Transforming hyperspectral images into chemical maps: A new deep learning based approach to hyperspectral image processing

2025-04-19

AI Summary

Traditional PLS regression for hyperspectral chemical mapping suffers from neglect of spatial context, noise sensitivity, and physically implausible outputs (e.g., out-of-bounds predictions). To address these limitations, this paper proposes an end-to-end deep learning framework that directly maps raw hyperspectral data to physically consistent chemical distribution maps. Its key contributions are: (1) an enhanced U-Net architecture explicitly modeling spatial correlations; (2) a spatial–physical joint loss function jointly optimizing spatial coherence (achieving 99.91% variance explained) and physical constraints (strictly enforcing output bounds of 0–100%); and (3) elimination of pixel-wise intermediate modeling, enabling globally consistent and interpretable chemical maps. Evaluated on pork fat content prediction, the method reduces RMSE by 9–13% relative to PLS, with all predictions satisfying physical feasibility constraints.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Representation Learning for Vision
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Current approaches to chemical map generation from hyperspectral images are based on models such as partial least squares (PLS) regression, generating pixel-wise predictions that do not consider spatial context and suffer from a high degree of noise. This study proposes an end-to-end deep learning approach using a modified version of U-Net and a custom loss function to directly obtain chemical maps from hyperspectral images, skipping all intermediate steps required for traditional pixel-wise analysis. We compare the U-Net with the traditional PLS regression on a real dataset of pork belly samples with associated mean fat reference values. The U-Net obtains a test set root mean squared error of between 9% and 13% lower than that of PLS regression on the task of mean fat prediction. At the same time, U-Net generates fine detail chemical maps where 99.91% of the variance is spatially correlated. Conversely, only 2.53% of the variance in the PLS-generated chemical maps is spatially correlated, indicating that each pixel-wise prediction is largely independent of neighboring pixels. Additionally, while the PLS-generated chemical maps contain predictions far beyond the physically possible range of 0-100%, U-Net learns to stay inside this range. Thus, the findings of this study indicate that U-Net is superior to PLS for chemical map generation.

Problem

• Develops deep learning for hyperspectral chemical mapping
• Improves accuracy over traditional PLS regression methods
• Enhances spatial correlation in chemical map predictions

Innovation

• U-Net deep learning for hyperspectral image processing
• Custom loss function ensures physically possible predictions
• Spatial context considered in chemical map generation