Improving Early Detection of Bud Rot in Oil Palm Through Digital Field Monitoring

Bud Rot (BR) is the most significant phytosanitary threat to oil palm cultivation in Colombia. Early detection is essential for effective curative management, but current methods for detecting BR in adult palms are subjective and unreliable. This research aimed to develop an integrated system for digital field monitoring and image analysis, testing two detection methods: computer-assisted detection and automatic detection using artificial intelligence (AI). Monthly monitoring was conducted over a 12-month period (January–December 2022) on 672 African oil palms (Elaeis guineensis), 15 years old and susceptible to BR. Disease monitoring focused on the incidence, cumulative incidence, and labor performance based on the number and spatial distribution of palms detected with BR, with or without the use of the device proposed. Results showed that automatic detection using AI had low effectiveness (17.1%), identifying only a small portion of actual cases. In contrast, computer-assisted detection significantly improved accuracy, reaching 78.6% during peak months and reducing detection time by up to two months compared to traditional methods, although, its maximum performance point only reached 4.7 ha/wage. The implementation of digital monitoring provides crucial technological support by considerably improving the effectiveness of early detection in BR curative management. Future advancements in AI-based detection are expected to further improve the efficiency and functionality of this approach.