Xiaojian Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Xiaojian Zhang has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Xilei Zhao
University of Florida
11 shared publications - Qian Ke
Department of Civil and Coastal Engineering University of Florida b Bloomberg 731 Lexington Avenue 1949 Stadium Rd 32611 Gainesville New York FL US USA
3 shared publications - Vladimir A. Paramygin
Department of Civil and Coastal Engineering, University of Florida, Gainesville, Florida
3 shared publications Xilei Zhao
3 shared publications- Yiming Xu
The University of Texas at Austin
3 shared publications - Arthriya Subgranon
Univ. of Florida
2 shared publications
Latest Publications
- Open Access
- 7 July 2026
- Published by Elsevier in International Journal of Disaster Risk Reduction
- Vol. 143
Examining the short-term impact of evacuation orders on traffic conditions: Evidence from Hurricane Ian
- 7 July 2026
- Published by Elsevier in International Journal of Disaster Risk Reduction
- Vol. 143
Open AccessExamining the short-term impact of evacuation orders on traffic conditions: Evidence from Hurricane Ian
- Open Access
- 20 May 2026
- Published by Springer Nature in Urban Lifeline
- Vol. 4  (1) , 14
Post-hurricane building damage assessment using street-view imagery and structured data: a multimodal deep learning approach
Post-event residential building damage assessment supports reconnaissance, screening, and recovery planning following major hazard events. Recent hurricanes have generated large volumes of satellite, aerial, and street-level imagery, creating challenges not of data scarcity but of integrating heterogeneous visual and contextual information into consistent and reviewable damage classifications. This study presents a multimodal deep-learning framework, the Multimodal Swin Transformer (MMST), that combines street-view imagery with structured building and hazard attributes to classify post-hurricane residential building damage. The model is evaluated using a curated dataset derived from extensive Structural Extreme Events Reconnaissance (StEER) field reconnaissance following Hurricane Ian (2022), which incorporates human interpretation, quality control, and selective sampling across impacted communities. Results show that integrating visual features with contextual information such as building age, building value, and wind speed improves classification performance relative to image-only baselines, achieving an accuracy of 92.67%. Attention-based visualizations further enable post-hoc inspection of image regions the model weighted most heavily, supporting qualitative review of model behavior rather than physical interpretation. The proposed MMST serves as a decision-support tool to augment reconnaissance workflows and enhance the continuity of critical community infrastructure in future hurricanes.
- 20 May 2026
- Published by Springer Nature in Urban Lifeline
- Vol. 4  (1) , 14
Open AccessPost-hurricane building damage assessment using street-view imagery and structured data: a multimodal deep learning approach
Post-event residential building damage assessment supports reconnaissance, screening, and recovery planning following major hazard events. Recent hurricanes have generated large volumes of satellite, aerial, and street-level imagery, creating challenges not of data scarcity but of integrating heterogeneous visual and contextual information into consistent and reviewable damage classifications. This study presents a multimodal deep-learning framework, the Multimodal Swin Transformer (MMST), that combines street-view imagery with structured building and hazard attributes to classify post-hurricane residential building damage. The model is evaluated using a curated dataset derived from extensive Structural Extreme Events Reconnaissance (StEER) field reconnaissance following Hurricane Ian (2022), which incorporates human interpretation, quality control, and selective sampling across impacted communities. Results show that integrating visual features with contextual information such as building age, building value, and wind speed improves classification performance relative to image-only baselines, achieving an accuracy of 92.67%. Attention-based visualizations further enable post-hoc inspection of image regions the model weighted most heavily, supporting qualitative review of model behavior rather than physical interpretation. The proposed MMST serves as a decision-support tool to augment reconnaissance workflows and enhance the continuity of critical community infrastructure in future hurricanes.
