Wednesday, September 04, 2024

 

Qunkasaura: New sauropod dinosaur from the Cretaceous discovered in the Iberian Peninsula




Faculty of Sciences of the University of Lisbon

General view of the Lo Hueco site during the excavation of Qunkasaura in 2007 

image: 

 General view of the Lo Hueco site during the excavation of Qunkasaura in 2007

view more 

Credit: GBE-UNED





new study led by Portuguese paleontologist Pedro Mocho, from the Instituto Dom Luiz of the Faculty of Sciences of the University of Lisbon (CIÊNCIAS), has just been published in the Communications Biology journal, which announces a new species of sauropod dinosaur that lived in Cuenca, Spain, 75 million years ago: Qunkasaura pintiquiniestra.

The more than 12,000 fossils collected from 2007 onwards during works to install the Madrid-Levante high-speed train (AVE) tracks revealed this deposit, giving rise to one of the most relevant collections of fossil vertebrates from the Upper Cretaceous of Europe. The collection has been studied continuously thanks to national projects and the Junta de Comunidades de Castilla-La Mancha, which has made it possible to significantly increase the understanding of the ecosystems of southwestern Europe during the Late Cretaceous and also identify several new species for science.

“The study of this specimen allowed us to identify for the first time the presence of two distinct lineages of saltasauroids in the same fossil locality. One of these groups, called Lirainosaurinae, is relatively known in the Iberian region and is characterized by small and medium-sized species, which evolved in an island ecosystem. In other words, Europe was a huge archipelago made up of several islands during the Late Cretaceous. However, Qunkasaura belongs to another group of sauropods, represented in the Iberian Peninsula by medium-large species 73 million years ago. This suggests to us that this lineage arrived in the Iberian Peninsula much later than other groups of dinosaurs”, explains Pedro Mocho, paleontologist at CIÊNCIAS.

One of the most relevant features of the Lo Hueco fossil record is the abundance of large partial skeletons of sauropod dinosaurs, which are rare in the rest of Europe. Qunkasaura pintiquiniestra stands out for being one of the most complete sauropod skeletons found in Europe, including cervical, dorsal and caudal vertebrae, part of the pelvic girdle and elements of the limbs. Their unique morphology, especially in the tail vertebrae, offers new insights into the non-avian dinosaurs of the Iberian Peninsula, a historically poorly understood group.

The study, now published in the Communications Biology journal, identifies Qunkasaura as a representative of the opisthocoelicaudine saltasaurids, a group present in the northern hemisphere (Laurasia). On the other hand, most Late Cretaceous sauropods from southwestern Europe, including Lohuecotitan pandafilandi, previously described from Lo Hueco, belong to the group Lirainosaurinae, a group of sauropods apparently exclusive to the European continent. This study suggests that Lo Hueco is the only place where the coexistence of both groups is known and proposes a new group of titanosaurs called Lohuecosauria, which includes representatives of both lineages. Lohuecosaurs may have originated on the southern continents (Gondwana) before dispersing globally.

The name Qunkasaura pintiquiniestra is made up of several geographic and cultural references close to the Lo Hueco site. "Qunka" refers to the oldest etymology of the toponym from the Cuenca and Fuentes area, "Saura" alludes to the feminine of the Latin saurus (lizard), but also pays homage to the painter Antonio Saura, and "pintiquiniestra" refers to the giant "Queen Pintiquiniestra", character from a novel mentioned in ‘Don Quijote de la Mancha’ by Cervantes.

“Fortunately, the Lo Hueco deposit also preserves several skeletons of sauropod dinosaurs to be determined, which may correspond to new species and which will help us understand how these animals evolved”, concludes Pedro Mocho.

The study is part of the research conducted by the Evolutionary Biology Group at UNED on ecosystems with dinosaurs in central Iberian Peninsula. Part of the skeleton of Qunkasaura is already on display in the Paleontological Museum of Castilla-La Mancha in Cuenca (Spain).

Reference

Mocho, P.; Escaso, F.; Marcos-Fernández, F.; Páramo, A.; Sanz, J. L.; Vidal, D.; Ortega, F. 2024. A Spanish saltasauroid titanosaur reveals Europe as a melting pot of endemic and immigrant sauropods in the Late Cretaceous. Communications Biology. DOI: https://doi.org/10.1038/s42003-024-06653-0

Restoration process of part of the remains of Qunkasaura.

