## Phase 175: Sovereign Weather & Climate ML — Spherical GNN Forecasting, Probabilistic Diffusion Climate Models, Direct Cyclone Prediction, Nowcasting, Climate Emulation & Downscaling

End-to-end sovereign replication and extension of the frontier
AI-for-Earth-sciences stack pioneered by Google DeepMind (GraphCast, GenCast,
FGN, WeatherNext), Huawei (Pangu-Weather), NVIDIA (FourCastNet, StormCast), and
Microsoft/Aurora. Targets medium-range deterministic forecasting, ensemble
probabilistic forecasting, tropical-cyclone direct prediction, minute-scale
precipitation nowcasting, decadal climate emulation, and statistical downscaling
— all from a single unified data, training, and serving pipeline. Integrates
with `@asase/agriculture`, `@oya/drones`, `@cybele/construction`,
`@galatea/fleet`, and `@veritas/news` via sovereign weather APIs.

Tech split: Python (~60%) for model training (PyTorch + JAX/Haiku parity) and
reanalysis ingestion; Rust (~20%) for Zarr/GRIB conversion and operational
ensemble workers; TypeScript (~20%) for orchestration, forecast APIs, and impact
integration.

Library layout: `libs/gaia/weather-data/`, `libs/gaia/graphcast/`,
`libs/gaia/gencast/`, `libs/gaia/cyclone-forecast/`, `libs/gaia/nowcast/`,
`libs/gaia/climate-emulator/`, `libs/gaia/downscale/`,
`libs/gaia/forecast-serving/`.

---

### 175.1 Reanalysis & Observation Data Foundation

#### 175.1.1 Reanalysis Archive Ingestion

- [x] **175.1.1.1** Build `@gaia/weather-data` ERA5 ingestion client against
      Copernicus CDS (cdsapi), pulling 1940–present hourly 0.25° surface fields
      (2m temperature, 10m u/v winds, MSLP, total precipitation, 2m dewpoint)
      and 37 pressure levels (geopotential, u/v, w, temperature, specific
      humidity) with GRIB2→Zarr conversion via `xarray + dask + kerchunk`,
      tiered MinIO storage (hot: last 5y, warm: 1990–, cold: 1940–1989)
- [x] **175.1.1.2** Build ERA5-Land high-resolution surface ingestion (0.1°
      hourly, 1950–present) for downscaling priors and hydrology features
- [x] **175.1.1.3** Build IFS HRES operational analysis ingestion (ECMWF MARS, 9
      km deterministic, 0/6/12/18 UTC cycles) for live initial conditions
- [x] **175.1.1.4** Build GFS operational ingestion (NOAA NOMADS, 13 km, four
      cycles) as fallback initial-condition source and cross-validation
- [x] **175.1.1.5** Build MERRA-2 ingestion (NASA GES DISC, 1980–present, 0.5° ×
      0.625°) for multi-reanalysis agreement scoring and aerosol inputs
- [x] **175.1.1.6** Build IBTrACS tropical-cyclone best-track ingestion
      (1842–present, all basins) with 6-hourly position, wind, pressure, radius
      fields — ground truth for cyclone-model training and evaluation

#### 175.1.2 Observation & Radar Ingestion

- [x] **175.1.2.1** Build NEXRAD Level-II ingestion (US radar mosaic, 250 m,
      2-min cadence) via AWS Open Data — primary nowcasting dataset
- [x] **175.1.2.2** Build OPERA composite ingestion (European radar, 2 km,
      5-min) for European nowcasting coverage
- [x] **175.1.2.3** Build GOES-R / MTG / Himawari geostationary satellite
      ingestion (16 bands, 10-min full disk) with CSPP / SatPy radiometric
      calibration and remapping to the model grid
- [x] **175.1.2.4** Build GPM IMERG satellite precipitation ingestion (0.1°
      half-hourly) for global nowcasting and tropical regions without radar
- [x] **175.1.2.5** Build automatic station network ingestion (METAR, SYNOP,
      BUFR, and ASOS) for verification, assimilation, and station-level bias
      correction
- [x] **175.1.2.6** Build lightning detection ingestion (GLM from GOES, EUCLID
      for Europe) for convective nowcasting labels and severe-weather triggers

