<![CDATA[The agricultural sector plays a strategic role in supporting Indonesia’s food security and national economy. Agricultural productivity in South Kalimantan Province, particularly in Barito Kuala Regency, is strongly influenced by climatic dynamics such as temperature variation, rainfall, and humidity. This study develops a crop yield prediction model for major food commodities (rice, corn, and tubers) based on weather factors using the Naïve Bayes algorithm as a Decision Support System (DSS) to mitigate crop failure risks. The research data were obtained from the Meteorology, Climatology, and Geophysics Agency (BMKG) and the Central Bureau of Statistics (BPS) of Barito Kuala Regency for the period 2018–2023, covering temperature, rainfall, humidity, sunlight duration, and yield production. The research stages include data preprocessing (cleaning, missing value imputation, augmentation, and labeling), machine learning modeling, and performance evaluation using accuracy and weighted F1-score metrics. The experimental results show that the Naïve Bayes model can classify crop yield categories (high, medium, low) with an accuracy of 90% and a weighted F1-score of 0.89. These results demonstrate stable and consistent performance across various climatic conditions. The main advantage of this study lies in the integration of local weather data with a lightweight machine learning model that is computationally efficient and easily implemented in regional agricultural prediction systems. This research provides a tangible contribution to strengthening food security and data-driven agricultural risk management in tropical humid regions such as South Kalimantan.]]>
Copyrights © 2025
