Wuhan ozone variability modeled with interpretable machine learning, 2019–2025
An interpretable machine-learning study of hourly ozone at one Wuhan monitoring site from 2019–2025 found strong short-term persistence and a ...
Tag: XGBoost
Explainable AI predicts strength of hybrid-reinforced welded aluminum joints
An optimized XGBoost model predicted the tensile strength of CNT–Si₃N₄-reinforced friction-welded aluminum joints from 25 experiments, while feature ablation showed ...
Aquila-optimized XGBoost improves reinforced subgrade strength predictions
An Aquila-optimized XGBoost model achieved an R² of 0.980 for predicting soaked CBR in 90 geosynthetic-reinforced subgrade tests, outperforming three ...
AI Model Flags Which Mild Stroke Patients Won’t Fully Recover After Clot-Busting Drugs
Researchers in China built an explainable XGBoost model using six routine admission variables to predict which mild stroke patients will ...
AI Model Predicts Lung Cancer Spread Using Routine PET Scans and Blood Tests
An interpretable machine-learning study shows that four routine clinical and PET/CT features can predict lymph node metastasis in lung cancer ...
Machine learning maps landslide danger across Ethiopia’s rift valley
A team of Ethiopian researchers tested four machine learning models against 770 mapped landslides in the Main Ethiopian Rift, finding ...
New 1 km global groundwater dataset brings hidden aquifer changes into view
A new global monthly groundwater dataset at 1 km resolution for 2002-2020 combines GRACE satellite gravity, environmental predictors and machine ...
Adaptive AI Framework Sharpens Intrusion Detection in Imbalanced Network Traffic
Researchers at VIT University propose AFI-ID, an intrusion detection framework that unifies adaptive feature selection with attention-based ensemble fusion, achieving ...
One EEG Electrode May Be Enough to Detect VR Motion Sickness
Researchers used SHAP-based explainable AI to identify a single EEG electrode and just seven features that detect virtual reality motion ...
Mapping Flood Danger to Thousands of Historic Buildings Along a Chinese River Basin
A new study combines hydrological simulation, machine learning and spatial statistics to rank flood risk for 5,482 historic buildings across ...
-
Mothers who receive childcare support from maternal grandparents show more parental warmth, finds NTU Singapore study
-
University of Seville Breaks 120-Year-Old Mystery, Revises a Key Einstein Concept
-
Bee body mass, pathogens and local climate influence heat tolerance
-
Researchers record first-ever images and data of a shark experiencing a boat strike
-
Groundbreaking Clinical Trial Reveals Lubiprostone Enhances Kidney Function
Embark on a thrilling journey of discovery with Scienmag.com—your ultimate source for cutting-edge breakthroughs. Immerse yourself in a world where curiosity knows no limits and tomorrow’s possibilities become today’s reality!