Rice False Smut Detection and Prescription Map Generation in a Complex Planting Environment, with Mixed Methods, Based on Near Earth Remote Sensing

Abstract

Rice false smut is known as the cancer of rice. The disease is becoming increasingly prominent and is one of the major diseases in rice. However, prevention and treatment of this disease relies on “Centralized pesticide spraying”. However, indiscriminate spraying leads to more pesticide residue, and impacts ecological and food safety. To obtain more objective results, different experimental planting forms are necessary. This study collected data at a complex planting environment based on “near earth remote sensing” using a frame-based hyperspectral device. We used mixed detection methods to differentiate between healthy rice and U. virens infected rice. There were 49 arrangements and more than 196 differentiation models between healthy and diseased rice, including 7 sowing data plots, 2 farm management types, and 23 pattern recognition methods. Finally, the real accuracy was mostly above 95%. In particular, with the increase of epoch and iteration, feature sequences based on deep learning could achieve better results; most of the accuracies were 100% with 100 epochs. We also found that differentiation accuracy was not necessarily correlated with the sowing dates and farm management. Finally, the detection method was verified according to the actual investigation results in the field. The prescription map of disease incidence was generated, which provided a theoretical basis for the follow-up precision plant protection work.