Add diagnostic windgust (support for multi-datasets)

.gitignore

@@ -55,3 +55,6 @@ uv.lock
 
 # evalml
 .evalml_snakemake_cmd.txt
+
+# Paper plotting scripts + their figure outputs (not part of the realv2 showcase)
+paper_plots/

config/windgust-peakweather.yaml

@@ -0,0 +1,84 @@
+# yaml-language-server: $schema=../workflow/tools/config.schema.json
+description: |
+  As windgust.yaml (realv2 VMAX_10M showcase), but verifies against PeakWeather
+  station observations instead of the REAL-CH1 gridded analysis.
+
+# One week of daily initialisations for verification.
+dates:
+  start: 2024-02-01T00:00
+  end: 2024-02-07T00:00
+  frequency: 24h
+
+runs:
+  - forecaster:
+      checkpoint: /scratch/mch/rradev/output/checkpoint/9efa01f8c7464328897edb2c03a407c2/inference-last.ckpt
+      label: realv2_vmax10m
+      steps: 0/120/6
+      config: resources/inference/configs/sgm-multidataset-forecaster-windgust-ich1.yaml
+      extra_requirements:
+        # checkpoint needs: (1) EmptyInput.create_input_state propagates the date
+        # (else KeyError 'date' in add_initial_forcings_to_input_state for the
+        - git+https://github.com/radiradev/anemoi-inference.git@fix/empty-input-propagate-date
+
+        - eccodes==2.39.1
+        - eccodes-cosmo-resources-python==2.38.3.1
+
+  - baseline:
+      label: ICON-CH1-ctrl
+      root: /store_new/mch/msopr/osm/ICON-CH1-EPS
+      steps: 0/33/6
+
+truth:
+  label: PeakWeather
+  root: output/data/observations/peakweather
+
+experiment:
+  params:
+    - VMAX_10M
+  stratification:
+    regions:
+      - jura
+      - mittelland
+      - voralpen
+      - alpennordhang
+      - innerealpentaeler
+      - alpensuedseite
+    root: /scratch/mch/bhendj/regions/Prognoseregionen_LV95_20220517
+  thresholds:
+    VMAX_10M:
+      gt: [10.0, 20.0, 30.0]
+  dashboard:
+    stratification:
+      - season
+
+showcase:
+  params:
+    - T_2M
+    - SP_10M
+    - VMAX_10M
+  meteograms:
+    enabled: false
+    stations: [JUN]
+  animations:
+    enabled: true
+    domains:
+      - icon-ch
+      - switzerland
+
+locations:
+  output_root: output/
+
+profile:
+  executor: slurm
+  global_resources:
+    gpus: 16
+  default_resources:
+    slurm_partition: "postproc"
+    cpus_per_task: 1
+    mem_mb_per_cpu: 1800
+    runtime: "1h"
+    gpus: 0
+    slurm_extra: "--exclusive"  # whole nodes; avoid oversubscription
+  jobs: 50
+  batch_rules:
+    plot_forecast_frame: 32

