David John Gagne II
@djgagnedos
Machine Learning Scientist at NSF NCAR in Boulder, CO. Interested in the linkages among AI, weather, climate, disasters, and impacts.
👀 Something special my team's been working on is set to arrive next week.
Noting the forecast for 9 PM Eastern tonight from the 20Z HRRR for no reason in particular.
UCAR posted its response to the government defense statement with some especially spicy retorts. Hearing is next Thursday. www.courtlistener.com/docket/72496...
The defense also produced a memo from OMB in November with their intent to break up NCAR and why. Docs available on the federal PACER system. Defense docs didn’t get uploaded to www.courtlistener.com/docket/72496... but can be found from there.
Relevant news to people who depend on government science funding and not just health. www.nytimes.com/2026/02/18/u...
All the Denver airport trains broke down so everyone had to walk across the bridge and somehow go from there. Looks like trains are starting to run again but there’s a big line down the escalators.
Lots of satellite mosaics in Houston at #AMS2026 but only one made of real tiles.
I'm providing an update on CREDIT at 4:30 PM today in 330A at #AMS2026. Here's a taste of some of the changing views on ML weather prediction I will be providing. (Thanks @plustssn.autumnsky.us for the last minute bug fix!)
Following the references for this letter leads to an even more entertaining citation.
Coaches as Crazy Taxi passengers: Kalen DeBoer vs James Franklin.
PSA: the wind components in the GFS and GEFS cube sphere tile netCDF files are already in Earth-relative coordinates. Figured this out by making this plot after two days of wondering why the transformed wind vectors wouldn't line up across tiles.
I got to visit Gary England’s studio back in 2006 with Dr. Carr’s freshman meteorology mentoring group. RIP Gary.
Dude on rock. Don’t want to show cops but there’s a bunch talking to him from a distance.
Good to know that our AI company overlords are already contemplating the Dr. Strangelove plan for riding out AGI.
Machine learning with ECMWF ICs leaning Kansas with some hope for Wray. GEFS and MPAS initial conditions leaning OK and eastern KS. Choose wisely. www2.mmm.ucar.edu/projects/nca...
In tales of WTF is going on with our data, I discovered that ERA5 has 20 Pa differences between the surface pressure and mean sea level pressure over the ocean in weird wavy patterns. MSLP is also smoother. GFS has much smaller variations (~2 Pa). Any idea what might be going on?
San Marino and Monaco only get a 10% tariff rate compared with the rest of the EU at 20%. I am sure that little loophole won't get exploited at all. Source: www.cnbc.com/2025/04/02/t...
It looks like there are 2 velocity couplets in the storm that just crossed into Mississippi. If we are already getting this kind of situation this early, it’s going to be a very long day for the tornado threat.
Looks like downslope winds on the south side of Boulder are warming things up quite a bit. Everyone else is stuck with the effects of overnight radiational cooling.
Open AI is so desperate for more high quality training data that they have reinvented expert systems.
Shocked and saddened to hear about the passing of Dr. Berrien Moore. In my time at OU he was a big advocate for improving the student experience in AGS and facilitated moving the Oklahoma Weather Lab to its bigger space. Even with all his commitments he still made time to chat and listen. RIP.
When I visited China a few weeks ago for a WMO conference, I got to see some of the investments they are putting into international training and it is quite substantial like this giant building. Article is a great dive into what is going on behind the scenes and the implications.