Rishav Jaiswal
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
Rishav Jaiswal has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Manoj Kumar Jha
Department of Information Technology, University of Maryland Global Campus, Adelphi, MD 20783, USA
5 shared publications Cancan Yang
McMaster Univ
2 shared publicationsMingsai Xu
Xiamen Univ
2 shared publications- Naresh Bhatta
Kathmandu Univ
2 shared publications - Pranav Kumar Jha
AI Solutions Architect, MKJHA Consulting, Inc., Severn, MD 21144, USA
2 shared publications - Rupesh Kumar Yadav
Department of Civil Engineering, College of Engineering, Design and Computing, University of Colorado, Denver, CO 80204, USA
2 shared publications
Latest Publications
- 1 February 2027
- Published by American Society of Civil Engineers (ASCE) in Journal of Structural Design and Construction Practice
- Vol. 32 (1) , 04026100
AI-Enhanced Data-Driven Approach to Model the Mechanical Behavior of Sustainable Geopolymer Concrete
The growing environmental burden of ordinary portland cement has accelerated the search for sustainable alternatives. Geopolymer concrete (GPC), synthesized from industrial byproducts such as fly ash and slag, is a promising candidate. However, its compressive strength is difficult to predict because numerous mix and curing variables interact in complex, nonlinear ways. This study develops and validates an interpretable machine learning framework for forecasting GPC compressive strength. A curated data set of 350 samples was used, containing eight independent variables, i.e., fly ash, ground granulated blast-furnace slag, NaOH molarity, coarse aggregate, recycled aggregate, curing temperature, curing time, and age of testing, and one dependent variable, i.e., compressive strength. Six models (linear regression, decision tree, gradient boosting, support vector regression, artificial neural networks, and random forest) were trained and optimized. Their outputs were integrated into a stacking ensemble, i.e., the super learner (SL) model, with random forest as the metalearner. Performance was evaluated using R 2 , root mean square error (RMSE), and mean absolute percentage error (MAPE) under 10-fold cross-validation and a held-out test set. The SL achieved R 2 = 0.994 , RMSE = 0.90 MPa , and MAPE = 1.4 % , consistently outperforming all base learners and surpassing results reported in recent studies when benchmarked under comparable variable ranges. Model interpretability was ensured through Shapley Additive exPlanations and permutation sensitivity analyses, which identified curing time, NaOH concentration, test age, and curing temperature as dominant predictors. The novelty of this work lies in demonstrating that a stacking ensemble with transparent feature attribution can markedly improve accuracy and trustworthiness in predicting GPC strength, offering a rapid and nondestructive tool for sustainable mix design optimization.
- 1 February 2027
- Published by American Society of Civil Engineers (ASCE) in Journal of Structural Design and Construction Practice
- Vol. 32 (1) , 04026100
AI-Enhanced Data-Driven Approach to Model the Mechanical Behavior of Sustainable Geopolymer Concrete
The growing environmental burden of ordinary portland cement has accelerated the search for sustainable alternatives. Geopolymer concrete (GPC), synthesized from industrial byproducts such as fly ash and slag, is a promising candidate. However, its compressive strength is difficult to predict because numerous mix and curing variables interact in complex, nonlinear ways. This study develops and validates an interpretable machine learning framework for forecasting GPC compressive strength. A curated data set of 350 samples was used, containing eight independent variables, i.e., fly ash, ground granulated blast-furnace slag, NaOH molarity, coarse aggregate, recycled aggregate, curing temperature, curing time, and age of testing, and one dependent variable, i.e., compressive strength. Six models (linear regression, decision tree, gradient boosting, support vector regression, artificial neural networks, and random forest) were trained and optimized. Their outputs were integrated into a stacking ensemble, i.e., the super learner (SL) model, with random forest as the metalearner. Performance was evaluated using R 2 , root mean square error (RMSE), and mean absolute percentage error (MAPE) under 10-fold cross-validation and a held-out test set. The SL achieved R 2 = 0.994 , RMSE = 0.90 MPa , and MAPE = 1.4 % , consistently outperforming all base learners and surpassing results reported in recent studies when benchmarked under comparable variable ranges. Model interpretability was ensured through Shapley Additive exPlanations and permutation sensitivity analyses, which identified curing time, NaOH concentration, test age, and curing temperature as dominant predictors. The novelty of this work lies in demonstrating that a stacking ensemble with transparent feature attribution can markedly improve accuracy and trustworthiness in predicting GPC strength, offering a rapid and nondestructive tool for sustainable mix design optimization.