#### 175.1.3 Data Catalogue & Sampling

- [x] **175.1.3.1** Define canonical `WeatherSample` schema — date, lead-time,
      grid specification (lat/lon or icosahedral level), pressure levels,
      surface variables, and provenance hash — with Zod validation and Zarr
      chunk alignment
- [x] **175.1.3.2** Build stratified training-sample loader (balanced across
      seasons, basins, extreme-event classes from IBTrACS / SPI / heat-wave
      indices) and curriculum scheduler that up-weights tropical cyclones,
      atmospheric rivers, and blocking events
- [x] **175.1.3.3** Build rolling train/val/test split enforcing strict temporal
      separation (train ≤2018, val 2019–2020, test 2021+) to prevent leakage
      through persistence and climate drift
- [x] **175.1.3.4** Build statistics package (per-variable, per-level mean / std
      / min / max) for model normalisation and denormalisation, stored versioned
      alongside each trained checkpoint

---

### 175.2 GraphCast-Class Deterministic Spherical GNN Forecasting

#### 175.2.1 Mesh & Encoder/Processor/Decoder

- [x] **175.2.1.1** Build icosahedral multi-mesh generator (M0 icosahedron → M6
      refinement with 40 962 nodes) with uniform-area triangular faces and
      pre-computed edge lists for every refinement level
- [x] **175.2.1.2** Implement Grid→Mesh encoder: for each mesh node, attend to
      nearby 0.25° grid nodes (radius ≈ 0.6×mesh edge length) via an MLP on
      (node_feature, grid_feature, relative_position) — identical semantics to
      the public GraphCast encoder
- [x] **175.2.1.3** Implement Mesh processor: 16 rounds of interaction-network
      message passing over all 6 refinement levels simultaneously (hierarchical
      multi-mesh) with residual updates and layer norm — produce updated mesh
      node embeddings
- [x] **175.2.1.4** Implement Mesh→Grid decoder: for each grid node, attend to
      its containing mesh triangle's 3 nodes via MLP, predict residual tendency
      relative to input state; add to input to produce +6h forecast
- [x] **175.2.1.5** Implement autoregressive rollout driver (6h step × up to 40
      steps = 10-day horizon) with checkpoint-supported gradient accumulation
      for multi-step fine-tuning

#### 175.2.2 Training & Scaling

- [ ] **175.2.2.1** Train GraphCast-Sovereign base (37M params, 1° ERA5):
      single-step MSE for 300k steps, then multi-step rollout fine-tune. Needs
      an owner decision on a compute budget — this is pod-scale weather-model
      training (TPU-v5e / H100-class), not a coding task; the ERA5/CMIP6 inputs
      are openly available but the training compute is not (stated 2026-09-18).
      `blocked:governance`
- [ ] **175.2.2.2** Train GraphCast-Sovereign-XL (0.25°, 226M params) on a
      TPU-v5e / H100 pod with FSDP2 and BF16. Needs an owner decision on a
      compute budget — this is pod-scale weather-model training (TPU-v5e /
      H100-class), not a coding task; the ERA5/CMIP6 inputs are openly available
      but the training compute is not (stated 2026-09-18). `blocked:governance`
- [x] **175.2.2.3** Build ensemble-of-Sovereigns (10 random seeds × different
      training subsets) for cheap deterministic ensemble baseline
- [x] **175.2.2.4** Implement per-variable, per-level, per-latitude loss
      weighting (area-weighted cos(lat) + published GraphCast variable weights)
      — critical for good polar and upper-air skill
- [x] **175.2.2.5** Build rollout-stability diagnostics (energy conservation,
      spectrum at T+240h vs ERA5 climatology, blur detector) and automatic
      early-stop on spectral collapse

---

### 175.3 GenCast-Class Probabilistic Diffusion Forecasting

#### 175.3.1 Diffusion World-State Model

- [x] **175.3.1.1** Implement state-diffusion model operating on +12h residuals
      over the icosahedral mesh (EDM parametrisation: preconditioned
      score-matching, ρ=7, σ_min 0.02, σ_max 88) with the Phase 175.2 GNN as the
      score network backbone conditioned on the previous two states
- [x] **175.3.1.2** Implement deterministic DPM-Solver++ sampler for 20-step
      ensemble generation (target parity with published GenCast 20-step skill)
      and stochastic Heun sampler for calibrated tail sampling
- [ ] **175.3.1.3** Train the ensemble-diffusion model on 1979–2018 ERA5 12h
      residuals with an EDM-weighted loss and validate CRPS vs IFS-ENS. Needs an
      owner decision on a compute budget — this is pod-scale weather-model
      training (TPU-v5e / H100-class), not a coding task; the ERA5/CMIP6 inputs
      are openly available but the training compute is not (stated 2026-09-18).
      `blocked:governance`
- [x] **175.3.1.4** Implement 50-member operational ensemble generation on
      single H100 / B200 (target ≤ 8 minutes wall-clock for 15-day 50-member
      forecast) with batched multi-seed sampling

