Transportation planning through pavement performance prediction modeling for Botswana gravel loss condition

Adewole S. Oladele, Vera Vokolkova, Jerome A. Egwurube

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Botswana is a Southern African country with an area of about 582,000 sq. km and its small population of about 2 million people. The road transportation network has grown beyond all expectations since independence in 1966. Out of the 18,300 km Botswana Public Highway Networks, gravel road networks are significant in providing access to rural areas where the majority of the population lives. Modelling of gravel loss conditions are required in order to predict their conditions in the future and provide information on the manner in which pavements perform. Such information can be applied to transportation planning, decision making processes and identification of future maintenance interventions. The results of previous attempts to develop gravel loss condition forecasting models using multiple linear regression (MLR) approach have not been reliable. This paper intended to develop accurate and reliable performance models which best capture the effects of gravel loss condition influencing factors using Feed Forward Neural Network (FFNN) modeling technique. As extension of knowledge in unpaved road transportation network, FFNN trained with Levenberg-Marquardt (L-M) method was used to develop gravel loss performance prediction model for Botswana gravel road networks to achieve a reliable result of a higher coefficient of determinant R2 = 0.94 compared with MLR analysis of R2 = 0.74.

Original languageEnglish
Title of host publicationAdvances in Civil Engineering II
Pages2976-2982
Number of pages7
Volume256-259
EditionPART 1
DOIs
Publication statusPublished - 2013
Event2nd International Conference on Civil Engineering and Transportation, ICCET 2012 - Guilin, China
Duration: Oct 27 2012Oct 28 2012

Publication series

NameApplied Mechanics and Materials
NumberPART 1
Volume256-259
ISSN (Print)16609336
ISSN (Electronic)16627482

Other

Other2nd International Conference on Civil Engineering and Transportation, ICCET 2012
CountryChina
CityGuilin
Period10/27/1210/28/12

Fingerprint

Gravel
Pavements
Gravel roads
Planning
Feedforward neural networks
Linear regression
Regression analysis
Decision making

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Oladele, A. S., Vokolkova, V., & Egwurube, J. A. (2013). Transportation planning through pavement performance prediction modeling for Botswana gravel loss condition. In Advances in Civil Engineering II (PART 1 ed., Vol. 256-259, pp. 2976-2982). (Applied Mechanics and Materials; Vol. 256-259, No. PART 1). https://doi.org/10.4028/www.scientific.net/AMM.256-259.2976
Oladele, Adewole S. ; Vokolkova, Vera ; Egwurube, Jerome A. / Transportation planning through pavement performance prediction modeling for Botswana gravel loss condition. Advances in Civil Engineering II. Vol. 256-259 PART 1. ed. 2013. pp. 2976-2982 (Applied Mechanics and Materials; PART 1).
@inproceedings{537c8e1bb5024fe9a8a79d8eb273fed3,
title = "Transportation planning through pavement performance prediction modeling for Botswana gravel loss condition",
abstract = "Botswana is a Southern African country with an area of about 582,000 sq. km and its small population of about 2 million people. The road transportation network has grown beyond all expectations since independence in 1966. Out of the 18,300 km Botswana Public Highway Networks, gravel road networks are significant in providing access to rural areas where the majority of the population lives. Modelling of gravel loss conditions are required in order to predict their conditions in the future and provide information on the manner in which pavements perform. Such information can be applied to transportation planning, decision making processes and identification of future maintenance interventions. The results of previous attempts to develop gravel loss condition forecasting models using multiple linear regression (MLR) approach have not been reliable. This paper intended to develop accurate and reliable performance models which best capture the effects of gravel loss condition influencing factors using Feed Forward Neural Network (FFNN) modeling technique. As extension of knowledge in unpaved road transportation network, FFNN trained with Levenberg-Marquardt (L-M) method was used to develop gravel loss performance prediction model for Botswana gravel road networks to achieve a reliable result of a higher coefficient of determinant R2 = 0.94 compared with MLR analysis of R2 = 0.74.",
author = "Oladele, {Adewole S.} and Vera Vokolkova and Egwurube, {Jerome A.}",
year = "2013",
doi = "10.4028/www.scientific.net/AMM.256-259.2976",
language = "English",
isbn = "9783037855652",
volume = "256-259",
series = "Applied Mechanics and Materials",
number = "PART 1",
pages = "2976--2982",
booktitle = "Advances in Civil Engineering II",
edition = "PART 1",

