Omar Smadi

Geotechnical asset management (GAM), transportation asset management (TAM), and performance management have progressively become routine terms at many transportation agencies throughout the United States, Canada, and world. Geotechnical assets represent the “foundational” platform for other transportation infrastructure assets. With their extensive presence and critical role in the highway network, evaluating the condition and deterioration mechanics of these assets through a proactive assessment and intervention program helps improve the overall network condition and avoid costly, disruptive, and risky serviceability and ultimate “failures.” This study presents a flexible and holistic GAM framework and workflow. To date, many GAM frameworks proposed in practice have focused on creating an asset inventory and inspection procedures. Although data collection and inspection procedures are the core of GAM, a functional and robust GAM program should address other components such as risk management as well as deterioration and performance modeling to be effectively integrated with other TAM programs and achieve agency objectives. This report provides a comprehensive discussion on asset inspection and condition evaluation procedures for four geotechnical asset families: soil slopes and embankments, rock slopes, retaining walls, and mechanically stabilized earth walls. Moreover, the research team developed applications and tools to facilitate asset inspection and condition evaluation, risk management at the asset and asset family levels, and performance deterioration modeling to allow for proactive implementation of the framework. The report summarizes the main findings, gaps, and recommendations from the study.

Pavement management systems depend on accurate maintenance histories, yet resurfacing activities are often missing or reported late in agency databases. This study presents an automated framework for detecting road resurfacing directly from multitemporal multispectral aerial imagery, independently of pavement condition records used for prediction. National Agriculture Imagery Program images from 2021 and 2023 were co-registered, radiometrically checked, resampled, combined into an eight-band temporal stack, and masked to roadway corridors. Pixel-level training labels were developed for approximately 4 km of state road in Adair County, Iowa, using verified resurfacing records and visual review. Four supervised classifiers, k-nearest neighbors, support vector machines, Random Forest, and maximum likelihood, were evaluated under multiple parameter settings. Pixel predictions were aggregated to 75 m roadway segments, and resurfacing decisions were assigned using class-1 coverage thresholds ranging from 20% to 90%. Approximately 200 km of two-lane state roads were used for holdout evaluation. Across 72 model-threshold combinations, the best-performing configuration was a Random Forest model with 30 trees, maximum depth 20, 1,000 samples per class, and a 30% coverage threshold. This configuration achieved 97.22% accuracy, 0.90 F1, 0.94 Macro-F1, 0.95 balanced accuracy, and 0.89 for both Matthews correlation coefficient and Cohen’s kappa. The workflow was implemented in an ArcGIS Pro toolbox, the Road Resurfacing Detector, which automates image preparation, classification, segment generation, coverage calculation, thresholding, and output mapping. The framework provides a practical approach for identifying candidate missing resurfacing records and supporting pavement-management quality control, auditing, and retrospective maintenance analysis across large transportation networks with minimal intervention.

Transportation Asset Management (TAM) is a strategic framework aimed at optimising the performance, longevity, and cost efficiency of transportation systems while supporting mobility, safety, and e...

Road pavement data plays a crucial role in establishing an effective pavement management system and enables agencies to make more accurate decisions on maintenance and rehabilitation plans. Traditional pavement data collection methods are time-consuming, costly, and labor-intensive, limiting their scalability for large-scale infrastructure assessment. Utilizing satellite/aerial imagery for extracting road pavement data is becoming increasingly popular because of the availability of high-resolution images, advancements in image processing and remote sensing techniques, enhanced computational power, and the presence of geographic information systems (GISs). This novel study integrates machine learning (ML), remote sensing, and a GIS to develop an automated tool based on a robust deep-learning model to extract the construction year from time-series aerial imagery. This study also employs pixel classification to automate differentiation between asphalt concrete (AC) and Portland cement concrete (PCC) road surface pixels using multispectral aerial imagery. The study area is the city of Ames in Story County, Iowa, where the model’s performance is rigorously assessed. Results demonstrate high accuracy in predicting road construction years, achieving 94% for both recall and precision. The AC and PCC surfaces were classified with 89% overall accuracy, 95.38% and 77.14% recall rates, respectively, and PCC demonstrated a high precision of 90%, compared to AC’s 88.57%. This study underscores the need for high-resolution multispectral imagery (30 cm or less) captured in spring with cloud cover below 10% for optimal accuracy. These findings highlight the potential of remote sensing and ML in improving pavement data collection, enhancing accuracy, and reducing manual effort. Higher-resolution imagery with an extended spectrum can further improve accuracy.

