Results 201 to 210 of about 776,810 (287)

Uniaxial compressive strength prediction and ratio parameter optimization of titanium tailings composite backfill materials using intelligent hybrid models

Deep Underground Science and Engineering, EarlyView.
Based on the 90 datasets, ERT and four optimization algorithms were used to build four hybrid models to predict the UCS of the backfill body. The SMA‐ERT model was the most effective model, and it can reliably guide the design of the backfill ratio parameters. Abstract This study analyzed the feasibility of using titanium (Ti) tailings as a backfilling
Weijun Liu, Zida Liu, Zhixiang Liu
wiley   +1 more source

Decomposition of Shapley additive explanations for a stacking model

Communications for Statistical Applications and Methods
openaire   +1 more source

Probabilistic prediction of rate‐dependent rock strength using natural gradient boosting and Gaussian process regression

Deep Underground Science and Engineering, EarlyView.
Probabilistic natural gradient boosting and Gaussian process regression models accurately predict rate‐dependent rock strength across lithologies. Static strength and strain rate dominate, while geometric factors have minimal influence, enabling interpretable and uncertainty‐aware predictions for dynamic geomechanical applications. Abstract The dynamic
Hadi Fathipour‐Azar
wiley   +1 more source

Prediction model for postoperative pulmonary complications after thoracoscopic surgery with machine learning algorithms and SHapley Additive exPlanations. [PDF]

J Thorac Dis
Wang S, Lin Y, Shi H, Liang P, Luo Z, Kong J, Huang J, Cheng M, Zhang B, Wang Y, Kan H, Liang L, Xie W.   +12 more
europepmc   +1 more source

Explainable hybrid stacking ensemble method for hard rock pillar stability prediction and engineering applications

Deep Underground Science and Engineering, EarlyView.
This research proposes an interpretable hybrid stacking ensemble framework, optimized by the Sparrow Search Algorithm, to enhance hard rock pillar stability prediction. By integrating six machine learning models—k‐nearest neighbors, support vector machines, random forests, Gradient Boosting Decision Tree, eXtreme Gradient Boosting, and Light Gradient ...
Ning Wang, Guoyan Zhao, Meng Wang, Taraka Pattela   +3 more
wiley   +1 more source

From patterns to predictions: a framework for the spatial epidemiology of wildlife diseases

Ecography, EarlyView.
Wildlife diseases pose a significant threat to biodiversity conservation, public health, and livestock. Spatial epidemiology provides a robust framework to understand disease dynamics and guide policy and management. However, the rapid proliferation of spatial methods has largely occurred in isolation across disciplines, leaving the field without a ...
Cesar Herraiz, Pelayo Acevedo
wiley   +1 more source

Interpretable machine learning model for predicting myocardial injury in intensive care unit patients using SHapley Additive exPlanations analysis. [PDF]

Sci Prog
Liu X, Chen G, Hao C, An Y, Zhao H.
europepmc   +1 more source

Toward a Paradigm Shift in Low‐Temperature SCR Catalyst Design: Defect Engineering and Data‐Driven Integration

ENERGY &ENVIRONMENTAL MATERIALS, EarlyView.
This work systematically reviews the key factors influencing the performance of low‐temperature NH3‐SCR. The mechanism and challenges of defect engineering strategies, such as oxygen vacancies, heteroatom doping, crystal facet exposure, and surface reconstruction, in controlling both activity and selectivity were analyzed.
Rongrong Kan, Pinjing He, Fan Lü, Hua Zhang   +3 more
wiley   +1 more source

Shapley additive explanations based feature selection reveals CXCL14 as a key immune-related gene in predicting idiopathic pulmonary fibrosis. [PDF]

Front Med (Lausanne)
Chen B, Huan L, Lu J, Yuan J.
europepmc   +1 more source

Electronic Structure Modulation in Dopant‐Controlled Single‐Atom Graphene Catalysts for Efficient Hydrogen Evolution: A Machine Learning and First‐Principles Study

ENERGY &ENVIRONMENTAL MATERIALS, EarlyView.
First‐principles DFT calculations and machine learning analysis show that heteroatom doping of graphene (G) significantly enhances the stabilization of transition‐metal single atoms by strengthening metal–support interactions and increasing charge transfer. N‐doped G exhibits higher adsorption energies, lower d‐band centers, and shorter TM–G bonds than
Sajjad Ali, Pir Muhammad Ismail, Muhammad Humayun, Mohamed Bououdina   +3 more
wiley   +1 more source