Scientists develop new AI method to forecast cyclone rapid intensification
2025-01-23
(Press-News.org)
Rapid Intensification (RI) of a tropical cyclone (TC), defined as a maximum sustained wind increase of at least 13 m/s within 24 hours, remains one of the most challenging weather phenomena to forecast because of its unpredictable and destructive nature. Although only 5% of TCs experience RI, its sudden and severe development poses significant risks to affected regions.
Traditional forecasting methods, such as numerical weather prediction and statistical approaches, often fail to consider the complex environmental and structural factors driving RI. While artificial intelligence (AI) has been explored as a means to improve RI prediction, most AI techniques have struggled with high false alarm rates and limited reliability.
To address this issue, researchers from the Institute of Oceanology of the Chinese Academy of Sciences (IOCAS) have developed a new model for forecasting RI of TCs based on "contrastive learning." This study was published in the Proceedings of the National Academy of Sciences (PNAS) on January 21.
The new model has two inputs: Input A, a known RI TC sample, and Input B, an unknown sample to be forecasted. It extracts features from both inputs and calculates their distance in a high-dimensional space. If the distance is small, Input B is forecasted as an RI TC; if large, it is classified as a non-RI TC. Each unknown sample is compared with 10 known RI TC samples, and if more than five of the comparisons classify it as an RI TC, it is then classified as such.
Additionally, this study uses satellite imagery alongside atmospheric and oceanic data to balance RI and non-RI TC data. The model learns to differentiate between RI and non-RI TCs by comparing the two inputs during training.
When tested on data from the Northwest Pacific between 2020 and 2021, the method achieved an impressive accuracy of 92.3% and reduced false alarms to 8.9%. Compared to existing techniques, it improved accuracy by 12% and reduced false alarms by a factor of three, representing a major advancement in forecasting.
Although the model was initially trained on reanalysis data, the researchers created an operational forecasting scenario by replacing the reanalysis data with ECMWF-IFS numerical model forecast data from 2020 to 2021 as input. The results demonstrated comparable forecasting accuracy, further validating the reliability of this approach and confirming its suitability for real-time forecasting scenarios. This capability can significantly enhance early warning systems, thus improving global disaster preparedness.
"This study addresses the challenges of low accuracy and high false alarm rates in RI TC forecasting," said Prof. LI Xiaofeng, the corresponding author. "Our method enhances understanding of these extreme events and supports better defenses against their devastating impacts."
END
ELSE PRESS RELEASES FROM THIS DATE:
2025-01-23
Two leading experts in the field of metamaterials from Tsinghua University co-authored a review article on this emerging scientific field in Engineering recently. Unlike traditional review articles, the authors interpret metamaterials from an artistic perspective. By drawing parallels with art, they reflect on significant achievements made over the past two decades and offer insights into the future development of the field. Their work introduces readers to the novel concept of metamaterials as “the art in materials science.”
Metamaterials refer to artificially engineered materials composed of structural units designed to exhibit extraordinary ...
2025-01-23
Researchers at University of California San Diego analyzed cannabis smoking practices in San Diego County to assess whether in-home smoking was associated with cannabis detection in children. The study, published in the Jan. 23, 2025, online edition of the Journal of the American Medical Association Network Open, found that in-home cannabis smoking increased the odds of child exposure to cannabis smoke.
Smoking is the most common method of cannabis use and is known to generate emissions that are harmful to those exposed. Cannabis is often smoked indoors, putting non-smokers such as children at risk for exposure.
“While the long-term health consequences of cannabis smoke are not ...
2025-01-23
COLUMBUS, Ohio – Adam Leroy, a professor of astronomy at The Ohio State University, has been named the recipient of the 2025 Henry Draper Medal.
The oldest medal awarded by the National Academy of Sciences, the Henry Draper Medal celebrates those who have made “a recent, original investigation in astronomical physics, of sufficient importance and benefit to science to merit such recognition.” It is awarded every four years.
Leroy’s work was selected for pathbreaking efforts that have characterized, “in unprecedented detail, the physical ...
