Publications

2024

1. Modeling of Spatially Embedded Networks via Regional Spatial Graph Convolutional Networks

   Xudong Fan, and Jürgen Hackl

   Computer-Aided Civil and Infrastructure Engineering, Jun 2024

   Abs

   

   Abstract Efficient representation of complex infrastructure systems is crucial for system-level management tasks, such as edge prediction, component classification, and decision-making. However, the complex interactions between the infrastructure systems and their spatial environments increased the complexity of network representation learning. This study introduces a novel geometric-based multimodal deep learning model for spatially embedded network representation learning, namely the regional spatial graph convolutional network (RSGCN). The developed RSGCN model simultaneously learns from the node’s multimodal spatial features. To evaluate the network representation performance, the introduced RSGCN model is used to embed different infrastructure networks into latent spaces and then reconstruct the networks. A synthetic network dataset, a California Highway Network, and a New Jersey Power Network were used as testbeds. The performance of the developed model is compared with two other state-of-the-art geometric deep learning models, GraphSAGE and Spatial Graph Convolutional Network. The results demonstrate the importance of considering regional information and the effectiveness of using novel graph convolutional neural networks for a more accurate representation of complex infrastructure systems.

2. Estimation of Unfrozen Water Content in Frozen Soils Based on Data Interpolation and Constrained Monotonic Neural Network

   Jiaxian Li, Junping Ren, and 4 more authors

   Cold Regions Science and Technology, Jun 2024
3. Potentials of Mitigating Pavement Frost Heave with Fungi

   Xijin Zhang, Yusheng Jiang, and 2 more authors

   In Geo-Congress 2024, Feb 2024

2023

1. Assessment of the Impacts of Climat Change on Water Supply System Pipe Failures

   Xudong Fan, Xijin Zhang, and 3 more authors

   Scientific Reports, Feb 2023

   Abs

   Climate change is projected to have profound impacts on the resilience and sustainability of built infrastructure. This study aims to understand the impacts of climate change on water supply systems and to facilitate adaptive actions. A premium database maintained by the Cleveland Water Division, Cleveland, Ohio, USA is analyzed. It contains 29,621 pipe failure records of 51,832 pipes over the past 30 years, representing one of the largest dataset in current literature. From the database, pipe failure rate models have been developed for water pipes made of different types of materials at different ages. The influence of climate (temperature and precipitation) on fragility of water pipes are obtained. Based on the developed climate-fragility failure rate models, the impacts of climate change on the water systems located in different geographic regions are evaluated by predicting the failure rate and number of failures in the water systems in the next 80 years (2020 to 2100). Climate models are used to predict weather under different climate change scenarios. The results demonstrate that the impacts of climate change on water supply system are likely complicated and are dependent upon factors such as the geographic location, pipe material, pipe age, and maintenance strategies. Water pipes in the cold regions may experience fewer number breaks due to the warmer weather and less severe winter, whereas those located in the hot regions may experience more failures associated with more corrosion. Different pipe replacement strategies are compared, which demonstrate the importance of considering the aging of water supply system in future maintenance decisions. This study enriches current understandings on the impacts of climate change on the water systems. The results will help water utilities to design climate change adaptation strategies.

2. A Deep Reinforcement Learning Model for Resilient Road Network Recovery under Earthquake or Flooding Hazards

   Xudong Fan, Xijin Zhang, and 2 more authors

   Journal of Infrastructure Preservation and Resilience, Feb 2023

   Abs

   Abstract As the backbone and the ‘blood vessel’ of modern cities, road networks provide critical support for community activities and economic growth, with their roles even more crucial due to the dramatic progress in urbanization. The service of road networks is subjected to the increasing frequency of high-consequence natural hazards such as earthquakes, floods, hurricanes, etc. Identifying resilient restoration sequences is essential to mitigate the disruption of such important infrastructure networks. This paper investigates a novel decision-support model to optimize post-disaster road network repair sequence. The model, named as GCN-DRL model, integrates the advantages of deep reinforced learning (DRL) with graph convolutional neural network (GCN), two emerging artificial intelligence (AI) techniques to achieve efficient recovery of road network service. The model is applied to analyze two cases of community road networks in the US that are subjected to different types of hazards, i.e., earthquakes and flooding. The performance of repair sequence by the GCN-DRL model is compared with two commonly used methods, i.e., repair sequence by the genetic algorithm and by prioritization based on graph importance with betweenness centrality. The results showed the decision sequence by GCN-DRL model consistently achieved superior performance in road network restoration than the conventional methods. The AI-based decision model also features high computational efficiency since the GCN-DRL model can be trained before the hazard. With a pre-trained GCN-DRL model, a close to optimal decision-making process can be made available rapidly for different types of new hazards, which is advantageous in efficiently responding to hazards when they happen. This study demonstrates the promise of a new AI-based decision support model to improve the resilience of road networks by enabling efficient post-hazards recovery.

