Where AI can help fight climate change, and where it can’t

Perched high in the valleys of California’s wine country, the Joanna Wells vineyards are a challenging place to grow grapes. About 3,000 feet above sea level, at the top of a mountain ridge, “it takes him 40 minutes from the main road to get there,” Wells says.

But Welles says the rocky hilltop terrain, with plenty of sunshine and ocean breezes, is the perfect place for the job.

But what’s not idyllic is California’s extreme weather.

“Every year tends to be more climatically extreme.”

She’s just one of a growing number of ventures, large and small, on the front lines of extreme weather.

To adapt to the changing mood of climate change, Wells and her vineyards are turning their attention to the power of machines. When she took over her business eight years ago, the vineyard already had soil monitors and rain gauges installed.

But what wasn’t there was the machine learning component. It’s software that allows operations to process data “in a way that offers this predictive aspect that hasn’t been there in the past.”

This means you can capture a wealth of information about everything from past extreme weather effects to current soil conditions. The data is then run through software to improve the analysis as more information is input.

It’s a way to monitor conditions, challenge the best times of the year, such as high altitude, and get predictive information such as frost and vine stress in one area, or potential for soil drying in another. .

It’s a “competitive advantage,” said Wells.

More and more companies are thinking about this competitive advantage, says Mike Lyons, managing partner of The Boston Consulting Group.

“Consumers actually care and are often willing to pay a premium for more climate-friendly products,” Lyons told Global News.

And by taking proactive action, rather than reacting after a disaster occurs, significant cost savings can be achieved, he says.

At the winery, machine learning tools are helping Wells stay ahead of the next weather disaster, including wildfires.

Fires have become a new reality of life throughout the year in many parts of California. There, too, AI is starting to play a key role in addressing the growing problem.

Rossella Arcucci, a researcher at Imperial College London, and her team are developing a software application that takes in vast amounts of information about fires, from wind speed to what people are tweeting, and performs predictive analytics on how to respond.

“We can start simulating what would happen if we put a (fire) barrier here or put a barrier there. Is the firefront working in a different way? Can you put out the fire?”

This kind of predictive analytics is also helping shipping in Arctic waters. This also includes cruise ships that increasingly navigate the waters of the region.

Researchers are using data from satellites hovering in space to monitor ice conditions. But in the summer months, the satellite has a hard time distinguishing between open water and melting sea ice. Big data and machine learning fill the gap.

“What AI can do is look for patterns in the data,” says Arctic researcher Jack Lundy. We can see if we are doing it,” he says.

It doesn’t completely eliminate the need for humans to do the work. “We want to be able to understand all the falling dominoes and be able to understand processes and problems from data,” he says.

However, in remote and dangerous areas such as the Arctic, it is possible to gather information such as predicting when and where ice will occur, which is important for ships.

At the heart of machine learning’s usefulness is this predictive ability.

“We can simulate thousands of scenarios in seconds and make decisions in near real time,” Arcucci said of the application of AI in firefighting.

That information can be used to determine how the crew will respond.

Instead of sending firefighters to dangerous locations to assess the best response, the future of firefighting includes how crews harness the power of big data.

Or how the winemaker uses the data.

Winemaker Joanna Wells says machine learning is one of the big strides to improve her business.

“We decided to evolve with that technology,” she says.

With extreme weather posing more threats, we had little choice but to adapt.

“Farming success is based on being proactive,” she adds.