Neural network trained on 20 years of Japan seismic data finds 3.3 times more earthquakes
A new deep-learning phase picker called PhaseNeXt, trained on 25 million JMA waveforms, detected roughly 3.3 times more events than ...
A new deep-learning phase picker called PhaseNeXt, trained on 25 million JMA waveforms, detected roughly 3.3 times more events than ...
Anesthesiology researchers argue that AI in perioperative care must be human-centered, warning that most models lack prospective validation and real-world ...
A multicenter study combined CT-derived radiomic features with clinical data in an XGBoost model that predicted outcomes after aneurysmal subarachnoid ...
The new OPCNet neural network fits highly oscillatory data by learning the dynamics of a linear ODE and fitting the ...
Simulations of the Yellow River delta front show that brief artificial water-sediment regulation pulses, covering only about 5.5 percent of ...
Researchers trained an XGBoost machine learning model to estimate the residual tensile strength of artificially aged silk textiles from nondestructive ...
Hourly smart meter readings can now reveal far more than a building's total electricity consumption. Researchers have developed COF-Tool, an ...
An unsupervised machine learning analysis of 452,020 Colombian Saber Pro exam records identified eight distinct student profiles spanning a 69-point ...
Researchers in Cameroon built and tested a machine learning model that predicts antiretroviral resistance from routine clinical data, with XGBoost ...
Researchers constructed a monthly Manufacturing Economic Policy Uncertainty index for the United States from 1985 to 2025 using machine learning ...
© 2025 Scienmag - Science Magazine
© 2025 Scienmag - Science Magazine