<![CDATA[Aviation safety is a concern in global air transportation, where adverse weather conditions, including heavy rainfall, high humidity, and strong winds, can disrupt flight operations and threaten passenger and crew safety. Sultan Mahmud Badaruddin II (SMB II) Airport in Palembang, South Sumatra, operates within a tropical climate marked by extreme humidity and frequent heavy rainfall. This study applies the interpretable Decision Tree algorithm using an information gain criterion to reproduce a multivariable weighted-scoring classification of same-day aviation weather risk and generate transparent, auditable decision rules. The study uses meteorological data from the Indonesian Meteorological, Climatological, and Geophysical Agency (BMKG), covering May 2025 to May 2026, comprising 371 daily records with five attributes: average temperature (Tāvg), relative humidity (RH_avg), rainfall (RR), wind direction (DDD_X), and wind speed (FF_avg). Risk labels were derived from a weighted-scoring system grounded in BMKG thresholds and references from the Civil Aviation Safety Regulation (CASR) and International Civil Aviation Organization (ICAO), yielding three classes: Safe (40.7%), Caution (39.1%), and Dangerous (20.2%). Data were split 80:20 with stratified sampling. The Synthetic Minority Over-sampling Technique (SMOTE) was applied to balance the training data. The model achieved 91.89% accuracy on the test set, with perfect recall on the Dangerous class (recall = 1.00, F1-score = 0.94). Because four of the five attributes are also used to construct the scoring labels, this accuracy primarily reflects the Decision Tree model's ability to reproduce the scoring structure rather than independently validating against actual operational risk.]]>