- Open Access
- 20 October 2026
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 10 (10) , 354
Synthetic Transit Trip-Record Generation Using Deep Generative Models for Travel Demand Modeling
Synthetic transit trip-record generation can support activity-based and agent-based travel demand modeling by providing disaggregate records with realistic spatial, temporal, and operational characteristics. Traditional population synthesis methods such as Iterative Proportional Fitting and Iterative Proportional Updating remain widely used, but high-dimensional mixed-type travel data can be difficult to reproduce. This study evaluates synthetic transit trip-record generation, rather than complete household- and person-level population synthesis, using the Minnesota Travel Behavior Inventory 2021 Transit On-Board Survey. Two established deep tabular generative models, Conditional Tabular Generative Adversarial Network (CTGAN) and Tabular Variational Autoencoder (TVAE), are evaluated alongside an independent empirical marginal-sampling baseline. Duration-derived variables are excluded from the primary analysis because 2081 of 2670 records lack observed alighting timestamps. Evaluation combines marginal fidelity, continuous correlation preservation, route–stop and route–time joint distributions, spatial Jensen–Shannon distance, and Train-on-Synthetic, Test-on-Real (TSTR) utility. The independent marginal baseline closely reproduces individual feature distributions but shows substantially weaker correlation preservation and downstream utility, demonstrating that strong univariate fidelity alone does not ensure preservation of task-relevant structure. TVAE shows the strongest continuous correlation fidelity, with a mean absolute correlation difference of 0.037, compared with 0.214 for CTGAN and 0.267 for the independent marginal baseline. However, TVAE has weaker marginal fidelity for boarding-stop ID, alighting-stop ID, and time period than both alternatives. Its TSTR accuracy of 0.530 has an overlapping 95% bootstrap confidence interval with the real-data benchmark accuracy of 0.500, providing no evidence of superior predictive utility. The results demonstrate the importance of complementary marginal, multivariate, spatial, and downstream validation when assessing synthetic transportation data.
- 20 October 2026
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 10 (10) , 354
Open AccessSynthetic Transit Trip-Record Generation Using Deep Generative Models for Travel Demand Modeling
Synthetic transit trip-record generation can support activity-based and agent-based travel demand modeling by providing disaggregate records with realistic spatial, temporal, and operational characteristics. Traditional population synthesis methods such as Iterative Proportional Fitting and Iterative Proportional Updating remain widely used, but high-dimensional mixed-type travel data can be difficult to reproduce. This study evaluates synthetic transit trip-record generation, rather than complete household- and person-level population synthesis, using the Minnesota Travel Behavior Inventory 2021 Transit On-Board Survey. Two established deep tabular generative models, Conditional Tabular Generative Adversarial Network (CTGAN) and Tabular Variational Autoencoder (TVAE), are evaluated alongside an independent empirical marginal-sampling baseline. Duration-derived variables are excluded from the primary analysis because 2081 of 2670 records lack observed alighting timestamps. Evaluation combines marginal fidelity, continuous correlation preservation, route–stop and route–time joint distributions, spatial Jensen–Shannon distance, and Train-on-Synthetic, Test-on-Real (TSTR) utility. The independent marginal baseline closely reproduces individual feature distributions but shows substantially weaker correlation preservation and downstream utility, demonstrating that strong univariate fidelity alone does not ensure preservation of task-relevant structure. TVAE shows the strongest continuous correlation fidelity, with a mean absolute correlation difference of 0.037, compared with 0.214 for CTGAN and 0.267 for the independent marginal baseline. However, TVAE has weaker marginal fidelity for boarding-stop ID, alighting-stop ID, and time period than both alternatives. Its TSTR accuracy of 0.530 has an overlapping 95% bootstrap confidence interval with the real-data benchmark accuracy of 0.500, providing no evidence of superior predictive utility. The results demonstrate the importance of complementary marginal, multivariate, spatial, and downstream validation when assessing synthetic transportation data.
- 1 June 2026
- Published by American Society of Civil Engineers (ASCE) in Journal of Structural Engineering
- Vol. 152 (6) , 04026063
Near-Ground Lateral Load Tests: Evaluating Ultrahigh-Performance Concrete for Enhanced Shear Performance in Precast Column-to-Pile Shaft Systems
Precast concrete columns connected to pile shaft foundations through socket connections rely on the thin-walled pile shaft for load transfer to the ground, which makes them inherently less ...
