Redirigiendo al acceso original de articulo en 16 segundos...
Inicio  /  Infrastructures  /  Vol: 5 Par: 11 (2020)  /  Artículo
ARTÍCULO
TITULO

Use of Deep Learning to Study Modeling Deterioration of Pavements a Case Study in Iowa

Seyed Amirhossein Hosseini    
Ahmad Alhasan and Omar Smadi    

Resumen

This paper describes the process and outcome of deterioration modeling for three different pavement types (asphalt, concrete, and composite) in the state of Iowa. Pavement condition data is collected by the Iowa Department of Transportation (DOT) and stored in a Pavement-Management Information System (PMIS). In the state of Iowa, the overall pavement condition is quantified using the Pavement Condition Index (PCI), which is a weighted average of indices representing different types of distress, roughness, and deflection. Deterioration models of PCI as a function of time were developed for the different pavement types using two modeling approaches. The first approach is the long/short-term memory (LSTM), a subset of a recurrent neural network. The second approach, used by the Iowa DOT, is developing individual regression models for each section of the different pavement types. A comparison is made between the two approaches to assess the accuracy of each model. The results show that the LSTM model achieved a higher prediction accuracy over time for all different pavement types.

 Artículos similares

       
 
Manuel López-Vicente and Gao-Lin Wu    
This special issue includes six articles that cover a variety of issues about the topic of soil and water conservation in agricultural systems, including the following: a bibliometric analysis of soil and water conservation in the Loess Region of China; ... ver más
Revista: Water

 
Gra?ina Masionyte     Pág. 599 - 607
crucial importance for corporate activity analysis performance and management decision-making.Object of the study ? to establish shortages of information supply in agricultural enterprise performanceanalysis process and to make proposals to address them.... ver más

 
Venkataramana Sridhar, Hyunwoo Kang and Syed A. Ali    
The Mekong River Basin (MRB) is one of the significant river basins in the world. For political and economic reasons, it has remained mostly in its natural condition. However, with population increases and rapid industrial growth in the Mekong region, th... ver más
Revista: Water

 
Nikola Pfauserová, Ondrej Slavík, Pavel Horký, Jitka Kolárová and Tomá? Randák    
The introduction of non-native species and human-altered habitats are currently the main threats to freshwater ecosystems. Due to predation and competition, biological invaders can cause extinctions and imperil the status of native species, and this phen... ver más
Revista: Water

 
Ludek Bures, Petra Sychova, Petr Maca, Radek Roub and Stepan Marval    
An appropriate digital elevation model (DEM) is required for purposes of hydrodynamic modelling of floods. Such a DEM describes a river?s bathymetry (bed topography) as well as its surrounding area. Extensive measurements for creating accurate bathymetry... ver más
Revista: Water