Lori Dengler | Artificial intelligence in the world of earthquakes and tsunamis – Times Standard

I know very little about artificial intelligence. From media headlines, artificial intelligence can seem like the biggest threat to human society or the solution to many problems. I thought it would be worth researching a bit to see how this could work in areas I know something about.

If you're like me, you probably know that AI has something to do with algorithms and can predict outcomes, but perhaps not much more than that. I've delved into a few of the basics of AI to better understand how it can be applied in earthquake detection, early warning, and tsunami prediction.

Computers and algorithms have been part of seismology for more than half a century. In my early years of graduate school in the late 1960s, I dragged boxes of punched cards to the computer center, often picking them up hours later only to discover a critical error that prevented me from completing my career. Mine was the only intelligence involved, and I often found it wanting.

A crucial advance in artificial intelligence is the ability of software to learn and adapt without human intervention. Doing so requires vast amounts of information about the task at hand, i.e. the machine learning part of the process. Traditional programming like I used to do with my punch card decks is like cooking. You carefully specify what goes into the recipe, giving a detailed set of instructions about what the computer is supposed to do with the data you've provided.

Machine learning (ML) is the “training” part of the AI ​​process, loading a massive amount of data into the system and identifying any number of patterns. Recognizing unwanted phone calls is an example that anyone with a smartphone uses on a daily basis. The data set is phone numbers and past behavior. Some numbers can be identified as belonging to marketing companies. Others are identified through message content and users' behavior. Every time you or someone else marks a message as spam, it goes into the larger database and the next time it is used, it is flagged as potential spam. ML allows the system to learn new things as it gets more data.

The AI ​​step is the algorithms that tell computers what to do with all the data they have obtained. For spam phone calls or email, the process of declaring the call spam or sending it to your spam folder is relatively simple. It's not a perfect system. I glance through my spam folder about every week to see if something important has ended up there, but errors are few.

There are many other AI/ML applications that are already part of your daily life. Your bank or financial institution uses AI to identify fraudulent transactions and healthcare systems include it in diagnosis and treatment options. If you use social media, the ads that appear in your feed depend on what you click or hide. I love crossword puzzles, and sometimes my search for a hip-hop star or an unusual piece of clothing will lead to a spike in unusual sponsored posts.

AI can be used as a descriptive tool to better understand what has already happened, to predict what is likely to happen next, or to make suggestions about options in the decision-making process. No matter the application, accuracy and usefulness depend on the data it relies on – quantity and quality matter!

Turning to seismology, my quick look at the GEOBASE benchmark found 400 citations including artificial intelligence or machine learning in the past five years. They cover a wide range of applications such as identifying small earthquakes and aftershocks in noisy environments, relationships between source and rupture properties, predicting ground motions, and identifying previously unnoticed signals that may give insight into source dynamics.

The topic that has received the most media attention and research is the use of artificial intelligence/machine learning as a tool for earthquake prediction. Predicting the location and magnitude of an earthquake days or weeks in advance has been the holy grail of seismology for more than a century. A 1913 Scientific American article declared, “The earthquake prediction is very close.” That angle turns out to be quite large.

The USGS ShakeAlert system does a good job of predicting earthquakes felt in the few seconds after rupture begins and before the strongest shake reaches you. This is a major advance that allows important systems to stop working and people to withdraw, cover and wait. But as of today, we have no reliable way to issue accurate alerts for a longer period of time.

The idea behind using AI/ML is to identify subtle patterns that can lead to longer period predictions. Many different approaches are used, some taking a laboratory approach, others using GPS data for sensitive ground level changes, electromagnetic signals, seismic patterns, or slow slip events.

China is a world leader in earthquake prediction using artificial intelligence. An international competition hosted in China attracted 600 participants from around the world. A team from the University of Texas won first place, as it accurately predicted 70% of earthquakes during a seven-month experiment in China. They used historical earthquake data and developed pattern recognition algorithms to make predictions. The Texas team accurately estimated the magnitude and predicted locations of 14 moderate earthquakes within 200 miles of the actual epicenter.

Although this achievement has received appreciation and media attention, it is by no means ready for prime time. In the same time period, it issued eight false warnings and missed one earthquake entirely. Forecasts only become actionable with a higher level of accuracy.