3. Machine Learning-Assisted Optimal Schedule of Underground Water Pipe Inspection

   Xudong Fan, and Xiong Yu

   Journal of Infrastructure Preservation and Resilience, Aug 2023

   Abs

   Abstract There are over 2.2 million miles of underground water pipes serving the cities in the United States. Many are in poor conditions and deteriorate rapidly. Failures of these pipes could cause enormous financial losses to the customers and communities. Inspection provides crucial information for pipe condition assessment and maintenance plan; it, however, is very expensive for underground pipes due to accessibility issues. Therefore, water agencies commonly face the challenge to 1) decide whether it is worthwhile to schedule expensive water pipe inspections under financial constraints, and 2) if so, how to optimize the inspection schedule to maximize its value. This study leverages the physical model and data-based ML (ML) models for underground water pipe failure prediction to shed light on these two important questions for decision making. Analyses are firstly conducted to assess the value of water pipe inspection. Results by use of a physical-based failure model and Monte Carlo simulations indicate that by inspecting pipe’s condition, i.e., assessment of pipe’s erosion depth, the uncertainty of water pipe failure prediction can be narrowed down by 51%. For optimal inspection schedule, an artificial neural network (ANN) model, trained with historical inspection data, is evaluated for its performance in forecasting the future pipe failure probability. The results showed that a biased pipe failure prediction can occur under limited rounds of inspection. However, incorporating more rounds of inspection allows to predict the pipe failure conditions over its life cycle. From this, an optimal inspection plan can be proposed to achieve the maximum benefits of inspection in uncertainty reduction. A few salient results from the analyses include 1) the optimal schedule for inspection is not necessarily equal in the time interval, 2) by setting the goal of uncertainty reduction, an optimal inspection schedule can be obtained, where ML (ML) model augmented by continuously training with inspection data allows to reliably predict water pipe failure conditions over its life cycle. While this study focuses on underground pipe inspection, the general observations and methodology are applicable to optimize the inspection of other types of infrastructure as well.

4. Uncertainty Quantification of a Deep Learning Model for Failure Rate Prediction of Water Distribution Networks

   Xudong Fan, Xijin Zhang, and 1 more author

   Reliability Engineering & System Safety, Aug 2023

   Abs

   

   Predicting the time-dependent pipe failure rate of the water distribution networks (WDNs) is important for planning its renewal budget but also challenging due to the complex factors involved. The recent development of machine learning techniques provides a novel approach for accurate failure rate prediction based on historical data. However, the inherited randomness and uncertainty of water pipe failures and machine learning algorithms are often ignored in the training and prediction process. This article develops an uncertainty quantification framework for deep learning-based WDN system-wide failure rate prediction. The framework integrates a probabilistic long short-term memory (LSTM) model with a Monte Carlo method. The historical climate data and WDN pipe maintenance data over the past 35 years for Cuyahoga County, USA, are used to illustrate this deep-learning model-based uncertainty quantification framework in this study. A statistical time series regression model, ARIMAX, is used as a comparison benchmark. The results show that the LSTM model outperforms the ARIMAX model in prediction accuracy in most years by considering the uncertainties. Besides, the uncertainty range of the LSTM model prediction is 50% of that of the ARIMAX model. The results also identified the major contributing factors to the uncertainties of LSTM machine learning model prediction. The proposed uncertainty framework features excellent extensibility and can be adapted to quantify uncertainties with other types of machine learning models.

