Physics-trained autoencoder tidies weather data but cannot beat raw inputs for evapotranspiration
A physics-regularized autoencoder cut dew-point inconsistency in reconstructed Delhi weather data by 87 percent, yet still could not beat XGBoost ...
Tag: Machine learning
AI reads everyday health questionnaires to flag Parkinson’s disease
A language-model-based AI called Quest2Dx screens for Parkinson's disease using self-reported health questionnaires, achieving AUROCs up to 0.977 and transferring ...
Architects and machines are becoming creative partners, not rivals
A new editorial in Architectural Intelligence argues that architecture is shifting from technology as a passive tool to a symbiotic ...
Ordered platinum intermetallics push fuel cell catalysts from binary alloys to high-entropy designs
A new review traces how long-range ordered platinum intermetallics, from binary PtCo to five-element high-entropy systems, deliver higher activity and ...
AI drug discovery tools dominated early-stage pharma research after COVID-19, review finds
A systematic review of 57 studies finds that AI-enabled Pharma 4.0 tools after COVID-19 concentrated on early-stage drug discovery metrics, ...
Random Forest Model Predicts Qanat Water Flow in Iranian Watershed
A study in Water Resources Management found that a random forest model achieved the lowest prediction error for qanat flowrate ...
Two-Stage Text Augmentation and Dual-Expert AI Model Reaches 98.5% Accuracy on Imbalanced Twitter Sentiment Data
A dual-expert framework combining paraphrase-based augmentation and aspect tokenization reached 98.5% accuracy on the imbalanced Twitter US-Airline Sentiment dataset, outperforming ...
Filler type barely moves the needle on ultra-high-performance concrete strength, database study finds
A database analysis of 2073 UHPC mixtures from 165 publications finds that filler type and dosage have only small associations ...
MRI Tract Patterns Sort ALS Patients into Three Subtypes Linked to Disease Severity
A diffusion MRI analysis grouped 73 ALS patients into three white matter subtypes whose imaging-derived disease stages correlated with clinical ...
CT radiomics model predicts which ureteral stones will pass without surgery
A machine learning model combining CT radiomics with clinical variables predicted spontaneous ureteral stone passage within four weeks with an ...
-
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!