My interest in artificial intelligence and machine learning peaked after I listened to a lecture last week on tsunami forecasting applications. Chris Moore of the National Oceanic and Atmospheric Administration (NOAA) is improving estimates of tsunami wave heights using the first few minutes of the tsunami wave train on deep-ocean instruments. Tsunamis are a problem because their actual time and space distribution is very limited. His team augmented the actual data by creating simulated sources from across the Pacific.

By training the software on thousands of simulated earthquakes, the group was able to obtain highly accurate predictions of the entire wave train by looking at just 12 minutes of real data. This could have implications for us the next time there's a big earthquake somewhere in the Pacific, by telling us not just when the first wave will arrive, but also the second, third, fourth and beyond, which ones are likely to be larger.

No matter how rosy the future of artificial intelligence in geosciences may be, prolonged ground shaking will still serve as a warning to get out of the tsunami danger zone.

Note: For a more detailed overview of AI and machine learning, visit https://mitsloan.mit.edu/ideas-made-to-matter/machine-learning-explained

Lori Dengler is professor emeritus of geology at Cal Poly Humboldt and an expert in tsunami and earthquake hazards. Questions or comments about this column, or want a free copy of the “Living on Shaky Ground” preparedness magazine? Leave a message at 707-826-6019 or email [email protected].

What Are The Main Benefits Of Comparing Car Insurance Quotes Online

LOS ANGELES, CA / ACCESSWIRE / June 24, 2020, / Compare-autoinsurance.Org has launched a new blog post that presents the main benefits of comparing multiple car insurance quotes. For more info and free online quotes, please visit https://compare-autoinsurance.Org/the-advantages-of-comparing-prices-with-car-insurance-quotes-online/ The modern society has numerous technological advantages. One important advantage is the speed at which information is sent and received. With the help of the internet, the shopping habits of many persons have drastically changed. The car insurance industry hasn't remained untouched by these changes. On the internet, drivers can compare insurance prices and find out which sellers have the best offers. View photos The advantages of comparing online car insurance quotes are the following: Online quotes can be obtained from anywhere and at any time. Unlike physical insurance agencies, websites don't have a specific schedule and they are available at any time. Drivers that have busy working schedules, can compare quotes from anywhere and at any time, even at midnight. Multiple choices. Almost all insurance providers, no matter if they are well-known brands or just local insurers, have an online presence. Online quotes will allow policyholders the chance to discover multiple insurance companies and check their prices. Drivers are no longer required to get quotes from just a few known insurance companies. Also, local and regional insurers can provide lower insurance rates for the same services. Accurate insurance estimates. Online quotes can only be accurate if the customers provide accurate and real info about their car models and driving history. Lying about past driving incidents can make the price estimates to be lower, but when dealing with an insurance company lying to them is useless. Usually, insurance companies will do research about a potential customer before granting him coverage. Online quotes can be sorted easily. Although drivers are recommended to not choose a policy just based on its price, drivers can easily sort quotes by insurance price. Using brokerage websites will allow drivers to get quotes from multiple insurers, thus making the comparison faster and easier. For additional info, money-saving tips, and free car insurance quotes, visit https://compare-autoinsurance.Org/ Compare-autoinsurance.Org is an online provider of life, home, health, and auto insurance quotes. This website is unique because it does not simply stick to one kind of insurance provider, but brings the clients the best deals from many different online insurance carriers. In this way, clients have access to offers from multiple carriers all in one place: this website. On this site, customers have access to quotes for insurance plans from various agencies, such as local or nationwide agencies, brand names insurance companies, etc. "Online quotes can easily help drivers obtain better car insurance deals. All they have to do is to complete an online form with accurate and real info, then compare prices", said Russell Rabichev, Marketing Director of Internet Marketing Company. CONTACT: Company Name: Internet Marketing CompanyPerson for contact Name: Gurgu CPhone Number: (818) 359-3898Email: [email protected]: https://compare-autoinsurance.Org/ SOURCE: Compare-autoinsurance.Org View source version on accesswire.Com:https://www.Accesswire.Com/595055/What-Are-The-Main-Benefits-Of-Comparing-Car-Insurance-Quotes-Online View photos