12 Jul 2025 - ICML 2025
I’m at ICML in Vancouver presenting Galileo. We’ll also be presenting 2 papers at the Terrabytes Workshop: our LFMC estimates using Galileo and WorldCereal’s integration of Presto.
I’m at ICML in Vancouver presenting Galileo. We’ll also be presenting 2 papers at the Terrabytes Workshop: our LFMC estimates using Galileo and WorldCereal’s integration of Presto.
I’m at the Living Planet Symposium in Vienna, where I’m talking about Presto and Galileo. In the same session, Christina Butsko will also talk about Presto’s deployment within the WorldCereal system. If you are also at LPS, come say hi!
Galileo is accepted to ICML! We develop a new self-supervised learning algorithm tailored to remote sensing, and use it to train a model which achieves state-of-the-art results across a diversity of remote sensing tasks (ranging from image segmentation to pixel-timeseries classification). Check out the code and paper.
I’m at ICLR in Singapore, helping to organize the Machine Learning for Remote Sensing Workshop.
I presented Presto and Galileo to NUS’s Centre for Remote Imaging, Sensing and Processing (CRISP), hosted by Dr. Soo Chin Liew.
I presented Presto and Galileo in the context of our work with WorldCereal at WorldCereal’s 3rd webinar - watch the recording here. This collaboration is featured on the NASA Harvest website too - link here.
I’m spending the summer working in Seattle at the Allen Institute for AI’s applied sciences team, under the mentorship of Patrick Beukema and Favyen Bastani.
I’ll be presenting Presto at SERVIR’s Geo-AI Working Group. Join here on Wednesday May 1st at 10am CMT.
I’m at ICLR in Kigali, helping to organize the Machine Learning for Remote Sensing Workshop. I’ll be moderating a panel at the workshop with Esther Rolf, Kristof Van Tricht, Abigail Annkah and Anthony Ortiz. Let me know if you’re at ICLR and would like to grab coffee!
We kicked off our food security project in Maui county (in partnership with Maui United Way, Responsible Markets and UHMC) visiting farmers and training students on Maui, Molokai and Lanai.
I taught introductions to machine learning to participants from RCMRD, as part of the Scalable Cropland Mapping component of the NASA SERVIR Eastern Africa Hub Training.
I’m at the Living Planet Symposium in Bonn (alongside lots of other Harvest folks), where I presented TIML at the Representation learning in EO session. If you are also at LPS, come say hi!
The CropHarvest dataset is accepted at NeurIPS, in the dataset and benchmarks track! We compile multiple agricultural land cover datasets, and couple it with satellite data in an ML-ready format. Check out the python package, paper, and tweet summary.
Along with Ivan Zvonkov, I presented Harvest’s work at AMLD Africa. We discussed what we’d learned developing and deploying agricultural land cover classification models.
I presented at the AI Data Readiness: What does ML Training Data Interoperability Mean to You? Breakout session, where I discussed Harvest’s work to combine agricultural land use datasets in a machine-learning friendly manner.
I presented at the Solving Training Data Bottlenecks for Artificial Intelligence/Machine Learning in Earth Science eLightning session, where I discussed the work I have been doing with Harvest to develop crop maps in data-sparse regions.
I presented at the Geo for Good public sector meetup, discussing Harvest’s work to create rapid response crop maps in Togo (and how we used Google Earth Engine to achieve this).
Check out the youtube recording of the meetup here!