Glossary of technical terms

Research

AgriNova AI's proposed 0–100 composite score, intended to bring several kinds of field information into one number so that fields can be prioritized for review. Its proposed input categories are NDVI (crop vigour), soil moisture, temperature stress and a water-stress index; how they would be weighted and calibrated for Canadian crops is still being researched. The AMI scores shown on this website are synthetic sample values, not measurements of any farm.

Source: AgriNova AI's own explanation; it cites no outside publisher.

A layer made when a satellite image is processed that marks the pixels covered by cloud or cloud shadow, so they can be left out before an index or a score is calculated. For Sentinel-2, the European Space Agency's Level-2A processing produces a scene classification map with classes for clouds (including cirrus), shadows, cloud shadows, vegetation, land without vegetation, water and snow. The mask is an automatic classification, not a check on the ground, so the image date and quality stay part of reading any map.

Source: European Space Agency, S2 Processing, SentiWiki (Copernicus). sentiwiki.copernicus.eu/web/s2-processing. Accessed October 4, 2026.

A different part of the same field that looks typical, checked on the same visit as the zone that looks different, so the two can be described side by side. A difference between them is something to record and look into on the ground, not a diagnosis.

Source: AgriNova AI's own explanation; it cites no outside publisher.

A pilot evaluated against a few key performance indicators (KPIs) that the farm and the provider agree in writing before it starts, each with a baseline, a way of measuring it and a date to review it. Agreeing the measures in advance lets the result be judged as it is, including a mixed or null result. AgriNova AI's pilot terms, including any KPIs, are not yet confirmed.

Source: AgriNova AI's own explanation; it cites no outside publisher.

A number calculated for each pixel of a satellite image from the near-infrared (NIR) and visible (VIS) light the surface reflects; NASA writes it as NDVI = (NIR − VIS) / (NIR + VIS), which always gives a value between −1 and +1. NASA explains that the chlorophyll in leaves strongly absorbs visible light, while the cell structure of leaves strongly reflects near-infrared light. In NASA's examples, very low values (0.1 and below) correspond to barren areas of rock, sand, or snow.

Source: NASA Earth Observatory, Measuring Vegetation (NDVI & EVI), NASA Science. science.nasa.gov/earth/earth-observatory/measuring-vegetation-ndvi-evi/. Accessed October 4, 2026.

The observation date is the day the satellite recorded the image; the processing date is the day that image was turned into the map, index or score you are looking at. A recently processed map can still show an older observation, so check the observation date before treating a pattern as current.

Source: AgriNova AI's own explanation; it cites no outside publisher.

Revisit is how often a satellite passes over the same place: the European Space Agency gives 10 days for each Sentinel-2 satellite and a nominal five-day revisit for the two-satellite constellation, at the Equator and under the same viewing conditions. A usable image is a pass in which the field can actually be seen, and NASA notes that clouds and aerosols can often block a satellite's view of the surface entirely. The time between usable images of a field can therefore be longer than the revisit, and a map may show an older usable image rather than the latest pass.

A European multi-spectral imaging mission of the Copernicus program whose satellites each carry an instrument that samples 13 spectral bands: four at 10-metre resolution (blue, green, red and near-infrared), six at 20 metres and three at 60 metres. The nominal constellation is two satellites, currently Sentinel-2B and Sentinel-2C (Sentinel-2C replaced Sentinel-2A in operation on January 21, 2025). Until December 31, 2026, Sentinel-2A also adds acquisitions in an extension campaign that improves the revisit for some areas.