Pemodelan Statistik Spasial dalam Prediksi Pola Sebaran Penyakit Tropis di Asia Tenggara

Tropical diseases remain a serious public health challenge in Southeast Asia, particularly malaria, which has high morbidity and mortality rates. The complexity of their spread is influenced by various factors, including climate, environment, and population, requiring a spatially-based analytical approach to understand their distribution patterns. This study aims to develop a regression-based spatial model to predict the spread of tropical diseases and identify hotspots in high-risk areas. The data used include tropical disease case reports from national health agencies, climate data (temperature, rainfall, humidity) from BMKG and WorldClim, and population data (density and mobility) from  BPS and other official sources. The analysis was conducted using a Geographic Information System GIS for spatial mapping, as well as the application of spatial regression models, namely the Spatial Lag Model SLM and Spatial Error Model SEM. The results show that the developed model is able to predict disease distribution with a high level of accuracy, demonstrated by statistical validation through AIC, and Morans I. One of the main findings is the identification of malaria hotspots with a confidence level of 93, as well as the mapping of tropical disease risk predictions covering the Southeast Asian region. These results have significant implications for public health policy, particularly in resource allocation, prevention program planning, and priority area-based interventions. Furthermore, this study recommends the integration of big data and machine learning technologies to enrich predictive models and develop more adaptive early warning systems. Thus, this research contributes to strengthening tropical disease control strategies in Southeast Asia with a comprehensive spatial data-driven approach.