Industry

Cloud innovation in pig weighing helps farmers improve safety and profitability

Share this post:

For many people, the mention of a “hearty breakfast” or “flavorful meal” conjures up the quiet sizzle, smoky flavor and savory aroma of bacon. Pork enthusiasts can count on their beloved bacon to deliver a consistent quality and experience — and that’s no accident. Pig farmers and processors know all too well that a pig’s weight and fat percentage are critical for pig production. If the animal weighs too much, it requires additional costly processing, and if the animal is too small, it fetches a lower market price. So, farmers are paid less if a pig’s weight is out of the acceptable range, which varies by country. Hitting this just right is one of the biggest challenges of pig production and dictates a farmer’s profitability.

In the four months or so that a farmer prepares a pig for production, he or she is typically only able to weigh a pig a few times. This gives little opportunity to adjust the animal’s diet and hit the target weight range by the pre-set production date. To estimate a pig’s weight, the farmer has three options: take the pig out of its pen and force it onto a scale, climb into the pig’s pen and measure the pig from head to tail and around the girth, or conduct a visual inspection. These manual processes are likely to yield inaccurate results, can be highly stressful for the pigs, and can be extremely difficult, time-consuming and dangerous for farmers. Imagine trying to corral or get in the pen with an approximately 110 kilogram (240 pound) scared animal. Truthfully, pig weighing is a bit of a guessing game, but these manual processes are how farmers around the world have done it for decades. Until now.

Transforming from manual to digital animal production

At Smart Agritech Solution of Sweden, we develop digital solutions for innovative animal production. Our startup is the brainchild of Per Eke-Göransson, an inventor and former pig farmer. He says, “Manual weighing is a painful task for both humans and animals. After having weighed pigs for years, manually in the summer heat, I started to think that there must be an easier way. The solution hit me after long and hard thinking, and I realized exactly how to do it.”

In the 1980s, Per had the idea to use photographs to create optical measurements to calculate a pig’s weight. However, his idea was ahead of its time: cameras were too expensive and technology was too immature. Per got a patent and invested in a 15-year-old algorithm that the Swedish Agricultural Institute of Farming had developed. Finally, photography and machine-learning technology have caught up, and Per partnered with a butcher and a technician to turn his idea into reality.

We contacted the IBM Garage because we had this genius concept, but we needed a system, cloud services, developers, quality assurance and so on. Plus, as a small startup, we wanted to boost the credibility of our solution with backing from a huge IT company. We knew no one would question IBM.

Addressing farmer challenges through cloud innovation

At the IBM Garage in Copenhagen, we participated in an IBM Design Thinking Workshop and a cloud innovation architecture workshop for Pig Scale, our digital pig-weighing solution. We greatly appreciated how well organized the process was and how much we involved the user’s perspective.

For our first minimum viable product (MVP), we decided to create assets that would have the biggest impact at EuroTier, the world’s largest farming conference, in Hannover, Germany. The deliverables included a clickable prototype to demonstrate how the front-end solution works, a conference booth design explaining the solution and its value for the farmer, and a video illustrating a pigsty and how we use machine learning and visual recognition to capture and analyze a pig’s weight.

With the IBM Garage, we built our MVP on IBM Cloud with IBM Watson Machine Learning. Every day, with no stress to the pigs or danger to the farmer, the solution will capture accurate 2-D photographs of pigs in their pens; determine their weight, growth rate and readiness for production; and alert the farmer about any growth anomalies. This allows the farmer to quickly adjust a pig’s diet to get the pig’s weight into the most profitable range.

The Pig Scale concept was extremely well received at EuroTier. In fact, more than 125 farmers, competitors and system integrators from around the world requested to buy our product or even purchase our company. We had never seen anything like it.

With such positive feedback on the first MVP, we quickly secured funding to build the second MVP — Pig Scale’s back-end system. We are currently working with the IBM Garage and the IBM Watson iLab team on the second iteration. Stay tuned because Pig Scale is going to be something to squeal about.

Schedule a no-charge visit with the IBM Garage to get started.

Managing Director, Smart Agritech Solution of Sweden

Helena Björk

Marketing Manager, Smart Agritech Solution of Sweden

More Industry stories

French insurer teams with IBM Services to develop fraud detection solution

Auto insurance fraud costs companies billions of dollars every year. Those losses trickle down to policyholders who absorb some of that risk in policy rate increases. Thélem assurances, a French property and casualty insurer whose motto is “Thélem innovates for you”, has launched an artificial intelligence program, prioritizing a fraud detection use case as its […]

Continue reading

Cloud innovation in real estate: Apleona and IBM rely on new technologies

Digitization does not stop at the proverbial concrete gold — real estate. In fact, the real estate industry is on the move. Companies are realizing the benefits of digital transformation and are capitalizing on the power of new technologies such as cloud, AI and blockchain. Take, for example, Apleona GmbH, one of Europe’s largest real […]

Continue reading

How predictive maintenance improves efficiencies across five industries

New technologies—including the rise of the Internet of Things (IoT)—and market pressures to reduce costs are pushing companies to move from reactive, condition-based maintenance and analytics to predictive maintenance. MarketsandMarkets forecasts the global predictive maintenance market size to grow from USD $3.0 billion in 2019 to USD $10.7 billion by 2024. Predictive maintenance is generally […]

Continue reading