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{177899,
        author = {Utkarsh Kumar Singh and Shivam Chauhan and Dr. Ajay Shankar},
        title = {Weather Forecast Using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {3367-3370},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=177899},
        abstract = {Weather foretelling is an essential part of our quotidian lives, helping us plan and prepare for what’s ahead lives, shaping opinions that impact society, the frugality, and the terrain. Traditional styles, like numerical downfall vaticination (NWP), depend on intricate physical models and demand significant computational power. In recent times, machine knowledge (ML) has gained attention as a important volition. By studying patterns in the downfall, we gain precious perceptivity that help us understand and prognosticate unborn conditions literal and real- time downfall data, ML can deliver hastily and constantly more accurate prognostications. This study delves into how ML ways can be applied to cast vital variables similar as Temperature, rush, and wind patterns come together to shape the world around us, impacting quotidian life and the terrain, and extreme downfall events. The study examines a variety of machine knowledge styles, ranging from straightforward approaches like direct retrogression to more advanced ways samples include support vector machines, decision trees, convolutional neural networks (CNNs), and long short- term memory networks (LSTMs), each offering unique ways to dissect and interpret data. short- term memory(LSTM) networks. It also tackles important challenges, including icing data responsibility, conforming models to different regions, and maintaining computational effectiveness. To assess the effectiveness of these styles, the study Evaluates how their performance measures up against traditional styles reading ways using criteria like mean absolute error (MAE) and root mean square error (RMSE). The findings illuminate the remarkable eventuality of Mean absolute error (MAE) and root mean square error (RMSE) are used to assess delicacy foretelling delicacy, especially for short- to medium- term prognostications. Integrating ML models with traditional drugs- rested styles offers the The eventuality for achieving indeed better results. unborn exploration Could work on making models more transparent, exercising data from satellite systems and IoT bias, and using advanced computing technologies to enable real- time foretelling. This study showcases how ML can transfigure downfall vaticination, making it hastily, farther dependable, and more effective.},
        keywords = {},
        month = {May},
        }