Commit graph

16 commits

Author SHA1 Message Date
05fd955067
README: note about RANDSEED 2024-08-30 19:02:18 +01:00
f46a86c9a4
README: Document SPLIT_VALIDATE, SPLIT_TEST 2024-08-30 18:49:38 +01:00
e15f6cd954
Update README w/proper paper link 2024-06-21 16:03:58 +01:00
d22dd6ff18
README: more tidy up 2023-11-30 17:08:50 +00:00
1cbb241786
README: tidy up 2023-11-30 17:02:08 +00:00
60674fb6b3
README: finish filling out 2023-11-30 16:32:46 +00:00
df621fd7d2
README: Continue filling out, but we're not there yet. 2023-11-29 17:31:47 +00:00
a1a2b105e6
README: Add under construction notice 2023-11-29 15:15:07 +00:00
1d8807793f
README: start expanding, buti ts not finished yet 2023-11-28 16:46:02 +00:00
d7fdf8f038
README: fix diagram 2023-07-06 15:31:13 +01:00
d93365a191
Update license to AGPL. 2023-07-06 15:16:11 +01:00
0c11ddca4b
rainfallwrangler does NOT mess up the ordering of the data 2022-10-18 19:07:14 +01:00
f2312c1184
fix crash 2022-08-31 16:25:27 +01:00
fe7a8b3fc0
Add 9 simple steps to use the rainfall radar model..... oh boy. 2022-08-31 16:18:28 +01:00
d9b9a4f9fc
note tos elf 2022-07-22 19:04:41 +01:00
8a9cd6c1c0
Lay out some basic scaffolding
I *really* hope this works. This is the 3rd major revision of this
model. I've learnt a ton of stuff between now and my last attempt, so
here's hoping that all goes well :D

The basic idea behind this attempt is *Contrastive Learning*. If we
don't get anything useful with this approach, then we can assume that
it's not really possible / feasible.

Something we need to watch out for is the variance (or rather lack
thereof) in the dataset. We have 1.5M timesteps, but not a whole lot
will be happening in most of those....

We may need to analyse the variance of the water depth data and extract
a subsample that's more balanced.
2022-05-13 19:06:15 +01:00