Tag: Machine learning

Researchers in Ecuador found that using wind speeds from upper atmospheric levels of the ERA5 reanalysis, rather than conventional near-ground ...

A new 200,000-question benchmark from Carnegie Mellon University reveals that leading vision-language models perform at random chance when interpreting engineering ...

A new PLOS Complex Systems paper lays out a unifying framework for autonomous agentic AI while cataloguing the hallucination, scalability, ...

A systematic review of 147 studies finds that accurate forest carbon accounting depends on integrating field measurements, remote sensing, and ...

Researchers have developed CL3AN-GNN, a graph neural network that borrows curriculum learning from education to progressively disentangle features and boost ...

Researchers in Türkiye used an explainable machine learning framework combining XGBoost and SHAP to identify age and postpartum diseases as ...

A new machine-learning workflow predicts pore pressure in Jurassic carbonate reservoirs of Pakistan's Kohat Plateau without sonic logs, using calibrated ...

Researchers have developed a hybrid particle-filter and neural network framework that predicts lithium-ion battery remaining useful life with 99.41 percent ...

An international team has released a globally standardized archive of about eight million underwater images of plankton and detritus collected ...

A new evaluation of Google's GraphCast against 549 rain gauges in South Korea finds the AI weather model excels at ...