A smartphone application for site-specific pest management based on deep learning and spatial interpolation

Pests can cause huge yield loss in crop production without timely and effective monitoring methods. The traditional method of manually counting pests is time-consuming and causes bias between different observers. Therefore, this study developed an Android -based smartphone application for automated pest counting using a deep learning model (YOLOv7 tiny). This study evaluated the smartphone application using twospotted spider mite (TSSM) detection as a case study and compared it with the manual counting method. The smartphone application records the total number of pests and the GPS coordinates into a MySQL database. The spatial interpolation method was used to generate a spatial distribution map of TSSM in real-time, which could guide growers to apply the right amount of pesticide at the right location. To train the deep learning model for TSSM detection, 3,348 images were collected using three smartphones. The YOLOv7 tiny model was trained at three input image sizes (160x160, 320x320, and 640x640 pixels). The model trained at 320x320 pixels was chosen to deploy on the smartphone application because of the superior performance for both detection accuracy and inference speed. The Android -based smartphone application was installed on two widely used smartphones (Samsung Galaxy S10e and LG Stylo 6) for field testing. The counting accuracy of TSSM motiles (all life stages except eggs) and TSSM eggs using the smartphone application was 78.1% and 75.3%, respectively. The average counting speed of the smartphone application was 233 s per strawberry (trifoliate) leaf. The smartphone application had higher counting accuracy (7.1% higher for TSSM motiles and 12.7% higher for TSSM eggs) and speed (29 s faster per leaf) than manual counting using a magnifying lens. The quick assessment of field conditions with smartphone technology can allow growers to implement quick management tactics and potentially reduce the amount of pesticides to manage TSSM, which can save growers money and protect the environment.