Research scientist on Microsoft's AI for Good team.
Joined January 2016
- Tweets185
- Following558
- Followers854
- Likes818
Do you ever look at the gdal command line and think "hey, I could probably implement a U-Net with just this?" If not, that's normal and healthy. If so, you'll really appreciate @isaaccorley_ and mine's latest post (you might also even if not though)! - geospatialml.com/posts/unet-…
Excited to announce that TerraKit and TerraTorch from @IBMResearch have joined the TorchGeo organization - github.com/torchgeo!!
Together with TorchGeo, these python packages provide geospatial ML datasets, foundation models, fine-tuning tools, and more!
New post with @isaaccorley_ : DeltaBit -- dense, satellite imagery-based change detection with AlphaEarth embeddings, running entirely in the browser. Check it out at geospatialml.com/posts/chang…
This is pt. 3 of our "Compressing Earth Embeddings" series. We:
- Compress per-pixel *differences* between two years of embeddings and store the top 8 PCA components as XYZ GeoTIFF tiles
- Use GeoTIFF.js to decode in-browser
- Use WebGPU compute shaders to train/inference
This lets users label a few examples of change → train a linear model → see predictions interactively as they scroll around Seattle → download change polygons. No backend services or desktop software needed!
Try it at calebrob.com/deltabit/
Caleb Robinson retweeted
Working on transfer learning and foundation models in remote sensing? We invite you to submit abstracts to our session IN005 at #AGU25 (agu.confex.com/agu/agu25/pre……) organized by @sherwang (MIT),@hannah_kerner (Arizona State), Siddharth Sachdeva, and me (Stanford).
Caleb Robinson retweeted
Researchers at @Microsoft’s AI for Good Lab, in collaboration with @WildNatureInst, have developed GIRAFFE, an open-source AI-driven system to automate the identification of individual giraffes.
Learn more about our new AI-powered tool. msft.it/6017SQgyW
Caleb Robinson retweeted
I'm hiring for a machine learning data scientist & research assistant for summer 2025!
Join me on a project on invasive species management with an innovative startup doing on-the-ground removal of environmentally destructive invasives.
Paid, full-time w/ possibility to extend.
ALT Join me in working on a project on invasive species management, by predicting species risk and planning capture strategies. This work will be in partnership with an innovative startup that is working directly to capture environmentally destructive invasive species in the US. This project will be to build predictive machine learning models and design harvest strategies for Inversa’s invasive species removal efforts. The primary goal is to develop usable ML models and optimization tools to inform practical environmental decision-making on the ground. There will also be opportunities to extend this work into a research publication for a top-tier AI venue. How to apply: Please send a CV and 3–5 paragraphs of your background/interests via email to <[email protected]> with the subject line "Application: ML for invasive species management". Applications will be reviewed on a rolling basis.
Caleb Robinson retweeted
An expanded version of our TorchGeo paper has been accepted to ACM TSAS @TheOfficialACM
In addition to even more benchmarks on remote sensing datasets, we provide a thorough survey of open-source libraries for deep learning for geospatial data
@calebrob6 @BDataScientist
Caleb Robinson retweeted
NOAA has posted satellite imagery from the areas affected by the Eaton, Hurst, and Palisades wildfires. The imagery is available through Maxar's Open Data program to support the emergency response community and the public: storms.ngs.noaa.gov/storms/2…
Disaster-specific @FEMA resources are available here: fema.gov/disaster/4856
ALT Aerial imagery of a neighborhood along the coast showing half of the houses burned
Caleb Robinson retweeted
The Climate Change AI workshop at NeurIPS tomorrow will be livestreamed for free, even if you weren't able to register for NeurIPS (which was oversubscribed this year)!
Another highlight of our #NeurIPS2024 workshop on Sunday will be a panel discussion on small vs big models in ML for climate impact, featuring Chris Bretherton, Anamika Dubey & @BDilkina.
Stream the whole workshop live & for free via our website: climatechange.ai/events/neur…
Caleb Robinson retweeted
🚨Our new review paper "Better, not just more: Data-centric ML for Earth Observation" 🌐🤖🛰️🔍 has finally been published in GRSM. Shifting the focus from models to data offers new possibilities to improve accuracy, generalization, and real-world impact: ieeexplore.ieee.org/document…
Joint work with @MarcCoru, Caroline Gevaert, @MKampffmeyer, @jeferssonalex, @MariaVakalopou1, @RonnyHaensch, Stine Hansen, @Keiller, Jonathan Prexl, @devistuia
Arxiv version: arxiv.org/abs/2312.05327
Caleb Robinson retweeted
'How geospatial AI can help us understand global scale challenges such as climate change or food insecurity. '- @tammyglazer
#Geospatial #GeospatialAI
1/ We released Fields of the World (FTW)-- a new satellite imagery + field boundary dataset with samples from 24 countries (now downloadable via torchgeo)! One cool part of this work is that we find that models trained on FTW have decent zero-shot performance in new locations:
a baseline for training and testing global models.
Paper: arxiv.org/abs/2409.16252
Code: github.com/fieldsoftheworld/…
Website: beta.source.coop/repositorie…
It was so fun working on this with @hannah_kerner, @jacobsn, @opencholmes, @GhoshPrivate, @Adeal_GIS, @matthmohr, @rdodhia, @BDataScientist, Snehal Chaudhari, Eddie Choi, and Jennifer Marcus!
1/🚀TorchGeo 0.6.0 is here!
TorchGeo is a python library for deep learning with geospatial datasets. This large update contains new datasets, foundation models, and more -- over 11 months of hard work from many contributors! See more details: github.com/microsoft/torchge…
4/ We've also done a lot of work on reproducibility. E.g. with Radiant MLHub shutting down, we've successfully migrated key datasets to Source Cooperative and AWS. This migration not only ensures continuity but also allowed us to simplify code!