Advancing Wheat Crop Analysis: A Survey of Deep Learning Approaches Using Hyperspectral Imaging
Fadi Abdeladhim Zidi, Abdelkrim Ouafi, Fares Bougourzi, Cosimo Distante, Abdelmalik Taleb-Ahmed
TL;DR
This survey addresses the problem of monitoring wheat health and yield under biotic/abiotic stresses by examining how deep learning methods can exploit hyperspectral imaging data. It presents a taxonomy of DL approaches divided into supervised, semi-supervised, and unsupervised learning, and surveys representative architectures such as CNNs, Transformers, and Mamba models, along with generative and diffusion-based techniques. It also catalogs public and private wheat-HSI datasets, discusses current applications in classification, disease detection, nutrient estimation, and yield prediction, and critically analyzes limitations like data availability and computational demands. The study highlights practical implications for precision agriculture, emphasizing the need for diverse open datasets, lightweight models, and self-supervised or meta-learning strategies to enable scalable, real-time wheat crop analysis using HSI.
Abstract
As one of the most widely cultivated and consumed crops, wheat is essential to global food security. However, wheat production is increasingly challenged by pests, diseases, climate change, and water scarcity, threatening yields. Traditional crop monitoring methods are labor-intensive and often ineffective for early issue detection. Hyperspectral imaging (HSI) has emerged as a non-destructive and efficient technology for remote crop health assessment. However, the high dimensionality of HSI data and limited availability of labeled samples present notable challenges. In recent years, deep learning has shown great promise in addressing these challenges due to its ability to extract and analysis complex structures. Despite advancements in applying deep learning methods to HSI data for wheat crop analysis, no comprehensive survey currently exists in this field. This review addresses this gap by summarizing benchmark datasets, tracking advancements in deep learning methods, and analyzing key applications such as variety classification, disease detection, and yield estimation. It also highlights the strengths, limitations, and future opportunities in leveraging deep learning methods for HSI-based wheat crop analysis. We have listed the current state-of-the-art papers and will continue tracking updating them in the following https://github.com/fadi-07/Awesome-Wheat-HSI-DeepLearning.