Benchmarks

Query station benchmark metrics for model evaluation and comparison.

Query station benchmark metrics

post

Query benchmark metrics (RMSE, MAE, quantiles) for forecast models evaluated against weather station observations.

Useful for:

• Comparing forecast model performance

• Evaluating model accuracy by region

• Analyzing forecast errors over time

Multi-Model Support:

• Query multiple models in a single request to compare performance

• Results include model name in each row for easy comparison

Geographic Filtering:

• market_zone: Filter by energy market zone (e.g., "DE", "FR")

• country_key: Filter by country code (e.g., "DE", "US")

Note: Either station_ids or geo must be provided (mutually exclusive).

Authentication: Requires API key.

For more information on benchmark metrics, see docs.jua.ai.

Authorizations

HTTPBearer

Query parameters

formatstring · enumOptional

Response format: 'json' for columnar JSON or 'arrow' for Apache Arrow IPC stream

Default: jsonPossible values:

Body

application/json

Query parameters for station benchmark data.

station_idsany ofOptional

List of specific station IDs to query. Mutually exclusive with geo filter.

string[]Optional

or

nullOptional

geoany ofOptional

Geographic filter for selecting stations by region. Mutually exclusive with station_ids.

or

nullOptional

start_timestring · date-timeRequired

Start time for benchmark period

end_timestring · date-timeRequired

End time for benchmark period

variablesany ofOptional

List of variables to compute metrics for

or

nullOptional

max_prediction_timedelta_minutesintegerOptional

Maximum prediction lead time in minutes

Default: 10080

Responses

200

Successfully retrieved benchmark metrics

application/jsonapplication/vnd.apache.arrow.stream

Responseany

400

Invalid query parameters

401

Authentication required

403

Insufficient permissions

422

Validation Error

application/json

post

/v1/station-benchmarks/metrics

HTTPcURLJavaScriptPython

POST /v1/station-benchmarks/metrics HTTP/1.1
Content-Type: application/json
Accept: */*
Content-Length: 182

{
  "models": [
    "ept2"
  ],
  "geo": {
    "type": "market_zone",
    "value": "DE"
  },
  "start_time": "2024-10-01T00:00:00Z",
  "end_time": "2024-10-07T00:00:00Z",
  "variables": [
    "air_temperature_at_height_level_2m"
  ]
}

Query by market zoneCompare multiple models

{
  "model": [
    "ept2",
    "ept2",
    "aifs",
    "aifs"
  ],
  "prediction_timedelta": [
    60,
    60,
    60,
    60
  ],
  "variable": [
    "air_temperature_at_height_level_2m",
    "air_temperature_at_height_level_2m",
    "air_temperature_at_height_level_2m",
    "air_temperature_at_height_level_2m"
  ],
  "metric": [
    "rmse",
    "mae",
    "rmse",
    "mae"
  ],
  "avg": [
    1.23,
    0.98,
    1.45,
    1.12
  ],
  "quantile_05": [
    0.45,
    0.34,
    0.56,
    0.42
  ],
  "quantile_25": [
    0.67,
    0.54,
    0.78,
    0.62
  ],
  "quantile_50": [
    0.89,
    0.76,
    1.01,
    0.89
  ],
  "quantile_75": [
    1.12,
    0.98,
    1.34,
    1.15
  ],
  "quantile_95": [
    1.87,
    1.54,
    2.1,
    1.87
  ],
  "sample_count": [
    15420,
    15420,
    15420,
    15420
  ]
}

Get available benchmark dates

get

Retrieve available dates for station benchmark data with optional filtering.

Useful for:

• Discovering available benchmark data

• Finding recent benchmark dates

• Planning benchmark queries

Authentication: Requires API key.

For more information, see docs.jua.ai.

Authorizations

HTTPBearer

Query parameters

modelany ofOptional

Optional model name to filter by

stringOptional

or

nullOptional

days_lookbackinteger · min: 1 · max: 365Optional

Number of days to look back from today

Default: 365

Responses

200

Successfully retrieved available dates

application/json

401

Authentication required

403

Insufficient permissions

422

Validation Error

application/json

500

Internal server error

get

/v1/station-benchmarks/available-dates

HTTPcURLJavaScriptPython

GET /v1/station-benchmarks/available-dates HTTP/1.1
Accept: */*

{
  "dates": [
    "2024-10-15",
    "2024-10-14",
    "2024-10-13"
  ]
}