#### 175.3.2 Calibration & Diagnostics

- [x] **175.3.2.1** Build CRPS, spread-skill ratio, rank histogram, and
      reliability-diagram calibration suite — computed daily on latest forecasts
      vs ERA5 analysis
- [x] **175.3.2.2** Build extreme-percentile verification (P99.9 precipitation,
      heat-wave return periods, wind-speed tails) — guards against
      distributional shortcut learning
- [x] **175.3.2.3** Build ensemble-member clustering and scenario extraction
      (k-means on principal components of +240h states) for narrative
      forecast-product generation

---

### 175.4 FGN-Class Direct Tropical Cyclone Prediction

#### 175.4.1 Functional Generative Cyclone Network

- [x] **175.4.1.1** Define cyclone functional output — at each 6h lead time,
      predict (probability-of-cyclone, center lat/lon, max sustained wind,
      central MSLP, RMW, R34/R50/R64 quadrants, eye formation flag) jointly as a
      differentiable head conditioned on the diffusion backbone latent
- [x] **175.4.1.2** Implement trajectory head: Transformer decoder over
      predicted cyclone centres conditioned on past 24h IBTrACS track + model
      latent, outputting 0–120h trajectory distribution with stochastic sampling
- [ ] **175.4.1.3** Train the cyclone model end-to-end with the combined
      position/intensity/category loss. Needs an owner decision on a compute
      budget — this is pod-scale weather-model training (TPU-v5e / H100-class),
      not a coding task; the ERA5/CMIP6 inputs are openly available but the
      training compute is not (stated 2026-09-18). `blocked:governance`
- [x] **175.4.1.4** Build automated NHC-compatible ATCF output generator (tech
      format: BASIN, CY, YYYYMMDDHH, TAU, LatN/S, LonE/W, Vmax, MSLP, category,
      R34/R50/R64) for ingestion by downstream emergency-response systems
- [x] **175.4.1.5** Integrate with `@oya/drones` (hurricane hunter drone swarm
      tasking), `@cybele/construction` (pre-storm asset hardening alerts), and
      `@veritas/news` (automated tropical-cyclone bulletin desk)

---

### 175.5 Minute-Scale Precipitation Nowcasting

#### 175.5.1 Radar Nowcasting Model

- [x] **175.5.1.1** Implement MetNet-3-class axial transformer over stacked
      radar composites (last 90 min, 2-min cadence) + geostationary satellite +
      topography + NWP boundary conditions → 0–12 h precipitation at 1 km, 5-min
      resolution
- [x] **175.5.1.2** Implement DGMR-class conditional GAN for ensemble
      precipitation nowcasting (4-member radar ensemble, skill against pySTEPS
      optical flow and operational UK Met Office nowcast)
- [x] **175.5.1.3** Build convective-mode classifier (stratiform vs convective
      vs tropical vs frontal) from radar + satellite + lightning for downstream
      model-mixture weighting
- [x] **175.5.1.4** Build CSI, POD, FAR, and FSS verification harness at
      0.1/1/5/10 mm h⁻¹ thresholds versus StageIV / radar-gauge blends

---

### 175.6 Climate Emulation & Long Rollouts

#### 175.6.1 ACE-Class Climate Emulator

- [ ] **175.6.1.1** Train the spherical-FNO / ACE-class climate emulator on
      CMIP6 control + SSP runs for 100-year rollouts. Needs an owner decision on
      a compute budget — this is pod-scale weather-model training (TPU-v5e /
      H100-class), not a coding task; the ERA5/CMIP6 inputs are openly available
      but the training compute is not (stated 2026-09-18). `blocked:governance`
- [x] **175.6.1.2** Build coupled sea-ice-albedo / soil-moisture feedback
      modules via FNO-in-FNO composition to preserve multi-scale feedbacks
- [x] **175.6.1.3** Implement decadal hindcast driver (1960–2020) validated
      against HadCRUT5, GISTEMP, AMIP-SST
- [x] **175.6.1.4** Build scenario emulator with tunable forcing (CO₂, CH₄,
      aerosol) for rapid what-if decision support, exposed via forecast API

