Deconfounding Multi-Cause Latent Confounders: A Factor-Model Approach to Climate Model Bias Correction

Gao, Wentao; Li, Jiuyong; Cheng, Debo; Liu, Lin; Liu, Jixue; Le, Thuc; Du, Xiaojing; Chen, Xiongren; Chen, Yun; Zhao, Yanchang

doi:10.24963/ijcai.2025/1071

Deconfounding Multi-Cause Latent Confounders: A Factor-Model Approach to Climate Model Bias Correction

Wentao Gao, Jiuyong Li, Debo Cheng, Lin Liu, Jixue Liu, Thuc Le, Xiaojing Du, Xiongren Chen, Yun Chen, Yanchang Zhao

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. AI and Social Good. Pages 9638-9646.

https://doi.org/10.24963/ijcai.2025/1071

Keywords

Data Mining: General
Humans and AI: General

Abstract

Global Climate Models (GCMs) are crucial for predicting future climate changes by simulating the Earth systems. However, GCM outputs exhibit systematic biases due to model uncertainties, parameterization simplifications, and inadequate representation of complex climate phenomena. Traditional bias correction methods, which rely on historical observation data and statistical techniques, often neglect unobserved confounders, leading to biased results. This paper proposes a novel bias correction approach to utilize both GCM and observational data to learn a factor model that captures multi-cause latent confounders. Inspired by recent advances in causality based time series deconfounding, our method first constructs a factor model to learn latent confounders from historical data and then applies them to enhance the bias correction process using advanced time series forecasting models. The experimental results demonstrate significant improvements in the accuracy of precipitation outputs. By addressing unobserved confounders, our approach offers a robust and theoretically grounded solution for climate model bias correction.

Wentao Gao, Jiuyong Li, Debo Cheng, Lin Liu, Jixue Liu, Thuc Le, Xiaojing Du, Xiongren Chen, Yun Chen, and Yanchang Zhao. 2025. Deconfounding Multi-Cause Latent Confounders: A Factor-Model Approach to Climate Model Bias Correction. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 9638–9646. https://doi.org/10.24963/ijcai.2025/1071

@inproceedings{ijcai2025p1071,
  title     = {Deconfounding Multi-Cause Latent Confounders: A Factor-Model Approach to Climate Model Bias Correction},
  author    = {Gao, Wentao and Li, Jiuyong and Cheng, Debo and Liu, Lin and Liu, Jixue and Le, Thuc and Du, Xiaojing and Chen, Xiongren and Chen, Yun and Zhao, Yanchang},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {9638--9646},
  year      = {2025},
  month     = {8},
  note      = {AI and Social Good},
  doi       = {10.24963/ijcai.2025/1071},
  url       = {https://doi.org/10.24963/ijcai.2025/1071},
}

TY  - CPAPER
TI  - Deconfounding Multi-Cause Latent Confounders: A Factor-Model Approach to Climate Model Bias Correction
AU  - Gao, Wentao
AU  - Li, Jiuyong
AU  - Cheng, Debo
AU  - Liu, Lin
AU  - Liu, Jixue
AU  - Le, Thuc
AU  - Du, Xiaojing
AU  - Chen, Xiongren
AU  - Chen, Yun
AU  - Zhao, Yanchang
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 9638
EP  - 9646
DO  - 10.24963/ijcai.2025/1071
UR  - https://doi.org/10.24963/ijcai.2025/1071
ER  -