#6346. Reassessment of climate zones for high-level pavement analysis using machine learning algorithms and NASA MERRA-2 data

October 2026publication date
Proposal available till 18-06-2025
4 total number of authors per manuscript0 $

The title of the journal is available only for the authors who have already paid for
Journal’s subject area:
Building and Construction;
Information Systems;
Artificial Intelligence;
Places in the authors’ list:
place 1place 2place 3place 4
FreeFreeFreeFree
2350 $1200 $1050 $900 $
Contract №6346.1 Contract №6346.2 Contract №6346.3 Contract №6346.4
1 place - free (for sale)
2 place - free (for sale)
3 place - free (for sale)
4 place - free (for sale)

Abstract:
Incorporating climate impact into pavement distress initiation and propagating modeling and management, suffers from the extent of weather data available, and ability to process into a useable form in a time and computationally inexpensive manner. Analysts have overcome this challenge by partitioning large geographic areas into regions with similarities in climate impact on pavement distress initiation and propagation. Historically, large geographical areas have been empirically carved out into smaller regions with similar climates by experienced geographers and climatologists. The availability of extensive weather data, comprising hundreds of meteorological variables reported with a high spatial and temporal resolution, has made the use of empirical methodologies for establishing climate regions obsolete and untenable. This paper presents a new machine learning methodology for (1) establishing pavement-specific climate regions and (2) accurately separating predictor climate attributes into climate regions for use in the pavement management and high-level analyses. The new methodology comprises stochastic and machine learning algorithms: correlation analysis, principal factor analysis, cluster analysis, and decision tree.
Keywords:
Climate; Correlation analysis; Decision tree; Pavement; Principal factor analysis; Supervised data classification; Unsupervised cluster analysis

Contacts :
0