Vision
Moving field science from occasional observations toward continuous monitoring.
Data, computing, and models
Ten years ago, the hard part was getting the data. Satellite imagery was expensive and difficult to access, computing power was limited, and many analytical tools had to be built from scratch.
Much of that is now a download or an API call. Landsat and Sentinel imagery are free, GPU time rents by the hour, and trained models are published with their weights. Fieldwork is still demanding and always will be. But the bottleneck has shifted: the hard part is turning all of these capabilities into science that works reliably, can be repeated, and gets better as new data arrive.
We make this process work.
What we're building toward
We are working toward field science that can operate continuously, rather than as a series of isolated campaigns.
- Analysis that doesn't stop
- Satellites continually deliver data and fly over field sites every few days. GPS base stations, seismographs, and water gages log data continuously. Drone flights can happen on short notice and repeatedly. We need to build analysis pipelines that keep up with the volume of continuous data, instead of rebuilding them after each data collection.
See Argus, our live Earth-observation monitor → - A queryable record
- We carefully curate data and metadata so that new observations can be compared with what we already know. Researchers work with the full context of previous results, building on previous observations rather than starting over.
Browse the data catalog → - AI as a collaborator
- Automated models and agents can flag observations worth a closer look and suggest where to look next, bringing them to researchers for interpretation.
- Reproducibility by default
- We use reproducible code and track data provenance, so that every result can be replicated. Data processing steps are both logged and verifiable, providing a complete chain of custody for scientific integrity.
How the pipelines work → - Rapid iteration
- We are developing tools to stream 3D data from the field to XR headsets in the lab, so a researcher with computing at hand can work alongside someone standing at the outcrop, rather than waiting until a campaign is over.
Visualization and XR → - Discovery is our measure
- The measure of success is simple: does this help researchers make rigorous, reproducible discoveries faster?
A faster feedback loop
Continuous monitoring lets us respond when the world changes. A satellite detects a fire, a river shifts course, a hillslope erodes, or vegetation begins to recover. New observations can trigger additional data collection and analysis, drawing a researcher's attention to what has changed and why.
We want data from satellites, drones, field instruments, and other sources to move quickly from the field into analysis and visualization. The infrastructure required to do this is substantial. Our goal is to make that infrastructure nearly invisible, so researchers can spend their time on the science.
Grounded in real research today
The lab's field, processing, analysis, and data services keep this vision grounded in research happening now, and they are where new collaborations begin.