News
How AI can improve storm surge forecasts to help save lives
storm surge forecasts: Hurricanes cause significant damage due to storm surge, which is influenced by wind and pressure. AI can enhance storm surge predictions, providing faster, more accurate information to aid evacuations and preparedness for coastal communities at risk.
Navid Tahvildari, Florida International University
Hurricanes are America’s most destructive natural hazards, causing more deaths and property damage than any other type of disaster. Since 1980, these powerful tropical storms have done more than US$1.5 trillion in damage and killed more than 7,000 people.
The No. 1 cause of the damages and deaths from hurricanes is storm surge.
Storm surge is the rise in the ocean’s water level, caused by a combination of powerful winds pushing water toward the coastline and reduced air pressure within the hurricane compared to the pressure outside of it. In addition to these factors, waves breaking close to the coast causes sea level to increase near the coastline, a phenomenon we call wave setup, which can be an important component of storm surge.
Accurate storm surge predictions are critical for giving coastal residents time to evacuate and giving emergency responders time to prepare. But storm surge forecasts at high resolution can be slow.
As a coastal engineer, I study how storm surge and waves interact with natural and human-made features on the ocean floor and coast and ways to mitigate their impact. I have used physics-based models for coastal flooding and have recently been exploring ways that artificial intelligence can improve the speed of storm surge forecasting.
How storm surge is forecast today
Today, operational storm surge forecasts rely on hydrodynamic models, which are based on the physics of water flow.
These models use current environmental conditions – such as how fast the storm is moving toward shore, its wind speed and direction, the timing of the tide, and the shape of the seafloor and the landscape – to compute the projected surge height and determine which locations are most at risk.
Hydrodynamic models have substantially improved in recent decades, and computers have become significantly more powerful, such that rapid low-resolution simulations are possible over very large areas. However, high-resolution simulation that provide neighborhood-level detail can take several hours to run.
Those hours can be critical for communities at risk to evacuate safely and for emergency responders to prepare adequately.
To forecast storm surge across a wide area, modelers break up the target area into many small pieces that together form a computational grid or mesh. Picture pixels in an image. The smaller the grid pieces, or cells, the higher the resolution and the more accurate the forecast. However, creating many small cells across a large area requires greater computing power, so forecasting storm surge takes longer as a result.
Forecasters can use low-resolution computer grids to speed up the process, but that reduces accuracy, leaving communities with more uncertainty about their flood risk.
AI can help speed that up.
How AI can create better forecasts
There are two main sources of uncertainty in storm surge predictions.
One involves the data fed into the computer model. A hurricane’s storm track and wind field, which determine where it will make landfall and how intense the surge will be, are still hard to forecast accurately more than a few days in advance. Changes to the coast and sea floor, such as from channel dredging or loss of salt marshes, mangroves or sand dunes, can affect the resistance that storm surge will face.
The second uncertainty involves the resolution of the computational grid, over which the mathematical equations of the surge and wave motion are solved. The resolution determines how well the model sees changes in landscape elevation and land cover and accounts for them, and at how much granularity the physics of hurricane surge and waves is solved.
AI models can produce detailed predictions faster. For example, engineers and scientists have developed AI models based on deep neural networks that can predict water levels along the coastline quickly and accurately by using data about the wind field. In some cases, these models have been more accurate than traditional hydrodynamic models.
AI can also develop forecasts for areas with little historic data, or be used to understand extreme conditions that may not have occurred there before.
For these forecasts, physics-based models can be used to generate synthetic data to train the AI on scenarios that might be possible but haven’t actually happened. Once an AI model is trained on both the historic and synthetic data, it can quickly generate surge forecasts using details about the wind and atmospheric pressure.
Training the AI on data from hydrodynamic models can also improve its ability to quickly generate inundation risk maps showing which streets or houses are likely to flood in extreme events that may not have a historical precedent but could happen in the future.
The future of AI for hurricane forecasting
AI is already being used in operational storm surge forecasts in a limited way, mainly to augment the commonly used physics-based models.
In addition to improving those methods, my team and other researchers have been developing ways to use AI for storm surge prediction using observed data, assessing the damage after hurricanes and processing camera images to deduce flood intensity. That can fill a critical gap in the data needed for validating storm surge models at granular levels.
As artificial intelligence models rapidly spread through every aspect of our lives and more data becomes available for training them, the technology offers potential to improve hurricane and storm surge forecasting in the future, giving coastal communities faster and more detailed warnings about the risks on the way.
Navid Tahvildari, Associate Professor of Civil and Environmental Engineering, Florida International University
This article is republished from The Conversation under a Creative Commons license. Read the original article.