Credit

GBE-UNED

Reconstruction of the life form of Qunkasaura pintiquiniestra.

Credit

José Antonio Peñas Artero

3D reconstruction of the Qunkasaura skeleton.

Credit

GBE-UNED


Psychedelics show promise for treating PTSD by suppressing learned fear responses



New research reveals how psychedelic drugs like psilocybin acutely reduce fear by altering activity in the amygdala, a key brain region involved in processing fear and anxiety




Genomic Press




MILWAUKEE, WI - Ongoing research is revealing how psychedelic drugs like psilocybin (the active ingredient in "magic mushrooms") and LSD may help treat post-traumatic stress disorder (PTSD) by suppressing learned fear responses. In a new Bench to Bedside peer-reviewed article published in the journal Psychedelics (ISSN: 2997-2671, Genomic Press, New York), researchers from the Medical College of Wisconsin provide an in-depth look at the neural mechanisms underlying psychedelics' acute fear-reducing effects in rodent models of PTSD.

The amygdala, an almond-shaped structure deep within the brain, plays a central role in fear learning and expression. Excitatory neurons in the lateral amygdala are activated by fearful stimuli, leading to a cascade of activity that drives fear responses. The new research proposes that psychedelic drugs suppress this fear-related activity by enhancing inhibitory signaling from GABAergic interneurons onto the excitatory neurons.

"Our hypothesis is that psychedelics acutely suppress learned fear responses by activating serotonin 2A receptors on inhibitory neurons in the amygdala," said the lead author Thomas Kelly, an MD/PhD candidate. "This leads to increased release of the inhibitory neurotransmitter GABA, which quiets the activity of excitatory neurons that normally drive fearful behaviors."

The finding that psychedelics' acute effects on fear require activation of serotonin 2A receptors aligns with the receptor's established role in the drugs' hallucinogenic effects. However, the authors emphasize the importance of considering the broader pharmacological profile and duration of action of different psychedelic compounds.

For example, the drug MDMA, which has shown promise for treating PTSD in late-stage clinical trials, does not directly activate serotonin 2A receptors. Instead, MDMA increases the release of serotonin, which then activates various serotonin receptor subtypes. The research suggests that psychedelics with faster onset and shorter duration of acute effects may be advantageous for PTSD treatment compared to longer-acting drugs like LSD.

"The insights from preclinical studies can help guide the design of clinical trials and treatment protocols that optimize the therapeutic potential of psychedelics for PTSD," said senior author Dr. Qing-song Liu. "By understanding the mechanisms and time-course of psychedelics' effects on fear circuitry, we can better harness these compounds in a clinical setting."

Several clinical trials are currently investigating psilocybin-assisted therapy for PTSD, with some protocols incorporating drug administration in combination with exposure therapy to promote fear extinction learning. As this research progresses, the amygdala is emerging as a key locus of interest for understanding how psychedelics may extinguish fearful memories and provide a novel treatment approach for PTSD and other fear-related disorders.

The full article, titled “Exploring the therapeutic potential of psychedelics: Fear extinction mechanisms and amygdala modulation,” was published online on 09 August 2024 and is freely available online at the website of Psychedelics (Genomic Press, New York): https://pp.genomicpress.com/aop/

Contact: Thomas J. Kelly Medical College of Wisconsin tjkelly@mcw.edu 1-920-427-6177

 

GLP-1 receptor agonist use and risk of suicide death



JAMA Internal Medicine



About The Study: 

This cohort study, including mostly patients with type 2 diabetes, does not show an association between use of glucagon-like peptide-1 (GLP-1) receptor agonists and an increased risk of suicide death, self-harm, or incident depression and anxiety-related disorders.



Corresponding Author: To contact the corresponding author, Peter Ueda, MD, PhD, email peter.ueda@ki.se.

To access the embargoed study: Visit our For The Media website at this link https://media.jamanetwork.com/

(doi:10.1001/jamainternmed.2024.4369)

Editor’s Note: Please see the article for additional information, including other authors, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.

