This paper investigates the interactions between state transportation agencies and local government bridge owners using a game theory-based framework. The framework includes a game involving two players with imperfect information, capturing the uncertainty faced by local bridge owners in their actions within infinitely repeated games. Initially, the strategy of inaction, or doing nothing, appears advantageous to local bridge owners by avoiding immediate costs. However, when state and/or federal agencies strategically provide additional information, such as demonstrating methods for calculating payoffs or directly providing them for budgetary planning, the optimal outcome is expected to shift toward collaboration between the two parties. Drawing on a comprehensive study of 182 bridges across three counties in Georgia, this research illustrates the efficacy of systematically determining payoffs, encompassing costs and benefits, within the proposed game theory framework. The study concludes that the proposed methodology enables state agencies and local bridge owners to achieve optimal outcomes and enhance their predictive capabilities for optimizing future interactions. This framework offers valuable insights for significantly improving locally owned bridge management and decision-making processes among state entities and local stakeholders.

Vehicle classification holds significant importance in various domains such as infrastructure design and freight analysis. This study presents an innovative composite deep-learning framework for accurate vehicle classification. The framework exploits two distinct types of features extracted from vehicle images: (1) high-level encodings from state-of-the-art vision transformers (ViTs), and (2) localized vehicle wheel position features obtained through real-time object detection models. The former encapsulates global and semantic characteristics, while the latter focuses on specific wheel (axle) positions. Within this composite model paradigm, we evaluate and compare the efficacy of four ViT models: the original ViT, Cross ViT, Transformer-in-Transformer, and Swin Transformer. Similarly, we assess four object detection models for extracting wheel position features: two Faster R-CNN models (with ResNet-50 and MobileNetv3 backbones) and two YOLO models (YOLOv4 and YOLOR). The ViT encodings and wheel position features are then combined and channeled into a multi-layer perceptron classifier for precise vehicle classification. To enhance the ViT model's effectiveness, we employ a wheel masking strategy during its training, which acts as a regularizer, promoting robust and complementary encodings. Our experimental results reveal that introducing randomness by masking a single wheel significantly enhances the inference performance across all composite models. However, masking more wheels introduces excessive noise and causes performance degradation. Furthermore, initializing ViT encoders with pretrained weights through self-supervised methods leads to additional performance improvements. Notably, our best model achieves an impressive Top-1 classification accuracy of 96.7% when categorizing 13 vehicle classes as defined by the Federal Highway Administration. The results underscore the efficacy of the proposed composite architecture in achieving high precision in vehicle classification tasks.

Falling weight deflectometer backcalculation is a structural health monitoring approach for estimating the dynamic modulus of flexible pavements. It consists of two key aspects: a computational pavement model and an optimization routine. When using gradient-based methods, the optimization problem is commonly ill-posed, whereby a unique solution does not necessarily exist. In this paper, a new tandem trust-region optimization algorithm is proposed for ill-posed falling weight deflectometer backcalcula-tion. The algorithm's performance is tested against existing optimization methods in the context of dynamic modulus estimation for flexible pavements, and the performance tests are simulated computa-tionally using practical values for material properties and geometry. The tandem trust-region algorithm combines the relative strengths of the subspace trust-region interior reflective method with those of the Levenberg-Marquardt algorithm. The increased computational expense of executing these two methods in parallel is negligible compared to the expense of other essential steps in backcalculation. For ill-posed problems, the performance tests indicate the tandem trust region algorithm has an overall reliability that is 33.9% higher than using only the subspace trust-region interior reflective method, and 56.9% higher than using only the Levenberg-Marquardt algorithm. Further, the new optimizer is 13.5% more reliable than a robust commercial option. (c) 2022 Elsevier Ltd. All rights reserved.