5. Analyses of Frost Susceptible Flexible Pavement Adaption for Climate Change

   Yusheng Jiang, Shafi Ullah, and 3 more authors

   In Geo-Risk 2023, Jul 2023
6. Use of an Artificial Neural Network Model for Estimation of Unfrozen Water Content in Frozen Soils

   Junping Ren, Xudong Fan, and 3 more authors

   Canadian Geotechnical Journal, Aug 2023

   Abs

   The variation of unfrozen water content (UWC) has a significant influence on the physical and mechanical behaviors of frozen soils. Several empirical, semi-empirical, physical, and theoretical models are available in the literature to estimate the UWC in frozen soils. However, these models have limitations due to the complex interactions of various influencing factors that are not well understood or fully established. For this reason, in the present study, an artificial neural network (ANN) modeling framework is proposed and the PyTorch package is used for predicting UWC. Extensive UWC data of various types of soils tested under various conditions were collected through an extensive search of the literature. The developed ANN model showed good performance for the testing dataset. Its performance was further compared with two traditional statistical models on four soils and found to outperform these traditional models. Detailed discussions on the developed ANN model, and its strengths and limitations in comparison to different other models are provided. The study demonstrates that the proposed ANN model is simple yet reliable for estimating the UWC of various soils. In addition, the summarized UWC data and the proposed machine learning modeling framework are valuable for future studies related to frozen soils.

7. A Novel Method to Improve the Soil Erosion Resistance with Fungi

   Xijin Zhang, Xudong Fan, and 2 more authors

   Acta Geotechnica, May 2023

   Abs

   This study evaluated an innovative method to improve soil erosion resistance by fungi. An edible filamentous fungus, Pleurotus ostreatus, was included in the study. The result showed that Pleurotus ostreatus is able to grow and completely cover the circular surface of 60.20 mm diameter in 15 days when inoculated on the top surface and in 20 days when inoculated 5 mm under the soil surface. The erosion resistance of fungi mediated soil samples was evaluated by a Simplified Scour Resistance Test (SSRT). The results showed that fungi-mediated sand samples demonstrated much higher erosion resistance compared with control sand sample, both in terms of increasing the critical flow velocity and reducing the slope of erosion rate versus flow velocity curve. The mechanism of improved erosion resistance was investigated. The microstructure measured by SEM test showed that the sand particles were entangled by fungal fibers. Chemical precipitations were observed on sand surface and attached to fungal hyphae, which were identified as calcite, calcium oxalate monohydrate and calcium oxalate dihydrate by FTIR spectra and XRD analysis. The fungi mycelium surface showed hydrophobic behaviors with an average measured contact angle of 116.42^∘. The hydrophobicity generated slip along the interface. Analyses with computational fluid dynamics (CFD) model indicated that the slip due to the hydrophobicity of fungi reduced the shear stress at the water-soil interface, which also improved the erosion resistance by fungi-mediated sand.

2022

1. A Graph Convolution Network-deep Reinforcement Learning Model for Resilient Water Distribution Network Repair Decisions

   Xudong Fan, Xijin Zhang, and 1 more author

   Computer-Aided Civil and Infrastructure Engineering, Oct 2022

   Abs

   

   Abstract Water distribution networks (WDNs) are critical infrastructure for communities. The dramatic expansion of the WDNs associated with urbanization makes them more vulnerable to high-consequence hazards such as earthquakes, which requires strategies to ensure their resilience. The resilience of a WDN is related to its ability to recover its service after disastrous events. Sound decisions on the repair sequence play a crucial role to ensure a resilient WDN recovery. This paper introduces the development of a graph convolutional neural network-integrated deep reinforcement learning (GCN-DRL) model to support optimal repair decisions to improve WDN resilience after earthquakes. A WDN resilience evaluation framework is first developed, which integrates the dynamic evolution of WDN performance indicators during the post-earthquake recovery process. The WDN performance indicator considers the relative importance of the service nodes and the extent of post-earthquake water needs that are satisfied. In this GCN-DRL model framework, the GCN encodes the information of the WDN. The topology and performance of service nodes (i.e., the degree of water that needs satisfaction) are inputs to the GCN; the outputs of GCN are the reward values (Q-values) corresponding to each repair action, which are fed into the DRL process to select the optimal repair sequence from a large action space to achieve highest system resilience. The GCN-DRL model is demonstrated on a testbed WDN subjected to three earthquake damage scenarios. The performance of the repair decisions by the GCN-DRL model is compared with those by four conventional decision methods. The results show that the recovery sequence by the GCN-DRL model achieved the highest system resilience index values and the fastest recovery of system performance. Besides, by using transfer learning based on a pre-trained model, the GCN-DRL model achieved high computational efficiency in determining the optimal repair sequences under new damage scenarios. This novel GCN-DRL model features robustness and universality to support optimal repair decisions to ensure resilient WDN recovery from earthquake damages.

