Development of Prediction System for Rice Disease Attacks using Thermal Imagery Approach

Information about the intensity of pests and diseases of rice is very much needed in planning and making policies related to production, handling pests and diseases, and agricultural insurance. Determination of the type and intensity of pest and rice disease attacks can be done through a manual approach, remote sensing technology using satellite, and UAV (drone) technology. In this study the UAV technology approach with a thermal camera will be used to estimate the level of rice disease. The general objective of this research is to develop an accurate system for predicting rice disease attacks using a thermal image approach. The specific objectives are 1) To determine the correlation between the intensity of rice disease attacks with thermal images, and 2) To establish the equation for estimating the intensity of rice disease attacks based on thermal images of plants affected by disease. In this study, thermal image capture will be performed using DJI Inspire 1 drones equipped with thermal cameras. In the initial stage, thermal imagery will be taken at several different heights to get the best image quality. In the next stage, thermal imagery will be taken on the affected rice fields to determine the intensity of the attacks. The height of the image is taken from the height that produces the best image quality. The image will be taken on the land affected by the disease and carried out every 2 weeks from the start indicated an attack until before harvest. At the same time, intensity measurements of disease attacks on the same land will be carried out manually according to standard procedures for determining pests and diseases issued by the Ministry of Agriculture. Thermal images obtained at this stage will be analyzed using PIX4D and ArcGis software. Furthermore, correlation analysis will be performed to get the relationship between the observed thermal image variables with the intensity of the attack, and to get the equation for estimating the intensity of the attack based on the parameters of the thermal image. After validation, it is hoped that the development of an accurate system for predicting rice disease attacks using the thermal image approach.