Home General How Taranis Uses AI to Provide Commodity Crop Insights to Farmers

How Taranis Uses AI to Provide Commodity Crop Insights to Farmers

It is expected that there will be over 9 billion people to feed by 2050. Predictions also show that the global yield has to double in a bid to meet the increased demand.

However, achieving this is not easy. Today, nearly 45% of all the crop calories in the world are converted into industrial products and biofuels or fed to livestock.

According to the co-founder of Taranis, Ofir Schlam, the lack of data is a major part of the problem. He co-established the agriculture-technology startup together with Ayal Karmi, Eli Bukchin and Asaf Horvitz.

The lack of data is causing many farmers to go about their work blindly. As such, they cannot come up with customized growth plans to various individual crops or even react to various threats such as weeds, parasites and diseases.

Currently, Ofir Schlam pitches his company’s AI platform as the ideal solution, which entails an integration of high-resolution sensors and imagery with an intelligent layer that draws both historical and real-time insights with over 90% accuracy.

The Taranis solution has certainly caught the attention of investors. Recently, the Tel Aviv-based company disclosed details regarding its $20 million Series B round of funding that was led by Viola Ventures.

The exercise propelled the total amount raised by Taranis to $30 million to date. Other investors including Gal Yarden, Eyal Gura, OurCrowd, Vertex Ventures, and Finistere Ventures also took part in the funding round.

The participation also included strategic investors such as Sumitomo, Corporation Europe, Cavallo Ventures, and Nutrien.

Taranis, which is a Microsoft Venture’s graduate, intends to use the investment to gain a bigger portion of the $1.5B global agriculture technology business.

“We are excited to advance our mission of providing farmers with the technology and know-how to effectively maximize crop yields while maintaining operational efficiency,” said Schlam. “We have already helped thousands of farmers monitor crops for potential hazards. Now we’re looking forward to expanding our footprint around the globe.”

Taranis UHR, the company’s main product, has the potential to capture multispectral images at 8 to 12cm through a proprietary sensor pod, which reduces motion blur.

Taranis maintains a fleet made up of 60 Cessna planes for capturing the imagery at scale, regularly at low altitudes of as low as 10 to 30 meters.

A section of the imaging technology is derived from San Francisco-based firm Mavrx, which was purchased by Taranis back in May.

Schlam said that a single plane has the potential to cover a maximum of 50,000 acres daily or even a 100-acre field in more than five minutes.

Once the collection of images is done, algorithms help to piece them together. This is the point where artificial intelligence comes into play. Taranis’ model analyzes and classifies a single grid segment while zooming into images of the crop at 0.3 to 0.5 mm for each pixel. According to Schlam, such a resolution is sufficient for counting beetles on a leaf.

Taranis goes beyond pictures to making forecasts. The company’s other data pipelines comprise of satellite imagery, drone imaging data, which makes up a weather prediction model that Schlam says is 75 times more comprehensive than sensors and off-the-shelf solutions.

Taranis’ artificial intelligence (AI) uses the data in reporting plant population irrespective of the crop’s growth stage.

It also calculates flower count, tree diameter, stand height, plant height, canopy cover, row spacing, row length, and plant emergence.

Additionally, it can spot when a weed sprouts, which comprises a potential threat as well as automatically categorizing it and recommending customized herbicide solutions.

The AI can also calculate the plant temperature, the soil’s water content, and the number of nutrients present in the vegetation.

The Taranis’ models operate in two modes including regional and site-specific. In the regional mode, it projects the suitability of disease outbreak conditions in the whole area as well as representing the potential risk through the entire area’s heat map.

In the latter, data is not only recorded in the field but it also considers pesticide applications, scout reports and data drawn from ground-based sensors coupled with records in regional weather stations.

All those forecasts and more are provided through both web and mobile applications, which prioritize crop areas for both investigation and direct scouts to help in filling out crop-based reports with voice memos, photos and the areas of interest that farm managers can analyze and view in real time.

Today, Taranis serves over 19,000 farms across various countries including Australia, Ukraine, Russia, Argentina, Brazil, US, and Canada.

The company boasts local offices in all these locations. These offices collectively have 60 agronomists who are involved in manually training the system and identifying problems.

At the moment, Taranis is targeting various commodity crops including potatoes, wheat, soybean, sugarcane, corn and cotton, and it charges $5 to $20 for each acre per season.


Subscribe to our newsletter

Signup today for free and be the first to get notified on the latest news and insights on artificial intelligence

KC Cheung
KC Cheung has over 18 years experience in the technology industry including media, payments, and software and has a keen interest in artificial intelligence, machine learning, deep learning, neural networks and its applications in business. Over the years he has worked with some of the leading technology companies, building and growing dynamic teams in a fast moving international environment.
- Advertisment -


AI Model Development isn’t the End; it’s the Beginning

AI model development isn’t the end; it’s the beginning. Like children, successful models need continuous nurturing and monitoring throughout their lifecycle. Parenting is exhilarating and, if...