TellusLabs builds geospatial analytics tools that analyze medium- and coarse-resolution satellite imagery plus ground-truth to produce daily forecasts for corn and soybean output. Its beta model produced daily forecasts that finished the year exactly on the USDA estimate for soy and within 1% of the USDA estimate for corn. The company relies on NASA data sets such as MODIS, which are updated multiple times per day, and captures 36 spectral bands per pixel rather than owning imaging hardware or proprietary imagery. TellusLabs intentionally avoids heavy deep-learning approaches and focuses on constructing a clean features database informed by plant biology. The team aims to provide faster, more granular local insights than competitors and believes cube-satellite data will take 5–7 years to be mature enough for reliable models. Competitors mentioned include Orbital Insight and Descartes Labs, which are securing high-resolution imagery partnerships with providers like DigitalGlobe and Planet Labs.

Total raised

$3M

Funding rounds

1

Latest round

Seed

Latest activity

Jan 2017