- Open Access
- 10 September 2024
- Published by Elsevier in Transportation Research Part A: Policy and Practice
- Vol. 190
Situational-aware multi-graph convolutional recurrent network (SA-MGCRN) for travel demand forecasting during wildfires
- 10 September 2024
- Published by Elsevier in Transportation Research Part A: Policy and Practice
- Vol. 190
Open AccessSituational-aware multi-graph convolutional recurrent network (SA-MGCRN) for travel demand forecasting during wildfires
- 21 June 2024
- Published by Springer Nature in GeoInformatica
- Vol. 29  (2) , 175-200
ICN: Interactive convolutional network for forecasting travel demand of shared micromobility
- 21 June 2024
- Published by Springer Nature in GeoInformatica
- Vol. 29  (2) , 175-200
ICN: Interactive convolutional network for forecasting travel demand of shared micromobility
- Open Access
- 13 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25  (10) , 14611-14627
Travel Demand Forecasting: A Fair AI Approach
Artificial Intelligence (AI) and machine learning have been increasingly adopted for travel demand forecasting. The AI-based travel demand forecasting models, though generate accurate predictions, may produce prediction biases and raise fairness issues. Using such biased models for decision-making may lead to transportation policies that exacerbate social inequalities. However, limited studies have been focused on addressing the fairness issues of these models. Therefore, in this study, we propose a novel methodology to develop fairness-aware, highly-accurate travel demand forecasting models. Particularly, the proposed methodology can enhance the fairness of AI models for multiple protected attributes (such as race and income) simultaneously. Specifically, we introduce a new fairness regularization term, which is explicitly designed to measure the correlation between prediction accuracy and multiple protected attributes, into the loss function of the travel demand forecasting model. We conduct two case studies to evaluate the performance of the proposed methodology using real-world ridesourcing-trip data in Chicago, IL and Austin, TX, respectively. Results highlight that our proposed methodology can effectively enhance fairness for multiple protected attributes while preserving prediction accuracy. Additionally, we have compared our methodology with three state-of-the-art methods that adopt the regularization term approach, and the results demonstrate that our approach significantly outperforms them in both preserving prediction accuracy and enhancing fairness. This study can provide transportation professionals with a new tool to achieve fair and accurate travel demand forecasting.
- 13 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25  (10) , 14611-14627
Open AccessTravel Demand Forecasting: A Fair AI Approach
Artificial Intelligence (AI) and machine learning have been increasingly adopted for travel demand forecasting. The AI-based travel demand forecasting models, though generate accurate predictions, may produce prediction biases and raise fairness issues. Using such biased models for decision-making may lead to transportation policies that exacerbate social inequalities. However, limited studies have been focused on addressing the fairness issues of these models. Therefore, in this study, we propose a novel methodology to develop fairness-aware, highly-accurate travel demand forecasting models. Particularly, the proposed methodology can enhance the fairness of AI models for multiple protected attributes (such as race and income) simultaneously. Specifically, we introduce a new fairness regularization term, which is explicitly designed to measure the correlation between prediction accuracy and multiple protected attributes, into the loss function of the travel demand forecasting model. We conduct two case studies to evaluate the performance of the proposed methodology using real-world ridesourcing-trip data in Chicago, IL and Austin, TX, respectively. Results highlight that our proposed methodology can effectively enhance fairness for multiple protected attributes while preserving prediction accuracy. Additionally, we have compared our methodology with three state-of-the-art methods that adopt the regularization term approach, and the results demonstrate that our approach significantly outperforms them in both preserving prediction accuracy and enhancing fairness. This study can provide transportation professionals with a new tool to achieve fair and accurate travel demand forecasting.
- Open Access
- 5 March 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14  (1) , 1-13
Modeling protective action decision-making in earthquakes by using explainable machine learning and video data
Earthquakes pose substantial threats to communities worldwide. Understanding how people respond to the fast-changing environment during earthquakes is crucial for reducing risks and saving lives. This study aims to study people’s protective action decision-making in earthquakes by leveraging explainable machine learning and video data. Specifically, this study first collected real-world CCTV footage and video postings from social media platforms, and then identified and annotated changes in the environment and people’s behavioral responses during the M7.1 2018 Anchorage earthquake. By using the fully annotated video data, we applied XGBoost, a widely-used machine learning method, to model and forecast people’s protective actions (e.g.,drop and cover,hold on, andevacuate) during the earthquake. Then, explainable machine learning techniques were used to reveal the complex, nonlinear relationships between different factors and people’s choices of protective actions. Modeling results confirm that social and environmental cues played critical roles in affecting the probability of different protective actions. Certain factors, such as the earthquake shaking intensity and number of people shown in the environment, displayed evident nonlinear relationships with the probability of choosing toevacuate. These findings can help emergency managers and policymakers design more effective protective action recommendations during earthquakes.