2. An Innovative Machine Learning Based Framework for Water Distribution Network Leakage Detection and Localization

   Xudong Fan, and Xiong (Bill) Yu

   Structural Health Monitoring, Jul 2022

   Abs

   

   Leakages in the underground water distribution networks (WDNs) waste over 1 billion gallon of water annually in the US and cause significant socio-economic loss to our communities. However, detecting and localization leakage in a WDN remains a challenging technical problem despite of significant progresses in this domain. The progresses in machine learning (ML) provides new ways to identify the leakage by data-driven methods. However, in-service WDNs are short of labeled data under leaking conditions, which makes it infeasible to use common ML models. This study proposed a novel machine learning (ML)-based framework for WDN leak detection and localization. This new framework, named clustering-then-localization semi-supervised learning (CtL-SSL), uses the topological relationship of WDN and its leakage characteristics for WDN partition and sensors placement, and subsequently utilizes the monitoring data for leakage detection and leakage localization. The CtL-SSL framework is applied to two testbed WDNs and achieves 95% leakage detection accuracy and around 83% final leakage localization accuracy by use of unbalanced data with less than 10% leaking data. The developed CtL-SSL framework advances the leak detection strategy by alleviating the data requirements, guiding optimal sensor placement, and locating leakage via WDN leakage zone partition. It features excellent scalability, extensibility, and upgradeability for applications to various types of WDNs. It will provide valuable a tool in sustainable management of the WDNs.

3. Machine Learning Based Water Pipe Failure Prediction: The Effects of Engineering, Geology, Climate and Socio-Economic Factors

   Xudong Fan, Xiaowei Wang, and 2 more authors

   Reliability Engineering & System Safety, Jul 2022

   Abs

   

   Underground water pipes deteriorate under the influence of various physical, mechanical, environmental, and social factors. Reliable pipe failure prediction is essential for a proactive management strategy of the water supply network (WSN), which is challenging for the conventional physics-based model. This study applied data-driven machine learning (ML) models to predict water pipe failures by leveraging the historical maintenance data heritage of a large water supply network. A multi-source data-aggregation framework was firstly established to integrate various contributing factors to underground pipe deterioration. The framework defined criteria for the integration of various data sources including the historical pipe break dataset, soil type dataset, topographical dataset, census dataset, and climate dataset. Based on the data, five ML algorithms, including LightGBM, Artificial Neural Network, Logistic Regression, K-Nearest Neighbors, and Support Vector Classification are developed for pipe failure prediction. LightGBM was found to achieve the best performance. The relative importance of major contributing factors on the water pipe failures was analyzed. Interestingly, the socioeconomic factors of a community are found to affect the probability of pipe failures. This study indicates that data-driven analysis that integrates the Machine Learning (ML) techniques and the proposed data integration framework has the potential to support reliable decision-making in WSN management.

4. Resilience of Water Distribution Network: Enhanced Recovery Assisted by Artificial Intelligence (AI) Considering Dynamic Water Demand Change

   Xudong Fan, and Xiong (Bill) Yu

   In Lifelines 2022, Nov 2022
5. A Topology-Based Evaluation of Resilience on Urban Road Networks against Epidemic Spread: Implications for COVID-19 Responses

   Junqing Tang, Huali Lin, and 3 more authors

   Frontiers in Public Health, Nov 2022
6. Development and Characterization of Novelly Grown Fire-Resistant Fungal Fibers

   Xijin Zhang, Yanjun Li, and 4 more authors

   Scientific Reports, Nov 2022
7. Naturally Grown Mycelium-Composite as Sustainable Building Insulation Materials

   Xijin Zhang, Jianying Hu, and 2 more authors

   Journal of Cleaner Production, Nov 2022

2021

1. Machine Learning Model and Strategy for Fast and Accurate Detection of Leaks in Water Supply Network

   Xudong Fan, Xijin Zhang, and 1 more author

   Journal of Infrastructure Preservation and Resilience, Dec 2021

   Abs

   

