https://www.granthaalayahpublication.org/ojs-sys/ijoest/issue/feed International Journal of Engineering Science Technologies 2025-10-08T11:22:23+00:00 IJOEST Editorial Notification editor@ijoest.com Open Journal Systems <p>International Journal of Engineering Science Technologies is an open access peer reviewed journal that provides bi-monthly publication of articles in all areas of Engineering, Technologies and Science. It is an international refereed e-journal. IJOEST have the aim to propagate innovative research and eminence in knowledge. IJOEST Journals has become a prominent contributor for the research communities and societies. IJOEST Journal is making the bridge between research and developments.</p> <p>Editor-in-chief:<br />Dr. Pratosh Bansal (Professor, Department of Information Technology, Institute of Engineering &amp; Technology, Devi Ahilya Vishwavidyalaya, India)</p> <p>Managing Editor:<br />Dr. Tina Porwal (PhD, Maharani Laxmibai Girls P.G. College, Indore, India)</p> https://www.granthaalayahpublication.org/ojs-sys/ijoest/article/view/710 PROBABILISTIC FORECASTING OF CLIMATE EXTREMES USING EXTREME VALUE THEORY AND DEEP GENERATIVE MODELS 2025-07-10T11:02:13+00:00 Chauhan Priyank Hasmukhbhai chauhanpriyank7701@gmail.com Ritu Khanna chauhanpriyank7701@gmail.com <p>Accurate forecasting of climate extremes such as floods, heatwaves, and severe storms is vital for risk mitigation and climate resilience planning. Traditional statistical models often fail to capture the nonlinear dynamics and tail dependencies inherent in such events. This paper proposes a novel hybrid framework that integrates Extreme Value Theory (EVT) with Deep Generative Models (DGMs), specifically Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs), for probabilistic modeling and simulation of rare climate phenomena. EVT is employed to model the marginal distributions of extreme events using the Generalized Pareto and Generalized Extreme Value distributions. Meanwhile, DGMs learn latent representations from high-dimensional climate data and synthesize realistic, tail-aware samples. The proposed model captures both the statistical rigor of EVT and the expressive power of deep learning. Empirical evaluations are conducted using ERA5 reanalysis and satellite datasets, focusing on extreme precipitation and temperature anomalies across diverse regions. Results show that the hybrid EVT–DGM framework significantly improves tail risk estimation, return level prediction, and generative quality compared to conventional models. This approach provides a robust tool for data-driven climate risk forecasting under uncertainty.</p> 2025-10-08T00:00:00+00:00 Copyright (c) 2025 Chauhan Priyank Hasmukhbhai, Dr. Ritu Khanna