Showing 20 articles starting at article 1
Categories: Geoscience: Landslides, Mathematics: Statistics
Published Artificial intelligence improves lung cancer diagnosis
(via sciencedaily.com) Original source A team of researchers has created a digital pathology platform based on artificial intelligence. The platform uses new algorithms developed by the team and enables fully automated analysis of tissue sections from lung cancer patients. The platform makes it possible to analyze digitized tissue samples on the computer for lung tumors more quickly and accurately than before.
Published New study reveals devastating power and colossal extent of a giant underwater avalanche off the Moroccan coast
(via sciencedaily.com) Original source New research has revealed how an underwater avalanche grew more than 100 times in size causing a massive trail of destruction as it traveled 2000km across the Atlantic Ocean seafloor off the North West coast of Africa. Researchers provide an unprecedented insight into the scale, force and impact of one of nature's mysterious phenomena, underwater avalanches.
Published Urban street networks, building density shape severity of floods
(via sciencedaily.com) Original source The design of streets and layout of buildings have an impact on a city's resilience in the face of increasingly severe floods brought on by climate change. Researchers look at buildings and other urban structures as physicists consider elements in complex material systems. With this insight, the researchers have developed a new approach to urban flood modelling and found their results helpful in analyzing city-to-city variations in flood risk globally.
Published Research shows statistical analysis can detect when ChatGPT is used to cheat on multiple-choice chemistry exams
(via sciencedaily.com) Original source Research revealed how the use of ChatGPT to cheat on general chemistry multiple-choice exams can be detected through specific statistical methods.
Published Sichuan Province earthquake offers lessons for landslide prediction from GNSS observations
(via sciencedaily.com) Original source Using data collected from a 2022 magnitude 6.8 earthquake in Luding County in China's Sichuan Province, researchers tested whether Global Navigation Satellite System (GNSS) observations could be used for rapid prediction of earthquake-triggered landslides.
Published Modern behavior explains prehistoric economies
(via sciencedaily.com) Original source What if the 'Market Economy' always existed? Archaeologists tried to answer this question by researching how much Bronze Age people used to spend to sustain their daily lives. Their results show that, starting at least 3,500 years ago, the spending habits of prehistoric Europeans were not substantially different from what they are today.
Published When allocating scarce resources with AI, randomization can improve fairness
(via sciencedaily.com) Original source Researchers argue that, in some situations where machine-learning models are used to allocate scarce resources or opportunities, randomizing decisions in a structured way may lead to fairer outcomes.
Published When to trust an AI model
(via sciencedaily.com) Original source A new technique enables huge machine-learning models to efficiently generate more accurate quantifications of their uncertainty about certain predictions. This could help practitioners determine whether to trust the model when it is deployed in real-world settings.
Published 2023 Rolling Hills Estates landslide likely began the winter before
(via sciencedaily.com) Original source Landslides triggered by intense rainfall can sometimes be predicted along with incoming storms, but dry-season landslides often take people by surprise. The July 2023 Rolling Hills Estates landslide that destroyed 12 homes seemed to come out of nowhere, but new research shows it began as early as December 2022. Researchers are developing a database that will enable scientists to plug in new data to monitor potential landslides in real time and possibly predict them.
Published Diagnosing different forms of dementia now possible using artificial intelligence
(via sciencedaily.com) Original source Ten million new cases of dementia are diagnosed each year but the presence of different dementia forms and overlapping symptoms can complicate diagnosis and delivery of effective treatments. Now researchers have developed an AI tool that can diagnose ten different types of dementia such as vascular dementia, Lewy body dementia, and frontotemporal dementia, even if they co-occur.
Published Balancing act: Novel wearable sensors and AI transform balance assessment
(via sciencedaily.com) Original source Traditional methods to assess balance often suffer from subjectivity, aren't comprehensive enough and can't be administered remotely. They also are expensive and require specialized equipment and clinical expertise. Using wearable sensors and advanced machine learning algorithms, researchers offer a practical and cost-effective solution for capturing detailed movement data, essential for balance analysis. This approach is more accessible and can be administered remotely, which could have significant implications for health care, rehabilitation, sports science or other fields where balance assessment is important.
Published New machine learning method can better predict spine surgery outcomes
(via sciencedaily.com) Original source Researchers combine AI and mobile health to predict recovery from lumbar spine surgery.
Published High groundwater depletion risk in South Korea in 2080s
(via sciencedaily.com) Original source Team utilizes advanced statistical techniques to project the future groundwater depletion risk.
Published Improving statistical methods to protect wildlife populations
(via sciencedaily.com) Original source In human populations, it is relatively easy to calculate demographic trends and make projections of the future if data on basic processes such as births and immigration is known. The data, given by individuals, can be also death and emigration, which subtract. In the wild, on the other hand, understanding the processes that determine wildlife demographic patterns is a highly complex challenge for the scientific community. Although a wide range of methods are now available to estimate births and deaths in wildlife, quantifying emigration and immigration has historically been difficult or impossible in many populations of interest, particularly in the case of threatened species.
Published Subduction zone splay faults compound hazards of great earthquakes
(via sciencedaily.com) Original source Groundbreaking research has provided new insight into the tectonic plate shifts that create some of the Earth's largest earthquakes and tsunamis.
Published Scientists use generative AI to answer complex questions in physics
(via sciencedaily.com) Original source Researchers used generative AI to develop a physics-informed technique to classify phase transitions in materials or physical systems that is much more efficient than existing machine-learning approaches.
Published Simulating diffusion using 'kinosons' and machine learning
(via sciencedaily.com) Original source Researchers have recast diffusion in multicomponent alloys as a sum of individual contributions, called 'kinosons.' Using machine learning to compute the statistical distribution of the individual contributions, they were able to model the alloy and calculate its diffusivity orders of magnitude more efficiently than computing whole trajectories.
Published Artificial intelligence tool detects male-female-related differences in brain structure
(via sciencedaily.com) Original source Artificial intelligence (AI) computer programs that process MRI results show differences in how the brains of men and women are organized at a cellular level, a new study shows. These variations were spotted in white matter, tissue primarily located in the human brain's innermost layer, which fosters communication between regions.
Published Century of statistical ecology reviewed
(via sciencedaily.com) Original source A special review examines highly-cited papers in statistical ecology. The review, which covers a century of research, details how models and concepts have evolved alongside increasing computational power.
Published New work extends the thermodynamic theory of computation
(via sciencedaily.com) Original source Physicists and computer scientists have recently expanded the modern theory of the thermodynamics of computation. By combining approaches from statistical physics and computer science, the researchers introduce mathematical equations that reveal the minimum and maximum predicted energy cost of computational processes that depend on randomness, which is a powerful tool in modern computers.