Satellites Reveal China’s Urban Waters Are Shrinking and Breaking Apart
A 24-year satellite analysis of the Beijing–Tianjin–Hebei region shows urban blue spaces shrinking and fragmenting, with population and vegetation factors ...
Tag: XGBoost
Cell Shape and Position Predict Fate in a Developing Epithelium
By tracking thousands of cells in live Xenopus embryos and applying machine learning, researchers show that cell shape, position, and ...
Machine Learning Predicts How Earthquake-Damaged Concrete Columns Will Behave Next
Researchers built an XGBoost-based surrogate model, trained on over a thousand simulated column tests, that predicts the residual hysteretic behavior ...
Smartwatch Data Guard: AutoML Spots Dangerous Vitals Anomalies With 98.9% Accuracy
Researchers at India's National Institutes of Technology used the TPOT AutoML framework to detect anomalies in smartwatch-generated vital signs over ...
Where Fat Settles May Shape Polycystic Ovary Syndrome Risk, Global Study Finds
A multi-modal study integrating global burden data, Mendelian randomization, and machine learning finds genetic and clinical evidence that regional fat ...
AI Model Flags Gastric Cancer in Patients With Psychological Symptoms
Researchers in Qingdao developed an interpretable XGBoost model that distinguishes gastric cancer from intestinal metaplasia in patients with psychological symptoms ...
Hidden Arsenic Hotspots Mapped in Karst Farmland With AI and Geostatistics
A study of 144 sites in Zhijin County, southwestern China, combines kriging, Geodetector, and explainable machine learning to map soil ...
Self-Driving Robot Reads Tomato Seedling Health With Light Alone
Chinese researchers have built an autonomous greenhouse robot that navigates seedling aisles with LiDAR, verifies leaf coverage in real time, ...
Brain Waves Reveal How Children With and Without Autism Process Emotion Differently
A new EEG study finds that children with autism show reduced frontal beta activity, heightened temporo-occipital delta activity, and lower ...
Machine Learning Spots Earthquake Fingerprints in Japan’s Ionosphere Before the Ground Shakes
A new study shows that a genetically optimized XGBoost model most accurately predicted ionospheric total electron content variations during Japan's ...
-
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!