Pavement temperature is one of the most important factors influencing the performance of flexible pavements. The major components of the Earth's heat balance system are downwelling shortwave radiation (D-SWR) from the sun, downwelling longwave radiation (D-LWR) from the atmosphere, and upwelling longwave radiation (U-LWR) emitted by the warm pavement surface. The Pavement ME Design (PMED) software (AASHTO, 2015. Mechanistic-empirical pavement design guide-a manual of practice. Washington, DC: AASHTO) computes temperature distributions in the pavement over depth and time using algorithms originally proposed by Dempsey et al. (1985. Environmental effects on pavements: theory manual. US Department of Transportation, Federal Highway Administration). These algorithms are largely empirical, depend heavily on imprecise corrections for cloud cover, and in some parts contradict atmospheric physics. Improved models for the major radiation components proposed here include: (1) D-SWR values modelled by the MERRA-2 climate re-analysis product from NASA (Rienecker et al., 2011. MERRA: NASA's modern-era retrospective analysis for research and applications. Journal of Climate, 24, 3624-3648); (2) D-LWR modelled using the Ids degrees (1981. A set of equations for full spectrum and 8-to 14-pm and 10.5-to 12.5-pm thermal radiation from cloudless skies. Water Resources Research, 17, 295-304) empirical parameterisation with a physics-consistent adjustment for cloud cover; and (3) U-LWR calculations without the physics-inconsistent cloud cover adjustment embedded in PMED. The D-SWR and D-LWR radiation models were evaluated via comparisons against ground-based radiation observations at 21 locations in the Solar Infrared Radiations Stations (SIRS) database. The MERRA-2 estimates of D-SWR, although not perfect, were found to agree substantially better than the current PMED models with the ground truth SIRS. The D-LWR fluxes from the Idso (1981. A set of equations for full spectrum and 8-to 14-mu m and 10.5-to 12.5-mu m thermal radiation from cloudless skies. Water Resources Research, 17, 295-304) parameterisation were also found to agree substantially better than the current PMED with the ground truth SIRS, with particularly striking improvements for the all-sky (i.e. including clouds) condition. A limited series of flexible pavement performance analyses were conducted to illustrate the potential practical impact of these radiation mod& changes. The new radiation models produced significantly higher pavement temperatures that lead to substantially higher total rutting, asphalt rutting, and bottom up fatigue cracking. These changes in distress magnitudes must be evaluated in qualitative terms only, as all analyses used the same field calibration coefficients for the distress models. The primary conclusion from this work is that the current radiation models incorporated in PMED are inaccurate and, in some cases, inconsistent with fundamental atmospheric physics. This can have significant impacts on predicted pavement performance. It is recommended that the current PMED radiation models be replaced by the new D-SWR, D-LWR, and U-LWR. New field calibration of the empirical distress models would be required after incorporating the new radiation models.

Data collected using sensors plays an essential role in active bridge health monitoring. When analyzing a large number of bridges in the U.S., the National Bridge Inventory data as been widely used. Yet, the database does not provide information about live loads, one of the most indeterminate variables for monitoring bridges. Such asymmetric information can lead to an adverse selection problem in making maintenance, rehabilitation, and repair decisions. This study proposes a data-driven reliability analysis to assess probabilities of bridge failure by synthesizing NBI data and Weigh-In-Motion (WIM) data for a large number of bridges in Georgia. On the resistance side, tree ensemble methods are employed to support the hypothesis that the NBI operating load rating represents the distribution of bridge resistance capacities which change over time. On the loading side, the live load distribution is derived from field data collected using WIM sensors. Our results show that the proposed WIM data-enabled reliability analysis substantially enhances information symmetry and provides a reliability index that supports monitoring of bridge conditions, depending on live loads and load-carrying capacities.

