How satellites and AI help fight wildfires today
This is a guest post by John W. Daily, a research professor in thermo fluid sciences at the University of Colorado Boulder. A version of this article is republished from The Conversation under a Creative Commons license.
As wind-driven wildfires spread through the Los Angeles area in January 2025, fire-spotting technology and computer models were helping firefighters understand the rapidly changing environment they were facing.
That technology has evolved over the years, yet some techniques are very similar to those used over 100 years ago.
I have spent several decades studying combustion, including wildfire behavior and the technology used to track fires and predict where wildfires might turn. Here's a quick tour of the key technologies used today.
Cameras and AI analysis to spot fires
First, the fire must be discovered.
Often wildfires are reported by people seeing smoke. That hasn't changed, but other ways fires are spotted have evolved.
In the early part of the 20th century, the newly established U.S. Forest Service built fire lookout towers around the country. The towers were topped by cabins with windows on all four walls and provided living space for the fire lookouts. The system was motivated by the Great Fire of 1910 that burned 3 million acres in Washington, Idaho and Montana and killed 87 people.
Today, cameras watch over many high-risk areas. California has more than 1,100 cameras watching for signs of smoke. Artificial intelligence systems continuously analyze the images to provide data for firefighters to quickly respond. AI is a way to train a computer program to recognize repetitive patterns: smoke plumes in the case of fire.
NOAA satellites paired with AI data analysis also generate alerts but over a wider area. They can detect heat signatures, map fire perimeters and burned areas, and track smoke and pollutants to assess air quality and health risks.
How to find out where a fire will go
Once a fire is spotted, one immediate task for firefighting teams is to estimate how the fire is going to behave so they can deploy their limited firefighting resources most effectively.
Fire managers have seen many fires and have a sense of the risks their regions face. Today, they also have computer simulations that combine data about the terrain, the materials burning and the weather to help predict how a fire is likely to spread.
Fuel models
Fuel models are based on the ecosystem involved, using fire history and laboratory testing. In Southern California, for example, much of the wildland fuel is chaparral, a type of shrubland with dense, rocky soil and highly flammable plants in a Mediterranean climate. Chaparral is one of the fastest-burning fuel types, and fires can spread quickly in that terrain.
For human-made structures, things are a bit more complex. The materials a house is made of – if it has wood siding, for example – and the environment around it, such as how close it is to trees or wooden fences, play an important role in how likely it is to burn and how it burns.How scientists study fire behavior in a lab.
Weather and terrain
Terrain is also important because it influences local winds and because fire tends to run faster uphill than down. Terrain data is well known thanks to satellite imagery and can easily be incorporated into computer codes.
Weather plays another critical role in fire behavior. Fires need oxygen to burn, and the windier it is, the more oxygen is available to the fire. High winds also tend to generate embers from burning vegetation that can be blown up to 5 miles in the highest winds, starting spot fires that can quickly spread.
Today, large computer simulations can forecast the weather. There are global models that cover the entire Earth and local models that cover smaller areas but with better resolution that provides greater detail.
Both provide real-time data on the weather for creating fire behavior simulations.
Modeling how flames spread
Flame-spread models can then estimate the likely movement of a fire.
Scientists build these models by studying past fires and conducting laboratory experiments, combined with mathematical models that incorporate the physics of fire. With local terrain, fuel and real-time weather information, these simulations can help fire managers predict a fire's likely behavior. Examples of how computer modeling can forecast a fire's spread. American Physical Society.
Advanced modeling can account for fuel details such as ground-level plant growth and tree canopies, including amount of cover, tree height and tree density. These models can estimate when a fire will reach the tree canopy and how that will affect the fire's spread.
Forecasting helps, but human judgment still required
All these tools are made available to firefighters in computer applications and can help fire crews as they respond to wildfires.
However, wind can rapidly change speed or direction, and new fires can start in unexpected places, meaning fire managers know they have to be prepared for many possible outcomes – not just the likely outcomes they see on their computer screens.
Ultimately, during a fire, firefighting strategy is based on human judgment informed by experience, as well as science and technology.
