Classification of Daily Weather Conditions using Decision Tree-Based Machine Learning Models: A Case Study of Kabul, Afghanistan

Authors

Ahmad Bilal Ahmadullah, Department of Energy Engineering, Engineering Faculty, Kandahar University, Kandahar 3801, AfghanistanFollow
Ahmad Shah Irshad, Department of Energy Engineering, Engineering Faculty, Kandahar University, Kandahar 3801, AfghanistanFollow
Basir Ahmad Khaled, Department of Hydraulics and Hydraulic Structures, Faculty of Environmental and Water Resources Engineering, Kabul Polytechnic University, Kabul 1010, AfghanistanFollow

Abstract

As global climate variability intensifies, the need for accurate and reliable weather forecasting becomes increasingly important. This study aimed to classify daily weather conditions in Kabul, Afghanistan, by comparing two decision-tree-based machine learning (ML) models that includes Decision Tree Classifier (DTC) and Extra Trees Classifier (ETC). A complete year dataset consisting of 366 daily meteorological observations collected from a central weather station in the region for 2024 was used. Results revealed that the DTC model consistently outperformed the ETC model, obtained an overall accuracy of 99% in both the training and testing phases, compared to the ETC model's accuracy of 96% (training) and 89% (testing). Specifically, the DTC model showed almost perfect weighted-average precision (0.99), recall (0.99), and F1-scores (0.99) for both phases training and testing respectively, whereas ETC demonstrated lower metrics in testing phase with weighted-average precision of 0.90, recall of 0.89, and F1-score of 0.88. Furthermore, sensitivity analysis demonstrated that precipitation probability is 40%, cloud cover is 31%, snow is 18%, temperature fleeks like max is 8%, and solar radiation is 3% as the most impactful variables in weather classification. Scientifically, this study contributes to enhancing the effectiveness of localized weather prediction, providing critical support for urban planning, agriculture, and disaster management decisions in regions with similar climatic conditions.

Recommended Citation

Ahmadullah, Ahmad Bilal; Irshad, Ahmad Shah; and Khaled, Basir Ahmad () "Classification of Daily Weather Conditions using Decision Tree-Based Machine Learning Models: A Case Study of Kabul, Afghanistan," AUIQ Technical Engineering Science: Vol. 2: Iss. 1, Article 6.
DOI: https://doi.org/10.70645/3078-3437.1025