Year: 2025
Type: article
Abstract: Predicting the amount of rain is important for many industries, including agriculture, water resource management, and disaster relief. The intricate spatiotemporal patterns of rainfall are often difficult for traditional technologies to adequately represent. By utilising historical data and meteorological variables, machine learning (ML) techniques present a viable method for improving rainfall prediction. Rainfall prediction tasks have been subjected to a variety of machine learning techniques, including as decision trees, random forests, support vector machines (SVM), and deep learning models. Hybrid models and ensemble approaches have also been suggested as ways to increase forecast robustness and accuracy. ML-based rainfall prediction exhibits a great deal of promise for rapid and accurate forecasting, supporting decision-making in crucial industries affected by weather variability.
Source: Journal of Neonatal Surgery
Authors: Viswanathan Ramasamy Reddy, Sukham Romen Singh, Elangovan Guruva Reddy, E. Punarselvam E. Punarselvam, T. Vengatesh T. Vengatesh
Language: English
Subfield: Environmental Engineering
Field: Environmental Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4409952457