抄録
As the world’s fourth-largest food crop, potato starch content is a critical quality indicator that determines its processing performance and industrial value. The process of starch accumulation is significantly affected by various climatic factors, such as temperature, precipitation, and light intensity, as well as their interactions. Relying on big data analysis techniques, this study integrates multi-regional and multi-year monitoring data on potato starch content and climatic conditions to construct a multi-dimensional data correlation system between climatic factors and starch formation. Through correlation analysis, principal component analysis, and multi-model machine learning algorithms, the sensitivity and contribution rates of major climatic variables to starch accumulation were quantitatively analyzed. Furthermore, combined with transcriptome data, a regulatory network model of climatic factors on the expression of key genes for starch synthesis was established, revealing the potential influence mechanism of climate change on starch metabolic pathways at the molecular level. Case verification demonstrates that this model can predict the changing trends of potato starch content under different climatic scenarios with high accuracy. This research provides a theoretical basis and data support for potato variety improvement and the optimization of climate-adaptive cultivation strategies, while also offering a new methodological reference for big data-driven research on precise crop quality regulation.
