CERES draws on public model inputs for rainfall (NASA POWER), vegetation (MODIS NDVI), conflict (UCDP GED), food security phase (IPC and Cadre Harmonisé) and market prices (WFP), plus FEWS NET, which supplies the grading proxy and is not a model input. The cards below cover all of them. All sources are publicly available. No proprietary data is used.
Each data stream feeds into a specific stage of the CERES pipeline. Sub-scores are combined into a composite stress score which drives the probabilistic forecast. See the Methodology page for full mathematical specification.
| Signal | Role in Pipeline | Stage |
|---|---|---|
| NASA POWER rainfall anomaly | Drought stress sub-score | Stress scoring |
| MODIS NDVI anomaly | Vegetation stress sub-score | Stress scoring |
| UCDP GED conflict events | Conflict intensity sub-score | Stress scoring |
| IPC / CH phase classification | Food security phase and food access sub-scores | Stress scoring |
| WFP market prices | Market deviation sub-score | Stress scoring |
| FEWS NET proxy | Outcome each forecast is graded against | Grading (T+90d) |
The current forecasts, the published runs and the graded ledger are free to download, with no account and no key. The current forecasts and the published runs are HXL-tagged CSV and the graded ledger is JSON. Licensed under CC BY 4.0.
Best for dashboards, situational awareness, and map data integrations.
Download ↓Best for time-series analysis, trend research, and calibration studies.
Download ↓Every prediction graded at T+90, with the proxy phase, the grading source and its Brier contribution.
Download ↓HXL-tagged CSV files: Row 1 = column headers · Row 2 = HXL hashtags · Row 3+ = data. They give Niger its ISO code, NER; site URLs and the JSON routes use NIG.
The same data the dashboard reads, open to anyone. No key, no sign-up.
Research collaboration: hello@northflow.no
Every model input comes from a public source.
Each source is named here with its provider, cadence and resolution.
Typical data latency for each source is listed here.