}

Oladele, AS, Vokolkova, V & Egwurube, JA 2013, Transportation planning through pavement performance prediction modeling for Botswana gravel loss condition. in Advances in Civil Engineering II. PART 1 edn, vol. 256-259, Applied Mechanics and Materials, no. PART 1, vol. 256-259, pp. 2976-2982, 2nd International Conference on Civil Engineering and Transportation, ICCET 2012, Guilin, China, 10/27/12. https://doi.org/10.4028/www.scientific.net/AMM.256-259.2976

Transportation planning through pavement performance prediction modeling for Botswana gravel loss condition. / Oladele, Adewole S.; Vokolkova, Vera; Egwurube, Jerome A.

Advances in Civil Engineering II. Vol. 256-259 PART 1. ed. 2013. p. 2976-2982 (Applied Mechanics and Materials; Vol. 256-259, No. PART 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Transportation planning through pavement performance prediction modeling for Botswana gravel loss condition

AU - Oladele, Adewole S.

AU - Vokolkova, Vera

AU - Egwurube, Jerome A.

PY - 2013

Y1 - 2013

N2 - Botswana is a Southern African country with an area of about 582,000 sq. km and its small population of about 2 million people. The road transportation network has grown beyond all expectations since independence in 1966. Out of the 18,300 km Botswana Public Highway Networks, gravel road networks are significant in providing access to rural areas where the majority of the population lives. Modelling of gravel loss conditions are required in order to predict their conditions in the future and provide information on the manner in which pavements perform. Such information can be applied to transportation planning, decision making processes and identification of future maintenance interventions. The results of previous attempts to develop gravel loss condition forecasting models using multiple linear regression (MLR) approach have not been reliable. This paper intended to develop accurate and reliable performance models which best capture the effects of gravel loss condition influencing factors using Feed Forward Neural Network (FFNN) modeling technique. As extension of knowledge in unpaved road transportation network, FFNN trained with Levenberg-Marquardt (L-M) method was used to develop gravel loss performance prediction model for Botswana gravel road networks to achieve a reliable result of a higher coefficient of determinant R2 = 0.94 compared with MLR analysis of R2 = 0.74.

AB - Botswana is a Southern African country with an area of about 582,000 sq. km and its small population of about 2 million people. The road transportation network has grown beyond all expectations since independence in 1966. Out of the 18,300 km Botswana Public Highway Networks, gravel road networks are significant in providing access to rural areas where the majority of the population lives. Modelling of gravel loss conditions are required in order to predict their conditions in the future and provide information on the manner in which pavements perform. Such information can be applied to transportation planning, decision making processes and identification of future maintenance interventions. The results of previous attempts to develop gravel loss condition forecasting models using multiple linear regression (MLR) approach have not been reliable. This paper intended to develop accurate and reliable performance models which best capture the effects of gravel loss condition influencing factors using Feed Forward Neural Network (FFNN) modeling technique. As extension of knowledge in unpaved road transportation network, FFNN trained with Levenberg-Marquardt (L-M) method was used to develop gravel loss performance prediction model for Botswana gravel road networks to achieve a reliable result of a higher coefficient of determinant R2 = 0.94 compared with MLR analysis of R2 = 0.74.

UR - http://www.scopus.com/inward/record.url?scp=84872943957&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872943957&partnerID=8YFLogxK

U2 - 10.4028/www.scientific.net/AMM.256-259.2976

DO - 10.4028/www.scientific.net/AMM.256-259.2976

M3 - Conference contribution

AN - SCOPUS:84872943957

SN - 9783037855652

VL - 256-259

T3 - Applied Mechanics and Materials

SP - 2976

EP - 2982

BT - Advances in Civil Engineering II

ER -

Oladele AS, Vokolkova V, Egwurube JA. Transportation planning through pavement performance prediction modeling for Botswana gravel loss condition. In Advances in Civil Engineering II. PART 1 ed. Vol. 256-259. 2013. p. 2976-2982. (Applied Mechanics and Materials; PART 1). https://doi.org/10.4028/www.scientific.net/AMM.256-259.2976