Goto

Collaborating Authors

Funding of $5.5m announced for machine learning for geothermal work

#artificialintelligence

University of Southern California (Los Angeles, CA): Developing novel data-driven predictive models for integration into real-time fault detection and diagnosis, and integrate those models by using predictive control algorithms to improve the efficiency of energy production operations in a geothermal power plant. The project will develop deep dynamic neural networks for fault prediction and predictive process control workflows to improve the efficiency of geothermal operations. Upflow Limited (Taupo, New Zealand): Making available multiple decades of closely-guarded production data from one of the world's longest operating geothermal fields, and combining it with the archives from the largest geothermal company operating in the U.S. Models developed from this massive data store will enable the creation of a prediction/recommendation engine that will help operators improve plant availability. Colorado School of Mines (Golden, CO): Applying new machine learning techniques to analyze remote-sensing images, with the goal of developing a process to identify the presence of blind geothermal resources based on surface characteristics. Colorado School of Mines will develop a methodology to automatically label data from hyperspectral images of Brady's Hot Springs, Desert Rock, and the Salton Sea.


New app warns you before an earthquake strikes

Mashable

As earthquake waves ripple out from a volatile fault line to the heart of a city, mere seconds of knowledge that the shakes are coming can save lives. That's according to the City of Los Angeles and experts who say that an earthquake early warning (EEW) system, which monitors seismic waves and notifies people when it detects that an earthquake is on the way, is a powerful way to mitigate harm. "We've previously talked about earthquakes as no warning events," Dr. Lori Peek, the director of the natural hazards center at the University of Colorado, Boulder, told Mashable over the phone. "In an earthquake, if you know what to do, and if you have a few seconds, you may be able to drop, cover, and hold on. And that really can make the difference between who lives, who is injured, and who dies." SEE ALSO: Photos of collapsed, cracked roads show the power of Alaska's earthquake Luckily for "quake-prone" Southern California, Los Angeles County just became the first place in the nation to get one.


Panasonic is building a 'smart city' in Colorado with high-tech highways, autonomous vehicles, and free WiFi

#artificialintelligence

Panasonic may be best known for consumer electronics, but it has started moving into high-tech urban design in recent years. The company is now building "smart city" infrastructure near Denver, Colorado, with the goal of turning the area into a "smart city" by 2026. The initiative is part of a larger Panasonic program Panasonic called CityNow. Although the definition of a "smart city" varies depending on who you ask, the term typically describes a metro area that prioritizes the use of technology in its infrastructure. On a 400-acre swath of empty land near the Denver Airport, the company has installed free WiFi, LED street lights, pollution sensors, a solar-powered microgrid, and security cameras.


Mayors Challenge Winners Target Justice, Homeless, Energy

U.S. News

The other prizes were awarded to Denver to place air quality sensors around schools: Durham, N.C., to create incentive programs to get drivers into public transportation; Fort Collins, Colorado, to help landlords make low-income housing safer and more energy-efficient; Huntington, West Virginia, to embed metal health professions with first responders to address the needs of opioids users; New Rochelle, New York, to implement virtual reality technology during public planning processes; and South Bend, Indiana, which will help low-income and part-time workers find reliable commuter transportation through ride shares.


Deep Learning at 15 PFlops Enables Training for Extreme Weather Identification at Scale

#artificialintelligence

Petaflop per second deep learning training performance on the NERSC (National Energy Research Scientific Computing Center) Cori supercomputer has given climate scientists the ability to use machine learning to identify extreme weather events in huge climate simulation datasets. Predictive accuracies ranging from 89.4% to as high as 99.1% show that trained deep learning neural networks (DNNs) can identify weather fronts, tropical cyclones, and long narrow air flows that transport water vapor from the tropics called atmospheric rivers. As with image recognition, Michael Wehner (senior staff scientist, LBNL) noted they found the machine learning output outperforms humans. The strong relationship between ground truth and the neural network prediction can be seen in the classification plus regression results reported by Wehner at the recent Intel Developer Conference in Denver, Colorado. When explaining the importance of this work, Wehner believes that the big impact lies in assessing the impact of climate change as exemplified by the recent painful experiences of hurricanes Harvey (tied with hurricane Katrina as the costliest tropical cyclone on record), Irma (the strongest storm on record to exist in the open Atlantic region), and Maria (regarded as the worst natural disaster on record in Dominica and Puerto Rico).