Integrating Remote Sensing and Meteorological Data to Predict Wheat Stripe Rust

Wheat stripe rust poses a serious threat to wheat production. An effective prediction method is important for food security. In this study, we developed model based on vegetation indices and meteorological features. First, time-series Sentinel-2 remote sensing images data, phenology (jointing date) was estimated using the harmonic analysis of combined with average cumulative temperature. Then, were extracted phenological information. Meteorological features screened correlation independent t-test analysis. Finally, random forest (RF) used construct rust. The results showed that RF input combination (phenological information-based features) produced higher accuracy kappa coefficient 88.7% 0.772, respectively. outperformed single-date image-based indices, overall improved from 62.9% 78.4%. These indicated combining can be prediction. provide guidance suggestions disease prevention in study area.