#  #  #

Embed this link to provide your readers free access to the full-text article This link will be live at the embargo time https://jamanetwork.com/journals/jamainternalmedicine/fullarticle/10.1001/jamainternmed.2024.4369?guestAccessKey=2dc15077-db5b-45cf-b2f1-f1fcf6020c5c&utm_source=For_The_Media&utm_medium=referral&utm_campaign=ftm_links&utm_content=tfl&utm_term=090324

 

Penn study finds taking semaglutide for weight management does not increase risk of depression or suicidal behavior in people without known major psychopathology


Analysis of over 3,500 participants in clinical trials finds no increased risk of mental health issues among those using the weight loss medication



University of Pennsylvania School of Medicine




PHILADELPHIA— Taking the weight loss medication semaglutide did not increase the risk of depressive symptoms, suicidal thoughts, or suicidal behavior in persons without known major mental health disorders, according to a new study led by researchers from the Perelman School of Medicine at the University of Pennsylvania published this week in JAMA Internal Medicine. Both the Food and Drug Administration (FDA) and the European Medicines Agency are actively monitoring the psychiatric safety of semaglutide and similar medications after post marketing surveillance reports of depression, suicidal thoughts (ideation), and suicidal behavior in patients taking the drugs for the management of type 2 diabetes or obesity.

Semaglutide has emerged as a significant advancement in the field of weight management. Initially developed as a treatment for type 2 diabetes, the drug gained widespread attention after clinical trials showed it reduced baseline body weight by approximately 10%-15%. Weekly injectable medications like semaglutide have become a popular option for healthcare providers to prescribe for patients. As many as 5 million Americans were prescribed semaglutide in 2023, with nearly four in ten taking it for weight management.

The new study, led by Thomas Wadden, PhD, a professor of Psychology in Psychiatry and the former director of Penn’s Center for Weight and Eating Disorders, analyzed data from over 3,500 participants across four major clinical trials. Researchers examined data from the Semaglutide Treatment Effect in People with obesity (STEP) trials – STEP 1, 2, 3, and 5. These studies were crucial in gaining approval from the FDA to use semaglutide 2.4 mg for obesity.

"The STEP trials provide strong evidence that semaglutide 2.4 mg reduces body weight and improves numerous health complications associated with obesity. Our new analyses provide assurance that the medication, when taken by individuals who are free of significant mental health concerns, does not increase the risk of depression, suicidal thoughts, or suicidal behavior,” Wadden said. He noted, however, that further study is needed of the psychiatric safety of semaglutide 2.4 mg when used by persons with current major depressive disorder, other serious mental illness (such as schizophrenia), or a history of suicide attempt. Individuals with such conditions were not included in the STEP trials.

The study examined changes in depressive symptoms using the Patient Health Questionnaire-9 (PHQ-9) and assessed suicidal ideation and behavior using the Columbia Suicide Severity Rating Scale. Across the 68-week STEP 1-3 trials, semaglutide-treated participants, as compared to those who received placebo, did not show an increased risk of developing moderately severe symptoms of depression or of suicidal thoughts or behavior. Similar findings were observed in the 104-week STEP 5 study.

Examining all four STEP trials, researchers found that 1% or fewer of participants reported suicidal ideation or behavior during treatment, with no differences between semaglutide 2.4 mg and placebo. Moreover, only 2.8% of the semaglutide-treated participants, versus 4.1% of those who received placebo, reported levels of depression at some point during treatment that required evaluation by a mental health professional. These rates are consistent with the risk of significant depression in the general population. “It is certainly possible that individuals with overweight or obesity who take semaglutide may experience depressive symptoms or suicidal ideation or behavior, but the data suggest that persons not taking semaglutide – in the placebo group in this study - are equally likely to experience these conditions,” said Gregory Brown, PhD, a study co-author and Director of the Penn Center for the Prevention of Suicide at the Perelman School of Medicine. Wadden and Brown noted that their study’s findings for semaglutide are consistent with results of the FDA’s most recent analysis of post-marketing surveillance data for this class of medications which did not find “evidence that use of these medicines causes suicidal thoughts or actions." 

If you or a loved one are experiencing a suicidal crisis or emotional distress call the Suicide and Crisis Lifeline at 988.

The study was funded by Novo Nordisk.

Editor’s Note: Wadden has received grants from Novo Nordisk, as well as consulting fees from Novo Nordisk, advisory board service fees from Weight Watchers, and grant support from Eli Lilly.

###

Penn Medicine is one of the world’s leading academic medical centers, dedicated to the related missions of medical education, biomedical research, excellence in patient care, and community service. The organization consists of the University of Pennsylvania Health System and Penn’s Raymond and Ruth Perelman School of Medicine, founded in 1765 as the nation’s first medical school.

