Showing 20 articles starting at article 121
< Previous 20 articles Next 20 articles >
Categories: Ecology: Research, Mathematics: Modeling
Published AI helps medical professionals read confusing EEGs to save lives
(via sciencedaily.com) Original source Researchers have developed an assistive machine learning model that greatly improves the ability of medical professionals to read the electroencephalography (EEG) charts of intensive care patients. Because EEG readings are the only method for knowing when unconscious patients are in danger of suffering a seizure or are having seizure-like events, the computational tool could help save thousands of lives each year.
Published Some species may tolerate climate change better than expected
(via sciencedaily.com) Original source A new model reassesses the proportion of terrestrial and marine species threatened with extinction by climate change. While the forecasts of traditional models estimate that the diversity of terrestrial species in tropical areas could decrease by 54% between now and 2041-2060, this model is more moderate, predicting a decrease of 39%. Nevertheless, this proportion remains alarming and confirms the importance of taking urgent measures to mitigate climate change and its impact on biodiversity.
Published Marine Protected Areas don't line up with core habitats of rare migratory fish, finds new research
(via sciencedaily.com) Original source 62% of Marine Protected Areas (MPAs) designated to protect rare migratory fish species are outside of their core habitats, according to a new modeling study.
Published Tracking animals without markers in the wild
(via sciencedaily.com) Original source Researchers developed a computer vision framework for posture estimation and identity tracking which they can use in indoor environments as well as in the wild. They have thus taken an important step towards markerless tracking of animals in the wild using computer vision and machine learning.
Published Research finds improving AI large language models helps better align with human brain activity
(via sciencedaily.com) Original source With generative artificial intelligence (GenAI) transforming the social interaction landscape in recent years, large language models (LLMs), which use deep-learning algorithms to train GenAI platforms to process language, have been put in the spotlight. A recent study found that LLMs perform more like the human brain when being trained in more similar ways as humans process language, which has brought important insights to brain studies and the development of AI models.
Published Global activity of seafloor biodiversity mapped
(via sciencedaily.com) Original source A team of scientists has used artificial intelligence (AI) to map the activities of seafloor invertebrate animals, such as worms, clams and shrimps, across all the oceans of the world.
Published Future climate impacts put whale diet at risk
(via sciencedaily.com) Original source A new study predicts future climate change impacts could disrupt the krill-heavy diet that humpback whales in the southern hemisphere consume.
Published Smoke covered 70% of California during biggest wildfire years
(via sciencedaily.com) Original source As much as 70 percent of California was covered by wildfire smoke during parts of 2020 and 2021, according to a new study.
Published Conservation of nature's strongholds needed to halt biodiversity loss
(via sciencedaily.com) Original source To achieve global biodiversity targets, conservationists and governments must prioritize the establishment and effective management of large, interconnected protected areas with high ecological integrity, researchers argue in a new essay.
Published Regional differences in bird diversity in agroforestry systems
(via sciencedaily.com) Original source The diversity and ecological functionality of bird communities in tropical agroforestry systems are shaped by the surrounding landscape, in particular the extent and composition of the forest.
Published How AI helps programming a quantum computer
(via sciencedaily.com) Original source Researchers have unveiled a novel method to prepare quantum operations on a given quantum computer, using a machine learning generative model to find the appropriate sequence of quantum gates to execute a quantum operation. The study marks a significant step forward in unleashing the full extent of quantum computing.
Published A rise in sea urchins and related damage to kelp forests impacts Oregon's gray whales and their food
(via sciencedaily.com) Original source A recent boom in the purple sea urchin population off the southern Oregon Coast appears to have had an indirect and negative impact on the gray whales that usually forage in the region, a new study shows.
Published Digging up good news for microbial studies
(via sciencedaily.com) Original source Findings indicate that soil stored under refrigerated or air-dried conditions can still retain the needed information for understanding microbial community composition and structure for many years.
Published Large language models can't effectively recognize users' motivation, but can support behavior change for those ready to act
(via sciencedaily.com) Original source Large language model-based chatbots can't effectively recognize users' motivation when they are hesitant about making healthy behavior changes, but they can support those who are committed to take action, say researchers.
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 Researchers wrestle with accuracy of AI technology used to create new drug candidates
(via sciencedaily.com) Original source Researchers have determined that a protein prediction technology can yield accurate results in the hunt to efficiently find the best possible drug candidates for many conditions.
Published From roots to resilience: investigating the vital role of microbes in coastal plant health
(via sciencedaily.com) Original source Understanding how salt marsh grass stays healthy is of crucial ecological importance, and studying the ways bacteria interact with these plants is key. Thanks to recent advances in genomic technology, biologists have begun to reveal never-before-seen ecological processes.
Published Wavefunction matching for solving quantum many-body problems
(via sciencedaily.com) Original source Strongly interacting systems play an important role in quantum physics and quantum chemistry. Stochastic methods such as Monte Carlo simulations are a proven method for investigating such systems. However, these methods reach their limits when so-called sign oscillations occur. This problem has now been solved using the new method of wavefunction matching.
Published Access to gardens and citizen science helps encourage conservation among children, study shows
(via sciencedaily.com) Original source Access to gardens and citizen science projects at school can help promote pro-conservation behaviour among pupils, a new study shows.
Published Climate change is most prominent threat to pollinators
(via sciencedaily.com) Original source A new article has found that climate change is the most prominent threat to pollinators -- such as bumblebees, wasps, and butterflies -- who are essential for biodiversity conservation, crop yields and food security. The research suggests that many of the threats to pollinators result from human activities.