LSTM+MA: A Time-Series Model for Predicting Pavement IRI
The accurate prediction of pavement performance is essential for transportation administration or management to appropriately allocate resources road maintenance and upkeep. The international roughness index (IRI) is one of the most commonly used pavement performance indicators to reflect the surfac...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Infrastructures |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2412-3811/10/1/10 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588379404894208 |
|---|---|
| author | Tianjie Zhang Alex Smith Huachun Zhai Yang Lu |
| author_facet | Tianjie Zhang Alex Smith Huachun Zhai Yang Lu |
| author_sort | Tianjie Zhang |
| collection | DOAJ |
| description | The accurate prediction of pavement performance is essential for transportation administration or management to appropriately allocate resources road maintenance and upkeep. The international roughness index (IRI) is one of the most commonly used pavement performance indicators to reflect the surface roughness. However, the existing research on IRI prediction mainly focuses on using linear regression or traditional machine learning, which cannot take into account the historical effects of IRI caused by climate, traffic, pavement construction and intermittent maintenance. In this work, a long short-term memory (LSTM)-based model, LSTM+MA, is proposed to predict the IRI of pavements using the time-series data extracted from the long-term pavement performance (LTPP) dataset. Effective preprocessing methods and hyperparameter fine-tuning are selected to improve the accuracy of the model. The performance of the LSTM+MA is compared with other state-of-the-art models, including logistic regressor (LR), support vector regressor (SVR), random forest (RF), K-nearest-neighbor regressor (KNR), fully connected neural network (FNN), XGBoost (XGB), recurrent neural network (RNN) and LSTM. The results show that selected preprocessing methods can help the model learn quickly from the data and reach high accuracy in small epochs. Also, it shows that the proposed LSTM+MA model significantly outperforms other models, with an <i>R</i><sup>2</sup> of 0.965 and a mean square error (MSE) of 0.030 in the test datasets. Moreover, an overfitting score is proposed in this work to represent the severity degree of the overfitting problem, and it shows that the proposed model does not suffer severely from overfitting. |
| format | Article |
| id | doaj-art-dfe6bccfa5824607a8bf891fb7603852 |
| institution | Kabale University |
| issn | 2412-3811 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Infrastructures |
| spelling | doaj-art-dfe6bccfa5824607a8bf891fb76038522025-01-24T13:35:23ZengMDPI AGInfrastructures2412-38112025-01-011011010.3390/infrastructures10010010LSTM+MA: A Time-Series Model for Predicting Pavement IRITianjie Zhang0Alex Smith1Huachun Zhai2Yang Lu3Computing PhD Program, College of Engineering, Boise State University, Boise, ID 83725, USADepartment of Computer Science, College of Engineering, Boise State University, Boise, ID 83725, USAIdaho Asphalt Supply Inc., Nampa, ID 83687, USADepartment of Civil Engineering, College of Engineering, Boise State University, Boise, ID 83725, USAThe accurate prediction of pavement performance is essential for transportation administration or management to appropriately allocate resources road maintenance and upkeep. The international roughness index (IRI) is one of the most commonly used pavement performance indicators to reflect the surface roughness. However, the existing research on IRI prediction mainly focuses on using linear regression or traditional machine learning, which cannot take into account the historical effects of IRI caused by climate, traffic, pavement construction and intermittent maintenance. In this work, a long short-term memory (LSTM)-based model, LSTM+MA, is proposed to predict the IRI of pavements using the time-series data extracted from the long-term pavement performance (LTPP) dataset. Effective preprocessing methods and hyperparameter fine-tuning are selected to improve the accuracy of the model. The performance of the LSTM+MA is compared with other state-of-the-art models, including logistic regressor (LR), support vector regressor (SVR), random forest (RF), K-nearest-neighbor regressor (KNR), fully connected neural network (FNN), XGBoost (XGB), recurrent neural network (RNN) and LSTM. The results show that selected preprocessing methods can help the model learn quickly from the data and reach high accuracy in small epochs. Also, it shows that the proposed LSTM+MA model significantly outperforms other models, with an <i>R</i><sup>2</sup> of 0.965 and a mean square error (MSE) of 0.030 in the test datasets. Moreover, an overfitting score is proposed in this work to represent the severity degree of the overfitting problem, and it shows that the proposed model does not suffer severely from overfitting.https://www.mdpi.com/2412-3811/10/1/10deep learninginternational roughness indexLSTMLTPP |
| spellingShingle | Tianjie Zhang Alex Smith Huachun Zhai Yang Lu LSTM+MA: A Time-Series Model for Predicting Pavement IRI Infrastructures deep learning international roughness index LSTM LTPP |
| title | LSTM+MA: A Time-Series Model for Predicting Pavement IRI |
| title_full | LSTM+MA: A Time-Series Model for Predicting Pavement IRI |
| title_fullStr | LSTM+MA: A Time-Series Model for Predicting Pavement IRI |
| title_full_unstemmed | LSTM+MA: A Time-Series Model for Predicting Pavement IRI |
| title_short | LSTM+MA: A Time-Series Model for Predicting Pavement IRI |
| title_sort | lstm ma a time series model for predicting pavement iri |
| topic | deep learning international roughness index LSTM LTPP |
| url | https://www.mdpi.com/2412-3811/10/1/10 |
| work_keys_str_mv | AT tianjiezhang lstmmaatimeseriesmodelforpredictingpavementiri AT alexsmith lstmmaatimeseriesmodelforpredictingpavementiri AT huachunzhai lstmmaatimeseriesmodelforpredictingpavementiri AT yanglu lstmmaatimeseriesmodelforpredictingpavementiri |