Introduction

The rapid increase in both the quantity and complexity of data that are being generated daily in the fields of environmental science, environmental engineering, and environmental monitoring and protection is leading to exciting advancements in our understanding of not only environmental change, but its impacts on health, equity, and justice in vulnerable populations. As environmental data streams are used in areas beyond environmental science (for example,  health, equity, and social good), there will be a continued need for methods that can fuse diverse data types and analyze these complex systems. This is especially relevant for health and sociodemographic datasets, which are often not as spatially and temporally resolved as environmental data, are prone to increase measurement error, and may be missing in some parts of the world, especially in the developing countries. Advanced data mining approaches have become indispensable tools for revealing hidden patterns or deducing latent dependencies for which conventional analytic methods face major limitations or challenges. Importantly, there is potential for improving such data mining techniques to support transfer learning for domain-specific studies, including environmental impacts on health and equity. Moreover, although climate change is a global phenomenon, its impact in developing countries is anticipated to be substantially greater than in developed countries. However, development of the appropriate tools for evaluating environmental risk factors and climate equity in developing countries is further hindered by limited, noisy or even nonexistent data records, especially in the healthcare sector. The analysis of complex environmental data in conjunction with health and demographics raises several interesting questions for development of future data mining tools for social good that yet remain largely understudied both in data mining, AI, environmental and public health communities.

The goal of this workshop is to provide an interdisciplinary forum for addressing the critical questions on the role of data mining for promoting climate justice, with the particular focus on healthcare applications. The workshop will offer a systematic linkage between the recent methodological advances in data mining, AI, climate studies, and health sciences, as well as will explore various fundamental challenges that arise when using data mining and AI for evaluating equity in health outcomes due to environmental exposure in developing countries. We invite papers in all forms of development and use of data mining, AI, statistical and other quantitative methods in topics that include: environmental sciences, environmental engineering, environmental monitoring and protection, environmental and climate justice, climate change and health, environmental exposures and health equity, and other relevant topics. Topics of interest include, but are not limited to:

• Domain-specific metrics for evaluation and integration of data mining tools with environmental, health, and equity data

• Data mining for climate change and impacts in the Asia‐Pacific

• Assessing AI’s impact on greenhouse gas emissions and climate change adaptation

• Novel analysis and modeling approaches to integration of environmental, health, and equity data

• Quantifying uncertainty in equity modeling

• Tackling climate change and environmental justice with machine learning

• Reducing data bias and increasing explainability of models for health and environmental justice

• Transfer learning from data rich to data poor environments

• Up and down sampling for data integration across data domains (e.g., health, climate, demographics)

• Ethical issues of predicting climate change impacts

This workshop will be an in-person event at ICDM 2023, taking place on December 1-4, 2023 in Shanghai, China. The session will cover invited talks, contributed talks, and a panel discussion.

 Keynote Speakers

TBA.

Organizing Committee

 Contact

For any questions, please contact us at dmc2he.icdm@gmail.com.