The Complex Role of AI in Fighting Wildfires

The recent wildfires in Los Angeles County have highlighted the complex role of artificial intelligence in fighting fires and potentially contributing to the conditions that fuel them. AI has become a promising tool for wildfire prediction and resource allocation, but its significant energy and water requirements raise legitimate concerns in a state already facing water scarcity.

This is not the first time the state has suffered wildfires. history of natural fires and human-caused fires. However, in recent decades, a worrying trend has emerged: wildfires are becoming increasingly large and destructive.

The Palisades fires are considered the most destructive in Los Angeles County history. Analysts say the projected damage is in the tens of billions of dollars. Reports confirmed that more than 20,000 acres were burned and more than 9,000 structures were damaged or destroyed. In addition, more than 150,000 people were evacuated in the Los Angeles area.

In response to the 2022 wildfires, Governor Gavin Newsom announced new initiatives to combat future fires. “We are leveraging cutting-edge technology in our wildfire-fighting efforts, exploring how innovations like artificial intelligence can help us identify threats faster and deploy resources more intelligently,” he said. explained Newsom.

One of the initiatives involved training an AI model to analyze video feeds to quickly detect fires. If the model identified a threat, it was programmed to alert a human team, which could act and put out the fire before it turned into a widespread disaster.

Using this AI model, CAL FIRE and ALERTCalifornia at the University of California, San Diego (UCSD) launched a trial implementation deploying a 24-hour surveillance network of 1,032 panoramic HD cameras , tilting and zooming for effective monitoring of active wildfires and other disasters. The cameras were installed in Los Angeles, Santa Barbara, Madera and other counties.

Were AI-powered cameras successful in containing the Palisades fires? Well, it’s difficult to assess the impact, because it’s difficult to determine how much potential inflammation was avoided or how much spread was mitigated by early intervention.

However, if conditions are against you, as was the case with the Palisades fires, AI is no match for Mother Nature. The fires spread so quickly that AI-powered cameras weren’t as useful as one might imagine.

“All fires start as small fires, but when they are driven by winds of 60 to 100 miles per hour and the fuel moves from grass and brush to houses filled with petroleum products, it is simply untenable.” shared Cal Fire spokesperson David Acuña.

California’s AI wildfire detection system has seen some success. In December, the Orange County Fire Authority (OCFA) used it to quickly detect and contain a fire in Black Star Canyon. This early detection limited the fire to less than a quarter acre.

AI has been used by several other projects to fight wildfires in California. Last year, researchers at the University of Southern California (USC) developed a new AI model that uses high-resolution satellite images to accurately predict the spread of wildfires.

The model combines satellite imagery with a sophisticated GenAI (cWGAN) algorithm to predict the likely path, intensity and growth rate of a fire. Trained on historical wildfire data, the model performed well in tests using real California wildfire data from 2020 to 2022.

Factors such as topography and weather also influence fire behavior, making it a very complex and non-linear process. This makes the performance of Wildfire AI models impressive. However, these systems are limited to early detection and warning. After all, they can’t change the Santa Ana winds or prevent the dry conditions that fuel these devastating fires.

Beyond these limitations, the massive data centers that power AI raise other environmental concerns, particularly regarding their significant water and energy requirements. Big tech companies are spend billions to build AI data centers to train and serve as great role models.

Southern California, which is often the scene of wildfires, is also a hub of the AI ​​boom. The region has seen an increase in energy consumption of AI data centers, leading to immense strain on state resources. The International Energy Agency (IEA) has reported that data centers, globally, used 2% of all electricity in 2022 and the IEA predicts that this figure could more than double by 2026.

The AI ​​data center requires millions of gallons of water for cooling. A single large data center can consume as much water as a city of 50,000 inhabitants. This staggering water consumption has a direct impact on the availability of water to fight fires. This is of particular concern during prolonged droughts and wildfires.

So why does AI need water? They need water to keep computers from overheating and malfunctioning. These systems often involve cooling towers that evaporate water to dissipate heat, much like sweating cools the human body.

Unless we find a more energy-efficient way to manage AI data centers, we will continue to consume valuable resources. It’s quite ironic that the very technology we’re considering to help us prevent and contain wildfires could be helping to make the situation worse.

It is encouraging to see some companies taking action in this direction. Microsoft is ready to start piloting waterless technology in new data center locations in Arizona and Wisconsin by 2026. As the trend toward sustainable practices continues, we can hope to save limited resources where they are needed most.