PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

Machine learning aids earthquake risk prediction

New framework developed by UT Austin engineers applies big data, supercomputing to soil liquefaction

Machine learning aids earthquake risk prediction
2021-06-23
(Press-News.org) Our homes and offices are only as solid as the ground beneath them. When that solid ground turns to liquid -- as sometimes happens during earthquakes -- it can topple buildings and bridges. This phenomenon is known as liquefaction, and it was a major feature of the 2011 earthquake in Christchurch, New Zealand, a magnitude 6.3 quake that killed 185 people and destroyed thousands of homes.

An upside of the Christchurch quake was that it was one of the most well-documented in history. Because New Zealand is seismically active, the city was instrumented with numerous sensors for monitoring earthquakes. Post-event reconnaissance provided a wealth of additional data on how the soil responded across the city.

"It's an enormous amount of data for our field," said post-doctoral researcher, Maria Giovanna Durante, a Marie Sklodowska Curie Fellow previously of The University of Texas at Austin (UT Austin). "We said, 'If we have thousands of data points, maybe we can find a trend.'"

Durante works with Prof. Ellen Rathje, Janet S. Cockrell Centennial Chair in Engineering at UT Austin and the principal investigator for the National Science Foundation-funded DesignSafe cyberinfrastructure, which supports research across the natural hazards community. Rathje's personal research on liquefaction led her to study the Christchurch event. She had been thinking about ways to incorporate machine learning into her research and this case seemed like a great place to start.

"For some time, I had been impressed with how machine learning was being incorporated into other fields, but it seemed we never had enough data in geotechnical engineering to utilize these methods," Rathje said. "However, when I saw the liquefaction data coming out of New Zealand, I knew we had a unique opportunity to finally apply AI techniques to our field."

The two researchers developed a machine learning model that predicted the amount of lateral movement that occurred when the Christchurch earthquake caused soil to lose its strength and shift relative to its surroundings.

The results were published online in Earthquake Spectra on April 2021.

"It's one of the first machine learning studies in our area of geotechnical engineering," Durante said.

The researchers first used a Random Forest approach with a binary classification to forecast whether lateral spreading movements occurred at a specific location. They then applied a multiclass classification approach to predict the amount of displacement, from none to more than 1 meter.

"We needed to put physics into our model and be able to recognize, understand, and visualize what the model does," Durante said. "For that reason, it was important to select specific input features that go with the phenomenon we study. We're not using the model as a black box-- we're trying to integrate our scientific knowledge as much as possible."

Durante and Rathje trained the model using data related to the peak ground shaking experienced (a trigger for liquefaction), the depth of the water table, the topographic slope, and other factors. In total, more than 7,000 data points from a small area of the city were used for training data -- a great improvement, as previous geotechnical machine learning studies had used only 200 data points.

They tested their model citywide on 2.5 million sites around the epicenter of the earthquake to determine the displacement. Their model predicted whether liquefaction occurred with 80% accuracy; it was 70% accurate at determining the amount of displacement.

The researchers used the Frontera supercomputer at the Texas Advanced Computing Center (TACC), one of the world's fastest, to train and test the model. TACC is a key partner on the DesignSafe project, providing computing resources, software, and storage to the natural hazards engineering community.

Access to Frontera provided Durante and Rathje machine learning capabilities on a scale previously unavailable to the field. Deriving the final machine learning model required testing 2,400 possible models.

"It would have taken years to do this research anywhere else," Durante said. "If you want to run a parametric study, or do a comprehensive analysis, you need to have computational power."

She hopes their machine learning liquefaction models will one day direct first-responders to the most urgent needs in the aftermath of an earthquake. "Emergency crews need guidance on what areas, and what structures, may be most at risk of collapse and focus their attention there," she said.

Sharing, Reproducibility, and Access

For Rathje, Durante, and a growing number of natural hazard engineers, a journal publication is not the only result of a research project. They also publish all of their data, models, and methods to the DesignSafe portal, a hub for research related to the impact of hurricanes, earthquakes, tsunamis, and other natural hazards on the built and natural environment.

"We did everything on the project in the DesignSafe portal," Durante said. "All the maps were made using QGIS, a mapping tool available on DesignSafe, using my computer as a way to connect to the cyberinfrastructure."

For their machine learning liquefaction model, they created a Jupyter notebook -- an interactive, web-based document that includes the dataset, code, and analyses. The notebook allows other scholars to reproduce the team's findings interactively, and test the machine learning model with their own data.

"It was important to us to make the materials available and make it reproducible," Durante said. "We want the whole community to move forward with these methods."

This new paradigm of data-sharing and collaboration is central to DesignSafe and helps the field progress more quickly, according Joy Pauschke, program director in NSF's Directorate for Engineering.

"Researchers are beginning to use AI methods with natural hazards research data, with exciting results," Pauschke said. "Adding machine learning tools to DesignSafe's data and other resources will lead to new insights and help speed advances that can improve disaster resilience."

