A farmer plants soybean seeds with the help of precision agriculture data collected via edge computing.

Aug 02 2022

Edge Computing Lets Agencies Conduct Complex Projects at a Distance

The USDA, Army and Postal Service are all experimenting with technology that saves money and improves information gathering.

Historically, farmers have managed multiple fields as a single unit, despite marked variations in soil quality, topography and drainage capacity that can exist in those acres.

To enable more granular oversight — for example, targeting weeds of a certain size, class or species for removal — the U.S. Department of Agriculture has been examining potential edge computing applications in the farming realm.

With edge computing, analysis happens at the same location the data is collected; latency, bandwidth and storage needs are reduced, offering time and cost savings. This also enables the efficient use in the field of more advanced analytic processes such as machine learning and artificial intelligence.

“We really need to transform how we manage our farms and be much more site-specific so we can reduce environmental pollutants, create more efficiencies and, most important, reduce overall production costs, which carries over into the price of food,” says Steven Mirsky, a research ecologist with the USDA’s Agricultural Research Service.

Given the real-time decision-making speed that edge computing offers, Mirsky expects its use within the federal government to grow.

“Edge computing is going to be everywhere,” he says. “What we can do on the edge is powerful, with many applications becoming more feasible.”

Click the banner to get customized cloud content by becoming an Insider.

Edge Computing Expands Agency Capabilities

Given the benefits edge technology can provide, government agencies are increasingly incorporating it into operations, says Adelaide O’Brien, government insights research director at IDC.

An IDC survey indicates 37 percent of federal agency decision-makers now have workloads deployed at the edge, and 50 percent plan to within the year. The volume of data created and processed at the edge is growing exponentially, O’Brien says.

“For military networks, the edge can gather petabytes of information through high-definition video or gather and process multiple types of electronic signals,” she says. “Processing can take place right on board aircraft and ships, and the results of onboard analysis can be sent to a centralized system.”

DISCOVER: How working on the edge can complement traditional cloud usage.

But quickly performing computations involving significant amounts of data requires considerable processing power. Information gathered through Internet of Things sensors and other devices in the field often must be transmitted back to another location to be analyzed, which is a time-consuming and inefficient process.

To ease that burden, the U.S. Army Engineer Research and Development Center (ERDC) is studying edge computing for military use.

“It’s replacing hypotheticals with actual live data, so it brings a truer environment for training,” says Timothy Garton, senior computer scientist within ERDC’s IT laboratory. “Instead of having to physically be somewhere for the training, you can now create a synthetic environment that provides all the conditions.”

31%

The percentage of government organizations that choose to deploy edge solutions primarily because the cost of other methods is prohibitive

Source: IDC, “Edge Computing: Transforming Government Operations,” April 2021

In 2018, ERDC began examining how edge computing could optimize computation execution time and use, Garton says.

The research center has also looked at adding information gathered via edge computing to synthetic training environments to enable soldiers to train on base instead of traveling. These virtual training situations often integrate active weather-related information — such as water conditions, terrain maps and drone imagery — into the experience to represent a situation more accurately.

ERDC has found that the technology will likely require multiple connectivity options, because specific resources and needs will vary based on each application.

“One of the things we were looking at was sending information to a Microsoft HoloLens headset for display. In a situation like that, you’re actually out in the field,” Garton says. “In the synthetic training environment, they’ve also got different virtual reality headsets to give you a true visual look at everything.

EXPLORE: Leveraging standards to optimize AI at the edge.

“In those environments, you can’t use Wi-Fi, and 5G requires so many towers and endpoints to mesh together, so we really had to look at how to use military satellite communications.”

NASA is another agency that employs edge computing, using a structure to process data from DNA sequencing performed aboard the International Space Station, which shrinks the timeframe for processing from weeks to mere minutes.

The agency has also used edge data processing capabilities to enable AI-based communication between two instruments installed aboard the ISS: the MAXI sky survey, which conducts a full-sky survey about every 90 minutes; and NICER, used to monitor stars about to become black holes.

The instruments can now notify one another to take more detailed measurements in an area of the sky where a new object has been spotted. That job previously required the use of two ground-based astrophysics facilities in different time zones.

How USPS Is Tracking Lost Objects with Edge

At the U.S. Postal Service, an edge-based system tracks packages with damaged, misprinted or otherwise unreadable labels. Previously, package sorters could only use information from the OCR address area on packages and scan their tracking barcode. In the new system, package images and other characteristics are automatically obtained as items are scanned for sorting.

NVIDIA V100 Tensor Core GPUs within AI-enabled HPE Apollo 6500 servers, located at USPS processing centers, can process 20 terabytes of package images daily from more than 1,000 mail processing machines.

Due to the volume of items the agency oversees, sending image data from each field processing site to a central location wouldn’t be possible logistically, according to Information Sciences Specialist Joanne Su.

LEARN ABOUT: How edge computing helps organizations solve common IT challenges.

Currently, a postal worker reviews package images and compares them to insights produced by the system’s AI model to confirm accuracy; the process, however, is mostly automatic. 

“The tracking barcode is still the primary information used to locate items,” Su says. “However, specialized graphics and labels are also used — packaging, logos, stamps, indicia and permits.

“The key elements here are the GPUs’ performing pattern classification and recognition, along with specially trained AI models. Our internal systems are used to distribute the results to other sites in the USPS network.”

Edge computing is going to be everywhere. What we can do on the edge is powerful, with many applications becoming more feasible.”

Steven Mirsky Research Ecologist, U.S. Department of Agriculture’s Agricultural Research Service

Enabling Farmers to Make Real-Time Decisions

USDA has been working with Microsoft’s FarmBeats project to collect data from disparate areas in working fields. For instance, data obtained from an in-field camera system is used to gauge water stress on corn, soybean and cotton plants.

Microsoft Azure’s cloud platform stores some data, but cellular connectivity isn’t always robust in rural settings, and time can be crucial when deploying automated processes such as herbicide or fertilizer application. To get around that, FarmBeats uses television white-space technology — unused TV channels that offer a lower-frequency connectivity option compared with alternatives such as 5G — and very high-frequency (VHF) channels to transmit data.

“If we want to arm farmers with real-time decision-making, we need solutions that are fast,” Mirsky says. “When using computer vision and AI to see and detect stress to inform a management decision, processing in the cloud is just incredibly time consuming and more challenging.

“The ability to train algorithms to work on small edge processing systems allows us to not move images and big files to the cloud and to work in the field instead.”

REVIEW: How agencies are using edge computing for data analytics.

Lance Cheung/U.S. Department of Agriculture

aaa 1

Register