UAVINE-XAI: eXplainable AI-Based Spectral Band Selection for Vineyard Monitoring Using UAV Hyperspectral Data
Olympia Kourounioti, Αναστάσιος Τέμενος, Nikos Temenos, Emmanouil Oikonomou, Anastasios Doulamis, Nikolaos Doulamis
Abstract
An efficient spectral band selection trustworthy machine learning (ML) framework for vineyard monitoring from uncrewed aerial vehicle (UAV) hyperspectral data is introduced. The UAV, equipped with Specim AFX-10, is used to capture data beyond the visible spectrum within the 400–1000 nm wavelength range for a total of 224 bands. Popular supervised ML algorithms are utilized for detecting vegetation canopy in vineyards and distinguishing it from existing land uses, namely ground and shadow. Explainable AI results accompany those from ML to identify the most important bands, and understand the contribution of their reflectance levels to the ML models. By doing so, the number of spectral bands is narrowed while maintaining the granularity of the HS data. Experimental results on UAVINE, a publicly available dataset, demonstrate excelling classification performance of random forest (RF) with an overall accuracy of 97.06%, and with precision, recall, and F1-scores following accordingly. With the use of the computationally efficient Tree SHAP algorithm applied on the RF, the bands B106 (677 nm—Red), B186 (897 nm—NIR), B211 (967 nm—NIR), and B39 (498 nm—Green) were identified as the most important ones to the model, enabling better visualization of the vineyard and band-based analysis for each one of the classes existing within the vineyard.