Weigh-In-Motion (WIM) data have been collected by state departments of transportation (DOT) in the U.S. and are anticipated to grow as state DOTs expand the number of WIM sites in order to better manage transportation infrastructure and enhance mobility. Traditional approaches for monitoring the vehicle weight measured in WIM systems include conducting statistical tests between two datasets obtained from two calibration visits. Depending on the frequency of visits, these traditional approaches are ineffective or resource-demanding for identifying calibration needs. Excessive vehicle-weight drifts exceeding 10% are usually indicative of poor performance by WIM systems. However, it has been difficult to consistently monitor such performance due to the sheer amount of data. In Georgia, the number of WIM sites have expanded from 12 to 29 in the past 3 years. This paper proposes a deep-learning-based temporal prediction approach for modeling sequential data and monitoring the time-history of the live loads imposed on roads and bridges. In total, 29 WIM sites in Georgia are analyzed to examine the effectiveness of a proposed temporal prediction approach for evaluating observed live loads. This study finds that the Jensen–Shannon divergence method is more effective than statistical difference tests, particularly when screening for live load anomalies. It is concluded that a LSTM neural network is able to capture temporal dynamics underlying the sequential load patterns observed in the WIM data and serves as an effective model for consistently monitoring the performance of WIM systems over time.

Temporal discounting is a cognitive behavior with important implications in preparing for high-impact and low-probability events. Evaluation of live-load effects has a great influence on the design, maintenance, and rehabilitation of bridges in the US. This study employed statistical methods to evaluate high-impact and low-probability bridge overloading events and proposes a cognitive approach to evaluating live-load factors because stakeholders discount the probability of observing overweight vehicles based on Kahneman and Tversky's prospect theory. This paper quantified the likelihood of observing extreme weights on bridges from 10 Weigh-In-Motion sites in Georgia using the extreme value theory. A sensitivity analysis showed how predicted live-load factors vary in response to the choice of a threshold or an extreme percentile. Subsequently, the process of predicting maximum live-load factors was validated using another state's data. It was concluded that a live-load factor is affected by a shape parameter and is numerically quantifiable for each site, and that near-term live-load factors are more salient for preparing bridges for high-risk, low-probability overloading events.

The current state of practice in traffic data quality control features rule-based data checking and validation processes, where the rules are subjective and insensitive to variation inherited with traffic data. In this paper, self-supervised deep learning approaches were explored to leverage the existence of multiple sources of traffic volume data, which permitted cross-checking of one data source against another for improved robustness. Two types of models were developed, aiming at detecting data anomalies at two distinct timescales. Particularly, a novel variational autoencoder (VAE)-based model was formulated for discerning data anomalies at the daily level and four recurrent model structures, including recurrent neural networks (RNN), gated recurrent units (GRU), long short-term memory (LSTM) units, and liquid time constant (LTC) networks, were evaluated for detecting anomalies in finer incremental timescales (i.e., 5-min intervals). The effectiveness of the proposed methods was demonstrated using two independent sources of traffic data from the Georgia Department of Transportation: (1) traffic counts collected by inductive loops as part of the statewide traffic count program, and (2) traffic volumes acquired by a video detection system as part of the Georgia 511, an advanced traveler information system in Georgia. Based on our experiments, the VAE-based model achieved a precision of 0.95, recall of 0.92, and F-1 score of 0.94. Among the recurrent models, the fully connected LTC produced the lowest prediction error and achieved a precision of 0.82, recall of 0.88, and F-1 score of 0.85. (C) 2022 American Society of Civil Engineers.

Saltmarshes, known to be ecologically sensitive areas, face disturbances such as vegetation dieback due to anthropogenic activities such as construction. The current construction specifications recommended by state highway agencies do not specifically require documenting or restoring any prior saltmarsh soil/interstitial water properties, nor do they require re-establishing saltmarsh vegetation; restoring the abiotic properties and appropriate vegetation would enhance the long-term functionality and ecology of a disturbed area. In order to have a successful restoration of disturbed saltmarshes with healthy vegetation, the relationship between vegetative species and the properties of saltmarsh soils and interstitial water must be fully understood. In this study, field and laboratory tests were conducted for the soil samples from eight different saltmarsh sites in the Southeastern US Atlantic coastal region, followed by the development of a random forest model; the aim is to identify correlation among saltmarsh predominant vegetation types, redox potential, and salinity. The results reveal that moisture content and sand content are two main drivers for the bulk density of saltmarsh soils, which directly affect plant growth and likely root development. Moreover, it is concluded that deploying modern machine learning algorithms, such as random forest, can help to identify desirable saltmarsh soil/water properties for re-establishing vegetative cover with the reduced time after construction activities.

