sophiearana commited on
Commit
b0ad262
·
verified ·
1 Parent(s): f278978

add comp requirements to model card

Browse files
Files changed (1) hide show
  1. README.md +28 -13
README.md CHANGED
@@ -1,13 +1,13 @@
1
- ---
2
- license: cc-by-4.0
3
- tags:
4
- - weather
5
- - numerical-weather-prediction
6
- - gnn
7
- - autoregressive
8
- - medium-range-forecast
9
- pipeline_tag: graph-ml
10
- ---
11
 
12
  # Model Card for FastNet-v1.1
13
 
@@ -89,10 +89,25 @@ Weighting was applied per-variable and was proportional to pressure level.
89
  #### Preprocessing
90
  Training data from each pressure level (including surface-level variables) are separately standardised to have zero mean and unit standard deviation, over latitude, longitude and time. Orography is rescaled to the unit interval, and land-sea mask, solar hour angle, time of year, latitude, and longitude require no change as they are already suitably normalised.
91
 
92
- ### Speed, Sizes, Times
93
-
94
  ## Evaluation
95
 
96
  FastNet is evaluated against ERA5 data using the WeatherBench 2 software package analysis for 2022. We compute the full rollout for all forecast valid times in 2022, re-gridding the output to a 1.5 degree latitude-longitude grid using a conservative re-gridding scheme.
97
 
98
- We also evaluate against the Met Office Global Model operational
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-4.0
3
+ tags:
4
+ - weather
5
+ - numerical-weather-prediction
6
+ - gnn
7
+ - autoregressive
8
+ - medium-range-forecast
9
+ pipeline_tag: graph-ml
10
+ ---
11
 
12
  # Model Card for FastNet-v1.1
13
 
 
89
  #### Preprocessing
90
  Training data from each pressure level (including surface-level variables) are separately standardised to have zero mean and unit standard deviation, over latitude, longitude and time. Orography is rescaled to the unit interval, and land-sea mask, solar hour angle, time of year, latitude, and longitude require no change as they are already suitably normalised.
91
 
 
 
92
  ## Evaluation
93
 
94
  FastNet is evaluated against ERA5 data using the WeatherBench 2 software package analysis for 2022. We compute the full rollout for all forecast valid times in 2022, re-gridding the output to a 1.5 degree latitude-longitude grid using a conservative re-gridding scheme.
95
 
96
+ We also evaluate against the Met Office Global Model operational
97
+
98
+ ## Computational Requirements
99
+
100
+ ### Hardware
101
+ For inference, FastNet-global runs on a single NVIDIA A100 GPU, though CPU inference is also supported. When using the GPU model file, we recommend a GPU with compute capability ≥ 8.0 (i.e. A100 or equivalent/higher).
102
+
103
+ ### Software
104
+
105
+ Inference dependencies are intentionally lightweight. Key packages include:
106
+ - torch — runs the model (load + rollout)
107
+ - xarray / zarr / dask — geospatial and meteorological data handling
108
+ - pyyaml — parsing inference configuration yaml files
109
+
110
+ Training dependencies (not required for inference, listed here for attribution):
111
+ - torch-harmonics — spherical harmonic transforms
112
+ - lightning — ML training framework
113
+ - icosphere — icosahedral grid handling