To help farmers get more from their fields, DigiFarm runs its precision agriculture platform on OCI

February 10, 2022 | 5 minute read
Text Size 100%:

A 15th-generation farmer in Norway, Nils Helset took over his family farm eight years ago and saw firsthand how usable land changes over time because of flooding, erosion, and other factors and how those difficult-to-predict variables affect crop management and production.

To manage those variables, Helset created a technology platform to optimize his own crop production, and it quickly evolved into DigiFarm, a business to help other farmers, beginning with a focus on field boundaries.

Technology, such as precision agriculture and crop monitoring, can vastly improve outputs and take the guesswork out of when and where to put seeds, fertilizer, and other inputs, but it can’t work if farmers don’t have a clear view of their land.

“Precision agriculture services and in-field analytics must start with accurate field boundary data, whether you’re talking about crop inputs, seeds, crop protection, fertilizer, yield prediction, and so on,” says Helset. “But at the time, existing field boundary data was either not available, inaccurate, or outdated. For example, the United States Department of Agriculture drew 32 million parcels of land by hand 13 years ago and then digitized them, and they haven’t been updated since then.”

Precision agriculture and other farming tech are critical to producing enough food to support the world’s growing population. Crop production needs to increase between 60% and 100% to feed the extra two billion people who might live on the planet by 2050, according to the Institute on the Environment.

To tackle the field boundary piece of this puzzle, DigiFarm’s platform uses neural network models to automatically detect field boundaries using high-resolution satellite data.

The tech behind the tool

After evaluating several vendors, Helset and team selected Oracle Cloud Infrastructure (OCI) to develop DigiFarm’s precision agriculture platform because OCI’s bare metal graphic processor units (GPUs) are vital to the kind of machine learning he runs.

“We selected Oracle because of the affordability and performance of the GPUs combined with Oracle’s extensive cloud footprint,” Helset says. “GPUs are very important for training deep neural network models. The higher the GPU performance, the better our models. And because we work in several different countries and regions, we needed the infrastructure to support that.”

“We built a global model,” says Konstantin Varik, cofounder and CTO at DigiFarm. “Because we use OCI, we can apply that model to any images from any place in the world and it works well.”

To make its platform work, DigiFarm first ingests optical satellite images from the European Space Agency from a public bucket in Amazon Web Services (AWS). Those images are then brought into an instance on OCI and placed into OCI Object Storage. DigiFarm next trains its deep neural network model to classify and enhance the resolution of those images in a private subnet on seven Oracle bare metal servers. Using a combination of Nvidia Tesla A100, V100, and P100 GPUs, DigiFarm applies its inference models to analyze the enhanced images and determine the precise boundaries of a farmer’s seeded acres. Using Oracle bare metal GPUs this way has helped DigiFarm improve performance and reduce costs.

“Our training and inference models are resource-intensive and need powerful GPU and CPU instances,” says Rohit Shetty, head of engineering and infrastructure at DigiFarm. “A typical virtual machine requires software that includes a 10% to 15% performance tax. GPUs don’t require that underlying software. Our processes run anywhere from 24 to 30 hours at each stage, so even a 10% improvement in performance means that we’re saving a couple of hours. We’re a small startup, so that time is crucial from both a delivery and a cost perspective.”

A graphic depicting the architecture for DigiFarm’s infrastructure.

When the boundaries are delineated, the images are stored in OCI Block Storage, turned into georeference maps, and made available to DigiFarm clients. DigiFarm's clients can access their georeference maps using Oracle API Gateway, which instructs OCI Functions to pull the delineated images from Block Storage.

To learn more about how DigiFarm runs its ag-tech platform on OCI, watch this episode of Built and Deployed.

So far, DigiFarm has helped approximately 14,000 farmers in 30 countries delineate their seeded field acre boundaries with 92% accuracy. The new images are 40 times more accurate than the existing models.

Creating a sustainable future for agriculture

Since its founding in 2019, DigiFarm has grown from two employees to 15, raised more than €2 million in funding, and delineated more than 120 million hectares of land.

Helset says that working with Oracle has enabled him to keep costs in check as the business grows. “We're saving 30% to 40% running our bare metal GPUs on Oracle compared to other vendors’ solutions. That represents $10,000 to $12,000 every month, which is big savings for us.”

OCI has also enabled performance improvements. “It's easy for us to deploy new instances in our region, which has been great in terms of efficiency,” says Helset. “We've seen that create a bit of a challenge with other vendors because of a lack of hardware or GPU provisions.”

DigiFarm is also a member of Oracle for Startups, a program that connects promising startups with cloud resources and enterprise expertise. “Oracle for Startups has exposed us to the extended Oracle network and given us more exposure in the markets we're moving into,” Helset says. “That’s helped us grow and navigate this startup journey. Oracle’s support has meant the world to us.”

The DigiFarm team recently tested its field boundary system outside of Norway and achieved the same high level of accuracy in the US, France, and Brazil.

Looking ahead

It’s difficult to predict what the future might bring in terms of food demand and production, but companies like DigiFarm have the potential to help farmers make data-driven decisions, reduce uncertainty, minimize production costs, and increase crop yields. So far, Helset says DigiFarm clients have seen yield potentials—the yield of a cultivar when grown in environments to which it’s adapted, with unlimited nutrients and water and stresses effectively controlled increase up to 10% and input costs decrease 15%.

The next product in DigiFarm’s pipeline is a crop classification and zoning model that can help farmers implement variable seeding rates, spraying, and yield predictions. These plans can also improve sustainability because an estimated 40% of the world’s fields are currently overfertilized.

“We believe that using technology to revolutionize how farmers identify, manage, and update field boundaries on a large scale is the most tangible way to build a sustainable future,” says Helset.

Justine Kavanaugh-Brown

Justine Kavanaugh-Brown is a senior writer at Oracle. She was previously a writer and editor for e.Republic’s Content Studio, where she worked with numerous enterprise technology companies.

Previous Post

Secure OCI Oracle Linux VMs with AIDE file integrity checking: Part 1

Arno Schots | 5 min read

Next Post

Running faster motor sport simulations on Oracle Cloud Infrastructure

Arnaud Froidmont | 3 min read