2025-01-23
Non-white communities had significantly less access to opioid medications commonly prescribed for moderate to severe pain than white communities over the decade beginning in 2011, according to a study by Weill Cornell Medicine researchers.
The findings, published Jan. 23 in Pain, stretched across all socioeconomic groups, and suggest that communities of color may be especially vulnerable to the unintended consequences of efforts to reduce unsafe use of opioid analgesics.
From 2011 to 2021, prescription opioid use dropped by about 50% ...
2025-01-23
The prevalence of diagnosed disorders from recurrent use of sedative, hypnotic and antianxiety medications in adolescents and young adults has increased sharply since 2001, according to Rutgers Health researchers.
Their study, published in Addiction, examined diagnoses of these disorders in adolescents and young adults between 2001 to 2019.
Sedative, hypnotic and antianxiety medications are used to treat a variety of conditions, including sleep and anxiety disorders. According to Harvard Health, consistent use of these drugs can lead to a higher tolerance for their effects, meaning patients require higher doses to achieve the intended effects.
For ...
2025-01-23
A recent study by researchers from Peking University demonstrates the potential of nuclear electric resonance to control the nuclear spins of nitrogen atoms in DNA using electric field gradients, thereby achieving artificial intervention to manipulate DNA for computation. Utilizing molecular dynamics simulations, quantum chemical computations and theoretical analyses, the research reveals how electric field gradient orientation patterns vary with DNA bases and nitrogen atom sites, encoding genetic and structural information into the direction of nitrogen nuclear spins. The research was published Dec. 12 in Intelligent Computing, a Science Partner ...
2025-01-23
“It has been postulated that the clinical benefit of adding POM results from enhanced immunocompetency.”
BUFFALO, NY - January 23, 2025 – A new editorial was published in Oncoscience’s Volume 12 on January 14, 2025, titled “Pomalidomide improved immune profiles in myeloma."
The editorial by researchers Hannah Seah, Vaishnavi Reddy Bade, Lakshmi Bhavani Potluri, Srikanth Talluri, and Rao H. Prabhala from Dana-Farber Cancer Institute, VA Boston Healthcare System, and Harvard Medical School, discuss how the drug pomalidomide (POM) can help improve the immune system ...
2025-01-23
The PREPSOIL project, a pivotal initiative within the EU's Mission Soil framework, will host an engaging webinar on February 13, 2025, focusing on the importance of soil literacy among young people. The event highlights the vital connection between young citizens and soil health, offering educators innovative ways to integrate soil-related topics into their curriculum.
As part of the Mission Soil's eight goals, increasing soil literacy across Member States aims to foster greater awareness, involvement, and proactive behavior toward soil health. By embedding soil health education in school curriculums, the initiative seeks to empower the next generation to take informed ...
2025-01-23
WASHINGTON, Jan. 23, 2025 – Many science fiction authors try to incorporate scientific principles into their work, but Ian Tregillis, who is a contributing author of the Wild Cards book series when he’s not working as a physicist at Los Alamos National Laboratory, took it one step further: He derived a formula to describe the dynamics of the fictional universe’s viral system.
In independent research published in the American Journal of Physics, from AIP Publishing, Tregillis and George R.R. Martin derive a formula for viral behavior in the Wild Cards universe.
Wild Cards is a science fiction series written by a collection of authors and ...
2025-01-23
The remains of the earliest dinosaurs may lie undiscovered in the Amazon and other equatorial regions of South America and Africa, suggests a new study led by UCL (University College London) researchers.
Currently, the oldest known dinosaur fossils date back about 230 million years and were unearthed further south in places including Brazil, Argentina and Zimbabwe. But the differences between these fossils suggest dinosaurs had already been evolving for some time, pointing to an origin millions of years earlier.
The new study, published in the journal Current Biology, accounted for gaps in ...
LAST 30 PRESS RELEASES:
[Press-News.org] Scientists develop new AI method to forecast cyclone rapid intensification
