sbrl-github/research-rainfallradar
1
0
Fork 0
mirror of https://github.com/sbrl/research-rainfallradar synced 2024-11-04 17:13:02 +00:00
Code Issues Projects Releases Packages Wiki Activity
Backup mirror of https://github.com/sbrl/research-rainfallradar A model to predict water depth data from rainfall radar information. https://github.com/sbrl/research-rainfallradar
510 commits 1 branch 0 tags 2.3 MiB
Python 70.1%
JavaScript 18.4%
Shell 11.5%
Find a file
Starbeamrainbowlabs 4703bdbea1
SLURM: add job file for encoderonly 
It's pretty much bugfixed, but illykin doesn't have enough RAM to support it at the moment :-(
2023-01-20 20:32:35 +00:00
.vscode vscode settings file 2022-08-11 16:38:25 +01:00
aimodel SLURM: add job file for encoderonly 2023-01-20 20:32:35 +00:00
rainfallwrangler finish comment 2022-11-11 18:55:35 +00:00
.gitignore properly handle water dimensions; add log files to .gitignore 2022-08-31 18:03:39 +01:00
LICENSE Initial commit 2022-05-13 19:08:14 +01:00
README.md rainfallwrangler does NOT mess up the ordering of the data 2022-10-18 19:07:14 +01:00

README.md

Rainfall Radar

A model to predict water depth data from rainfall radar information.

This is the 3rd major version of this model.

Unfortunately using this model is rather complicated and involves a large number of steps. There is no way around this. This README (will) explain it the best I can though.

System Requirements

  • Linux (Windows may work but is untested. You will probably have a bad day if you use Windows)
  • Node.js (a recent version - i.e. v16+ - the version in the default Ubuntu repositories is too old)
  • Python 3.8+
  • Nvidia GPU (16GiB RAM+ is strongly recommended) + CUDA and CuDNN (see this table for which versions you need)
  • Experience with the command line
  • 1TiB disk space free
  • Lots of time and patience

Overview

The process of using this model is as follows.

  1. Apply for access to CEDA's 1km rainfall radar dataset
  2. Obtain rainfall radar data (use nimrod-data-downloader)
  3. Obtain a heightmap (or Digital Elevation Model, as it's sometimes known) from the Ordnance Survey (can't remember the link, please PR to add this)
  4. Use terrain50-cli to slice the the output from steps #2 and #3 to be exactly the same size [TODO: Preprocess to extract just a single river basin from the data]
  5. Push through HAIL-CAESAR (this fork has the ability to handle streams of .asc files rather than each time step having it's own filename)
  6. Use rainfallwrangler in this repository (finally!) to convert the output to .json.gz then .tfrecord files
  7. Pretrain a contrastive learning model
  8. Encode the rainfall radar data with the contrastive learning model you pretrained
  9. Train the actual model to predict water depth

Only steps #6 to #9 actually use code in this repository.

rainfallwrangler

rainfallwrangler is a Node.js application to wrangle the dataset into something more appropriate for training an AI efficiently. The rainfall radar and water depth data are considered temporally to be regular time steps. Here's a diagram explaining the terminology:

NOW
│                       │         │Water depth
│▼ Rainfall Radar Data ▼│[Offset] │▼
├─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┬─┼─┬─┬─┬─┬─┼─┐
│ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │
│ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │
│ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │
│ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │
└─┴─┴─┴─┴─┴─┴─┴─┴─┴─┴─┴─┼─┴─┴─┴─┴─┴─┘
                        │
◄────────── Timesteps ─────────────►

Note to self: 150.12 hashes/sec on i7-4770 4c8t, ???.?? hashes/sec on Viper compute

After double checking, rainfallwrangler does NOT mess with the ordering of the data.