- 5 March 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14  (1) , 1-13
Open AccessModeling protective action decision-making in earthquakes by using explainable machine learning and video data
Earthquakes pose substantial threats to communities worldwide. Understanding how people respond to the fast-changing environment during earthquakes is crucial for reducing risks and saving lives. This study aims to study people’s protective action decision-making in earthquakes by leveraging explainable machine learning and video data. Specifically, this study first collected real-world CCTV footage and video postings from social media platforms, and then identified and annotated changes in the environment and people’s behavioral responses during the M7.1 2018 Anchorage earthquake. By using the fully annotated video data, we applied XGBoost, a widely-used machine learning method, to model and forecast people’s protective actions (e.g.,drop and cover,hold on, andevacuate) during the earthquake. Then, explainable machine learning techniques were used to reveal the complex, nonlinear relationships between different factors and people’s choices of protective actions. Modeling results confirm that social and environmental cues played critical roles in affecting the probability of different protective actions. Certain factors, such as the earthquake shaking intensity and number of people shown in the environment, displayed evident nonlinear relationships with the probability of choosing toevacuate. These findings can help emergency managers and policymakers design more effective protective action recommendations during earthquakes.
- Open Access
- 13 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 7-12
Causality-informed Rapid Post-hurricane Building Damage Detection in Large Scale from InSAR Imagery
Timely and accurate assessment of hurricane-induced building damage is crucial for effective post-hurricane response and recovery efforts. Recently, remote sensing technologies provide large-scale optical or Interferometric Synthetic Aperture Radar (InSAR) imagery data immediately after a disastrous event, which can be readily used to conduct rapid building damage assessment. Compared to optical satellite imageries, the Synthetic Aperture Radar can penetrate cloud cover and provide more complete spatial cover-age of damaged zones in various weather conditions. However, these InSAR imageries often contain highly noisy and mixed signals induced by co-occurring or co-located building damage, flood, flood/wind-induced vegetation changes, as well as anthropogenic activities, making it challenging to extract accurate building damage information. In this paper, we introduced a causality-informed Bayesian network inference approach for rapid post-hurricane building damage detection from InSAR imagery. This approach encoded complex causal dependencies among wind, flood, building damage, and InSAR imagery using a holistic causal Bayesian network. Based on the causal Bayesian network, we further jointly inferred the large-scale unobserved building damage by fusing the information from InSAR imagery with prior physical models of flood and wind, without the need for ground truth labels. Furthermore, we validated our estimation results in a real-world devastating hurricane---the 2022 Hurricane Ian. We gathered and annotated building damage ground truth data in Lee County, Florida, and compared the introduced method's estimation results with the ground truth and benchmarked it against state-of-the-art models to assess the effectiveness of our proposed method. Results show that our method achieves rapid and accurate detection of building damage, with significantly reduced processing time compared to traditional manual inspection methods.