STM Daily News is a vibrant news blog dedicated to sharing the brighter side of human experiences. Emphasizing positive, uplifting stories, the site focuses on delivering inspiring, informative, and well-researched content. With a commitment to accurate, fair, and responsible journalism, STM Daily News aims to foster a community of readers passionate about positive change and engaged in meaningful conversations. Join the movement and explore stories that celebrate the positive impacts shaping our world.
STM Daily News
Woman Charged With Felony Animal Cruelty in Santa Ana Puppy Killing
Santa Ana Puppy Killing: Prosecutors have filed felony charges against a 75-year-old Anaheim woman accused of deliberately running over and killing her puppy, Blackey, in Santa Ana.
Last Updated on October 3, 2026 by Daily News Staff
SANTA ANA, Calif. — A 75-year-old Anaheim woman accused of deliberately running over and killing her puppy on a Santa Ana street has now been formally charged with felony animal cruelty, marking a major development in a case that drew widespread attention after surveillance video was released by police.
The Orange County District Attorney’s Office announced Friday, October 2, that Hanh Minh Nguyen, 75, of Anaheim, has been charged with one felony count of animal cruelty, one felony count of animal abuse by a caretaker, and a felony enhancement alleging the personal use of a weapon — a vehicle — to kill the animal.
Nguyen was arrested by Santa Ana police on Thursday, October 1, after investigators used automated license plate reader technology to identify the green Honda Odyssey seen in surveillance footage from the September 8 incident. Police subsequently located Nguyen and found the minivan at her Anaheim residence.
According to the District Attorney’s Office, Nguyen was released from custody after posting $20,000 bail. She is scheduled to appear at the Central Justice Center in Santa Ana on November 2, 2026, in Department C55.
Surveillance video led to investigation
The case began on September 8 at approximately 9:15 a.m., when Santa Ana Animal Services officers responded to a report of a dead black-and-white male pit bull-mix puppy on West Park Lane.
Surveillance footage obtained during the investigation showed a woman removing the puppy from a minivan and placing food near the driver’s side of the vehicle. Authorities allege the woman then slowly drove forward as the puppy approached the food, running over the animal with the vehicle’s rear tire before leaving the scene.
The puppy, identified by authorities as Blackey, died.
The District Attorney’s Office describes Blackey as a 9-week-old puppy. Earlier statements and local news reports described him as approximately 9 months old.
Santa Ana police released surveillance footage of the incident on September 30 and appealed to the public for help identifying the driver.
Within a day, investigators said automated license plate reader technology helped them trace the Honda Odyssey to Nguyen. Police found the vehicle in her garage and took her into custody.
Police previously said Nguyen acknowledged owning and abandoning Blackey. According to the Los Angeles Times, a Santa Ana Police Department spokesperson said Nguyen told detectives she had left the puppy because he had been annoying her boyfriend by biting his shoes and belongings. Police said she acknowledged abandoning the dog but did not admit to intentionally running him over.
Prosecutors file felony charges
The filing of felony charges moves the case beyond the initial police investigation and into the Orange County court system.
Orange County District Attorney Todd Spitzer condemned the alleged killing in announcing the charges and said his office intends to prosecute acts of violence against animals.
Deputy District Attorney Danica Drotman of the Orange County District Attorney’s Animal Cruelty Unit is prosecuting the case.
Nguyen is accused of the offenses and has not been convicted. The allegations against her will now be addressed through the court process.
Her next scheduled court appearance is November 2.
STM Daily News will continue following the case and provide updates as additional information becomes available.
Source and Related Links
- Orange County District Attorney — October 2 charging announcement
- The DA’s release is the strongest source for this update. It provides case number 26CF4923, the exact charges, $20,000 bail, November 2 court date and the prosecutor assigned to the case. Orange County District Attorney
- For corroborating coverage, CBS Los Angeles reports the arrest, use of automated license-plate readers and the subsequent felony charges. CBS News
- CBS Los Angeles — arrest and charges update
- NBC Los Angeles — felony charges update
College Life
Is College Worth It? New U.S. News Rankings Put More Weight on What Graduates Earn
Is college worth it? MIT has taken the No. 1 spot in the 2027 U.S. News Best Colleges rankings, ending Princeton’s 15-year run. But a new Earnings by Major metric could be even more important for families asking whether college is worth the investment.
For millions of students and families, choosing a college increasingly comes down to a basic question: Is college worth it?
The latest U.S. News & World Report Best Colleges rankings are attempting to provide another piece of information to help answer that question.
The 2027 rankings place the Massachusetts Institute of Technology (MIT) at No. 1 among National Universities, ending Princeton University’s 15-year run at the top. But perhaps the bigger story for prospective students isn’t which university occupies the No. 1 position.
It’s a significant change in how U.S. News measures the value of attending college.
