1
Paid research for PhD and Postdocs this summer
2
This year’s research theme…
AI for climate extremes
3
Sentinel 2
D-Orbit Wild Ride Mission
4
D-Orbit D-Sense Camera
Small, Rapid Downloads
Rapid flood-extent maps for first responders
OR
Launched June 2021
Unibap Accelerated
Compute Platform
ML�On-Board
5
Rapidly create detailed flood extent maps on huge scales.
10m Resolution
Building Scale
From open NASA and ESA data†
400,000 km2
Country Scale
Mapped in less than �one week*
Map Scale
Tasmania (68,401 km2)
Launceston Area
Flooded Buildings
Powered by FDL’S mature AI mapping tech and Google Cloud.
January
Recruitment
February
March
June
April
May
October
November
December
Data preparation & challenge definition
July
August
September
Information �session
24 Feb
Data preparation & challenge definition
ESL 2025
ESL 2025
Refinement phase
Refinement phase
Applications closed
31 Mar
Sprint �kick-off
16 Jun
Live showcase
9 Aug
Technical
showcase
Sept
Results released
Faculty confirmed
Teams 2025 announced
AGU
15-19 Dec
NeurIPs
9-15 Dec
2026
applications�open
| 2025 Timeline
7
In person
Virtual
16 June - 8 August 2025 8 weeks
FDL Formal Friday (F3) Directions
scoped
FDL Formal Friday (F3)
Validation
Technical
Concept Memo
Live Showcase
8 August
FDL Formal Friday (F3) ML Workflow
Technical Showcase
October
Bootcamp
16 - 20 June
Exploration
23 - 27 June
Development
30 June - 4 July
(MAX Q)
7 - 11 July
Calibration
14 - 18 July
Improvement
21 - 25 July
Write up
28 - 1 August
Digital showcase
4 - 8 August
Living Planet Symposium �23-27 June (Vienna)
Countdown Phase - 2
Partner briefing
Researcher briefing
Countdown Phase - 1
Virtual
2 June - 20 June 2 weeks
Sprint 2025 Timeline
Community is at our core.
NeurIPS
Luxembourg
Even Virtual
That time Adam got a Titan from Jensen
ESA - Frascati, Italy
8
“I think FDL is uniquely positioned to put the right people on the job at the right time and producing ‘firsts’ in terms of applications.
9
Atilim Güneş Baydin
“I would have to say it's the model of rapid development plus the guts to tackle super big problems. It's quite an adaptive model. I have not seen it elsewhere and I tried to propose it to some universities or to the National Academies of Sciences. In academic science, things tend to more much slower and researchers are more likely to take on incremental problems instead of large ones, because they also need to maximize their chances of publishing.
”-Anamaria Berea
10
“What really made FDL special for me was the community, collaborative atmosphere the group was, with someone always willing to help and the fact your working in cutting edge problems”-Laura Hayes
11
“Making the right connections in the right setting. Connecting people in general. Connecting machine learning researchers with space scientists, connecting these researchers with industry who provide resources, then connecting all of these with space agencies, etc.”
-Atilim Güneş Baydin
12
“What I've been telling people is that the model of putting scientists and ML experts at the same desk for 2 months to work on a specific problem is the best way (in my opinion/experience) for scientists to really understand how to use ML properly in their research. Too often you see scientists trying to apply ML where it shouldn't be applied (e.g., where there isn't a good human-labeled dataset, so they just use models for training) , or not taking care to avoid common pitfalls in ML research (e.g., not putting aside a test set in the beginning).
There is so much nuance in applying ML to scientific problems and the focused, small-team approach of FDL really facilitated rapid learning in the best way possible, I think. I tried several times to learn ML "on the side" and failed because 1) it's hard/complicated, 2) postdocs and grad students are already over-worked, and 3) it's very different from traditional science. I know of a lot of colleagues who have or are going through the same thing. The intensive approach of FDL really helps to get you over the large learning curve as fast as possible. It was pretty amazing.”
-Megan Ansdell
13
14
Key Details
15
17
Thank you.