Advances in machine learning require rich datasets, precisely like the data from the Christchurch earthquake. "All of the information about the Christchurch event was available on a website," Durante said. "That's not so common in our community, and without that, this study would not have been impossible."

Advances also require high-performance computing systems to test out new approaches and apply them to new fields.

The researchers continue to refine the machine learning model for liquefaction. Further research, they say, is needed to develop machine learning models that are generalizable to other earthquake events and geologic settings.

Durante, who returned to her native Italy this year, says one thing she hopes to take back from the U.S. is the ability for research to impact public policy.

She cited a recent project working with Scott Brandenberg and Jonathan Stewart (University of California, Los Angeles) that developed a new methodology to determine whether a retaining wall would collapse during an earthquake. Less than three years after the beginning of their research, the recommended seismic provisions for new buildings and other structures in the U.S. included their methodology.

"I want my work to have an impact on everyday life," Durante said. "In the U.S., there is more of a direct connection between research and real life, and that's something that I would like to bring back home."

INFORMATION:


[Attachments] See images for this press release:
Machine learning aids earthquake risk prediction

ELSE PRESS RELEASES FROM THIS DATE:

Major risk of eye injuries from padel, research ophthalmologists say

Major risk of eye injuries from padel, research ophthalmologists say
2021-06-23
Several eye clinics around Sweden are seeing a rise in eye damage related to the racket sport padel. In an article in the Journal of the Swedish Medical Association (Läkartidningen), eye researchers affiliated with the University of Gothenburg state that padel is a potential high-risk sport for eye injuries, and that wearing protective goggles is a good idea. Ball sports are often associated with an increased risk of eye injuries, and the risk seems to be even greater with padel, a sport that is now highly popular in Sweden (and should not be confused with the North American "paddle tennis"). "The ...

Magneto-thermal imaging brings synchrotron capabilities to the lab

2021-06-23
ITHACA, N.Y. - Coming soon to a lab tabletop near you: a method of magneto-thermal imaging that offers nanoscale and picosecond resolution previously available only in synchrotron facilities. This innovation in spatial and temporal resolution will give researchers extraordinary views into the magnetic properties of a range of materials, from metals to insulators, all from the comfort of their labs, potentially boosting the development of magnetic storage devices. "Magnetic X-ray microscopy is a relatively rare bird," said Greg Fuchs, associate professor of applied and engineering physics, who led the project. "The magnetic ...

Novel lncRNA, Caren, counteracts heart failure progression

Novel lncRNA, Caren, counteracts heart failure progression
2021-06-23
A research collaboration based in Kumamoto University (Japan) has identified a novel lncRNA, Caren, that is abundantly expressed in cardiomyocytes. They showed that it enhances energy production by increasing the number of mitochondria in cardiomyocytes, and inhibits activation of the ATM protein, a key player in the DNA damage response pathway that accelerates heart failure severity. Caren RNA in cardiomyocytes is reduced by aging and high blood pressure (hypertension), which can lead to heart failure, and markedly reduced in the hearts of heart failure patients. The researchers believe that ...

2.5 grammes of pure cocoa found to improve visual acuity in daylight

2.5 grammes of pure cocoa found to improve visual acuity in daylight
2021-06-23
Eating 2.5 grams of pure natural cocoa powder serves to improve visual acuity in healthy young adults and in daylight conditions, according to research by the Universidad Complutense de Madrid (UCM) and the ICTAN (Institute of Food and Nutrition Science and Technology) of the CSIC. The study, published in the Journal of Functional Foods, analyse the effects of two dietary polyphenols: cocoa flavanols and red berry anthocyanins. "Although this was the baseline hypothesis, we did not see any effect either on adaptation to darkness or on visual acuity measured in low light conditions (mesopic vision), either with cocoa or with berries," indicates María Cinta Puell Marín, researcher at the Optometry and Vision ...

Higher selenium and manganese levels during pregnancy may protect babies from future high blood pressure

2021-06-23
Children who were exposed to higher levels of trace minerals manganese and selenium during their mothers' pregnancy had a lower risk of high blood pressure in childhood, according to a study led by researchers at the Johns Hopkins Bloomberg School of Public Health. The researchers analyzed the levels of toxic metals and trace minerals in blood samples drawn from nearly 1,200 women in the Boston area who gave birth between 2002 and 2013. They found that higher levels of selenium or manganese in the mothers' blood were associated with lower blood pressure readings in their children ...

Blood test promising for predicting response in metastatic HPV-positive throat cancer

2021-06-23
A sensitive blood test being developed by a team of researchers at the University of Michigan Rogel Cancer Center shows promise for predicting whether patients with metastatic HPV-positive throat cancer will respond to treatment months earlier than standard imaging scans. That's according to a study, published in Oncotarget, validating the test in a small group of patients with metastatic human papillomavirus-related oropharyngeal squamous cell carcinoma -- a type of head and neck cancer that develops in the back of the mouth and in the throat. If the test can quickly determine that a treatment approach isn't ...