Effective pavement management systems are essential for accurately predicting pavement conditions and efficiently planning and scheduling maintenance, rehabilitation, and reconstruction activities. Significant efforts are dedicated to developing accurate pavement condition prediction models using machine learning (ML) at the state level. Conversely, insufficient investment, poor quality, and large variations in local roads data have resulted in less attention to modeling local pavement conditions. This study develops eight Bayesian-optimized single-estimator and ensemble ML classification models to predict local pavement roughness. Moreover, the classification granularity of pavement condition was investigated to assess its impact on the predictive power of various ML models. The results reveal that ML classification models with fewer classes exhibit higher accuracy and more stability in precision over recall values, in contrast to models with larger number of classes. The ensemble ML models surpass their single-estimator counterparts, with the category boosting algorithm demonstrating the highest performance, achieving testing accuracies of 0.77 and 0.65 for the three-level and five-level classifications, respectively. Hence, it is recommended to employ ensemble ML algorithms and a smaller number of classes to develop reliable, accurate, and stable predictive models for local roads with imbalanced condition data. This research helps transportation agencies improve their pavement condition prediction, thereby optimizing pavement management and resource allocation.

This study proposes a novel framework for determining variables’ weights in transportation assets condition indices calculations using statistical and machine learning techniques. The methodology leverages subjective ratings alongside objective measurements to derive data-driven weights. The motivation for this study lies in addressing the limitations of existing expert-based weighting methods for condition indices, which often lack transparency and consistency; this research aims to provide a data-driven framework that enhances accuracy and reliability in infrastructure asset management. A case study was performed as a proof of concept of the proposed framework by applying the framework to obtain data-driven weights for pavement condition index (PCI) calculations using data for the city of West Des Moines, Iowa. Random forest models performed effectively in modeling the relationship between the overall condition index (OCI) and the objective measures and provided feature importance scores that were converted into weights. The data-driven weights showed strong correlation with existing expert-based weights, validating their accuracy while capturing contextual variations between pavement types. The results indicate that the proposed framework achieved high model accuracy, demonstrated by R-squared values of 0.83 and 0.91 for rigid and composite pavements, respectively. Additionally, the data-driven weights showed strong correlations (R-squared values of 0.85 and 0.98) with existing expert-based weights, validating their effectiveness. This advanceIRIment offers transportation agencies an enhanced tool for prioritizing maintenance and resource allocation, ultimately leading to improved infrastructure longevity. Additionally, this approach shows promise for application across various transportation assets based on the yielded results.

Trail pavement roughness significantly impacts user experience and safety. Measuring roughness over large areas using traditional equipment is challenging and expensive. The utilization of smartphones and bicycles offers a more feasible approach to measuring trail roughness, but the current methods to capture data using these have accuracy limitations. While machine learning has the potential to improve accuracy, there have been few applications of real-time roughness evaluation. This study proposes a hybrid ensemble machine learning model that combines sequence-based modeling with support vector regression (SVR) to estimate trail roughness using smartphone sensor data mounted on bicycles. The hybrid model outperformed traditional methods like double integration and whole-body vibration in roughness estimation. For the 0.031 mi (50 m) segments, it reduced RMSE by 54–74% for asphalt concrete (AC) trails and 50–59% for Portland cement concrete (PCC) trails. For the 0.31 mi (499 m) segments, RMSE reductions of 37–60% and 49–56% for AC and PCC trails were achieved, respectively. Additionally, the hybrid model outperformed the base random forest model by 17%, highlighting the effectiveness of combining ensemble learning with sequence modeling and SVR. These results demonstrate that the hybrid model provides a cost-effective, scalable, and highly accurate alternative for large-scale trail roughness monitoring and assessment.

Transportation asset management has historically overlooked equity considerations. However, recently, there has been a significant increase in concerns about this issue, leading to a range of research and practices aimed at achieving more equitable outcomes. Yet, addressing equity is challenging and time-consuming, given its complexity and multifaceted nature. Several factors can significantly impact the outcome of an analysis, including the definition of equity, the evaluation and quantification of its impacts, and the community classification. As a result, there can be a wide range of interpretations of what constitutes equity. Therefore, there is no single correct or incorrect approach for equity evaluation, and different perspectives, impacts, and analysis methods could be considered for this purpose. This study reviews previous research on how transportation agencies are integrating equity into transportation asset management, particularly pavement management systems. The primary objective is to investigate important equity factors for pavement management and propose a prototype framework that integrates economic, environmental, and social equity considerations into the decision-making process for pavement maintenance, rehabilitation, and reconstruction projects. The proposed framework consists of two main steps: (1) defining objectives based on the three equity dimensions, and (2) analyzing key factors for identifying underserved areas through a case study approach. The case study analyzed pavement condition and sociodemographic data for California’s Bay Area. Statistical analysis and a machine learning method revealed that areas with higher poverty rates and worse air quality tend to have poorer pavement conditions, highlighting the need to consider these factors when defining underserved areas in Bay Area and promoting equity in pavement management decision-making. The proposed framework incorporates an optimization problem to simultaneously minimize disparities in pavement conditions between underserved and other areas, reduce greenhouse gas emissions from construction and traffic disruptions, and maximize overall network pavement condition subject to budget constraints. By incorporating all three equity aspects into a quantitative decision-support framework with specific objectives, this study proposes a novel approach for transportation agencies to promote sustainable and equitable asset management practices.