The Perelman School of Medicine is consistently among the nation's top recipients of funding from the National Institutes of Health, with $550 million awarded in the 2022 fiscal year. Home to a proud history of “firsts” in medicine, Penn Medicine teams have pioneered discoveries and innovations that have shaped modern medicine, including recent breakthroughs such as CAR T cell therapy for cancer and the mRNA technology used in COVID-19 vaccines.

The University of Pennsylvania Health System’s patient care facilities stretch from the Susquehanna River in Pennsylvania to the New Jersey shore. These include the Hospital of the University of Pennsylvania, Penn Presbyterian Medical Center, Chester County Hospital, Lancaster General Health, Penn Medicine Princeton Health, and Pennsylvania Hospital—the nation’s first hospital, founded in 1751. Additional facilities and enterprises include Good Shepherd Penn Partners, Penn Medicine at Home, Lancaster Behavioral Health Hospital, and Princeton House Behavioral Health, among others.

Penn Medicine is an $11.1 billion enterprise powered by more than 49,000 talented faculty and staff.

 

 SYSTEMIC RACIST MEDICINE

Study: racial and ethnic designation inaccuracies in children’s medical records may impede equity efforts



Michigan hospital collaborative uncovers substantial errors in data critical to identifying and addressing inequities and disparities in children’s health



Michigan Medicine - University of Michigan





ANN ARBOR, Mich. – Leaders at three Michigan hospitals aiming to address equity issues for pediatric patients wanted to start with inspecting data key to identifying potential inequities.

What they learned: much of those data are inaccurate.

A study from the Michigan Child Health Equity Collaborative, or Mi-CHEC, found substantial errors across the three health systems in racial and ethnic designations in their electronic medical records. Accuracy of these designations are important to clinical care improvement efforts yet error rates of race in electronic medical records ranged from 22% to 59% while errors in ethnicity ranged from 5% to 35%, according to the findings in JAMA Network Open.

“The goal of MI-CHEC is to identify inequities affecting children’s health and implement improvement strategies to address them. But if the data regarding race and ethnicity are wrong, there’s a real risk of missing some inequities and even trying to correct inequities that may not exist,” said lead author and Mi-CHEC founder Gary L. Freed, M.D., M.P.H., professor in the department of pediatrics at the U-M Medical School.

“This is the first step to better understanding the misattribution in racial and ethnic designations in medical records. There are no perfect data; however, if we don’t know the degree of accuracy in the race and ethnicity of our patient populations, we are truly flying blind when we and others are assessing equity and disparity.”   

The study reflects the first published data from Mi-CHEC, which comprises the state’s three largest pediatric hospitals, including U-M Health C.S. Mott Children’s Hospital, Children’s Hospital of Michigan and Corewell Health Helen DeVos Children’s Hospital.

Expanded designation choices associated with greater errors

Researchers compared the specific racial and designations made by more than 3,400 parents to what was listed in their children’s medical records in outpatient clinics, emergency departments and hospital units across health systems between 2023 and 2024.

Reasons for the discrepancies are still being assessed, but authors point out associations between errors in designations and the evolving range and number of potential categories used by health systems for racial and ethnic attribution.

Options for race designation across hospitals ranged from six at one system to 49 in another while options for ethnicity ranged from two to 10. 

Some health systems have chosen consistency with the U.S. Census Bureau designations, Freed notes, while others have expanded the choices available for patients as part of inclusivity programs. 

Additionally, hospitals rarely verify the accuracy of racial and ethnic attribution in secondary data or health records, especially for children.

“There have been significant, well-intentioned efforts over the last several years at many institutions to expand the choices for patients to designate their own race or ethnicity to promote inclusion among our patient populations,” Freed said. “However, we found that a greater number of choices may lead to greater error in the electronic medical record.”

It’s important to understand how these errors may affect quality improvement efforts when working to identify health inequities or disparities for children with such conditions as asthma, obesity, diabetes and other health issues, Freed notes.

“Error rates of this magnitude influence the reliability of studies focused on inequities and disparities,” he said. “If we don’t know which children are which race or ethnicity we won’t know if there’s a problem and if efforts to fix the problem are successful or not.”

“This may undermine strategies to improve care.”

Freed adds that similar errors may be prevalent at other hospitals across the country, and collaborative members hope to encourage other systems to assess their own data accuracy as well.

Mi-CHEC will also be working on quality improvement efforts to both correct current error rates within the collaborative’s health systems and prevent future errors from occurring, he says. In the interim period, teams have developed statistical correction factors to improve accuracy in the collaborative’s assessments of inequities.

