Litcius/Paper detail

Quantitative Estimation of Wheat Stripe Rust Disease Index Using Unmanned Aerial Vehicle Hyperspectral Imagery and Innovative Vegetation Indices

Jie Deng, Rui Wang, Lujia Yang, Xuan Lv, Ziqian Yang, Kai Zhang, Congying Zhou, Pengju Li, Zhifang Wang, Ahsan Abdullah, Zhanhong Ma

2023IEEE Transactions on Geoscience and Remote Sensing29 citationsDOI

Abstract

This study aimed to identify and assess vegetation indices (VIs) and their optimal band combinations using unmanned aerial vehicle (UAV) hyperspectral imagery for the quantitative inversion of wheat stripe rust. This would offer guidance for selecting rust-resistant phenotypes and facilitate large-scale disease monitoring using aerial and spaceborne remote sensing images. The experimental design encompassed 960 wheat varieties (strains) in agricultural fields. Hyperspectral imagery was acquired at 100m altitude during different disease stages, and disease index (DI) was investigated per plot. A custom program explored VIs with two, three, and four bands using 30 calculation methods and 3,463,790 band combinations. Regression models employed three-fold cross-validation and multilayer perceptron (MLP) algorithms, with the mean R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> value indicating optimal index and band combinations. The results revealed that the chosen VIs were effective in inverting the DI. Selected two-band VIs included MGRVI (531, 571), with R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> =0.746±0.01618; the optimal three-band VIs was ARI2 (531, 550±10, 640±25), with R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> =0.755±0.00896; and the best four-band VIs was DBSI (531, 551, 750, 799), with R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> =0.778±0.01300, which was comparable to full-band modeling (R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> =0.775±0.01508). The models’ performance improved with an increasing number of bands in the VIs. This study demonstrated that appropriate multi-VIs modeling enhances performance compared to single-VIs modeling, e.g., six combinations of VIs achieved R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> =0.790±0.01141. These findings underscore the potential of integrating machine learning algorithms and vegetation indices for quantifying wheat rust diseases, laying the foundation for developing airborne and spaceborne imaging sensors for large-scale wheat rust monitoring.

Topics & Concepts

Hyperspectral imagingRemote sensingArtificial intelligenceVegetation (pathology)Computer scienceRust (programming language)MathematicsGeologyPathologyProgramming languageMedicineRemote Sensing in AgricultureRemote Sensing and LiDAR ApplicationsWheat and Barley Genetics and Pathology