---

### 175.7 Fine-Scale Downscaling & Bias Correction

#### 175.7.1 Statistical / ML Downscaling

- [ ] **175.7.1.1** Train the CorrDiff-class residual-diffusion downscaling
      model (25 km → 2 km) conditioned on the coarse forecasts. Needs an owner
      decision on a compute budget — this is pod-scale weather-model training
      (TPU-v5e / H100-class), not a coding task; the ERA5/CMIP6 inputs are
      openly available but the training compute is not (stated 2026-09-18).
      `blocked:governance`
- [x] **175.7.1.2** Train station-bias correction MLP/XGBoost heads per
      METAR/SYNOP station consuming the 25 km ensemble for site-specific
      forecast calibration (1–10 day)
- [x] **175.7.1.3** Build multivariate quantile-mapping bias correction for
      derived variables (wind-power density, heating/cooling-degree days,
      growing-degree days) used by `@asase/agriculture` and energy agents
- [x] **175.7.1.4** Build urban-downscaling module (50 m, diurnal UHI-aware) on
      top of European Urban Atlas + OSM land-use for `@cybele/construction` and
      `@themis/governance` climate-adaptation products

---

### 175.8 Operational Forecast Serving & Integration

#### 175.8.1 Forecast APIs & SLAs

- [x] **175.8.1.1** Build `@gaia/forecast-serving` BFF exposing
      `/forecast/deterministic`, `/forecast/ensemble`, `/forecast/cyclone`,
      `/forecast/nowcast`, `/forecast/climate-scenario` with OpenAPI 3.1 specs,
      per-tenant rate limiting, and signed-URL GRIB/Zarr output streaming
- [x] **175.8.1.2** Build live operational cycle runner (four daily cycles
      aligned with 00/06/12/18 UTC HRES analysis) with automatic
      initial-condition fetch, forecast launch, publication, and rollback on
      stability-diagnostic failure
- [x] **175.8.1.3** Build forecast-product warehouse (Zarr on MinIO with STAC
      1.0 catalogue, OGC EDR / OGC API Features endpoints) for external
      scientific users and `@veritas/news` editorial system
- [x] **175.8.1.4** Build alerting integration with CAP 1.2 profile publication
      (`urn:oid:2.49.0.1.840.1`) for severe-weather events — wired to
      `@kuanyin/emergency` and `@oshun/shell-routines` weather alerts
- [x] **175.8.1.5** Build latency / skill / availability SLO dashboard (Grafana)
      — p95 cycle completion < 20 min on H100-40 cluster, 24h deterministic RMSE
      within 2% of published GraphCast baseline

#### 175.8.2 Downstream Domain Integration

- [x] **175.8.2.1** Wire forecasts into `@asase/agriculture` crop-model ensemble
      and irrigation/planting decision agent — quantify yield-lift from ML
      weather vs IFS HRES baseline in A/B
- [x] **175.8.2.2** Wire cyclone-forecast into `@oya/drones` mission planner
      (no-fly cones, evacuation-swarm tasking) and `@galatea/fleet` outdoor
      robot safety gating
- [x] **175.8.2.3** Wire renewable-energy potential (solar GHI, wind 100m,
      hydro-inflow) into `@lakshmi/finance` energy trading / capacity planning
- [x] **175.8.2.4** Wire nowcast + lightning into `@uzume/live-performance`
      outdoor-event weather dashboard and `@aphrodite/streaming` outdoor shoot
      risk scoring

---

### 175.9 Data Flywheel & Evaluation

#### 175.9.1 Continuous Improvement

- [x] **175.9.1.1** Extend Phase 85 data flywheel with a `weather-outcomes`
      collector — forecast vs analysis deltas per cycle, per variable, per
      lead-time, per region — continuously fed back into training-data
      difficulty weighting (Phase 89.4.1.8) and retraining triggers (Phase
      85.17.1.5)
- [x] **175.9.1.2** Build public-benchmark suite (WeatherBench-2 + ECMWF
      scorecards + NHC-verification + pysteps-verification) with automated
      leaderboard publication per checkpoint to the Phase 91 evaluation hub
- [x] **175.9.1.3** Build red-team / stress-test suite: hurricane Ian 2022,
      Hurricane Lee 2023, 2021 Pacific Northwest heat dome, February 2021 Texas
      cold snap, July 2022 UK record heat — require every new checkpoint to
      match or exceed the prior on all cases before promotion
- [x] **175.9.1.4** Build observational-obs feedback — compare operational
      forecasts against surface station / radiosonde / buoy arrivals in real
      time, feed per-station residuals back into 175.7.1.2 station-bias heads
- [ ] **175.9.1.5** Publish a scientific paper and open-weights release for each
      major model class. Needs an owner decision on a compute budget — this is
      pod-scale weather-model training (TPU-v5e / H100-class), not a coding
      task; the ERA5/CMIP6 inputs are openly available but the training compute
      is not (stated 2026-09-18). It also depends on the trained models existing
      and is a human authoring/release act. `blocked:governance`

---