Current strategies for prioritizing bridge preventive maintenance, rehabilitation, or replacement (MRR) include predicting future conditions by delineating depreciation rates from existing conditions and preventive MRR activities. Such predictions are overly conservative because element interactions, although present, are not considered in quantifying bridge deterioration. This study proposes a novel prioritization mechanism that leverages time-dependent element interactions, referred to as coactiveness, in predicting bridge performance resulting from MRR activities. The proposed coactive model hypothesizes that if one repairs one element, it should reduce the deterioration of other elements. The improved elements in turn reduce the deterioration of the repaired element, improving the overall health of a bridge. The element-level bridge inspection data from three southeastern US states (Alabama, Georgia, and Florida) are investigated to illustrate the capability of the proposed mechanism. In Georgia, the results show that changes in the condition of expansion joints are most critical to the long-term performance of bridge elements. Alabama's bridge management strategy slows the depreciation of expansion joints when more MRR resources are allocated to its deck elements. It is concluded that early preventive maintenance implemented in Florida is effective and has a similar effect as leveraging the proposed prioritization mechanism in enhancing bridge long-term performance.

The pavement Mechanistic-Empirical (ME) design requires high-dimensional traffic feature inputs by categories, including Vehicle Class Distributions (VCD), Monthly Distribution Factors (MDF), Hourly Distribution Factors (HDF), and Normalized Axles Load Spectra (NALS). In simplifying the Pavement ME design practice, Truck Traffic Classification (TTC) groups are commonly used for characterizing traffic inputs. Thus, properly defining TTC groups is critical for state-specific pavement ME design practice. In this study, the truck traffic data from existing Weight-in-Motion (WIM) stations were mined to develop specific TTC groups to assist with pavement ME design practice in Georgia. An effective data analytics procedure was developed by leveraging unsupervised machine learning techniques to reduce the high-dimensional traffic features by stratified Principal Component Analysis (PCA), followed by K-means clustering to establish appropriate TTC groups. For a case study, the performance of two typical designs was evaluated using the AASHTOWare pavement mechanistic-empirical (ME) design software with respect to two scenarios of traffic inputs: (1) the derived cluster-based groups, and (2) the national default TTC groups. The results indicated that direct application of the national default TTC groups resulted in over-design of pavement structure in Georgia. Therefore, it is highly recommended that customized TTC groups should be developed using state-specific WIM data.

First Name is required invalid characters Last Name is required invalid characters Email Address is required Invalid Email Address Invalid Email Address

This paper compares the predicted distresses (via in the AASHTOWare Pavement ME Design software (PMED)) of asphalt concrete (AC) and jointed plain concrete pavement (JPCP) using four different climate data sources. These sources also include the Modern Era Retrospective Analysis for Research and Application (MERRA) Versions 1.0 and 2.0 (MERRA-1 and MERRA-2). Pavement performance predictions generated using these data showed disagreement among some of the climate data sources, especially for MERRA-2. Comprehensive diurnal and other time-series analyses of the raw climate data found significant disagreements in the percent sunshine estimates. Percent sunshine is used in the PMED environmental effects model to semi-empirically estimate the downwelling shortwave radiation reaching the pavement surface. Both MERRA data (MERRA -1 and MERRA-2) independently provide direct predictions of downwelling surface shortwave radiation (SSR). The direct model predictions of SSR were used to back calculate 'synthetic' per cent sunshine for input into the PMED. The use of the synthetic per cent sunshine derived from the predicted SSR eliminated nearly all discrepancies in the predicted pavement performance using MERRA-1 versus MERRA-2 data. Based on these results, the authors recommend that SSR rather than per cent sunshine be used as a direct input to the PMED.

First Name is required invalid characters Last Name is required invalid characters Email Address is required Invalid Email Address Invalid Email Address