Detection of fusarium head blight in wheat using hyperspectral data and deep learning

作者：

Highlights：

• A new AI method for the detection of fusarium head blight in wheat is implemented.

• Conversion of line-based hyperspectral data to image-based data.

• Eight different light-weight Convolutional Neural Networks were used for the study.

• It was able to effectively predict pixels belonging to Fusarium from canopy data.

• The proposed approach shows potential model development for field canopy data.

摘要

•A new AI method for the detection of fusarium head blight in wheat is implemented.•Conversion of line-based hyperspectral data to image-based data.•Eight different light-weight Convolutional Neural Networks were used for the study.•It was able to effectively predict pixels belonging to Fusarium from canopy data.•The proposed approach shows potential model development for field canopy data.

论文关键词：Artificial intelligence in agriculture,Convolutional Neural Network,Crop disease detection,Fusarium head blight,Hyperspectral image,Transfer learning

论文评审过程：Received 3 January 2022, Revised 1 July 2022, Accepted 18 July 2022, Available online 21 July 2022, Version of Record 31 July 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118240