Jowaria Khan 🚀

Jowaria Khan

(she/her)

PhD. Candidate

University of Michigan, Ann Arbor

Professional Summary

I am a Ph.D. candidate in Computer Science & Engineering at the University of Michigan, where my research focuses on applying machine learning and computer vision to environmental and public health challenges. At present, I develop geospatial AI methods to detect and predict PFAS contamination in water systems, collaborating with nonprofits, government agencies, and interdisciplinary teams to ensure real-world impact.

Education

PhD. Computer Science (AI Lab)

University of Michigan, Ann Arbor

BSc. Computer Engineering

American University of Sharjah

Interests

Health Care Computer Vision Social Good Human Computer Interaction AI Ethics
📚 My Research
My research lies at the intersection of computer vision, machine learning, and environmental sustainability. I design deep learning frameworks for geospatial data that integrate satellite imagery, environmental monitoring, and limited ground truth samples to assess risk under uncertainty. A central goal of my work is to create socially responsible AI tools that are interpretable, data-efficient, and usable by policymakers and local communities. I am particularly interested in approaches that connect data-driven learning with insights from scientific and physical models, such as hydrological flow and chemical transport processes, to ensure predictions remain both accurate and scientifically grounded.
Featured Publications
Tangent Schrödinger Bridge Matching: Learning Stochastic Transport with Mechanistic Sensitivities featured image

Tangent Schrödinger Bridge Matching: Learning Stochastic Transport with Mechanistic Sensitivities

Diffusion Schrödinger bridges learn stochastic transports between endpoint distributions while remaining close to a reference diffusion, enabling flexible modeling of stochastic …

avatar
Jowaria Khan
•
Adapting Actively on the Fly: Relevance-Guided Online Meta-Learning with Latent Concepts for Geospatial Discovery featured image

Adapting Actively on the Fly: Relevance-Guided Online Meta-Learning with Latent Concepts for Geospatial Discovery

In environmental monitoring, data collection is often costly, sparse, and shaped by urgent public-health needs. This is particularly true for cancer-causing PFAS (Per- and …

avatar
Jowaria Khan
•
Examining Reliance Patterns on AI Advice in Medical Imaging: A Mixed-Methods Randomized Crossover Experiment featured image

Examining Reliance Patterns on AI Advice in Medical Imaging: A Mixed-Methods Randomized Crossover Experiment

Background: Artificial intelligence (AI) holds significant potential to support diagnostic decision-making; however, evidence regarding its clinical utility remains mixed. Often, …

Susanne Gaube
•
FOCUS on Contamination: Hydrology-Informed Noise-Aware Learning for Geospatial PFAS Mapping featured image

FOCUS on Contamination: Hydrology-Informed Noise-Aware Learning for Geospatial PFAS Mapping

Per- and polyfluoroalkyl substances (PFAS) are persistent environmental contaminants with significant public-health impacts, yet large-scale monitoring remains severely limited due …

avatar
Jowaria Khan
•
Recent Publications
(2026). Tangent Schrödinger Bridge Matching: Learning Stochastic Transport with Mechanistic Sensitivities. In NeurIPS, AI for Stochastic Dynamics [Under review at ICLR 2027].
(2026). Adapting Actively on the Fly: Relevance-Guided Online Meta-Learning with Latent Concepts for Geospatial Discovery. In NeurIPS (Main Track).
(2026). Examining Reliance Patterns on AI Advice in Medical Imaging: A Mixed-Methods Randomized Crossover Experiment. In The Lancet Digital Health.
(2026). FOCUS on Contamination: Hydrology-Informed Noise-Aware Learning for Geospatial PFAS Mapping. In ICLR, Machine Learning for Remote Sensing [Spotlight Oral — ~ 10% acceptance, Best Paper Award] [Under review at AAAI 2027].
(2024). AI-Driven Predictive Modeling of PFAS Contamination in Aquatic Ecosystems: Exploring A Geospatial Approach. In NeurIPS, Climate Change AI.
PDF
Recent & Upcoming Talks
ICLR ML4RS featured image

ICLR ML4RS

I presented this work at the ICLR 2026 ML4RS (Machine Learning for Remote Sensing) Workshop, which focuses on bridging the gap between research and real-world applications. The …

avatar
Jowaria Khan
•
MIT Senseable City Lab featured image

MIT Senseable City Lab

I presented this talk to MIT Senseable City Lab and its global City Science research network, sharing recent work on using geospatial AI to support scalable environmental …

avatar
Jowaria Khan
•
AAMAS Autonomous Agents for Social Good 2025 Workshop Presentation featured image

AAMAS Autonomous Agents for Social Good 2025 Workshop Presentation

I presented this work at the AAMAS 2025 Autonomous Agents for Social Good workshop, introducing FOCUS, a geospatial AI framework for predicting PFAS contamination under limited …

avatar
Jowaria Khan
•
Environmental Working Group (EWG) featured image

Environmental Working Group (EWG)

I gave a talk at the Environmental Working Group (EWG) on the role of geospatial AI in addressing PFAS contamination and broader environmental health challenges. The discussion …

avatar
Jowaria Khan
•