Order from Lab 7F3630

Private weather sensors

Private ground station readings from farms, wind parks and airports at 1 minute or finer, from stations that feed no public archive, with exact position and elevation. Every sensor must come with its calibration and maintenance records, and the licence must let us train commercial models and keep the weights.

How answering works

Any number of people fill one order. The lab receives one dataset, in its own columns.

Your agent reads the order
It looks at what you hold and says which columns you can fill, and what is missing.
Mora checks what you send
Every record: no copies, no personal data, not already public, not on Mora from someone else.
The lab pays per record it accepts
The lab named the price. You fill as much of the order as you can.

The columns the lab wants

You do not need every column. Mora says which ones each dataset fills.

Column Type What it must hold

station_id id One physical ground station, stable across the whole dataset

observed_at timestamp (UTC) Time of the reading, 1 second to 1 minute step (10-minute statistics accepted for wind parks)

variable label wind speed, wind direction, gust, air temperature, humidity, pressure, rain, irradiance, soil moisture, visibility, ceiling

value number The measured value, as recorded, not interpolated

unit text SI unit of the value

sensor_id id Which physical instrument made the reading, linking to its calibration

height_m number Mounting height of the sensor above ground

aggregation label instant, mean, max or std over the interval

interval_s number Length of the reporting interval in seconds

qc_flag label The operator's quality flag for this reading

is_gap_filled boolean True if the value was filled in rather than measured

latitude, longitude, elevation_m number Exact station position and height above sea level

site_kind label farm, wind park or airport

feeds_public_network boolean + text Whether the station already reports to a public archive, and which

sensor make, model, serial_hash, installed_at, removed_at text / date Identity and service life of each instrument

calibration record record calibrated_at, laboratory, accreditation number, reference, coefficients before and after, as-found error, uncertainty, valid_until, certificate hash

maintenance event record happened_at, kind (swap, clean, relocate, outage), note

Column	Type	What it must hold
`station_id`	id	One physical ground station, stable across the whole dataset
`observed_at`	timestamp (UTC)	Time of the reading, 1 second to 1 minute step (10-minute statistics accepted for wind parks)
`variable`	label	wind speed, wind direction, gust, air temperature, humidity, pressure, rain, irradiance, soil moisture, visibility, ceiling
`value`	number	The measured value, as recorded, not interpolated
`unit`	text	SI unit of the value
`sensor_id`	id	Which physical instrument made the reading, linking to its calibration
`height_m`	number	Mounting height of the sensor above ground
`aggregation`	label	instant, mean, max or std over the interval
`interval_s`	number	Length of the reporting interval in seconds
`qc_flag`	label	The operator's quality flag for this reading
`is_gap_filled`	boolean	True if the value was filled in rather than measured
`latitude, longitude, elevation_m`	number	Exact station position and height above sea level
`site_kind`	label	farm, wind park or airport
`feeds_public_network`	boolean + text	Whether the station already reports to a public archive, and which
`sensor make, model, serial_hash, installed_at, removed_at`	text / date	Identity and service life of each instrument
`calibration record`	record	calibrated_at, laboratory, accreditation number, reference, coefficients before and after, as-found error, uncertainty, valid_until, certificate hash
`maintenance event`	record	happened_at, kind (swap, clean, relocate, outage), note

How much, in the lab's words

2,000 station-years at 1-minute resolution or finer, from at least 300 stations with 3 continuous years each (about 1 billion rows). Quality bar: 95% of timestamps present per station-year, 90% of sensor-months under a valid calibration.

stations
observations
sensors
calibrations
maintenance