Potato Late Blight Severity and Epidemic Period Prediction Based on Vis/NIR Spectroscopy

Late blight caused by Phytophthora infestans is a destructive disease in potato production, which can lead to crop failure severe cases. This study combined visible/near-infrared (Vis/NIR) spectroscopy with machine learning (ML) and chemometric methods for rapid detection of late blight. The determination severity was accomplished two directly or indirectly based on differences reflectance. One approach utilize ML algorithms build model that reflects the relationship between level spectral Another method first use partial least squares construct predictive internal physicochemical values, such as relative chlorophyll content (SPAD) peroxidase (POD) activity, then an classify levels predicted values. classification accuracy these could reach up 99 95%, respectively. changes values during development were further investigated. Regression models fitting SPAD value POD activity developed temperature incubation time, coefficients 0.961 0.997, prediction epidemic period realized combining regression 88.5%. It demonstrated non-destructive Vis/NIR feasible. Furthermore, it possible guide control throughout period.