   Abstract The water supply network (WSN) is subjected to leaks that compromise its service to the communities, which, however, is challenging to identify with conventional approaches before the consequences surface. This study developed Machine Learning (ML) models to detect leaks in the WDN. Water pressure data under leaking versus non-leaking conditions were generated with holistic WSN simulation code EPANET considering factors such as the fluctuating user demands, data noise, and the extent of leaks, etc. The results indicate that Artificial Neural Network (ANN), a supervised ML model, can accurately classify leaking versus non-leaking conditions; it, however, requires balanced dataset under both leaking and non-leaking conditions, which is difficult for a real WSN that mostly operate under normal service condition. Autoencoder neural network (AE), an unsupervised ML model, is further developed to detect leak with unbalanced data. The results show AE ML model achieved high accuracy when leaks occur in pipes inside the sensor monitoring area, while the accuracy is compromised otherwise. This observation will provide guidelines to deploy monitoring sensors to cover the desired monitoring area. A novel strategy is proposed based on multiple independent detection attempts to further increase the reliability of leak detection by the AE and is found to significantly reduce the probability of false alarm. The trained AE model and leak detection strategy is further tested on a testbed WSN and achieved promising results. The ML model and leak detection strategy can be readily deployed for in-service WSNs using data obtained with internet-of-things (IoTs) technologies such as smart meters.

2. Novel Strategies to Grow Natural Fibers with Improved Thermal Stability and Fire Resistance

   Xijin Zhang, Xudong Fan, and 6 more authors

   Journal of Cleaner Production, Dec 2021
3. PSO-SVM-based Deep Displacement Prediction of Majiagou Landslide Considering the Deformation Hysteresis Effect

   Lei Zhang, Bin Shi, and 4 more authors

   Landslides, Jan 2021
4. Study on the Behaviors of Fungi-Concrete Surface Interactions and Theoretical Assessment of Its Potentials for Durable Concrete with Fungal-Mediated Self-Healing

   Xijin Zhang, Xudong Fan, and 3 more authors

   Journal of Cleaner Production, Jan 2021

2020

1. A Generalized Predictive Model for TiO2–Catalyzed Photo-Degradation Rate Constants of Water Contaminants through Artificial Neural Network

   Zhuoying Jiang, Jiajie Hu, and 6 more authors

   Environmental Research, Jan 2020
2. Framework for Seismic Damage and Renewal Cost Analysis of Buried Water Pipelines

   Ram K. Mazumder, Xudong Fan, and 3 more authors

   Journal of Pipeline Systems Engineering and Practice, Nov 2020

   Abs

   Buried water pipelines suffer extensive damages when subjected to earthquake loading. Probable seismic damage of buried pipelines is typically estimated based on empirical analyses, where the effects of corrosion deterioration are often neglected. Corrosion-induced deterioration weakens the pipeline resistance capacity, which in turn significantly reduces the seismic reliability of water distribution systems (WDS). Improved seismic damage estimation of buried water pipelines needs to consider the effect of corrosion on their seismic performance to assist with the development of an effective and efficient renewal strategy. Hence, the first part of this study improves a current US guideline on seismic repair rate (RR) estimation, based on the observed effects of corrosion on pipeline damages during a recent earthquake (2014 Napa earthquake). Then, a renewal strategy is proposed that addresses the vulnerability of pipelines from the topological viewpoint in addition to the condition index and failure impact index commonly used in practice decisions. In addition, water distribution networks are often large and complex, which leads to considerable computational time and cost for seismic risk assessment. In this study, a computationally efficient methodology named SeismoPi is developed using Python-based open-source libraries for estimating the seismic damage of buried pipelines. The methodology is capable of performing scenario-based seismic damage analysis of complex buried water networks, identifying critical segments and system connectivity, and estimating the renewal cost. The method presents the interactive outputs on maps so that decision makers can easily visualize the results and identify the riskiest segments that need to be rehabilitated. SeismoPi assists decision makers in developing WDS renewable strategies that account for the effects of corrosion deterioration on their seismic performance. Applications of the proposed framework are demonstrated on a few small- to large-sized water distribution systems.

3. A Deep Neural Network Combined with Molecular Fingerprints (DNN-MF) to Develop Predictive Models for Hydroxyl Radical Rate Constants of Water Contaminants

   Shifa Zhong, Jiajie Hu, and 3 more authors

   Journal of hazardous materials, Nov 2020

2019

1. Behaviors of Expansive Soils Mixed with Polymeric Stabilizing Foams

   Xijin Zhang, Xiong (Bill) Yu, and 2 more authors

   In Geo-Congress 2019, Mar 2019