Integrasi Data Science dan Scientific Modeling dalam Analisis Perubahan Iklim untuk Mendukung Pengambilan Keputusan Berkelanjutan

Abstract

Climate change is a global challenge with significant impacts on the environment, economy, public health, and food security. Its complexity requires advanced analytical approaches capable of processing large datasets and generating accurate predictive models to support sustainable decision-making. This study aims to integrate Data Science and Scientific Modeling to analyze climate change patterns and identify key factors influencing regional climate dynamics. The dataset includes air temperature, rainfall, humidity, carbon emissions, and land cover data collected from official sources over the past ten years. The research process involves data collection, data cleaning, exploratory analysis, predictive model development, and model evaluation using statistical indicators. Data Science methods are applied through data analysis, visualization, and machine learning algorithms to uncover hidden patterns beyond conventional analysis. Scientific Modeling is used to simulate climate change scenarios based on environmental and human activity variables. The results show that increased carbon emissions and land use changes significantly influence rising annual temperatures and shifting rainfall patterns. The developed model achieves high predictive accuracy for medium- and long-term climate trends. Furthermore, simulations indicate that emission reduction policies and green area expansion can improve climate stability. This integrated approach enhances analytical quality and supports evidence-based climate policy development.