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Technical.ly
31-01-2025
- Technical.ly
How satellites and AI help fight wildfires today
This is a guest post by John W. Daily, a research professor in thermo fluid sciences at the University of Colorado Boulder. A version of this article is republished from The Conversation under a Creative Commons license. As wind-driven wildfires spread through the Los Angeles area in January 2025, fire-spotting technology and computer models were helping firefighters understand the rapidly changing environment they were facing. That technology has evolved over the years, yet some techniques are very similar to those used over 100 years ago. I have spent several decades studying combustion, including wildfire behavior and the technology used to track fires and predict where wildfires might turn. Here's a quick tour of the key technologies used today. Cameras and AI analysis to spot fires First, the fire must be discovered. Often wildfires are reported by people seeing smoke. That hasn't changed, but other ways fires are spotted have evolved. In the early part of the 20th century, the newly established U.S. Forest Service built fire lookout towers around the country. The towers were topped by cabins with windows on all four walls and provided living space for the fire lookouts. The system was motivated by the Great Fire of 1910 that burned 3 million acres in Washington, Idaho and Montana and killed 87 people. Today, cameras watch over many high-risk areas. California has more than 1,100 cameras watching for signs of smoke. Artificial intelligence systems continuously analyze the images to provide data for firefighters to quickly respond. AI is a way to train a computer program to recognize repetitive patterns: smoke plumes in the case of fire. NOAA satellites paired with AI data analysis also generate alerts but over a wider area. They can detect heat signatures, map fire perimeters and burned areas, and track smoke and pollutants to assess air quality and health risks. How to find out where a fire will go Once a fire is spotted, one immediate task for firefighting teams is to estimate how the fire is going to behave so they can deploy their limited firefighting resources most effectively. Fire managers have seen many fires and have a sense of the risks their regions face. Today, they also have computer simulations that combine data about the terrain, the materials burning and the weather to help predict how a fire is likely to spread. Fuel models Fuel models are based on the ecosystem involved, using fire history and laboratory testing. In Southern California, for example, much of the wildland fuel is chaparral, a type of shrubland with dense, rocky soil and highly flammable plants in a Mediterranean climate. Chaparral is one of the fastest-burning fuel types, and fires can spread quickly in that terrain. For human-made structures, things are a bit more complex. The materials a house is made of – if it has wood siding, for example – and the environment around it, such as how close it is to trees or wooden fences, play an important role in how likely it is to burn and how it scientists study fire behavior in a lab. Weather and terrain Terrain is also important because it influences local winds and because fire tends to run faster uphill than down. Terrain data is well known thanks to satellite imagery and can easily be incorporated into computer codes. Weather plays another critical role in fire behavior. Fires need oxygen to burn, and the windier it is, the more oxygen is available to the fire. High winds also tend to generate embers from burning vegetation that can be blown up to 5 miles in the highest winds, starting spot fires that can quickly spread. Today, large computer simulations can forecast the weather. There are global models that cover the entire Earth and local models that cover smaller areas but with better resolution that provides greater detail. Both provide real-time data on the weather for creating fire behavior simulations. Modeling how flames spread Flame-spread models can then estimate the likely movement of a fire. Scientists build these models by studying past fires and conducting laboratory experiments, combined with mathematical models that incorporate the physics of fire. With local terrain, fuel and real-time weather information, these simulations can help fire managers predict a fire's likely behavior. Examples of how computer modeling can forecast a fire's spread. American Physical Society. Advanced modeling can account for fuel details such as ground-level plant growth and tree canopies, including amount of cover, tree height and tree density. These models can estimate when a fire will reach the tree canopy and how that will affect the fire's spread. Forecasting helps, but human judgment still required All these tools are made available to firefighters in computer applications and can help fire crews as they respond to wildfires. However, wind can rapidly change speed or direction, and new fires can start in unexpected places, meaning fire managers know they have to be prepared for many possible outcomes – not just the likely outcomes they see on their computer screens. Ultimately, during a fire, firefighting strategy is based on human judgment informed by experience, as well as science and technology.
