Comparative Analysis of Weather-Based Indexes and the Actuaries Climate Index$^{TM}$ for Crop Yield Prediction

Climate change poses significant challenges to agriculture sector, affecting both crop productivity and economic stability. This study investigates the utility of climate indexes in predicting crop yields under diverse climatic conditions. Using generalized statistical models and machine learning algorithms, this research compares the predictive performance of long-established weather-based indexes with the Actuaries Climate Index$^{TM}$ (ACI), a newer entrant in the field, showcasing its potential for real-time applications and broader applicability across various sectors. To enhance model reliability and address multicollinearity among weather-related variables, the study incorporates both principal component analysis and functional principal component analysis. A total of 22 models, each constructed with different explanatory variables, highlight the significant impact of wind speed and sea-level changes alongside temperature and precipitation on crop yield variability. Furthermore, the ACI exhibits strong predictive capabilities, offering valuable insights for climate risk assessment and decision-making in agriculture and insurance-related sectors.