Agriculture & food data: yields, soil, weather and satellite

Agriculture is being reshaped by data, from satellite-derived crop indicators to soil sensors and commodity prices. This guide covers the agriculture and food data landscape, the earth-observation backbone behind much of it, and how to source and deliver it.

Available across the EU. DataSupplier sources and delivers this data in all 27 European Union countries — including Germany, France, Spain, Italy, the Netherlands and Poland — and across the EEA, in the format and cadence you need.

Why agricultural data matters now

Climate volatility, food security and sustainability rules are pushing agriculture and food businesses to ground decisions in data. External data brings crop, soil, weather and market context together to forecast yields, manage risk and optimise supply.

The agriculture & food data landscape

• Crop and yield: yield data, crop-use and production data.
• Soil and field: soil quality and irrigation data.
• Weather and satellite: meteorological data and satellite-derived indicators.
• Livestock and machinery: livestock monitoring and farm-machinery telemetry.
• Food supply chain: agricultural commodity prices, cold-chain monitoring and food-consumption data.

The earth-observation backbone

Much agricultural data derives from satellite earth observation, notably the EU Copernicus programme and its Sentinel satellites, which provide vegetation, moisture and land-use indicators. Combining these with weather and ground data is where most analytical value lies.

Common use cases

Yield forecasting, precision agriculture, agricultural-risk and insurance assessment, commodity trading, and food-supply-chain monitoring including cold chain.

Sourcing considerations

Spatial and temporal resolution vary, and combining satellite, weather and ground data demands consistent geospatial referencing. Some farm-level data is personal or commercially sensitive, and licensing for derived products needs checking.

Delivery and cadence

Monitoring uses periodic batches and geospatial formats; some risk and cold-chain use cases want near-real-time feeds. Consistent geocoding and time alignment are essential.

Governance

Where data relates to individual farms or operators, privacy and confidentiality apply. Provenance and licensing documentation matter for insurance, subsidy and tender work.

How agricultural data is built

Most agricultural insight is a fusion of three layers: satellite earth observation (Copernicus Sentinel optical and radar, plus commercial high-resolution), weather (observations and forecasts), and ground data (soil tests, farm-machinery telemetry, field records). Optical imagery yields vegetation indices like NDVI but is limited by cloud; radar sees through it; weather explains variation; ground data calibrates. The analytical value comes from aligning these on a common field geometry and time grid.

From imagery to agronomic insight

Raw imagery is rarely the deliverable. It becomes useful as derived indicators, crop classification, biomass and moisture proxies, anomaly detection, that map to agronomic decisions. Combining a yield model with weather and soil context, at field or sub-field resolution, is what supports precision agriculture, yield forecasting and agricultural-risk assessment.

An agriculture data checklist

• What spatial and temporal resolution does the use case actually need?
• Are optical and radar combined to handle cloud cover?
• Is everything aligned on a consistent field geometry and time grid?
• Is farm-level data treated as confidential or personal where relevant?
• Are derived indicators provided, or just raw imagery?

Sources & further reading

• Copernicus / European Space Agency: Sentinel earth-observation data.
• Eurostat: agricultural statistics.
• FAO: food and agriculture statistics (FAOSTAT).
• European Commission: Common Agricultural Policy data.