Harnessing AI for agriculture utilizing color-condition camera sensors and thermal imaging drones for crop color-condition detection and predictive yield analysis with inventory management system

Technological Gaps and Challenges for Agriculture in the Philippines Such advancements may be relevant to other countries as well but we should also consider that there is greater potential of technology adoption with these purposes than ever befo re, especially those small-scale farmers from local areas who have less accessibility on technological trendsetting. In this study, we attempt to solve these problems using Artificial Intelligence (AI) in order to improve crop monitoring and predictive yiel d amidst the climate change. Color-condition detection using Convolutional Neural Networks (CNN) with 76.97% accuracy and predictive analysis by Artificial Neural Network(ANN). This optimizes the timing of planting and harvest, depending on the combination of these algorithms. This study aims to capture the crops’ maturity through color-condition detection and gather data for yield analysis by capturing the thermal temperature of the soil. The AI can identify crop health and maturity issues, such as nutrient deficiencies. It will also enhance crop yield predictions by inputting information such as soil types, temperature, fertilizers used, and weather conditions. Additionally, this study implements a partial website system to serve as an interface for the images captured by the camera attached to the drone. This website also showcases the goals of the proposed study. Furthermore, it includes a crop stock and inventory management feature to reduce paper usage and promote an eco-friendly environment. Through this innovation, local farmers can adapt to new technologies, improve farm productivity, reduce crop wastage, and strengthen their ability to meet market demands while promoting sustainable practices.