An Interpretable Nonlinear Intelligent Bias Correction Method for FY-4A/GIIRS Hyperspectral Infrared Brightness Temperatures
Remote Sensing · 01.03.2026 · 18 (5) · 748
DOI: 10.3390/rs18050748 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 01.03.2026. Verfasst von Gen Wang und 9 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Anhui Province, Outstanding Youth Science Fund for Universities in Anhui Province of Anhui Province Higher Education Scientific Research Project, Anhui Provincial Program for Science and Engineering Teachers from Universities to Take Tem-porary Positions in Enterprises for Practical Experience.
Abstract (Originalsprache)
The hyperspectral infrared observations of the Geostationary Interferometric Infrared Sounder (GIIRS) on the Fengyun-4A (FY-4A) satellite are an important data source for numerical weather prediction (NWP) assimilation. However, there are systematic differences between observed and simulated brightness temperatures (i.e., the observation increments contain predictable systematic bias components). To address the issue that traditional linear methods struggle to capture the nonlinear relationships between biases and forecast predictors, this study proposes an intelligent bias correction method that integrates ensemble learning and explainable artificial intelligence. First, the entropy reduction method is used to select 69 mid-wave channels. Then, Random Forest, XGBoost, LightGBM, Decision Tree, and Extra Tree are used as base learners to construct a weighted average ensemble model. Training and validation are conducted using high-frequency clear-sky observation data from FY-4A/GIIRS during Typhoon Lekima. The results show that: (1) the ensemble learning correction method outperforms single models and traditional offline methods, with root mean square errors of brightness temperature bias of less than 0.9209 K for the training set and 1.4447 K for the test set; (2) Shapley Additive Explanations (SHAP)-based interpretability analysis reveals the contribution and nonlinear influence mechanisms of factors such as longitude, atmospheric thickness, surface temperature, and total precipitable water on bias correction. This study provides an intelligent bias correction framework with both high precision and explainability, offering a reference for the bias correction and assimilation applications of hyperspectral satellite observations like GIIRS.
Förderung
- Natural Science Foundation of Anhui Province
- Outstanding Youth Science Fund for Universities in Anhui Province of Anhui Province Higher Education Scientific Research Project
- Anhui Provincial Program for Science and Engineering Teachers from Universities to Take Tem-porary Positions in Enterprises for Practical Experience
- Key Research and Development Program Projects of Anhui Province
Zitieren
APA
Wang, G., Xu, B., Ye, S., Zhi, X., Zhang, T., Yang, Y., Liu, Y., Xie, F., Liu, Q., & Zhang, H. (2026). An Interpretable Nonlinear Intelligent Bias Correction Method for FY-4A/GIIRS Hyperspectral Infrared Brightness Temperatures. Remote Sensing, 18(5), 748. https://doi.org/10.3390/rs18050748
Vancouver
Wang G, Xu B, Ye S, Zhi X, Zhang T, Yang Y, et al. An Interpretable Nonlinear Intelligent Bias Correction Method for FY-4A/GIIRS Hyperspectral Infrared Brightness Temperatures. Remote Sensing. 2026;18(5):748. doi:10.3390/rs18050748
BibTeX
@article{Wang2026,
author = {Wang, Gen and Xu, Bing and Ye, Song and Zhi, Xiefei and Zhang, Tiening and Yang, Youpeng and Liu, Yang and Xie, Feng and Liu, Qiao and Zhang, Haili},
title = {An Interpretable Nonlinear Intelligent Bias Correction Method for FY-4A/GIIRS Hyperspectral Infrared Brightness Temperatures},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {5},
pages = {748},
doi = {10.3390/rs18050748}
}
EUVIMED