- 13 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 7-12
Open AccessCausality-informed Rapid Post-hurricane Building Damage Detection in Large Scale from InSAR Imagery
Timely and accurate assessment of hurricane-induced building damage is crucial for effective post-hurricane response and recovery efforts. Recently, remote sensing technologies provide large-scale optical or Interferometric Synthetic Aperture Radar (InSAR) imagery data immediately after a disastrous event, which can be readily used to conduct rapid building damage assessment. Compared to optical satellite imageries, the Synthetic Aperture Radar can penetrate cloud cover and provide more complete spatial cover-age of damaged zones in various weather conditions. However, these InSAR imageries often contain highly noisy and mixed signals induced by co-occurring or co-located building damage, flood, flood/wind-induced vegetation changes, as well as anthropogenic activities, making it challenging to extract accurate building damage information. In this paper, we introduced a causality-informed Bayesian network inference approach for rapid post-hurricane building damage detection from InSAR imagery. This approach encoded complex causal dependencies among wind, flood, building damage, and InSAR imagery using a holistic causal Bayesian network. Based on the causal Bayesian network, we further jointly inferred the large-scale unobserved building damage by fusing the information from InSAR imagery with prior physical models of flood and wind, without the need for ground truth labels. Furthermore, we validated our estimation results in a real-world devastating hurricane---the 2022 Hurricane Ian. We gathered and annotated building damage ground truth data in Lee County, Florida, and compared the introduced method's estimation results with the ground truth and benchmarked it against state-of-the-art models to assess the effectiveness of our proposed method. Results show that our method achieves rapid and accurate detection of building damage, with significantly reduced processing time compared to traditional manual inspection methods.
- Open Access
Causality-informed Rapid Post-hurricane Building Damage Detection in Large Scale from InSAR Imagery
Timely and accurate assessment of hurricane-induced building damage is crucial for effective post-hurricane response and recovery efforts. Recently, remote sensing technologies provide large-scale optical or Interferometric Synthetic Aperture Radar (InSAR) imagery data immediately after a disastrous event, which can be readily used to conduct rapid building damage assessment. Compared to optical satellite imageries, the Synthetic Aperture Radar can penetrate cloud cover and provide more complete spatial coverage of damaged zones in various weather conditions. However, these InSAR imageries often contain highly noisy and mixed signals induced by co-occurring or co-located building damage, flood, flood/wind-induced vegetation changes, as well as anthropogenic activities, making it challenging to extract accurate building damage information. In this paper, we introduced an approach for rapid post-hurricane building damage detection from InSAR imagery. This approach encoded complex causal dependencies among wind, flood, building damage, and InSAR imagery using a holistic causal Bayesian network. Based on the causal Bayesian network, we further jointly inferred the large-scale unobserved building damage by fusing the information from InSAR imagery with prior physical models of flood and wind, without the need for ground truth labels. Furthermore, we validated our estimation results in a real-world devastating hurricane -- the 2022 Hurricane Ian. We gathered and annotated building damage ground truth data in Lee County, Florida, and compared the introduced method's estimation results with the ground truth and benchmarked it against state-of-the-art models to assess the effectiveness of our proposed method. Results show that our method achieves rapid and accurate detection of building damage, with significantly reduced processing time compared to traditional manual inspection methods.
Open AccessCausality-informed Rapid Post-hurricane Building Damage Detection in Large Scale from InSAR Imagery
Timely and accurate assessment of hurricane-induced building damage is crucial for effective post-hurricane response and recovery efforts. Recently, remote sensing technologies provide large-scale optical or Interferometric Synthetic Aperture Radar (InSAR) imagery data immediately after a disastrous event, which can be readily used to conduct rapid building damage assessment. Compared to optical satellite imageries, the Synthetic Aperture Radar can penetrate cloud cover and provide more complete spatial coverage of damaged zones in various weather conditions. However, these InSAR imageries often contain highly noisy and mixed signals induced by co-occurring or co-located building damage, flood, flood/wind-induced vegetation changes, as well as anthropogenic activities, making it challenging to extract accurate building damage information. In this paper, we introduced an approach for rapid post-hurricane building damage detection from InSAR imagery. This approach encoded complex causal dependencies among wind, flood, building damage, and InSAR imagery using a holistic causal Bayesian network. Based on the causal Bayesian network, we further jointly inferred the large-scale unobserved building damage by fusing the information from InSAR imagery with prior physical models of flood and wind, without the need for ground truth labels. Furthermore, we validated our estimation results in a real-world devastating hurricane -- the 2022 Hurricane Ian. We gathered and annotated building damage ground truth data in Lee County, Florida, and compared the introduced method's estimation results with the ground truth and benchmarked it against state-of-the-art models to assess the effectiveness of our proposed method. Results show that our method achieves rapid and accurate detection of building damage, with significantly reduced processing time compared to traditional manual inspection methods.