Machine Learning Approaches for Wind Speed Prediction: A Case Study in Ajman, UAE

Authors

  • Kais Muhammed Fasel University of Bolton
  • Peter Farrell University of Bolton
  • Abdul Salam Darwish University of Bolton

DOI:

https://doi.org/10.14464/ess.v11i9.675

Abstract

This study presents a novel methodology for error-correcting publicly available NASA wind data and making it more accurate for location-specific wind resource assessments for the emirate of Ajman, UAE. The approach integrates maximum climate and environmental variables, data-driven techniques and machine learning algorithms, addressing the inherent errors in publicly available NASA satellite data. The study establishes error correction factors for satellite-derived wind speed data, enhancing the dependability of wind speed data for sustainable wind resource assessment and power production forecasting. The findings of this study have significant implications for wind energy industry stakeholders and the government for decision-making and sustainability initiatives.

Author Biographies

Kais Muhammed Fasel, University of Bolton

School of Civil Engineering and Built Environment

Peter Farrell, University of Bolton

School of Civil Engineering and Built Environment

Abdul Salam Darwish, University of Bolton

School of Civil Engineering and Built Environment

ESS

Downloads

Published

2024-09-05