Technical.ly
22-01-2025
- Technical.ly
How Philly cops can use the city's $800k for police drones to improve safety while avoiding unchecked surveillance
u003cemu003eThis is a guest post by u003c/emu003eDrexel University's u003ca href=u0022https:// Kaneu003c/au003e, professor of criminology and justice studies, and u003ca href=u0022https:// Hyattu003c/au003e, associate professor of criminology and justice studiesu003cemu003e. A version of this article is republished from u003c/emu003eu003ca href=u0022https:// Conversationu003c/au003eu003cemu003e under a Creative Commons license.u003c/emu003e Philadelphia 's plans to expand its use of police-operated drones signals a pivotal shift in how the city seeks to protect – and surveil – its citizens. According to the city's Citizen Police Oversight Commission, the Philadelphia Police Department had two drones as of early 2024. These were, the commission says, primarily used by SWAT teams to scout locations before serving high-risk warrants. The 2025 city budget earmarks over US$800,000 for police drones, a spokesperson from the department's Office of Public Affairs told us via email in response to our questions. The spokesperson also confirmed that Philadelphia police are conducting test flights in Kensington and the surrounding area as part of the initial phase of a ' Drone First Responder ' program. For now, they say, they're simply gathering data on how quickly drones respond to certain types of 911 calls compared with traditional police responses. Police technology can evolve rapidly, and many police agencies across the country already use drones – including as first responders. This technology may make the operation of law enforcement agencies more efficient and perhaps safer for officers, as they can have eyes on a scene from a safe distance. But many privacy advocates and members of the public have raised concerns about the privacy implications. We are Philadelphia-based criminologists and researchers who seek to understand the impact of policing practices and technologies, including body-worn cameras and Tasers, on police legitimacy and public policy. We see how drone policing can pose an almost entirely new set of potential benefits – and risks. Practical uses for police drones Drones are already used for many commercial and recreational purposes. In Pennsylvania, police drones have recently been used in traffic management and searches for fugitives. These devices can be equipped with facial recognition, AI, gunfire detection and other new tech that has the potential to transform the scope and nature of the data that police can collect. Drones can provide rapid emergency responses, such as locating missing persons in remote areas or delivering medical supplies to accident victims in hard-to-reach locations. During critical situations, they can offer live intelligence by transmitting real-time aerial footage of active crime scenes, such as armed standoffs or large-scale public disturbances. This allows officers to effectively strategize without immediate exposure to danger. Additionally, drones can reduce the risk of officer injuries during dangerous live pursuits by tracking fleeing suspects from the air, minimizing the need for high-speed vehicle chases or foot pursuits through hazardous environments. Drones present new privacy concerns Given their small size, aerial maneuverability and, in many cases, ability to record audio and video, drones present new and specific challenges to Fourth Amendment protections, particularly against unreasonable searches and seizures. In the 1967 Katz v. United States case, the Supreme Court decided people are protected from being recorded by the police in places where they may reasonably expect privacy. While that case was about a closed phone booth, the logic has been expanded over the years to protect people from new technological intrusion, such as thermal vision. However, police do not need a warrant to observe and record activities that are visible to the public. In the 1988 case Florida v. Riley, for example, the court decided that police were permissibly able to look into someone's yard from a helicopter hovering at 400 feet. While drones are capable of flying much higher than 400 feet, they can also linger 40 feet, or even 4 feet, from a yard, building or window. And they do so in almost complete silence. Though the Supreme Court has yet to decide whether it is reasonable for people to assume they are protected from drone-based imaging, the highest state court in Michigan recently allowed police to use warrantless drone-recorded footage to count the number of cars on a fenced property in pursuit of a civil zoning violation. While each state is still able to set its own rules, privacy advocates are concerned that drone surveillance could be used to collect evidence without judicial oversight, or to surveil people without legal limitations or consequences for the violation of constitutional privacy rights. Low-income communities and communities of color often bear the brunt of overpolicing and surveillance, and drone usage in these neighborhoods could exacerbate existing inequities by increasing scrutiny, perpetuating bias and reinforcing systemic distrust of policing. Philadelphia's track record concerning 'stop-and-frisk' pedestrian stops sheds important light on those concerns. 