Glossary
The terms you will see in TERRASENSE screens and reports, in plain language.
| Term | Meaning |
|---|---|
| NDVI | Greenness computed from red and near-infrared light. Higher with more, healthier leaves. |
| ΔNDVI | NDVI after minus NDVI before a disaster. The bigger the drop, the stronger the suspicion. |
| NDMI | Leaf moisture from near-infrared and shortwave infrared. Low values point to water stress. |
| Sentinel-2 | Copernicus optical satellites. 10 m resolution, revisiting about every 5 days. |
| L2A | Sentinel-2 product with atmospheric effects removed. |
| SCL | Sentinel-2 scene classification, used to drop cloud and shadow cells. |
| Sentinel-1 | Copernicus radar satellites that image regardless of cloud, rain or night. |
| VV · dB | The radar polarisation (vertical send, vertical receive) and the unit of signal strength. Water returns a low signal. |
| SAM2 | Segment Anything Model 2, an image segmentation AI used to draw parcel candidates. |
| Parcel candidate | A field boundary candidate split from the satellite photo. Not an official boundary. |
| Degree-days | Daily mean temperature above the crop base temperature, summed over the season (paddy 10 °C, upland 5 °C, orchard 7 °C). |
| Growth stage | Green-up, vegetative, peak or senescence, picked from the NDVI curve. Not a heading or harvest date. |
| Damage-suspect area | Summed area (ha) of graded 10 m cells. |
| Loss share (satellite) | Share of the field taken by suspect cells. Different from the assessed loss rate. |
| Survey points (D, C) | Damage points D1–D3 and healthy control C1. |
| GeoJSON | An open file format for map locations and shapes, read by GIS and field apps. |
| Lodging | Crops knocked flat by wind and rain. |
| First screening | An initial call that decides what to check in the field. Not a final verdict. |
| Certified loss assessor | A qualified professional who surveys and assesses losses, for example in crop insurance. |
Work with us
See your county’s fields from orbit, before the next storm.
We start with a satellite screening of your area from public data, then compare the results with your own field survey records. No equipment goes in the field.