For the first time, the rankings include an Earnings by Major factor designed to examine what graduates earn after leaving school — and to compare those earnings with graduates who studied the same subjects elsewhere.
Is College Worth It? U.S. News Looks Beyond Graduation
College has traditionally been promoted as an investment in a person’s future. But as families confront tuition, housing expenses and the possibility of student debt, simply earning a degree may no longer be enough information when deciding where — or whether — to attend.
Students increasingly want to know what happens after graduation.
The new U.S. News Earnings by Major metric examines graduate earnings four years after graduation using data from the U.S. Department of Education’s College Scorecard.
Importantly, the system doesn’t simply compare the average salary of graduates from one university with another.
Instead, earnings are compared within specific academic disciplines.
That distinction matters.
A university graduating large numbers of engineers, computer scientists or students entering other relatively high-paying occupations could otherwise appear to produce stronger financial outcomes simply because of the subjects its students choose to study.
Comparing graduates within similar fields is intended to provide a clearer picture of how graduates from different institutions fare financially.
From Student Debt to Graduate Earnings
The new Earnings by Major metric replaces the Graduate Indebtedness factor previously used by U.S. News.
That represents an important shift in perspective.
Instead of focusing primarily on how much debt students accumulate, the new measure looks at one aspect of what students may receive financially from their education after entering the workforce.
The metric examines employed federal financial aid recipients whose highest degree is a bachelor’s degree.
According to U.S. News, the approach is intended to reduce the influence of family financial advantages and provide a better indication of the economic value institutions may contribute to graduates.
That doesn’t mean earnings alone determine whether a college education is worthwhile.
But for a student potentially investing tens of thousands of dollars — and several years of their life — knowing how graduates in a particular major perform economically can be an important part of the decision.
MIT Takes the No. 1 Spot
Against that changing methodology, MIT moved into the No. 1 position among National Universities in the 2027 rankings.
The top three are:
- Massachusetts Institute of Technology
- Princeton University
- Harvard University
Princeton’s move to second place ends a run at No. 1 that began with the 2012 edition of the rankings.
Among National Liberal Arts Colleges, Williams College remained No. 1, followed by Amherst College at No. 2. Bowdoin College, Claremont McKenna College, Pomona College and Swarthmore College tied for third.
Nearly 1,700 institutions were evaluated in the 2027 edition.
Outcomes Are Becoming a Bigger Part of the Equation
The addition of graduate earnings is part of a broader emphasis on student outcomes in the U.S. News methodology.
U.S. News says outcomes now account for more than half of a school’s total score.
Institutions can be evaluated using as many as 17 weighted measures, including graduation and retention rates, social mobility for lower-income students, post-graduate earnings, faculty resources and academic peer assessments.
The shift reflects a changing conversation surrounding higher education.
For generations, students were often encouraged to focus heavily on getting into the most prestigious college possible. Today’s students may also be asking more practical questions:
How much will it cost?
How much financial aid will I receive?
How much debt might I have when I graduate?
What do graduates in my intended major earn?
And perhaps most importantly:
Will the investment pay off for me?
College Value Isn’t Just About Salary
Graduate earnings can provide useful information, but salary shouldn’t be treated as the sole measurement of the value of higher education.
Different careers have dramatically different compensation structures.
A graduate pursuing teaching, public service, social work, the arts or nonprofit work may earn less than someone entering engineering, finance or technology while still considering their education worthwhile.
There are also benefits of higher education that are difficult to capture in a salary statistic.
That’s why students comparing schools may want to look beyond an institution’s overall ranking and examine factors such as net price after financial aid, scholarships, graduation rates, student debt, internship opportunities, career placement, location and the strength of the program they actually intend to study.
The best-known university isn’t automatically the best financial or educational choice for every student.
Economic Diversity Also Gets Attention
The 2027 rankings also highlight economic diversity among highly ranked institutions.
According to U.S. News, MIT and Princeton rank third and fourth, respectively, among the top 25 National Universities in the percentage of students receiving federal Pell Grants.
Pell Grants generally assist undergraduate students with significant financial need and typically do not have to be repaid.
Among the top 25 National Liberal Arts Colleges, Amherst College ranked highest for economic diversity under the U.S. News measure.
A New Ranking Looks at In-State Value
U.S. News is also placing additional attention on affordability for students considering public universities.
The 2027 edition introduces a Best Value Schools for In-State Students ranking, which evaluates public universities based on academic quality and affordability for residents.
The University of North Carolina at Chapel Hill took the No. 1 position in the inaugural ranking.
That category could be particularly relevant to families deciding whether the prestige associated with attending a private or out-of-state university justifies potentially higher costs compared with attending a public institution in their home state.
