• Skip to primary navigation
  • Skip to main content
  • Skip to footer

DTD Lab

DTD Lab
  • Research
  • Events
  • People
  • Opportunities
  • About
  • News
  • Support
  • Subscribe

Research & Programming

Community Climate Knowledge and Multimodal Climate AI

About Project Team Funding In the News

What if weather and climate modeling built upon community expertise to create more localized, specific models?

The Community Climate Knowledge and Multimodal Climate AI project seeks to safeguard and foreground the weather and climate knowledges of place-based communities – such as tribes, agricultural communities, counties, and neighborhood associations — while developing systems, processes, and resources that blend such unstructured climate information with the structured data that AI-based climate models currently use.

Overview

Data models are critical to how we understand our weather and climate. Yet, these models have often left out local communities who hold critical weather and climate expertise.

Building on previous work by Ava Birdwell and Drs. Mona Sloane, Antonios Mamalakis, and Charity Nyele, we explore the possibility of integrating diverse climate knowledges in participatory processes to improve climate modeling practices, particularly for localized downscaling.

By integrating unstructured community climate knowledge — such as oral histories or local records — with AI climate models, we seek to strengthen climate modeling practices while building systems in which communities are included and valued.

Aims for this work include more robust, inclusive climate modeling practices; improved processes for integrating community climate knowledges into AI climate models; and an open dataset of community climate knowledge sources.

Project Team

This project, spearheaded by Postdoctoral Fellow Aashka Dave, is a partnership between Sloane Lab, the Digital Technology for Democracy Lab, Mamalakis Lab, and Aikyam Lab.

Headshot of Aashka Dave

2025-27 Postdoctoral Research Fellow

Aashka Dave

Aashka Dave is a postdoctoral research fellow at the Digital Technology for Democracy Lab at the University of Virginia. She completed her PhD in information and library science at UNC Chapel Hill, where she is an affiliate at UNC’s Center for Information, Technology, and Public Life.

Dave’s work puts into conversation issues of climate risk, information ecosystems, and human-centered design. As a postdoctoral fellow, she plans to expand her dissertation work to write a book exploring the data-fied ways that climate risk is priced into our lives, how that risk is politicized, and how it might be more effectively communicated to the public.

Dave has previously worked as a design thinking and innovation fellow for Innovate Carolina; a media researcher at the MIT Media Lab and Harvard Kennedy School; and on digital projects at The Associated Press. She holds an MS in comparative media studies from MIT, and bachelor’s degrees in journalism and Romance languages from the University of Georgia.

Full Profile
Headshot of Mona Sloane

DTD Lab Faculty Co-Lead

Mona Sloane

Affiliations

  • Assistant Professor of Data Science, School of Data Science
  • Assistant Professor of Media Studies, Department of Media Studies, College and Graduate School of Arts & Sciences

Bio

Mona Sloane is an assistant professor of data science and media studies at the University of Virginia (UVA). As a sociologist, she studies the intersection of technology and society, specifically in the context of AI design, use, and policy. At UVA, she is a faculty co-lead in the Digital Technology for Democracy Lab, affiliated faculty with the department of women, gender and sexuality, and faculty affiliate with the Thriving Youth in a Digital Environment research initiative. She also convenes the Co-Opting AI series and serves as the editor of the Co-Opting AI book series at the University of California Press as well as the Technology Editor for Public Books. Mona’s book Predicted: How AI Is Restructuring Social Life is available now with the University of California Press. Her growing research group, Sloane Lab, conducts empirical research on the implications of technology for the organization of social life. Its focus lies on AI as a social phenomenon that intersects with wider cultural, economic, material, and political conditions. The lab spearheads social science leadership in applied work on responsible AI, public scholarship, and technology policy.

View Full Profile >>

Headshot of Antonios Mamalakis

Assistant Professor of Data Science and Environmental Sciences, UVA

Antonios Mamalakis

Affiliations

  • Assistant Professor of Data Science, School of Data Science
  • Assistant Professor of Environmental Sciences, Department of Environmental Sciences

Bio

Antonios Mamalakis is an environmental data scientist interested in exploring data science tools like statistical and Bayesian analysis, machine/deep learning, and explainable AI to solve challenges in environmental applications. Among others, these challenges include improving predictive skill of hydroclimate and extreme events, understanding climate teleconnections and predictability, advancing climate attribution and causal discovery, etc.

