Showing 20 articles starting at article 41
< Previous 20 articles Next 20 articles >
Categories: Ecology: Research, Mathematics: Modeling
Published Are AI-chatbots suitable for hospitals?



Large language models may pass medical exams with flying colors but using them for diagnoses would currently be grossly negligent. Medical chatbots make hasty diagnoses, do not adhere to guidelines, and would put patients' lives at risk. A team has systematically investigated whether this form of artificial intelligence (AI) would be suitable for everyday clinical practice. Despite the current shortcomings, the researchers see potential in the technology. They have published a method that can be used to test the reliability of future medical chatbots.
Published Scientists use AI to predict a wildfire's next move



Researchers have developed a new model that combines generative AI and satellite data to accurately forecast wildfire spread.
Published The most endangered fish are the least studied



The most threatened reef fishes are also the most overlooked by scientists and the general public. Scientists measured the level of human interest in 2,408 species of marine reef fish and found that the attention of the scientific community is attracted by the commercial value more than the ecological value of the fishes. The public, on the other hand, is primarily influenced by the aesthetic characteristics of certain species, such as the red lionfish (Pterois volitans) and the mandarinfish (Synchiropus splendidus).
Published Reef pest feasts on 'sea sawdust'



Researchers have uncovered an under the sea phenomenon where coral-destroying crown-of-thorns starfish larvae have been feasting on blue-green algae bacteria known as 'sea sawdust'.
Published Discovery of a hybrid lineage offers clues to how trees adapt to climate change



The discovery of a hybrid population of poplar trees in western Wyoming has provided insight into how natural hybridization informs the evolution of many plant species, according to researchers. They also said their discovery suggests that genetic exchange between species may be critical for adaptation to environmental change.
Published Logged forests can still have ecological value -- if not pushed too far



Researchers have analysed data from 127 studies to reveal 'thresholds' for when logged rainforests lose the ability to sustain themselves. The results could widen the scope of which forests are considered 'worth' conserving, but also show how much logging degrades forests beyond the point of no return.
Published Scientists use machine learning to predict diversity of tree species in forests



Researchers used machine learning to generate highly detailed maps of over 100 million individual trees from 24 sites across the U.S. These maps provide information about individual tree species and conditions, which can greatly aid conservation efforts and other ecological projects.
Published How to assess a general-purpose AI model's reliability before it's deployed



A new technique estimates the reliability of a self-supervised foundation model, like those that power ChatGPT, without the need to know what task that model will be deployed on later.
Published Researchers find that frogs can quickly increase their tolerance to pesticides



Although there is a large body of research on pests evolving tolerances for the pesticides meant to destroy them, there have been considerably fewer studies on how non-target animals in these ecosystems may do the same.
Published Unlocking the mystery of preexisting drug resistance: New study sheds light on cancer evolution



The evolution of resistance to diseases, from infectious illnesses to cancers, poses a formidable challenge. Despite the expectation that resistance-conferring mutations would dwindle in the absence of treatment due to a reduced growth rate, preexisting resistance is pervasive across diseases that evolve -- like cancer and pathogens -- defying conventional wisdom.
Published A new neural network makes decisions like a human would



Researchers are training neural networks to make decisions more like humans would. This science of human decision-making is only just being applied to machine learning, but developing a neural network even closer to the actual human brain may make it more reliable, according to the researchers.
Published History shows that humans are good for biodiversity... sometimes



Humans have been an important driver of vegetation change over thousands of years, and, in some places, had positive impacts on biodiversity, according to a new study.
Published Loss of oxygen in lakes and oceans a major threat to ecosystems, society, and planet



Oxygen is a fundamental requirement of life, and the loss of oxygen in water, referred to as aquatic deoxygenation, is a threat to life at all levels. In fact, researchers describe how ongoing deoxygenation presents a major threat to the stability of the planet as a whole.
Published Study examines urban forests across the United States



Tree-planting campaigns have been underway in the United States, especially in cities, as part of climate mitigation efforts given the many environmental benefits of urban forests. But a new study finds that some areas within urban forests in the U.S., may be more capable than trees growing around city home lawns in adapting to a warmer climate.
Published When to trust an AI model



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 Artificial intelligence speeds up heart scans, saving doctors' time, and could lead to better treatment for heart conditions



Researchers have developed a groundbreaking method for analysing heart MRI scans with the help of artificial intelligence, which could save valuable time and resources, as well as improve care for patients.
Published Mapping the world's fungi from air samples



Researchers have found that the key to a quick and cost-effective mapping of biodiversity has been right in front of our eyes all along, but at the same time invisible -- i.e., in the air that surrounds us.
Published Researchers customize AI tools for digital pathology



Scientists developed and tested new artificial intelligence (AI) tools tailored to digital pathology--a rapidly growing field that uses high-resolution digital images created from tissue samples to help diagnose disease and guide treatment.
Published Researchers introduce generative AI for databases



Researchers have developed an easy-to-use tool that enables someone to perform complicated statistical analyses on tabular data using just a few keystrokes. Their method combines probabilistic AI models with the programming language SQL to provide faster and more accurate results than other methods.
Published Global database reveals large gaps in our knowledge of four-footed animals



Researchers developed TetrapodTraits -- a global database of animals with four feet -- which can now be applied for better ecology, evolution and conservation research.