Browse Articles
Discover research articles across all indexed journals
Optimizing equivalent testing for scaled projectile penetration into multilayer concrete targets with fuse overload via layer-by-layer chasing-catching methodology
Distinctive Kinetic Signatures of Surface Segregation Processes in Bimetallic Nanoparticle Catalysis
Machine learning analysis of greenhouse gas sources impacting Africa’s food security nexus
Basicity–Controlled C–H Bond Activation by a Structurally Characterized Ni(III)–Hydroxo Complex
Unraveling the luminescence secrets of turquoise nucleus cultivated pearls
DNA Framework Nanoruler-Directed Surface Fluorescence Enhancement as a Sensing Platform for MicroRNA Detection
Distinguishing the flow of airborne microorganisms along with environmental conditions and their influence on historic heritage buildings
Emerging Complex Behavior Driven by Self-Organization: Dynamic Covalent Libraries of Acylhydrazones in Water
Machine learning approaches for predicting the structural number of flexible pavements based on subgrade soil properties
Abstract This study presents a machine learning approach to predict the structural number of flexible pavements using subgrade soil properties and environmental conditions. Four algorithms were evaluated, including random forest, extreme gradient boosting, gradient boosting, and K nearest neighbors. The dataset was prepared by converting resilient modulus values into structural numbers using the bisection method applied to the American Association of State Highway and Transportation Officials 1993 design equation. Input variables included moisture content, dry unit weight, weighted plasticity index, and the number of freeze and thaw cycles. Each model was trained and tested using standard performance metrics. Gradient boosting achieved the highest accuracy with a determination coefficient of 0.917. Moisture content was identified as the most significant predictor in most models. The findings demonstrate that machine learning models can accurately predict pavement thickness requirements based on readily available soil and environmental data. This approach reduces reliance on expensive and time-consuming laboratory tests and provides a practical and efficient tool for pavement design. This study highlights the potential of machine learning models in enhancing pavement design by accurately predicting structural performance parameters based on soil and environmental factors.
After you left
Super-Resolution Imaging of Semiconductor Nanopatterns Using the Non-Bridging-Oxygen-Hole-Center-Based Photoluminescence Enhancement Effect
Traces of dipnoan fish document the earliest adaptations of vertebrates to move on land
Lighting Up Healing: Green Light-Driven Dual Gasotransmitters Release against MRSA Wound Infections
A simulation approach to assessing vegetation configuration effects on thermal comfort in cold region pocket parks
Abstract Pocket parks, play a crucial role in enhancing residents’ thermal comfort and promoting ecological sustainability. Despite their significance, thermal comfort in cold-region spaces remains underexplored, especially vegetation impacts. This study investigates the impact of vegetation configuration on cold-region pocket park thermal environments, using Changchun as a case study via field measurements and ENVI-met simulations. Through the integration of Mean Thermal Sensation Vote (MTSV) and Physiological Equivalent Temperature (PET) indices, the study established the thermal comfort range for Changchun during transitional seasons as 16.69–23.63 ℃, with a thermal neutral temperature of 20.16 ℃. The study developed 27 experimental scenarios to analyze vegetation parameters—tree coverage, Leaf Area Density (LAD), and green patterns. Orthogonal design analysis of simulation results identified the hierarchical impact on thermal comfort: tree coverage > LAD > green patterns. The study proposes three optimal vegetation design strategies for cold-region pocket parks: (1) maintain tree coverage above 50% (ideally 70%); (2) select tree species to complement coverage with LAD of 1.2–1.4; (3) adopt tree-grass combined green patterns for green space layouts. This research presents novel insights and practical guidelines for designing vegetation in micro-scale green spaces in cold-region cities, advocating a sustainable model integrating ecological and social well-being.