Physics-informed recurrent network reaches 81.2% validation ROC-AUC in Mount Umyeon case study
A Mount Umyeon case study found that a physics-informed recurrent network achieved an 81.20% validation ROC-AUC for annual landslide peak ...
Tag: ROC–AUC
Machine Learning Outperforms Expert Weighting in Mapping Landslide Risk in India’s Western Ghats
A new study in Kerala's Western Ghats shows a Random Forest machine learning model, validated with an AUC of 0.99, ...
Fuzzy Logic Outperforms AI in New South Africa Landslide Risk Maps
A new GIS-based study in South Africa's Bushveld Igneous Complex found that Fuzzy Logic modelling outperformed both expert-driven AHP and ...
Scientists map landslide danger along a lifeline highway in the Indian Himalaya
A new AHP-based landslide susceptibility map of the Solan-Shimla highway in Himachal Pradesh identifies the most dangerous slopes along a ...
Gossip Meets Federation: Teaching AI to Spot Breast Cancer Without Sharing Patient Data
A new study compares federated averaging, decentralized gossip learning, and a hybrid of the two for classifying invasive ductal carcinoma ...
Satellite-Derived River Networks Sharpen AHP Flood Hazard Maps in Iran
A new study shows that replacing conventional river networks with satellite-derived data significantly improves the accuracy of AHP-based flood hazard ...
Simple Statistical Model Outperforms Expert Judgment in Mapping Deadly Landslide Risk in Northern Pakistan
A new comparative study of the Sheringal–Kumrat Road in Upper Dir, Pakistan, shows a simple statistical index model outperforming expert-based ...
-
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!