Prior to joining UVA, he worked as a research scientist at Colorado State University, where he pioneered the investigation of the fidelity of explainable AI tools for applications in the geosciences. Some of his papers have garnered international attention and have been highlighted by publishers. Examples include “A new interhemispheric teleconnection increases predictability of winter precipitation in southwestern US,” published in Nature Communications; “Zonally contrasting shifts of the tropical rain belt in response to climate change,” published in Nature Climate Change; and “Underestimated MJO variability in CMIP6 models,”published in Geophysical Research Letters. Antonios serves as an Associate Editor for the AMS journal “Artificial Intelligence for the Earth Systems.”

Mamalakis holds a Ph.D. in Civil and Environmental Engineering from University of California, Irvine, and a M.Sc. in the same major from University of Patras, Greece.

View More >>

Headshot of Chirag Agarwal

DTD Lab Faculty Affiliate

Chirag Agarwal

Chirag Agarwal is an assistant professor of data science and leads the Aikyam lab, which focuses on developing trustworthy machine learning frameworks that go beyond training models for specific downstream tasks and satisfy trustworthy properties, such as explainability, fairness, and robustness.

Before joining UVA, he was a postdoctoral research fellow at Harvard University and completed his PhD at the University of Illinois at Chicago in electrical and computer engineering and bachelor’s degree in electronics and communication. His PhD thesis was on the “Robustness and Explainability of Deep Neural Networks,” and his research encompasses different trustworthy topics, such as explainability, fairness, robustness, privacy, transferability estimation, and their intersection in the age of large-scale models. He has developed the first-of-its-kind, large-scale, in-depth study to support systematic, reproducible, and efficient evaluations of post hoc explanation methods for (un)structured data to understand algorithmic decision-making on diverse tasks ranging from bail decisions to loan credit recommendations.

Agarwal has published in top-tier machine learning and computer vision conferences (NeurIPS, ICML, ICLR, UAI, AISTATS, CVPR, SIGIR, ACCV) as well as in top journals in datasets (Nature Scientific Data) and health care (Journal of Clinical Sleep Medicine and Cardiovascular Digital Health Journal). His research has received Spotlight and Oral presentations at NeurIPS, ICML, CVPR, and ICIP conferences, and industrial grants from Adobe, Microsoft, and Google to support his work on trustworthy machine learning.

View Full Profile >>

Headshot of Sabine Segaloff

Research Assistant, UVA

Sabine Segaloff

Sabine Segaloff is a PhD student at the University of Virginia’s School of Data Science and a research assistant in the Sloane Lab. Synthesizing a background in archaeology and mathematics, her research treats data pipelines as stratigraphic sites, focusing on the formation processes that shape digital records. She is interested in critical technical practice and the development of upstream interventions to champion the honesty of complex data systems. Her work applies archaeological rigor to the excavation of data infrastructure, using reflexive methodologies to account for the role of the engineer in shaping the site of the data.

Headshot of Caroline Brewczak

Undergraduate Research Assistant

Caroline Brewczak

Funding

This project is supported by a Co-Lab Grant from UVA’s Environmental Institute.

In the News

Amazon data center landscape
  • Multimodal Climate AI

Data Science Team Receives $70,000 Environmental Institute CoLab Grant

UVA Data Science research team received a $70,000 Environmental Institute grant to develop AI climate models that incorporate community knowledge for local decision-making.

datascience.virginia.edu

Earth covered with trees against a gray background
  • Multimodal Climate AI

From Climate AI to Post-Flood Health Risks: UVA Funds New Environmental Research Projects

Congratulations to DTD Lab members Mona Sloane, Chirag Agarwal, and Aashka Dave, who are among the team recipients of a $70k CoLab grant from UVA's Environmental Institute for a new interdisciplinary project, "Community Climate Knowledge and Multimodal Climate AI”. CoLab grants support projects that represent novel and interdisciplinary approaches required to address some of the most pressing climate crises with high potential for societal impact.

environment.virginia.edu

Make a gift to support the Lab's interdisciplinary research, initiatives, and activities

Support the DTD Lab

Donate

Footer

DTD Lab
  • Non-Discrimination Notice
  • Consumer Information
  • Accessibility
  • Emergency
  • FOIA
  • Privacy
  • Subscribe

Contact Us

722 Preston Avenue, Suite 201 Charlottesville, VA 22903

uva-dtdlab@virginia.edu

YouTube

Site by Charlottesville SEO Web Development.

© 2026 By the Rector and Visitors of the University of Virginia