Sustainable long-term wind speed forecasting using hybrid LSTM and random forest regression models

View at publisher Summarise with VIRAT
Authors: T. Magesh, G. Devi, L. Annie Isabella, J. Jayaudhaya, Raja Thangavelu, M. Thiyagesan
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

As worldwide demand for energy rises and traditional fuel resources dwindle, sources of clean energy such as wind energy become increasingly important. Hybrid LSTM and RF model to predict long-term wind speed ahead: An efficient approach for sustainability. Using a three-year period of wind information from Coimbatore, Tamil Nadu, the algorithm combines RFR’s ability to capture linear correlations and seasonal with LSTM’s ability to deal with complicated nonlinear trends and long-term dependencies. The hybrid model surpasses individual models in performance parameters such as MSE, RMSE, and MAE, with a R 2 value of 0.9795 and a precision of 97.82%. This expanded predictive capacity delivers useful information for wind energy, weather, and planning for the environment, increasing the preciseness of the wind speed estimates and enabling more reliable renewable energy systems.

Fields of Study & Subjects

Energy Load and Power Forecasting Solar Radiation and Photovoltaics Stock Market Forecasting Methods

Publication details

Journal / source
CRC Press eBooks
Pages
326–333
Publication date
19 March 2026
Language
EN
Document type
Book chapter