“These findings help us understand the limitations of our data and how we can account for those limitations as we continue our work to address inequities and disparities affecting pediatric patients and their families,” Freed said.

Additional authors include Brittany Bogan, MHSA, and Susan Woolford, M.D., of U-M; Adam Nicholson, M.D., of Corewell Health Helen DeVos Children’s Hospital; and Deborah Niedbala, M.S.N., of the Children's Hospital of Michigan.

About Mi-CHEC: Mi-CHEC, funded in partnership with the Michigan Department of Health and Human Services, is designed to engage hospitals in identifying and measuring pediatric healthcare inequities within their organizations. Mi-CHEC facilitates the sharing of topics for investigation, research methods, data, and quality improvement strategies across member hospitals. Learn more.

 

Research Brief: 50-year generation gap in Minnesota’s longest-lived fish



Three-year study identifies conservation concern for native Minnesota fish




University of Minnesota

Bigmouth buffalo migration in an around Rice Lake National Wildlife Refuge 

image: 

Bigmouth buffalo migration in an around Rice Lake National Wildlife Refuge

view more 

Credit: Credit: Alec Lackmann




Duluth, MN – A recent study in one of the most pristine spawning grounds for a Minnesota fish found a half-century gap between successful broods. And that number's climbing.

That’s according to new research on the bigmouth buffalo (Ictiobus cyprinellus) from the University of Minnesota Duluth (UMD), recently published in Scientific Reports. The study was led by Alec Lackmann, PhD, an ichthyologist and assistant professor of Mathematics and Statistics, and Mark Clark, PhD, a professor of Biology, both from the Swenson College of Science and Engineering at UMD. 

The bigmouth buffalo is a fish that’s native to Minnesota and known for its longevity. Researchers wanted to find out more about the species, especially how they migrate, spawn, and how often their offspring live into adulthood. For three years, from 2021 through 2023, Lackmann and his team studied the recreational exploitation (bowfishing, spearfishing, hook-and-line angling) of the species, and analyzed the bigmouth buffalo migration in and around Rice Lake National Wildlife Refuge, near McGregor, Minnesota. 

Results of the study include:

  • Discovery of one of the oldest known populations of vertebrate (median age of 79 years as of 2024)
  • A more than 60-year generation gap since the last major recruitment event occurred in this population, again exposing the stark vulnerability of bigmouth buffalo in Minnesota.
  • Confirmation that fish are successfully migrating and breeding, but the young are not surviving, likely due to the predator gauntlet they face on their way to adulthood.
  • Highlights the unique management challenges of bigmouth buffalo, including highly variable spawning durations year to year, and the need to protect adults as they grow and invest disproportionately more into reproduction.

Lackmann and Clark have studied buffalofishes before, and their research from 2019 went so far as to extend the previously thought maximum age of bigmouth buffalo from around 25 years of age, to more than 100 years of age through improved aging techniques. Lackmann et al.’s subsequent bigmouth buffalo studies in North Dakota (2021) and Canada (2023) documented environmental conditions related to their sporadic recruitment success, and his team’s 2023 study published in Scientific Reports found the second genus of animal ever for which three or more species (buffalofishes) have known lifespans greater than 100 years.

“No one's really looked at the spawning phenology of bigmouth buffalo before,” said Lackmann.

Over the course of the Rice Lake study, he and his team examined nearly 400 adult fish, taking measurements of each fish’s length and weight, whether it had spawned, its physical features, and age. Researchers were able to conclude that water control measures established in 1953 were correlated with a reduced likelihood of later generations, and of the 390 fish studied, only one was from a hatch-year after 1971. The study also revealed bigmouth buffalo were successfully reproducing, but by mid‐to‐late summer, the young were conspicuously absent, having likely succumbed to predation by northern pike and other predators. 

“We have found that more than 95 percent of the current population hatched prior to the 1960s,” said Lackmann. With that much of a gap, it's surprising that the buffalofish have survived for generations. But, according to Lackmann, it speaks to the amazing attributes of these fish. “This species evolved to have a long lifespan for an adaptive reason: to bridge these long gaps that can naturally occur.”

During the 1970s, the bigmouth buffalo was recorded as declining in Canada, Minnesota, and North Dakota and became a protected species in Canada. In the USA, population declines are exacerbated by wasteful recreational bowfishing, lack of fisheries management, and overall lack of knowledge. 

