Machine learning for temperature analysis in Ouagadougou: A Random forest perspective
Loading...
Date
2024-08-01
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
EDRAAK
Abstract
Temperature variety analysis is pivotal for understanding climate patterns and foreseeing future changes especially in parched and semiarid regions This study investigates the application of the RF algorithm for temperature prediction in Ouagadougou Burkina Faso leveraging historical climate data The demonstrate is prepared on Climate Investigate Unit CRU data to evaluate its prescient performance in capturing seasonal and long-term temperature patterns Comparative analysis is conducted to evaluate the viability of RF against conventional forecasting strategies The results show that the RF model illustrates tall predictive accuracy making it a dependable tool for temperature estimating in bone-dry climates These discoveries contribute to climate versatility techniques and decision-making for sustainable natural arranging within the region.
Description
Keywords
Random Forest, Prophet model, Arid Climate, Predictive Modeling
Citation
Ali, G., & Robert, W. Machine learning for temperature analysis in Ouagadougou: A Random forest perspective