5 lessons from stop and frisk The landmark stop-and-frisk case Bailey v. City of Philadelphia led to a federal consent decree over the Philadelphia Police Department's stop-and-frisk practices. This decree was called the ' Bailey agreement.' It required the Philadelphia police to document all stop-and-frisk encounters, revise their policies and training to comply with constitutional standards, and reduce stops that lacked reasonable suspicion or were influenced by racial bias. The agreement also established independent monitoring and public reporting to ensure transparency and accountability. Data analyses were regularly submitted to a federal judge for oversight. The lessons from Bailey can inform how the Philadelphia Police Department might approach its drone program to avoid overreach. Misuse of these drones can directly affect the perceived legitimacy of police, already a fraught issue in some communities. Here are several ways Philadelphia could avoid the pitfalls of unchecked surveillance when it comes to police drones. 1. Real-time monitoring Real-time monitoring by an independent oversight body of drone deployments, along with clear documentation of each mission, would enable regular oversight like the structured checks in Bailey. 2. Transparency Public reporting could help ensure community members understand the purposes and limitations of drone usage in their neighborhoods. An independent oversight body or a citizen review board could issue regular reports summarizing deployment data, such as the number of drone flights, their general locations and purposes, and the outcomes of those operations, along with details on data management and compliance with privacy safeguards. Transparency around how data collected by police drones will be managed is essential for maintaining public trust. Data retention and deletion policies could reassure residents that drone data isn't being stockpiled indefinitely but rather used only for its intended purpose. 3. Limited usage Protocols can limit the scope of drone surveillance to specific, critical-use cases – such as emergencies or search-and-rescue operations – and avoid use for regular monitoring of public spaces. A narrowly defined scope would clarify that drones serve as targeted, situational tools rather than blanket surveillance devices. 4. Ethics training and education Ethics training could be part of drone operator preparation to help pilots manage the gray areas of surveillance and ensure that deployments respect constitutional rights. To further the culture of police accountability, drone operators and officers alike should understand that surveillance tools – whether stop-and-frisk or drones – have far-reaching implications for community relationships and the broader perception of justice. 5. Demonstrate effectiveness Bailey's monitoring process relied on metrics to evaluate stop-and-frisk practices, uncover patterns of misuse and guide reforms. Similarly, police might track the extent to which drones improve response times, reduce crime or enhance public safety in meaningful ways. Such evaluations would require transparency in reporting results – and not just the successes but also the failures and unintended consequences. Without evidence-based assessments, public skepticism could prevail and undermine the technology's legitimacy. With clear guidelines, community involvement and legal accountability, we believe drones can enhance safety without compromising civil liberties, and foster rather than erode public trust.
Technical.ly
15-10-2024
- Technical.ly
Trump and Harris share common ground on US technology policy, but are sharply divided on science
This is a guest post by Kenneth Evans, scholar in science and technology policy at Rice University. A version of this article is republished from The Conversation under a Creative Commons license. For the first time in American history, quantum computing was mentioned by a candidate during a presidential debate, on Sept. 10, 2024. After Vice President Kamala Harris brought up quantum technology, she and former President Donald Trump went on to have a heated back-and-forth about American chipmaking and China's rise in semiconductor manufacturing. Science and technology policy usually takes a back seat to issues such as immigration, the economy and health care during election season. What's changed for 2024? From COVID-19 to climate change, ChatGPT to, yes, quantum computers, science-related issues are on the minds of American policymakers and voters alike. The federal government spends nearly US$200 billion each year on scientific research and development to address these challenges and many others. Presidents and Congress, however, rarely agree on how – and how much – money should be spent on science. With the increasing public focus on global competitiveness, the climate crisis and artificial intelligence, a closer look at Trump's and Harris' records on science and technology policy could provide a hint about how they'd approach these topics if elected this fall. Two distinct visions for science funding If politics can be described as 'who gets what and when,' U.S. science and technology policy can be assessed through the annual budget process for R&D. By this measure, the differences between the Trump and Biden-Harris administrations couldn't