Air Gap Solution Enables Farmers to Deploy Machine Learning Without an Internet Connection

Air Gap Solution Enables Farmers to Deploy Machine Learning Without an Internet Connection

Ensuring your farm equipment is using all the latest and greatest machine learning models can be very challenging. Connectivity can be scarce and expensive if you’re using satellites, says Jason Campbell, director of architecture at Wallaroo.

His company therefore launched the Air Gap Edge Deploy feature to enable enterprises to easily deploy and manage machine learning models at the edge in environments without IP connectivity. Think oil derricks, gas pipelines and transmission lines for energy and utilities; and autonomous equipment in Smart Manufacturing and Smart Agriculture.

We spoke to Jason Campbell about the air gap solution and how it could benefit farmers.

Why was the Air Gap Edge Deploy feature developed?

“There are many reasons why companies (not just farmers) might seek to deploy machine learning via air space. For example, equipment may be far from internet connectivity at the edge, such as in oil derricks, gas pipelines or in agriculture, perhaps a combine harvester in a rural area away from a cell phone tower.Also, the increase in cybercrime has led some companies to explore the option of isolation to keep their systems safe By isolating their networks from external networks, they are able to prevent vulnerabilities associated with those connections, such as data breaches and ransomware attacks that can cost billions in losses .

How does the Air Gap Edge Deploy feature work?

“You can train a machine learning model anywhere, in the cloud or on-premises. But from there, you’ll need a remote connection (e.g., to the actual farm equipment you’re on). want to deploy the template, we provide more details on how it works here.

Why is this relevant for crop growers?

“Agricultural equipment generates more data than ever. John Deere’s technical director, in an interview with The Verge, said their agricultural equipment has essentially become “mobile sensor suites with computational capability.” Combining this sensor data with AI enables crop growers to use the right amount of water, fertilizer, pesticides, and more. for each individual plant. Also, crop growers rely more on robots to pick different crops using computer vision, etc.

Essentially, the data and AI you get as a farmer is a better yield while lowering your input costs. But ensuring that your equipment uses all the latest and greatest machine learning models is very difficult. And you also need to think about the flow of data to the data scientists who trained the model. All of this sensor data can amount to gigabytes or even terabytes of data per day.

Connectivity is scarce and can be expensive if you use satellites. So for the equipment owner or repairman, it’s much more cost effective to use something like this air gap solution to deploy the machine learning model into the equipment as well as take the production data out so that you can ensure that your models are always accurate and efficient. More information on what this inbound and outbound data stream looks like here.

What are the costs for a producer using this air gap solution?

“As you see a greater shift to equipment as a service (EaaS), more of those costs will be borne by owners and repairers of farm equipment who then resell it to farmers as part of broader smart agricultural services. So, a farmer will pay for AI services, which will include state-of-the-art machine learning as part of it. »

And what are the financial benefits for producers?

“The adoption of machine learning in agricultural production has become a necessity given the needs to increase food production while balancing sustainability. ML has already started to make an impact, providing insights that help increase the productivity, using less water, fertilizers, pesticides, etc. yield.”

Can you give a practical example?

“We already have examples of agricultural equipment automatically adjusting water, nutrients and other chemicals used down to the plant level using sensor data combined with AI. As for our own air gap solution, we don’t have any examples to share, but we do have some in other industries, especially manufacturing. In fact, we are working with the US Space Force on deploying state-of-the-art machine learning for their fleet of satellites.

Similar Posts

Leave a Reply

Your email address will not be published.