2026-04-14T04:39:20Zhttps://recercat.cat/oai/request
oai:recercat.cat:20.500.12327/47902025-10-23T05:28:11Zcom_2072_4428com_2072_4427col_2072_487898
RECERCAT author Engstrøm, Ole-Christian Galbo author Albano-Gaglio, Michela author Dreier, Erik Schou author Bouzembrak, Yamine author Font i Furnols, Maria author Mishra, Puneet author Pedersen, Kim Steenstrup other Indústries Alimentàries group Qualitat i Tecnologia Alimentària 2025-10-23T05:28:11Z 2025-10-23T05:28:11Z 2025-07-16 Engstrøm, Ole-Christian Galbo, Michela Albano‐Gaglio, Erik Schou Dreier, Yamine Bouzembrak, Maria Font‐i‐Furnols, Puneet Mishra, and Kim Steenstrup Pedersen. 2025. “Transforming hyperspectral images into chemical maps: a novel End‐to‐End Deep Learning approach”. Journal of Chemometrics, 39(8): e70041. doi:10.1002/cem.70041. 0886-9383 http://hdl.handle.net/20.500.12327/4790 https://doi.org/10.1002/cem.70041 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. The U-Net is compared 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. eng Attribution 4.0 International Transforming hyperspectral images into chemical maps: a novel End‐to‐End Deep Learning approach info:eu-repo/semantics/article