be starker. In his first budget request to Congress, in 2017, Trump spurned decades of precedent, proposing historic cuts across nearly every federal science agency. In particular, Trump targeted climate-related programs at the Department of Energy, the National Oceanic and Atmospheric Administration and the Environmental Protection Agency. Trump's fiscal policy took a page from Reagan-era conservative orthodoxy, prioritizing military spending over social programs, including R&D. Unlike Reagan, however, Trump also took aim at basic research funding, an area with long-standing bipartisan support in Congress. His three subsequent budget proposals were no different: across-the-board reductions to federal research programs, while pushing for increases to defense technology development and demonstration projects. Congress rebuked nearly all of Trump's requests. Instead, it passed some of the largest increases to federal R&D programs in U.S. history, even before accounting for emergency spending packages funded as part of the government's pandemic response. In contrast, the Biden-Harris administration made science and innovation a centerpiece of its early policy agenda – with budgets to match. Leveraging the slim Democratic majority during the 117th Congress, Biden and Harris shepherded three landmark bills into law: the Infrastructure Investment and Jobs Act, the Inflation Reduction Act and the CHIPS and Science Act. These laws contain significant R&D provisions focused on environmental projects (IIJA), clean energy (IRA) and American semiconductor manufacturing (CHIPS). CHIPS set up programs within the National Science Foundation and the Department of Commerce to create regional technology hubs in support of American manufacturing. The act also set ambitious funding targets for federal science agencies, especially at NSF, calling for its budget to be doubled from $9 billion to over $18 billion over the course of five years. Despite its initial push for R&D, the Biden-Harris administration's final two budget proposals offered far less to science. Years of deficit spending and a new Republican majority in the House cast a cloud of budget austerity over Congress. Instead of moving toward doubling NSF's budget, the agency suffered an 8% decrease in fiscal year 2024 – its biggest cut in over three decades. For FY2025, which runs from Oct. 1, 2024, through Sept. 30, 2025, Biden and Harris requested a meager 3% increase for NSF, billions of dollars short of CHIPS-enacted spending levels. An emerging consensus on China On technology policy, Biden and Harris share more with Trump than they let on. Their approach to competing with China on tech follows Trump's lead: They've expanded tariffs on Chinese goods and severely limited China's access to American-made computer chips and semiconductor manufacturing equipment. Biden and Harris have also ramped up research security efforts intended to protect U.S. ideas and innovation from China. Trump launched the China Initiative as an attempt to stop the Chinese government from stealing American research. The Biden-Harris administration ended the program in 2022, but pieces of it remain in place. Scientific collaborations between the United States and China continue to decline, to the detriment of American scientific leadership. The Biden-Harris administration has also drawn from Trump-era policy to strengthen America's leadership in ' industries of the future.' The term, coined by Trump's then-chief science adviser Kelvin Droegemeier, refers to five emerging technology areas: AI, quantum science, advanced manufacturing, advanced communications and biotechnology. This language has been parroted by the Biden-Harris administration as part of its focus on American manufacturing and throughout Harris' campaign, including during the debate. In short, both candidates align with the emerging Washington bipartisan consensus on China: innovation policy at home, strategic decoupling abroad. Science advice not always a welcome resource Trump's dismissal of and at times outright contempt for scientific consensus is well documented. From ' Sharpiegate,' when he mapped his own projected path for Hurricane Dorian, to pulling out of the Paris climate agreement, World Health Organization and the Iran nuclear deal, Trump has demonstrated an unwillingness to accept any advice, let alone from scientists. Indeed, Trump took over two years to hire Droegemeier as director of the White House Office of Science and Technology Policy, or OSTP, doubling the previous record for the length of time a president has gone without a scientific adviser. This absence was no doubt reflected in Trump's short-on-science budget requests to Congress, especially during the beginning of his administration. On the other hand, the Biden-Harris administration has promoted science and innovation as a core part of its broader economic policy agenda. It elevated the role of OSTP: Biden is the first president to name his science adviser – a position currently held by Arati Prabhakar – as a member of his Cabinet. By law, the president is required to appoint an OSTP director. But it is up to the president to decide how and when to use their advice. If the new White House wants the U.S. to remain a global leader in R&D, the science adviser will need to continue to fight for it.
