Hannah Kerner

Assistant Professor · School of Computing and Augmented Intelligence · Arizona State University

Hannah Kerner is an Assistant Professor in the School of Computing and Augmented Intelligence at Arizona State University. Her research focuses on advancing the foundations and applications of machine learning to foster a better future for all. Her lab's research topics include machine learning for remote sensing, algorithmic bias, and machine learning theory.

She translates research advances to real-world impact through her roles as the AI/Machine Learning Lead for NASA Harvest and NASA Acres, Center Faculty for the ASU Center for Global Discovery and Conservation Science (GDCS), and Research Advisor for Taylor Geospatial. She has been recognized by multiple research awards including the NSF CAREER Award (2025), Schmidt Sciences AI2050 Early Career Fellowship (2025), and Forbes 30 Under 30 in Science (2021).

email · Tempe, AZ

CV Google Scholar GitHub LinkedIn Twitter ORCID
Hannah Kerner
Assistant Professor, ASU
AI Lead, NASA Harvest & NASA Acres
Research Advisor, Taylor Geospatial
Center Faculty, ASU GDCS
In the press
Finding the fields of the world
Featured

Finding the fields of the world

ASU News covers the lab's open-source AI ecosystem for mapping global agricultural field boundaries, built with NASA, Microsoft AI for Good, and the Taylor Geospatial Engine. The first global benchmark dataset, pretrained models, and a no-code web explorer are now in the hands of partners across four continents.

ASU News · May 8, 2025

All press features →

Research

Research themes.

Machine learning for remote sensing

Satellite data is a distinct modality with unique spatial, temporal, and spectral structure. We design algorithms, models, datasets, and tools tailored to the unique nature of satellite data.

Fields of The World Pretrain Where? Galileo OlmoEarth MOMO Mars-Bench Presto Geo-Bench Geo-Bench-2

Bias and robustness

Aggregate metrics often hide where and why ML models fail. We develop methods, metrics, and benchmarks that surface biases and failure modes in interpretable, actionable ways.

DBA DBAC Geo-bias

Sustainable computing

We develop ML systems that learn and predict efficiently without sacrificing generality, and scalable model families that fit a wide range of compute budgets.

Multi-Head LatentMoE Presto OlmoEarth
Selected papers

Recent work. See all publications or Google Scholar for the full list.

  1. OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation
    Henry Herzog, Favyen Bastani, Yawen Zhang, Gabriel Tseng, Joseph Redmon, Hadrien Sablon, Ryan Park, Jacob Morrison, et al.
    CVPR 2026
    paper bibtex
  2. MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications
    Mirali Purohit, Bimal Gajera, Irish Mehta, Bhanu Tokas, Jacob Adler, Steven Lu, Scott Dickenshied, Serina Diniega, Brian Bue, Umaa Rebbapragada, et al.
    CVPR 2026
    paper bibtex
  3. Galileo: Learning Global & Local Features of Many Remote Sensing Modalities
    Gabriel Tseng, Anthony Fuller, Marlena Reil, Henry Herzog, Patrick Beukema, Favyen Bastani, James R. Green, Evan Shelhamer, Hannah Kerner, David Rolnick
    ICML 2025
    paper code bibtex
  4. Mars-Bench: A Benchmark for Evaluating Foundation Models for Mars Science Tasks
    Mirali Purohit, Bimal Gajera, Vatsal Malaviya, Irish Mehta, Kunal Sunil Kasodekar, Jacob Adler, Steven Lu, Umaa Rebbapragada, Hannah Kerner
    NeurIPS Datasets & Benchmarks 2025
    paper code bibtex
  5. PRUE: A Practical Recipe for Field Boundary Segmentation at Scale
    Gedeon Muhawenayo, Caleb Robinson, Subash Khanal, Zhanpei Fang, Isaac Corley, Alexander Wollam, Tianyi Gao, Leonard Strnad, Ryan Avery, Lyndon Estes, et al.
    CVPR 2026
    paper bibtex
  6. Position: Mission Critical — Satellite Data is a Distinct Modality in Machine Learning
    Esther Rolf, Konstantin Klemmer, Caleb Robinson, Hannah Kerner
    ICML 2024 · Spotlight
    paper bibtex
Code & data

Open-source models, datasets, and tutorials.

Models

galileo

Geospatial foundation model. Multi-modal, multi-scale, pretrained on 9 sensors.
… ★ … forks github ↑

presto

Lightweight pretrained transformer for remote sensing time series.
… ★ … forks github ↑

olmoearth

Geospatial foundation model pretrained on multiple sensors and datasets. Led by Ai2.
… ★ … forks github ↑

prue

Pretrained model for agricultural field boundary extraction.
… ★ … forks github ↑

momo

The first multi-sensor foundation model for Mars remote sensing.
… ★ … forks github ↑
Datasets & benchmarks

fields-of-the-world

Global field-boundary benchmark, pretrained models, web explorer, and CLI.
… ★ … forks github ↑

mars-bench

First benchmark for evaluating foundation models on Mars science tasks.
… ★ … forks github ↑

geo-bench

Benchmark for Earth remote sensing foundation models.
… ★ … forks github ↑

geo-bench-2

Successor to Geo-Bench with broader task and domain coverage for Earth observation foundation models.
… ★ … forks github ↑

cropharvest

Global satellite dataset for crop type classification.
… ★ … forks github ↑
Tutorials

Agriculture monitoring with Fields of The World

NeurIPS 2025 · Climate Change AI workshop
Hands-on tutorial showing how to use FTW pretrained models and the FTW CLI to map agricultural field boundaries from Sentinel-2 imagery.
colab ↑ repo ↑

Cropland Mapping using Geospatial Embeddings

ICLR 2026 · ML for Remote Sensing workshop
Practical guide to using geospatial embeddings (Presto, AlphaEarth) for cropland classification, demonstrated in Togo. Shows how embeddings simplify ML workflows for land-cover mapping.
paper ↑ website ↑

Fields of The World: A Field Guide for Extracting Agricultural Field Boundaries

ICLR 2026 · ML for Remote Sensing workshop
A field guide for using the FTW ecosystem to extract agricultural field boundaries from satellite imagery — covering models, the CLI, and the web explorer.
paper ↑ repo ↑
Group

Kerner Lab.

Postdocs & research staff
PhD students

Full group page (M.S., undergrads, alumni) →

Joining the lab

If you're interested in any role with the group (postdoc, PhD, MS, visitor, intern, etc.), please use the form below instead of emailing me — I can't reliably respond to individual emails.

Form for ASU students  → Form for non-ASU applicants  →
Teaching

Courses at ASU.

Contact

Email: email. For lab opportunities, please use the interest forms. Also on Google Scholar, GitHub, LinkedIn, and Twitter.