California is Using AI to Spot Wildfires Early (cnn.com) 31
CNN reports:
The California Department of Forestry and Fire Protection [known as Cal Fire] says it has a new tool to battle wildfires before they explode — artificial intelligence. "I think it is a game changer ... It has enhanced our abilities to validate situational awareness and then respond in a quick fashion," Phillip SeLegue, Cal Fire's staff chief for fire intelligence, told CNN.
Deep in the California wilderness of the Cleveland National Forest in San Diego County, a fire started in the middle of a July night. No fire officials were in the area, but AI was watching and alerted the authorities. "The dispatch center there was not aware of the fire," said Scott Slumpff, battalion chief of the intel program at Cal Fire, who was testing the new technology at the time and received the initial alert. Cal Fire, in partnership with the University of California at San Diego's Alert California program and its network of more than 1,000 cameras across the state, is using the technology to spot fires early. "The camera had done its 360 [degree turn], identified an anomaly, stopped and was zoomed in," Slumpff explained. He then confirmed it was a fire and immediately dispatched resources. "They were able to hold it to a 10 by 10 [foot] spot out in the middle of the forest..."
The pilot program was so successful, Cal Fire expanded the technology at the beginning of September to all 21 of its dispatch centers across the state... Cal Fire says 40% of fires since July 10 have been detected by AI before a 911 call was received — and the technology is continuing to learn and improve.
"We have multiple successes of fires at night that had gone undetected that we were able to suppress before a 911 call had even come into the command centers," Cal Fire's staff chief for fire intelligence, told CNN.
"The fires you don't hear about in the news is the greatest success."
Deep in the California wilderness of the Cleveland National Forest in San Diego County, a fire started in the middle of a July night. No fire officials were in the area, but AI was watching and alerted the authorities. "The dispatch center there was not aware of the fire," said Scott Slumpff, battalion chief of the intel program at Cal Fire, who was testing the new technology at the time and received the initial alert. Cal Fire, in partnership with the University of California at San Diego's Alert California program and its network of more than 1,000 cameras across the state, is using the technology to spot fires early. "The camera had done its 360 [degree turn], identified an anomaly, stopped and was zoomed in," Slumpff explained. He then confirmed it was a fire and immediately dispatched resources. "They were able to hold it to a 10 by 10 [foot] spot out in the middle of the forest..."
The pilot program was so successful, Cal Fire expanded the technology at the beginning of September to all 21 of its dispatch centers across the state... Cal Fire says 40% of fires since July 10 have been detected by AI before a 911 call was received — and the technology is continuing to learn and improve.
"We have multiple successes of fires at night that had gone undetected that we were able to suppress before a 911 call had even come into the command centers," Cal Fire's staff chief for fire intelligence, told CNN.
"The fires you don't hear about in the news is the greatest success."
Excellent (Score:3)
Re: (Score:3)
Try reading the article if you can’t figure out the obvious: “Sometimes it’s going to be smoke from a wildfire. Other times it’s going to be something harmless, like mist or dust.
The trick is teaching the AI to know the difference.
“The learning part of it comes in with the human intervention to say ‘that looked like smoke, but that wasn’t smoke; it was dust,’” Norton told CNN. “Then the next time the camera picks something up, it’s less likel
Re: (Score:2)
Bayesian statistics isn't AI!
If you think AI doesn't use statistics, you don't understand how neural nets work.
when filtering forest fires, you can't afford false negative.
Nonsense. Firefighters have limited budgets. They can't chase every possible whiff of dust, mist, or smoke.
Re: (Score:3)
Since when do you need "AI" to detect a fricking fire?
When you can't hire an army of people to stare at thousands of cameras for hours and not get bored
It's really hard for a person to stare at a boring image for weeks, looking for a rare event
It's easier for a robot
Re: (Score:2)
Using a differential of IR scans from satellites (known good vs now) seems like it would be far more effective and hardly take any "AI". But maybe they can't play buzzword bingo with their budget? (And if satellites don't have enough resolution, you can use drones.
