Big Data

Feeding the planet as the climate changes with rapid analytics on IBM Cloud

Share this post:

SmartRural climateThe latest climate research indicates that the planet might be warming at an even faster rate than previously thought. As extreme weather events such as droughts become more common, it’s becoming more difficult and costly for farmers to irrigate their fields, making crop failures more likely.

The current world population of 7.3 billion is expected to reach 8.5 billion by 2030. To support the growing population, agricultural producers around the world must make every acre of arable land count.

Drone images send data volumes soaring

SmartRural is working to help farmers produce more. Founded three years ago, SmartRural uses a fleet of camera-equipped drones to fly high over fields and vineyards to capture hundreds of clear aerial images across the light spectrum. But, because our company captures so much data, it would take a human being hundreds of painstaking hours to analyze it all. Instead, we developed machine learning algorithms to do the legwork. For a deeper dive into the work the company is doing, read the IBM case study.

SmartRural’s offering is starting to take off in Spain and the wider world. Increasing numbers of farmers want to harness SmartRural analytics to figure out better ways to irrigate, fertilize and protect their land from threats including pests. Here’s the catch: SmartRural was managing and maintaining its analytics infrastructure in-house, and we knew that scaling out to capture all of the market demand was going to be extremely expensive.

Growing in a cost-effective way with IBM Cloud

When you’re a startup like SmartRural, cashflow is life. We knew that the cloud model was the best way to avoid onerous capital costs. To create an environment optimized to SmartRural’s highly parallelized machine learning workloads, we decided that a bare metal solution was the way to go.

After taking an in-depth look at some of the world’s largest cloud providers, since global scalability is also one of the company’s key goals, SmartRural leadership realized that IBM could deliver the bare metal environment we were looking for in a cost-effective way.

Within a couple of weeks, we’d spun up our analytics environment on two dedicated bare metal servers in the IBM Cloud. The results have been dramatic. We can now train our machine learning models 15 percent faster and process the data up to 60 percent faster. This means SmartRural can turn hundreds of drone images into actionable insight rapidly, empowering the company to serve more farmers each growing season.

SmartRural’s work with IBM Cloud is just getting started, and we think the impact is going to be extremely positive, both for our growing business and for the environment.

To learn more, check out the IBM case study.

More Big Data stories

Data science helps Norway’s fish farmers keep salmon populations healthy

Aquaculture is one of Norway’s most important industries. Our fish farms produce 65 percent of the world’s supply of Atlantic salmon and employ thousands of people in coastal communities. At the Seafood Innovation Cluster, our mission is to help the industry grow and flourish while ensuring that fish stocks are managed responsibly, thereby protecting Norway’s […]

Continue reading

Comtelsat helps politicians keep broadcasts timely with IBM Aspera

Reuters Institute for the Study of Journalism concluded that for half a century, traditional television news has been the most widely used, most important and most shared source of news in most countries. That is not going to change overnight, but audiences are increasingly moving away from traditional television and towards digital platforms, such as […]

Continue reading

Constance Hotels, Resorts and Golf connects islands of data using IBM Cloud

As the poet John Donne once wrote, “No man is an island.” To understand an individual, you must understand them in the wider context of their relationships. The same is true of data. What you can learn from a single source of data in isolation is limited. When you combine that data with other data […]

Continue reading