Tag: Machine learning

New research shows that coarse, smoothed labels in continental-scale AI mineral prospectivity maps artificially inflate model performance while erasing high-probability ...

A three-year benchmark in Indonesia's Sunda Strait shows deep learning models, especially a compact direct multi-step CNN-GRU, deliver the most ...

A foundation model-based AI system called WeedNet identifies 1,593 weed species with 91.02 percent accuracy and reaches 97.38 percent accuracy ...

A pilot study from the University of Bern shows that computational fluid dynamics built from routine CT angiography and ultrasound ...

A machine learning-guided search has produced a tungsten bronze oxide ceramic that combines a high dielectric constant, ultralow loss and ...

A new study comparing AI-based and physics-based weather forecasts finds both systematically underestimate heat-related mortality in Europe, but data-driven models ...

A new framework called VR-FraudNet forces large language models to propose structured fraud explanations that a fixed deterministic verifier must ...

A new review argues that fluoride health risk assessments focused solely on drinking water underestimate true exposure and proposes an ...

A new PLOS Water study finds that machine learning bias correction can transform flawed satellite rainfall and modelled river discharge ...

A new deep-learning method called VIMA converts tissue patches into numerical fingerprints and uses rigorous statistics to uncover disease-associated spatial ...