A red tractor driving in an agricultural landscape. Photo.

Artificial intelligent agriculture

DigiFarm is one of Norway's leading agri-tech startups specializing in the development of deep neural networks for automatic detection of field boundaries and sown areas based on high-resolution satellite data. This is primarily used by their customers for verification of subsidies, crop forecasts, variable fertilization/spraying, carbon mapping, sustainability and traceability verification, grain species detection and regenerative agriculture.

DigiFarm´s core operation consists of the development of technology and model training of deep neural networks that can automatically detect field boundaries, sown area, and other objects within land changes such as trees, bogs, shade (from trees), telephone poles, irrigation divots. The models are trained in several international regions including Europe, South America, APAC (Thailand, Vietnam, and India) as well as the USA and Canada.

This requires a large amount of image data as well as annotation data for training models as they process from over 300 million hectares of satellite data with 1 m resolution every month from 3 different dates of data, as well as to detect 30 million hectares with land changes.

According to CEO and Founder, Nils Helset, this requires a stable, secure, and high-performance HPC infrastructure with GPUs. DigiFarm has been part of several cloud-based startup programs including Google Cloud for Startups (A100 alpha program), AWS Activate, AWS Open Earth Initiative, Microsoft for Startups, NVIDIA Inception, and Oracle for Startups, but each of these platforms and programs has several challenges:

  • GPU costs - the average price of GPUs (NVIDIA V100 and P100) is approx. $ 2.75 per hour - we currently use 35 GPUs constantly for our development where this time price becomes too expensive for our operations, especially with regards to there being restrictions on the type of GPUs you have access to free cloud credits and startup programs, in Azure (Microsoft for Startup) you only have access to K80 while in AWS, Google and Oracle then A100 is not available, only V100 and P100.
     
  • Workshop and technical support - because we have a complex computer process infrastructure with many variables and different elements, it is incredibly useful for us to have a continuous dialogue with the National Competence Centre for HPC that helps us with the optimization of our processes.

Areal photo of fields.
Accurate boundary data can help the estimated 570 million farmers and growers worldwide boost their yields and lower their input costs.

 

We are dependent on a technological partner who can assist and support us through this process. We could not find a better partner than the NCC, who has been the optimal partner for us. We strongly believe in having a national network (HPC) and program for artificial intelligence (AI) startups that will contribute to a stronger ecosystem in Norway for the development of new and sustainable technologies. This makes us more competitive in international environments.
Nils Helset, CEO and Founder, Digifarm

 

To the Annual Report 2021