TZstats Lab - Projects

AI for Social Good and Society

The AI for Social Good and Society (AI4SGS) Initiative is a bold interdisciplinary effort to apply artificial intelligence to some of the world’s most pressing social and public health challenges.

AI for Social Good and Society
AutoClimDS: Climate Data Science Agentic AI

We explore genAI tools to lower the barriers in Climate Data Science in collaboration with AWS.

Currect subprojects include: Knowledge graph construction and expansion. Development of agents for data acquision, analysis, modeling, visualization, etc. Evaluation through case studies.

AutoClimDS: Climate Data Science Agentic AI
NSF-STC: Learning the Earth with AI and Physics

Learning the Earth with Artificial Intelligence and Physics (LEAP) is an NSF Science and Technology Center (STC) launched in 2021. LEAP’s mission is to increase the reliability, utility, and reach of climate projections through the integration of climate and data science.

NSF-STC: Learning the Earth with AI and Physics
Statistical Machine Learning for Ecology

A long-time collaboration between Professors Tian Zheng and Professor Maria Uriarte on using machine learning to unlock potentials of new data types to understand the impact of climate change on tropical forests.

Statistical Machine Learning for Ecology
Collaboratory at Columbia - An Aspen Grove of Data Science Education

The Collaboratory is both a set of “data science in context” educational approaches, as well as a meta-model for an accelerator program that allows different institutions to respond flexibly to their own disciplinary heterogeneity in terms of data science educational needs. The novelty of the Collaboratory lies in its crowd-sourcing approach to creating new data science pedagogy and its ability to kindle transdisciplinary collaboration in doing so. Read our Havard Data Science Review article to learn more.

Collaboratory at Columbia - An Aspen Grove of Data Science Education
Applied Data Science at Columbia

Applied Data Science at Columbia is a project-based learning course that started in 2016. It employs the common task framework and runs 5 mini project cycles during one semester to give students a broad exposure to various areas in data science. Projects are developed and updated each year, drawing inspirations from active research, challenges and interesting public datasets.

Applied Data Science at Columbia
Statistical Methods for Aggregated Relational Data

A core and active research area of the TZstats lab.

Statistical Methods for Aggregated Relational Data