Mengyuan Ren
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Mengyuan Ren has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Bin Wang
Peking University
1 shared publication - Bo Pan
Yunnan Provincial Key Lab of Soil Carbon Sequestration and Pollution Control, Faculty of Environmental Science & Engineering, Kunming University of Science & Technology, Kunming 650500, Yunnan, China
1 shared publication Fei Xia
Independent Researcher
1 shared publication- Guofeng Shen
Peking University
1 shared publication - Le Zhang
University of Electronic Science and Technology of China
1 shared publication - Michael S. Bloom
Department of Global and Community Health, George Mason University, Fairfax, VA, USA
1 shared publication
Latest Publications
- Open Access
- 28 July 2026
- Published by New Horizon Press Limited in Artificial Intelligence & Environment
- Vol. 1 (3) , 135
From R2 to W2: rethinking predictive metrics for AI models in environmental health
Artificial intelligence (AI) has been increasingly used in environmental health research to predict pollutant concentrations, human exposure levels, and disease risks. However, the evaluation of predictive models depends largely on traditional metrics such as the coefficient of determination (R2) or predicted R2, which is frequently misinterpreted in predictive modeling contexts. In many studies, R2 is used interchangeably with predictive performance metrics, potentially leading to overestimation of model reliability. Moreover, conventional evaluation indicators primarily quantify correlation or error magnitude and may fail to detect systematic prediction bias across exposure gradients. As a result, models with high apparent accuracy can still exhibit discriminatory prediction patterns, such as consistent overestimation or underestimation across the prediction range. Here, we clarify the distinction between the R2 and predictive squared correlation coefficient (Q2), and highlight the overlooked issue of prediction discrimination in AI-based environmental modeling. To address this limitation, we propose an integrated evaluation metric, W2, which combines predictive accuracy with a penalty for systematic deviation from the 1:1 prediction line, as demonstrated with real environmental health data. This provides an auxiliary tool for assessing predictive reliability and improving the methodological rigor of AI-driven environmental health studies.
- 28 July 2026
- Published by New Horizon Press Limited in Artificial Intelligence & Environment
- Vol. 1 (3) , 135
Open AccessFrom R2 to W2: rethinking predictive metrics for AI models in environmental health
Artificial intelligence (AI) has been increasingly used in environmental health research to predict pollutant concentrations, human exposure levels, and disease risks. However, the evaluation of predictive models depends largely on traditional metrics such as the coefficient of determination (R2) or predicted R2, which is frequently misinterpreted in predictive modeling contexts. In many studies, R2 is used interchangeably with predictive performance metrics, potentially leading to overestimation of model reliability. Moreover, conventional evaluation indicators primarily quantify correlation or error magnitude and may fail to detect systematic prediction bias across exposure gradients. As a result, models with high apparent accuracy can still exhibit discriminatory prediction patterns, such as consistent overestimation or underestimation across the prediction range. Here, we clarify the distinction between the R2 and predictive squared correlation coefficient (Q2), and highlight the overlooked issue of prediction discrimination in AI-based environmental modeling. To address this limitation, we propose an integrated evaluation metric, W2, which combines predictive accuracy with a penalty for systematic deviation from the 1:1 prediction line, as demonstrated with real environmental health data. This provides an auxiliary tool for assessing predictive reliability and improving the methodological rigor of AI-driven environmental health studies.