Reactive and inconsistent practices hamstring efforts to manage invasive plants in the US

2021-06-23
AMHERST, Mass. - As summer unfolds, more than 500 species of invasive plants will be taking root in fields, lawns, and gardens across the US. As plants continue to move north driven by climate change, the number of invasives will only increase. Unfortunately, inconsistent regulations that vary from state to state means that invasive plants have an edge on our attempts to control them. However, new research from the University of Massachusetts Amherst recently published in the Journal of Applied Ecology suggests that we already have an answer in hand - communication. "We know that invasive plants are causing both ecological and economic harm in the US," says Emily Fusco, one of the paper's lead authors and a postdoctoral research fellow in the department of environmental conservation ...

Researchers use AI to track cognitive deviation in aging brains

Researchers use AI to track cognitive deviation in aging brains
2021-06-23
OAK BROOK, Ill. - Researchers have developed an artificial intelligence (AI)-based brain age prediction model to quantify deviations from a healthy brain-aging trajectory in patients with mild cognitive impairment, according to a study published in Radiology: Artificial Intelligence. The model has the potential to aid in early detection of cognitive impairment at an individual level. Amnestic mild cognitive impairment (aMCI) is a transition phase from normal aging to Alzheimer's disease (AD). People with aMCI have memory deficits that are more ...

Toxic workplaces increase risk of depression by 300%

Toxic workplaces increase risk of depression by 300%
2021-06-23
A year-long Australian population study has found that full time workers employed by organisations that fail to prioritise their employees' mental health have a threefold increased risk of being diagnosed with depression. And while working long hours is a risk factor for dying from cardiovascular disease or having a stroke, poor management practices pose a greater risk for depression, the researchers found. The University of South Australia study, published in the British Medical Journal today, is led by UniSA's Psychosocial Safety Climate Observatory, the world's first research platform exploring workplace psychological health and safety. Psychosocial safety climate (PSC) is the term used to describe management practices ...

How to make lithium-ion batteries invincible

How to make lithium-ion batteries invincible
2021-06-23
In our future electrified world, the demand for battery storage is projected to be enormous, reaching to upwards of 2 to 10 terawatt-hours (TWh) of annual battery production by 2030, from less than 0.5 TWh today. However, concerns are growing as to whether key raw materials will be adequate to meet this future demand. The lithium-ion battery - the dominant technology for the foreseeable future - has a component made of cobalt and nickel, and those two metals face severe supply constraints on the global market. Now, after several years of research led by Lawrence Berkeley National Laboratory (Berkeley Lab), scientists have made significant progress in developing battery cathodes using ...

LAST 30 PRESS RELEASES:

International collaboration enabled participatory stock assessment on glass eel fisheries in West Java, Indonesia

Enhanced melanoma vaccine offers improved survival for men

Nearly one-third of patients with TBI have marginal or inadequate health literacy

Genetic causes of cerebral palsy uncovered through whole-genome sequencing

Modesty and boastfulness – perception depends on usual performance

Do sweeteners increase your appetite? New evidence from randomised controlled trial says no 

Women with obesity do not need to gain weight during pregnancy, new study suggests

Individuals with multiple sclerosis face substantially greater risk of hospitalisation and death from COVID-19, despite high rates of vaccination

Study shows obesity in childhood associated with a more than doubling of risk of developing multiple sclerosis in early adulthood

Rice Emerging Scholars Program receives $2.5M NSF grant to boost STEM education

Virtual rehabilitation provides benefits for stroke recovery

Generative AI develops potential new drugs for antibiotic-resistant bacteria

Biofuels could help island nations survive a global catastrophe, study suggests

NJIT research team discovering how fluids behave in nanopores with NSF grant

New study shows association of historical housing discrimination and shortfalls in colon cancer treatment

Social media use may help to empower plastic surgery patients

Q&A: How to train AI when you don't have enough data

Wayne State University researchers uncover potential treatment targets for Zika virus-related eye abnormalities

Discovering Van Gogh in the wild: scientists unveil a new gecko species

Small birds spice up the already diverse diet of spotted hyenas in Namibia

Imaging detects transient “hypoxic pockets” in the mouse brain

Dissolved organic matter could be used to track and improve the health of freshwaters

Indoor air quality standards in public buildings would boost health and economy, say international experts

Positive associations between premenstrual disorders and perinatal depression

New imaging method illuminates oxygen's journey in the brain

Researchers discover key gene for toxic alkaloid in barley

New approach to monitoring freshwater quality can identify sources of pollution, and predict their effects

Bidirectional link between premenstrual disorders and perinatal depression

Cell division quality control ‘stopwatch’ uncovered

Vaccine protects cattle from bovine tuberculosis, may eliminate disease

[Press-News.org] Machine learning aids earthquake risk prediction
New framework developed by UT Austin engineers applies big data, supercomputing to soil liquefaction