The Rankings Look Different This Year
There is another important caveat when comparing the 2027 results with previous years.
Changes to the Carnegie Classification framework resulted in approximately 20% of previously ranked institutions moving into different U.S. News categories.
Because some colleges are now being compared against different groups of institutions, their 2027 rankings may not be directly comparable with previous years.
The changes also expanded eligibility, allowing additional institutions specializing in areas such as engineering, business and health to enter the rankings.
U.S. News also introduced an undergraduate economics specialty ranking while continuing rankings covering areas such as social mobility, innovation, historically Black colleges and universities, artificial intelligence programs, internships, undergraduate research and study-abroad opportunities.
Public Universities, HBCUs and Social Mobility
Among public National Universities, the University of California, Berkeley and UCLA tied for the No. 1 position, followed by the University of Michigan–Ann Arbor.
The top three Historically Black Colleges and Universities were:
- Spelman College
- Howard University
- Tuskegee University
For social mobility among National Universities, Florida International University and the University of California, Riverside tied for No. 1, with Oakland City University ranked third.
These categories illustrate another reason students may want to look deeper than a school’s overall national position. Different rankings can reveal institutions performing particularly well in areas that may matter more to an individual student.
So, Is College Worth It?
There isn’t one answer that applies to every student.
The cost of attending, financial aid, chosen major, career goals, likelihood of graduating and potential debt can dramatically change the financial equation.
A college with a famous name and high national ranking could be a poor financial choice for one student while a less prominent public university with generous financial aid could be an excellent investment for another.
That’s what makes the addition of Earnings by Major noteworthy.
Instead of asking only “Which college ranks highest?”, prospective students now have another reason to ask a much more personal question:
“What am I paying for — and what could I realistically get in return?”
MIT replacing Princeton at No. 1 makes the headline.
But for students and parents trying to decide whether college is worth the cost, the growing emphasis on outcomes, affordability and post-graduation earnings may ultimately be the more important story.
Source: U.S. News & World Report, 2027 Best Colleges rankings, released September 22, 2026.
U.S. News & World Report press release:
MIT Claims No. 1 Spot in U.S. News 2027 Best Colleges Rankings PR Newswire
Stay Informed with STM Daily News
From education and personal finance to technology, lifestyle, transportation and the stories shaping our everyday lives, STM Daily News keeps you informed about what matters — and why it matters. Get more news, useful insights and the latest updates by visiting STM Daily News and subscribe to stay connected to the stories worth knowing.
Forgotten Genius Fridays
Sarah Boone Improved the Ironing Board by Thinking About the Sleeve
Sarah Boone didn’t invent the first ironing board. The New Haven dressmaker patented a clever improvement shaped for pressing sleeves and fitted clothing.
Forgotten Genius | STM Daily News
Try ironing a sleeve on a wide, flat board. The fabric bunches, the seams curve, and pressing one side can leave a crease on the other. For dressmaker Sarah Boone, that everyday frustration presented a problem she could solve.
Working in New Haven, Connecticut, Boone designed an ironing board shaped for sleeves and fitted garments. Her board was narrow enough for a sleeve to slip over it, allowing one side to be pressed without flattening the other. Its curved edges followed the lines of a sleeve’s seams, while its supports helped position the board for different uses.
Boone filed her patent application in 1891. On April 26, 1892, she received U.S. Patent No. 473,653 for her improvement.
Boone did not invent the first ironing board. What she patented was a thoughtful redesign for a particular task. That distinction makes her achievement more interesting: she understood how the tool was used, recognized where it fell short, and changed its shape to make the work easier.
The patent drawing brings her idea to life. Instead of the broad surface most people picture when they hear “ironing board,” Boone’s design looks almost like the part of a garment it was meant to support. It is a practical solution from someone who knew the job firsthand.
That is the heart of Sarah Boone’s story. Invention does not always begin with an entirely new machine. Sometimes it begins when a person doing familiar work asks a better question: What would this tool look like if it truly fit the task?
Boone answered with a design—and secured a place in the history of Black innovation.
References:
Sarah Boone’s Original Ironing Board Patent — U.S. Patent No. 473,653, granted April 26, 1892. Includes her description, construction details, and original drawings.
USPTO: Beyond Baker’s List—Black Innovation Then and Now — Identifies Boone as a New Haven dressmaker who patented an improved ironing board shaped for bodices and sleeves.
USPTO: Found on Baker’s List — Background on Henry Baker’s work documenting Black patent holders, providing historical context for the Forgotten Genius series.
Explore more inventors and innovators in STM Daily News’ Forgotten Genius series.
Sources: U.S. Patent and Trademark Office; Sarah Boone’s original 1892 patent, available through Google Patents.