config/windgust.yaml

@@ -0,0 +1,84 @@
+# yaml-language-server: $schema=../workflow/tools/config.schema.json
+description: |
+  Showcase the multi-output "realv2" anemoi architecture (ICON-CH1 cutout forecaster
+  with a diagnostic VMAX_10M stream on the REAL-CH1 / ICON-CH1 1km grid).
+
+# One week of daily initialisations for verification.
+dates:
+  start: 2024-02-01T00:00
+  end: 2024-02-07T00:00
+  frequency: 24h
+
+runs:
+  - forecaster:
+      checkpoint: /scratch/mch/rradev/output/checkpoint/9efa01f8c7464328897edb2c03a407c2/inference-last.ckpt
+      label: realv2_vmax10m
+      steps: 0/120/6
+      config: resources/inference/configs/sgm-multidataset-forecaster-windgust-ich1.yaml
+      extra_requirements:
+        # checkpoint needs: (1) EmptyInput.create_input_state propagates the date
+        # (else KeyError 'date' in add_initial_forcings_to_input_state for the
+        - git+https://github.com/radiradev/anemoi-inference.git@fix/empty-input-propagate-date
+
+        - eccodes==2.39.1
+        - eccodes-cosmo-resources-python==2.38.3.1
+
+  - baseline:
+      label: ICON-CH1-ctrl
+      root: /store_new/mch/msopr/osm/ICON-CH1-EPS
+      steps: 0/33/6
+
+truth:
+  label: REAL-CH1
+  root: /store_new/mch/msopr/ml/datasets/mch-realch1-fdb-1km-2005-2025-1h-pl13-v2.0.zarr
+
+experiment:
+  params:
+    - VMAX_10M
+  stratification:
+    regions:
+      - jura
+      - mittelland
+      - voralpen
+      - alpennordhang
+      - innerealpentaeler
+      - alpensuedseite
+    root: /scratch/mch/bhendj/regions/Prognoseregionen_LV95_20220517
+  thresholds:
+    VMAX_10M:
+      gt: [10.0, 20.0, 30.0]
+  dashboard:
+    stratification:
+      - season
+
+showcase:
+  params:
+    - T_2M
+    - SP_10M
+    - VMAX_10M
+  meteograms:
+    enabled: false
+    stations: [JUN]
+  animations:
+    enabled: true
+    domains:
+      - icon-ch
+      - switzerland
+
+locations:
+  output_root: output/
+
+profile:
+  executor: slurm
+  global_resources:
+    gpus: 16
+  default_resources:
+    slurm_partition: "postproc"
+    cpus_per_task: 1
+    mem_mb_per_cpu: 1800
+    runtime: "1h"
+    gpus: 0
+    slurm_extra: "--exclusive"  # whole nodes; avoid oversubscription
+  jobs: 50
+  batch_rules:
+    plot_forecast_frame: 32

resources/inference/configs/sgm-multidataset-forecaster-windgust-ich1.yaml

@@ -0,0 +1,58 @@
+lead_time: 120h
+write_initial_state: true
+allow_nans: true
+
+env:
+  ANEMOI_INFERENCE_NUM_CHUNKS: 8 # OOM error if not set
+
+# inputs
+input:
+  test:
+    use_original_paths: true
+
+output:
+  # Global cutout state (ICON-CH1 LAM + AIFS N320 global).
+  data:
+    tee:
+      - grib:
+          path: grib/{date}{time:04}_{step:03}.grib
+          encoding:
+            typeOfGeneratingProcess: 2
+            centre: lssw
+          templates:
+            samples: resources/templates_index_icon.yaml
+          post_processors:
+            - extract_mask: # keep only LAM points
+                mask: "lam_0/cutout_mask"
+                as_slice: true
+      - grib:
+          path: grib/ifs-{date}{time:04}_{step:03}.grib
+          encoding:
+            typeOfGeneratingProcess: 2
+            centre: ecmf
+          templates:
+            samples: resources/templates_index_ifs.yaml
+          post_processors:
+            - extract_mask: # removes LAM points
+                mask: "lam_0/cutout_mask"
+                as_slice: true
+                inverse: true
+            - assign_mask: # fill local/global overlapping points with nan
+                mask: "global/cutout_mask"
+  # Dianostic decoder on ICON grid only
+  realv2:
+    grib:
+      path: grib/realv2-{date}{time:04}_{step:03}.grib
+      # diagnostic is first valid at the model step (e.g. +6h)
+      write_initial_state: false
+      encoding:
+        typeOfGeneratingProcess: 2
+        centre: lssw
+      templates:
+        samples: resources/templates_index_realch1.yaml
+
+# Remaps the `data` stream's IFS variable names (2t, 10u, tp, ...) to the COSMO
+# shortNames expected by the ICON GRIB templates, and gives the realv2 VMAX_10M
+# diagnostic a whole-hour max period (['6h', '12h']) so its GRIB time-processing
+# is encoded correctly.
+patch_metadata: resources/sgm-windgust-ich1-patch.yaml