Geospatial learning for large-scale transport infrastructure depth prediction

Pengcheng Zhang; Wen Yi; Yongze Song; Giles Thomson; Peng Wu; Nasrin Aghamohammadi

doi:10.1016/j.jag.2024.103986

Back

Geospatial learning for large-scale transport infrastructure depth prediction

Journal article

Open access

Peer reviewed

Geospatial learning for large-scale transport infrastructure depth prediction

Pengcheng Zhang, Wen Yi, Yongze Song, Giles Thomson, Peng Wu and Nasrin Aghamohammadi

International journal of applied earth observation and geoinformation, Vol.132, 103986

2024

DOI: https://doi.org/10.1016/j.jag.2024.103986

Files and links (1)

pdf

Published3.64 MBDownload View

Published (Version of Record)CC BY V4.0, Open Access

Abstract

Geospatial intelligence

GIS

Remote sensing

Sustainable infrastructure

Vehicle-based laser scanning

Transportation infrastructure supports the smooth mobility of humans, commodities, and services. Pavement depth measures the quality of road infrastructure through representing the thickness of road surfaces, and influences various aspects of construction projects. However, accurately modeling and predicting pavement depth has been a critical challenge due to diverse and complex factors, such as weather dynamics, traffic patterns, maintenance interventions, and environmental fluctuations. This study develops a second-dimension spatial learning (SDSL) model that integrates geospatial models and machine learning for large-scale pavement depth prediction. SDSL models are implemented in pavement prediction for eight distinct regions in Western Australia, and they are validated using the observation of pavement depth through cross-validation. Results demonstrate that the proposed SDSL models can more accurately predict large-scale pavement depth than the existing first-dimension spatial learning (FDSL) models, with 17.3% to 37.6% increase of R2 values, 1.46% to 16.5% reduction of RMSE, 1.7% to 31.1% reduction of MAE and 21.0% reduction of prediction uncertainty. SDSL models enhance effective infrastructure management by accurately predicting pavement depth, essential for maintaining large-scale transportation infrastructure. The study significantly contributes to the efficient management of sustainable infrastructure assets, saving time and money.

Details

Title: Geospatial learning for large-scale transport infrastructure depth prediction
Authors/Creators: Pengcheng Zhang - Hong Kong Polytechnic University
Wen Yi - Hong Kong Polytechnic University
Yongze Song - Curtin University
Giles Thomson - Curtin University
Peng Wu - Curtin University
Nasrin Aghamohammadi - Curtin University
Publication Details: International journal of applied earth observation and geoinformation, Vol.132, 103986
Publisher: Elsevier B.V.
Identifiers: 991005681250307891
Murdoch Affiliation: School of Engineering and Energy; Surface Analysis and Materials Engineering Research Group; College of Science, Technology, Engineering and Mathematics
Language: English
Resource Type: Journal article

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

#9 Industry, Innovation and Infrastructure

Metrics

200 File views/ downloads

61 Record Views

3 Times Cited - Web of Science

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types: Domestic collaboration; International collaboration
Citation topics: 7 Engineering & Materials Science; 7.300 Asphalt; 7.300.908 Asphalt Performance
Web Of Science research areas: Remote Sensing
ESI research areas: Geosciences