Fire free California forests (Score:2, Insightful)
Without the small fires that California's forests need every year to clear out the underbrush, what is going to remove all that dry fuel that builds up year after year?
Eventually the underbrush will be loaded with so many years of dry fuel the fire storm will make previous fires look like a match stick.
Before we started stamping out every fire immediately the forests would have numerous smaller fires that cleared out the underbrush but didn't burn hot enough to kill trees. The bigger fires we get now every
Re: (Score:2)
I knew I'd be modded down, have been before for saying the same thing. I lived in California for 40+ years down wind of a major fire zone so I'm a lot more familiar than the mods from wherever the fuck who mod down facts that don't feel good.
Thanks for the support. I'm glad to see there are still pro-fact people here who understand and believe in science.
Re: (Score:2)
We need to stop fucking with nature. We're just not very good at it.
Aren't we way past the point of that though? We've strung powerlines across thousands of miles of terrain. We carve out landscapes for cities, towns canals, farms and roads. We've spent the last 150 years digging out materials that took millions of years to create and would likely remained buried for millions more and pumped it into the atmosphere in the blink of eye.
If anything we are exceedingly good at fucking with nature by the fact nature decided to give us these big old cerebral cortexes. If the
Re: (Score:2)
We are past it in the sense that we are not going to roll back civilization and go back to caves but there is absolutely no reason to continue a known-stupid forestry management policy that directly causes the huge conflagrations that otherwise would be super rare instead of every few short years.
I'm not at all anti-civilization or anti-advancement. I am anti-stupid and the California forest management policies are idiotic, relatively recent and need to stop.
Re: (Score:1)
People shouldn't be living in the California hills that burn. They should be nature preserves.
But our government subsidizes the bad behavior by building roads, funding fire departments, mandating cheap insurance, and bailing them out after every fire.
Your tax dollars are paying for all of this.
Re: (Score:2)
I'm not disagreeing but would note that the fires don't just impact the people living in near/them. I lived mannnny miles downwind for a few years and it was fucking horrible when the smoke hit, the sky darkened at noon and it was painful to breathe indoors. Forget going out, that was suicide without a quality mask.
Re: (Score:3)
Re: (Score:2)
Endothermic reaction? Does it have to be one of those?
There was a guy years ago trying to develop liquid nitrogen munitions to simultaneously freeze out and squelch fires, but nobody seemed interested. Perhaps the risk of nitrogen hypoxia in the immediate vicinity of the munition was unattractive.
Re: (Score:2)
Are you? Nobody else was even remotely interested in your line of inquiry. You're lucky anyone even responded.
Re: (Score:2)
A cubic meter of Liquid nitrogen costs $2000.
A cubic meter of water costs $0.07.
That might be why nobody was interested.
Re: (Score:2)
True, but water isn't as good for oxygen displacement (generally). Plus you're thinking of LN2 as a byproduct of industrial reactions which is likely where you got your pricing data. This guy wanted to use sodium azide (yow!) and water:
https://iwma.net/fileadmin/use... [iwma.net]
Re: (Score:1)
Great. You are dumb in multiple dimensions.
Re: (Score:2)
You have just won a one-way ticket to Lahaina on Maui. The locals will be informed of your arrival and supplied with various cooking implements to properly welcome you and your opinions.
Great, now video surveillance is AI. (Score:1, Troll)
Next up, motion detection will be AI.
Every basic algorithm might as well be called AI now. Look, my computer sorted my MP3s alphabetically! AI is wonderful!
Re: (Score:1)
"What do you for a living?"
"I'm a former programmer turned former consultant turned AI. I sell my services to idiots that both pass my "wants return to work" filter and my "calls everything AI filter" for 10 times what a consultant charges."
"OK, but isn't that fraud?"
"They never ask what the A or the I stands for. They want to pay money go to a magic show and be tricked without knowing how it's done? I'm happy to oblige."
How they trained the AI (Score:1)
Select all images with a
wildfire
Click verify once there are none left.