2825-2832},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=174090},
        abstract = {The study, Maharashtra Drought Analysis Data, utilizes the LSTM (Long Short-Term Memory) model to predict climate variables such as the Standardized Precipitation Index (SPI) to enhance drought forecasting in Maharashtra. The methodology begins with meticulous data collection from reliable meteorological sources, focusing on the dataset, which contains records of precipitation, and SPI across various timeframes (1-month to 12-month). This database spans several years, capturing temporal climate variability for long-term trend analysis. Data are preprocessed to handle missing values, outliers, and inconsistencies to ensure integrity and reliability of time series analysis. Exploratory Data Analysis (EDA) uses visualization techniques to identify trends, seasonal, and long-term climate variability to comprehend SPI behavior. Joint temperature charts and line plots highlight inter-annual and seasonal climate trends. LSTM shows a better prediction performance of 94.72% in comparison to other time series models, representing complex temporal relationships with precision. The study enhances decision-making and forecasting drought, with application in agriculture, water resources management, and environmental monitoring in Maharashtra. The study demonstrates the strength of LSTM to climate forecasting, providing valuable information for overcoming the effect of drought, minimizing the optimal resource utilization, and achieving sustainable development.},
        keywords = {Drought prediction, Drought analysis, Remote sensing, Standardized Precipitation Index (SPI), Precipitation trends.},
        month = {March},
        }