Hyperspectral soil heavy metal prediction via privileged-informed residual correction

Mangafić, Alen (author), Oštir, Krištof (author), Kolar, Mitja (author), Zupan, Marko (author)

This study integrates hyperspectral remote sensing with chemical and pedological data to estimate Zn, Pb, and Cd concentrations in the upper soil layers. Conducted in agricultural fields east and northeast of Celje, Slovenia, an area impacted by past industrial activities such as zinc ore smelting, the research integrates remote sensing and soil sampling to rapidly identify and map soil pollution over large surfaces. A multi-sensor approach was employed, combining two hyperspectral cameras (VNIR and SWIR, aerial), laboratory spectrometry, soil parameters, and content of chemical covariates measured with portable XRF and ICP-OES with a direct comparison of both techniques for this specific purpose. Accurate atmospheric and signal transformations were performed to improve modeling. The importance of covariates was thoroughly evaluated using conditional permutations to assess their contribution to the prediction of metal concentrations. The proposed framework utilizes spectral data and privileged information during training, improving prediction accuracy through a multi-stage model architecture. Here, a base model trained on spectral data is corrected using privileged information. During inference, the model functions without relying on privileged data providing a scalable and cost-effective solution for large-scale environmental monitoring. Our model achieved a reduction of predicted RMSE for Zn and Cd maps in comparison to the baseline models, translating to more precise identification of possibly polluted zones. However, for Pb, no improvements were observed, potentially due to variability in the data, including spectral issues or imbalances in the training and test datasets.

• Language: English
• Keywords: hyperspectral imagery, aerial remote sensing, imaging spectroscopy, digital soil mapping, pedometric mapping, onesnaženost tal, environmental monitoring, residual modeling
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FGG - Faculty of Civil and Geodetic Engineering; FKKT - Faculty of Chemistry and Chemical Technology; BF - Biotechnical Faculty
• Publication status: Published
• Publication version: Version of Record
• Year: 2025
• Number of pages: 32 str.
• Numbering: Vol. 17, iss. 12, art. 1987
• PID: 20.500.12556/RUL-169951
• UDC: 504
• ISSN on article: 2072-4292
• DOI: 10.3390/rs17121987
• COBISS.SI-ID: 240480259
• Publication date in RUL: 26.06.2025

Record is a part of a journal

• Title: Remote sensing
• Shortened title: Remote sens.
• Publisher: MDPI
• ISSN: 2072-4292
• COBISS.SI-ID: 32345133

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

• Language: Slovenian
• Keywords: hiperspektralni posnetki, daljinsko zaznavanje iz zraka, slikovna spektroskopija, digitalno kartiranje tal, pedometrično kartiranje, onesnaženost tal, okoljsko spremljanje, modeliranje ostankov

Projects

• Funder: ARIS - Slovenian Research and Innovation Agency
• Project number: P1-0153
• Name: Raziskave in razvoj analiznih metod in postopkov

• Funder: ARIS - Slovenian Research and Innovation Agency
• Project number: P2-0406
• Name: Opazovanje Zemlje in geoinformatika