For Lackmann, this study further underscores the importance of implementing basic principles of fisheries management to protect bigmouth buffalo and other native species. Lackmann acknowledges that steps are currently underway to protect native fishes in the state of Minnesota, such as the “No Junk Fish Bill” that became law this spring, but he says there remains much work to be done in practice. For example, unlimited exploitation across the entire year remains open on bigmouth buffalo throughout Minnesota as of September 2024.

“There is 50-year recruitment failure for bigmouth buffalo in this system, even though we know that they're migrating and spawning annually. This is something that's completely unparalleled in the animal kingdom as far as we know, for a species to be going so long without successfully having another generation,” said Lackmann. “When you couple that with the current, unlimited and unregulated nature of their exploitation that's been increasing, especially in the past 10 years with the rise of bowfishing, there is extreme concern for the long-term sustainability of this species.”

Multiple lines of evidence indicate that the long‐lived bigmouth buffalo is vulnerable, that a precautionary approach is immediately needed, and that the unlimited and unregulated kill‐fishery be closed. Lackmann et. al.

In addition to Lackmann and Clark from the University of Minnesota Duluth, the study was in collaboration with the Aitkin County Soil and Water Conservation District, the United States Fish and Wildlife Service, and North Dakota State University.

 

 

 

 

 

Think simpler, flow faster


Researchers use deep learning to accelerate solution of Navier-Stokes equations for fluid dynamics problems

Peer-Reviewed Publication

Intelligent Computing

Solutions generated by model B3 tested with circular obstacles 

image: 

Contour plots (A, C, E, G) compare the input conditions, traditional finite difference method solutions, and the solutions generated by model B3, the most advanced model in the study. Velocity profiles (B, D, F, H) display detailed velocity information at specific cross-sections of the simulation domain.

view more 

Credit: SHEN WANG ET AL.




Analyzing and simulating fluid flow is a challenging mathematical problem that impacts various scenarios, including video game engines, ocean current modeling and hurricane forecasting. The core of this challenge lies in solving the Navier–Stokes equations, a set of classical equations that describe fluid dynamics. Recently, deep learning has emerged as a powerful tool to accelerate equation solving. Using this technique, a team designed a novel approach that can provide accurate solutions 1,000 times faster than traditional equation solvers. The team’s study was published June 26 in Intelligent Computing, a Science Partner Journal.

The team tested their approach on a three-variable lid-driven cavity flow problem in a large 512 × 512 computational domain. In the experiment, conducted on a consumer desktop system with an Intel Core i5 8400 processor, their method achieved inference latencies of just 7 milliseconds per input, a great improvement compared to the 10 seconds required by traditional finite difference methods.

Apart from being swift, the new deep learning approach is also low-cost and highly adaptable, thus could be used to make real-time predictions on everyday digital devices. It integrates the efficiency of supervised learning techniques with the necessary physics of traditional methods.

Although other supervised learning models can rapidly simulate and predict the closest numerical solutions to the Navier–Stokes equations, their performance is constrained by the labeled training data, which could lack the size, diversity and fundamental physical information needed to solve the equations.

To work around data-driven limitations and reduce computation load, the team trained a series of models stage by stage in a weakly supervised way. Initially, only a minimal amount of pre-computed “warm-up” data was used to facilitate model initialization. This allowed the base models to quickly adapt to the fundamental dynamics of fluid flow before progressing to more complex scenarios and eliminated the need for extensive labeled datasets.

All models are based on a convolutional U-Net architecture, which the team customized for complex fluid dynamics problems. As a modified autoencoder, the U-Net consists of an encoder that compresses the input data into compact representations, and a decoder that reconstructs this data back into high-resolution outputs. The encoder and decoder are connected through skip connections, which help preserve important features and improve the quality of the outputs.

To ensure the outputs adhere to the necessary constraints, the team also developed a custom loss function that incorporates both data-driven and physics-informed components.

Like traditional methods, the team's approach uses a 2D matrix to represent the computational domain, which sets the determining constraints of the fluid dynamics problems. The constraints include geometric constraints such as the size and shape of the domain, physical constraints such as the physical features of the flow and applicable physical laws, and boundary conditions that define the problems mathematically. This format allows unknown variables to be directly integrated into the constraints as part of the input data so that the trained models can handle various boundary conditions and geometries, including unseen complicated cases.