Multi-model ensembles for object detection in multispectral images: A case study for precision agriculture

Abstract

Every year, 20%–40% of the global harvest is lost to pests and diseases, underlining the need for rapid and accurate diagnosis. Precision agriculture exploits intelligent devices, such as robots and drones, to enable early detection of pathogens through non-destructive imaging techniques and AI processing. In this study, we exploit Deep Learning techniques for handling multispectral images in agriculture field. In particular, we introduce an adaptive Multi-Model Ensemble framework that processes multispectral data without dimensionality reduction, fully exploiting spectral information to improve early disease detection. Furthermore, several comparisons with dimensionality reduction and data combinations were conducted, exploring different image stack configurations to find the optimal solution in disease detection. We validated our approach on a dataset of tomato plants affected by Tuta Absoluta and Leveillula Taurica , where it improves the ability of disease identification and classification even at early developmental stages, offering promising perspectives for phytosanitary monitoring and sustainable resource management. • Scalable MME pipeline for object detection in multispectral imagery. • Adaptive integration of spectral bands without dimensionality reduction. • Comparative analysis of multispectral strategies, including false color. • Validation on real and public agricultural data for disease detection. • MME applicable in the range UV, VIS, NIR, SWIR, and LWIR for reliable analysis.