Smokey Bear is usually right – you can help prevent wildfires – but it’s not all up to you. Use fire resistant building materials, establishignition zonesand avoiding fire-related activities when it’s hot, dry and windy are actions that, ideally, we can all take.
The scientific community also has a preventive role to play in the face of natural disasters, urbanization and climate change. Recent advances in this field, such as attempts to predict fire behavior before it becomes unmanageable, are the result of an ambitious project to build a continental network of smart sensors that monitor environmental change.
The Sage Project, of which the University of Utah is a partner institution, is a $9 million National Science Foundation (NSF)-funded initiative launched in 2019 and led by researchers at the Northwestern-Argonne Institute of Science and Engineering (NAISE), a collaboration between Northwestern University and the US Department of Energy’s Argonne National Laboratory. Other Sage partners include the University of Colorado, University of California San Diego, Northern Illinois University and George Mason University.
“Sage is a next-generation software framework flexible enough to adapt to both urban and environmental monitoring,” said Dan Reed, Ph.D., professor of computer science at the University; chairman of the National Science Board (NSB), the decision-making body of the NSF; and the chief architect of the Sage project.
Manish Parashar, Ph.D., director of the U Institute of Scientific Computing and Imaging (SCI), meanwhile, is overseeing an effort to write code for the planning and analysis functions on the three U-shaped sensor nodes – one at the Taft-Nicholson Center for Environmental Human Sciences in Lakeview, Montana; one atop Tower 102 in downtown Salt Lake City; and one on the roof of the Rio Tinto Center, which houses the Natural History Museum of Utah (NHMU).
When Reed presented the project to the U’s Council of Academic Deans, NHMU executive director Jason Cryan said he “immediately raised his hand to propose NHMU as the first potential installation site for the Utah”.
The idea behind Sage is to move advanced machine learning algorithms to “edge computing”. The traditional method involved deploying sensors and collecting data later. Previous systems could log data to hard drives retrieved from sensors several times a year or upload only a fraction of the data to a cloud server over a slow wireless connection. Edge computing, on the other hand, allows data to be analyzed and measured almost immediately, by instruments located near or at the data collection site. Sage devices, Reed explained, process images, sound, vibrations and other data to create measurements that can’t be obtained as easily from conventional sensor arrays.
The Sage project draws heavily on lessons learned from the Array of Things (AoT) project, part of the smart cities initiative announced in 2015 by former President Barack Obama. AoT operates an open-source intelligent sensing and edge computing platform called Waggle, developed at Argonne National Laboratory.
Primarily funded by the NSF, AoT was a collaborative effort between scientists, universities, federal and local government, industry partners, and communities to collect real-time data about urban environments. AoT is the brainchild of Charlie Catlett, a senior computer scientist in Argonne’s Mathematics and Computer Science (MCS) division, Sage co-principal investigator, and Reed’s longtime friend and colleague.
Catlett’s vision was to create a “fitness tracker for the city”: a vast network of low-cost sensors placed throughout Chicago capable of measuring everything from urban heat islands to noise pollution.
“When you think about how we’ve traditionally done social science, people go out and do surveys. When you ask people, sometimes they say what they think you want to hear,” Reed said. “It’s a bit like your doctor advising you to eat a more balanced diet and exercise more, which ends up being a promise most of us make and break as soon as we leave the office. of the doctor. With AoT, the idea became, instead of surveys, why don’t we just measure what’s really going on? »
Reed said launching the AoT project required a considerable amount of civic discussion about acceptable data use “because putting cameras in the middle of town doesn’t exactly instill trust in the community.”
“One of the agreed rules was that the raw footage would never leave the cameras, only derived, anonymized statistics,” Reed said. “The other realization was that the volume of data is too large to be pushed back to the central site, so being able to do edge AI has reduced bandwidth requirements while allowing for greater privacy.”
Sage’s cyberinfrastructure connects small, powerful computers directly to nodes, most of which have high-resolution cameras (including a thermal camera), microphones, weather measurements and air quality sensors, and sends the information to central servers. The distributed system allows researchers to quickly analyze and respond to huge amounts of data, without having to transfer everything to the lab.
Although Sage devices are intended to measure local and regional environmental changes, the sensors are often sensitive enough to detect changes thousands of miles away. For example, Reed said Sage sensors detected the atmospheric pressure wave from a volcanic eruption in Tonga that produced the largest atmospheric explosion in recorded history.
In addition to U-maintained nodes, Sage technology continues to be tested in AoT environments; the University of California San Diego’s WIFIRE project, which provides real-time data on wildfire prevention and response to approximately 80 towers in Southern California; and NSF’s National Ecological Observatory Network (NEON), a collection of hundreds of terrestrial and aquatic measurement sites across the United States that collect data on plants, animals, soil, water, and atmosphere.
“NEON provides expert ecological data from sites across the continent to power the most important science being done today,” Reed said. “NEON is essential for tracking and understanding the impact of human activities on local flora and fauna as the environment changes.”
A brief overview of Sage sensor nodes (source: Dan Reed)
- Each node operates over wired or wireless Ethernet connections, or Starlink, the Taft-Nicholson Center’s highest bandwidth option.
- Nodes periodically send data back to the Waggle Platform and other Argonne-hosted infrastructure.
- A real-time information dashboard displays still images recorded by an upper and lower camera, infrared views, 30-second audio clips and environmental conditions, such as pressure, temperature and humidity.
- The sensors are managed by Raspberry Pi microcontrollers and an AI engine powered by an Nvidia graphics processing unit (GPU), with pluggable connectors capable of supporting additional sensors.
- Code can be scheduled to run on nodes.
- The nodes perform a myriad of environmental monitoring tasks, ranging from detecting changes in air quality and weather conditions to recognizing different bird species and their migratory habits.
Reed is also excited about Sage’s potential to “engage K-12 students in true citizen science.”
“Nodes have places where young people can plug in their own low-cost sensors,” Reed said. “Just imagine students interacting with this technology, too, excited that they can do real science, write code, build sensors and capture real-time data, instead of just reading examples. in a manual.”
#Sage #sensors #monitor #environment #support #advanced #theU