Rice (Oryza sativa L.) Growth Modeling Based on Growth Degree Day (GDD) and Artificial Intelligence Algorithms

Rice (Oryza sativa L.) growth prediction is key for precise rice production. However, the traditional linear forecasting model ineffective under rapidly changing climate conditions. Here we show that rate (Gr) can be well-predicted by artificial intelligence (AI)-based neural networks (ANN) and gene-expression programming (GEP), with accumulated air temperatures based on degree day (GDD). In total, 10,246 Gr from 95 cultivations were obtained three cultivars, TK9, TNG71, KH147, in Central Southern Taiwan. The performance was evaluated Pearson correlation coefficient (r), root mean square error (RMSE), relative RMSE (r-RMSE) whole period (lifecycle), as well average specific stages (transplanting, 50% initial tillering, panicle initiation, heading, physiological maturity). results lifecycle modeling showed ANN GEP models had comparable r (0.9893), but lowest (3.83 days) r-RMSE (7.24%). stage stages, each has its own best-fit period. Overall, recommended considering performance, applicability, routine farming work. This study may lead to smart production due enhanced capacity predict field.