A Hybrid Spatiotemporal Learning for the Regional Agroclimatic Mapping and Genotypic Resilience Analysis: A Case Study of Areca Nut Yield in Central Karnataka

Abstract

The last few years have witnessed an exponential rise in the demand of precision agriculture that needs a robust agroclimatic mapping. The nonlinearity, spatial, temporal and region-specific climate interactions which governs the production makes the crop–climate mapping a challenging task. Centered on areca nut yield, in the present study, a novel spatiotemporal integrated hybrid RF attention-BiLSTM framework is developed to analyze the crop and climate associations in Central Karnataka. By integrating a comprehensive data preprocessing strategy, including missing-value estimation, outlier treatment, scale normalization, data stratification, and SMOTE–ENN resampling, the developed model captured the region-specific climate sensitive production pattern. The hybrid model achieved an R2 value of 0.914, RMSE of 0.39, and correlation coefficient of 0.956, outperforming conventional models. The repeated-run, statistical, and ablation analyses further demonstrated the model consistency and the effectiveness of integrated hybrid framework. Further, a genotype analysis is performed to analyze resilience and stability of different areca nut varieties. The overall statistical results confirm robustness of the proposed framework, where the ability to amalgamate data-level optimization, attention-driven temporal learning, and ensemble modeling enables it robust and hence well-suited for complex, real-world time-series agroclimatic mapping and prediction tasks for areca nut precision agriculture decisions.