LTPP data-based investigation on asphalt pavement performance using geospatial hot spot analysis and decision tree models

Zhang, Kun; Wang, Zhongren

doi:10.1016/j.ijtst.2022.06.007

Cited by 9 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GIS capabilities were employed to find highway sections that received multiple reconstructions over their planning prospect [136], apply geotechnical considerations in a highway layout [102], detect utility conflicts in railway projects prior to construction [38], prioritize maintenance plans [137], create a geo-enabled geometric design for highways, conduct environmental assessment of concrete mixes [138], and optimize construction site material distribution layout [139]. Studies also employed GIS for pavement performance analysis to investigate the impact of different factors such as precipitation, [140][141][142], mass movement susceptibility prediction [143], sustainability-based management [144], construction quality evaluation [27], functional road classification [145], and climate change risk assessment of critical infrastructure [146]. More innovative approaches engineered an integrated system of Augmented Reality (AR) and GIS to map subterranean utilities using mobile devices [147].…”

Section: Geospatial Analysis Tools For Project Planning (Geospatial A...mentioning

confidence: 99%

Civil Integrated Management (CIM) for Advanced Level Applications to Transportation Infrastructure: A State-of-the-Art Review

Taheri,

Sobanjo

2024

Infrastructures

View full text Add to dashboard Cite

The recent rise in the applications of advanced technologies in the sustainable design and construction of transportation infrastructure demands an appropriate medium for their integration and utilization. The relatively new concept of Civil Integrated Management (CIM) is such a medium; it enhances the development of digital twins for infrastructure and also embodies various practices and tools, including the collection, organization, and data-management techniques of digital data for transportation infrastructure projects. This paper presents a comprehensive analysis of advanced CIM tools and technologies and categorizes its findings into the following research topics: application of advanced surveying methods (Advanced Surveying); geospatial analysis tools for project planning (Geospatial Analysis); multidimensional virtual design models (nD Modeling); Integrated Geospatial and Building Information Modeling (GeoBIM); and transportation infrastructure maintenance and rehabilitation planning (Asset Management). Despite challenges such as modeling complexity, technology investment, and data security, the integration of GIS, BIM, and artificial intelligence within asset-management systems hold the potential to improve infrastructure’s structural integrity and long-term performance through automated monitoring, analysis, and predictive maintenance during its lifetime.

show abstract

Section: Geospatial Analysis Tools For Project Planning (Geospatial A...mentioning

confidence: 99%

Civil Integrated Management (CIM) for Advanced Level Applications to Transportation Infrastructure: A State-of-the-Art Review

Taheri,

Sobanjo

2024

Infrastructures

View full text Add to dashboard Cite

show abstract

“…It identifies highand low-value clusters of regional elements at different spatial locations by calculating the Getis-Ord G i * statistics for each element in the dataset. That is, it identifies the spatial distribution pattern of cold and hot spots in the study area [39] . The equation [40] is as follows:…”

Section: Original Function X Variable Y Variable Restrictions Meaning...mentioning

confidence: 99%

Spatial Agglomeration and Diffusion of Population Based on a Regional Density Function Approach: A Case Study of Shandong Province in China

Zhao,

Chen

2023

j. of geogr. res.

View full text Add to dashboard Cite

Population density functions have long been used to describe the spatial structure of regional population distributions. Several studies have been conducted to examine the population distribution in Shandong Province, China, but few have applied regional density functions to the analysis. Therefore, based on the 2000, 2010, and 2020 population censuses, this study used monocentric and polycentric regional density functions to study the characteristics of population agglomeration and diffusion in Shandong. This is followed by an in-depth discussion based on population growth rate data and hot- and cold-spot analyses. The results showed that the Shandong Province population was spatially unevenly distributed. Population growth rates were higher in urban centers and counties, with more significant changes in population size in the eastern coastal areas than in the inland areas. As verified in this study, the logarithmic form of the single-center regional density function R2 was greater than 0.8, which was in line with the population spatial structure of Shandong Province. During the study period, the estimated population density of the regional center and the absolute value of the regional population density gradient both increased, indicating a clear and increasing trend of centripetal agglomeration of regional centers over the study period. Overall, the R2 value of the multicenter region density function was higher than that of the single-center region density function. The polycentric regional density function showed that the population density gradient of some centers had a downward trend, which reflected the spatial development trend of outward diffusion in these centers. Meanwhile, the variation in the estimated population density and the population density gradient exhibited differences in the central population distribution patterns at different levels.

show abstract

“…A geospatial hotspot analysis using decision tree models suggested that fatigue cracking is highly correlated with truck traffic loads [17]. The present research study also considers the effect of truckloads to find their direct impact on asphalt cracking.…”

Section: Introductionmentioning

confidence: 96%

Ensemble Learning Approach for Developing Performance Models of Flexible Pavement

Taheri,

Sobanjo

2024

Infrastructures

View full text Add to dashboard Cite

This research utilizes the Long-Term Pavement Performance database, focusing on devel-oping a predictive model for flexible pavement performance in the Southern United States. Analyzing 367 pavement sections, this study investigates crucial factors influencing asphaltic concrete (AC) pavement deterioration, such as structural and material components, air voids, compaction density, temperature at laydown, traffic load, precipitation, and freeze–thaw cycles. The objective of this study is to develop a predictive machine learning model for AC pavement wheel path cracking (WpCrAr) and the age at which cracking initiates (WpCrAr) as performance indicators. This study thoroughly investigated three ensemble machine learning models, including random forest, extremely randomized trees (ETR), and extreme gradient boosting (XGBoost). It was observed that XGBoost, optimized using Bayesian methods, emerged as the most effective among the evaluated models, demonstrating good predictive accuracy, with an R2 of 0.79 for WpCrAr and 0.92 for AgeCrack and mean absolute errors of 1.07 and 0.74, respectively. The most important features influencing crack initiation and progression were identified, including equivalent single axle load (ESAL), pavement age, number of layers, precipitation, and freeze–thaw cycles. This paper also showed the impact of pavement material combinations for base and subgrade layers on the delay of crack initiation.

show abstract

LTPP data-based investigation on asphalt pavement performance using geospatial hot spot analysis and decision tree models

Cited by 9 publications

References 17 publications

Civil Integrated Management (CIM) for Advanced Level Applications to Transportation Infrastructure: A State-of-the-Art Review

Civil Integrated Management (CIM) for Advanced Level Applications to Transportation Infrastructure: A State-of-the-Art Review

Spatial Agglomeration and Diffusion of Population Based on a Regional Density Function Approach: A Case Study of Shandong Province in China

Ensemble Learning Approach for Developing Performance Models of Flexible Pavement

Contact Info

Product

Resources

About