- 1 June 2026
- Published by American Society of Civil Engineers (ASCE) in Journal of Structural Engineering
- Vol. 152 (6) , 04026063
Near-Ground Lateral Load Tests: Evaluating Ultrahigh-Performance Concrete for Enhanced Shear Performance in Precast Column-to-Pile Shaft Systems
Precast concrete columns connected to pile shaft foundations through socket connections rely on the thin-walled pile shaft for load transfer to the ground, which makes them inherently less ...
- Open Access
- 6 April 2026
- Published by Elsevier in Structures
- Vol. 88
An interpretable machine learning approach for shear capacity prediction of prestressed UHPC bridge girders with GUI deployment
- 6 April 2026
- Published by Elsevier in Structures
- Vol. 88
Open AccessAn interpretable machine learning approach for shear capacity prediction of prestressed UHPC bridge girders with GUI deployment
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Using Machine Learning to Examine the Disparity in Transportation Equity
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Using Machine Learning to Examine the Disparity in Transportation Equity
- 23 November 2025
- Published by Springer Nature
- p. 73-85
Coastal Bridge Climate Vulnerability Mapping: Network-Level Flood Scour Risk Assessment in Nova Scotia
- 23 November 2025
- Published by Springer Nature
- p. 73-85
Coastal Bridge Climate Vulnerability Mapping: Network-Level Flood Scour Risk Assessment in Nova Scotia
- Open Access
- 3 November 2025
- Published by MDPI AG in Future Transportation
- Vol. 5 (4) , 161
A Machine Learning Approach to Traffic Congestion Hotspot Identification and Prediction
Travel-time delays due to recurring congestion cause productivity loss, increase the likelihood of accidents, and lead to environmental pollution due to greenhouse gas emissions. The National Highway Traffic Safety Administration in the United States has listed several driver assistance technologies that are now common in most newer vehicles. While these technologies can help reduce the likelihood of traffic-related accidents, they do little to reduce recurring congestion in urban areas. Recurring congestion during rush hours is prevalent, for example, along Interstate 95 and Capital Beltway 495 in the Baltimore-Washington area. Such congestion also enhances the likelihood of crashes. Previous approaches to hotspot identification are primarily theoretical, which limits their practical applicability. In this paper, we develop a Machine Learning (ML) approach that integrates geospatial data with artificial neural networks to predict traffic congestion hotspots during rush hour. The approach uses live traffic sensor data. A case study from Maryland is presented. The result shows top hotspot segments across Maryland. Using a snapshot of hotspots at eight different time periods, the likelihood of hotspot locations is predicted using an artificial neural network. The framework is validated using live loop detector data (speed and volume) from Maryland freeways, particularly I-495 and I-95. The research can serve as a valuable tool for traffic congestion hotspot identification and travel-time prediction.
- 3 November 2025
- Published by MDPI AG in Future Transportation
- Vol. 5 (4) , 161
Open AccessA Machine Learning Approach to Traffic Congestion Hotspot Identification and Prediction
Travel-time delays due to recurring congestion cause productivity loss, increase the likelihood of accidents, and lead to environmental pollution due to greenhouse gas emissions. The National Highway Traffic Safety Administration in the United States has listed several driver assistance technologies that are now common in most newer vehicles. While these technologies can help reduce the likelihood of traffic-related accidents, they do little to reduce recurring congestion in urban areas. Recurring congestion during rush hours is prevalent, for example, along Interstate 95 and Capital Beltway 495 in the Baltimore-Washington area. Such congestion also enhances the likelihood of crashes. Previous approaches to hotspot identification are primarily theoretical, which limits their practical applicability. In this paper, we develop a Machine Learning (ML) approach that integrates geospatial data with artificial neural networks to predict traffic congestion hotspots during rush hour. The approach uses live traffic sensor data. A case study from Maryland is presented. The result shows top hotspot segments across Maryland. Using a snapshot of hotspots at eight different time periods, the likelihood of hotspot locations is predicted using an artificial neural network. The framework is validated using live loop detector data (speed and volume) from Maryland freeways, particularly I-495 and I-95. The research can serve as a valuable tool for traffic congestion hotspot identification and travel-time prediction.
- 27 September 2025
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2680 (1) , 748-763
Assessing Disparities in Road Transport Services in Kenya: Geographic Information System and Machine Learning Approach
Regional disparities in road infrastructure access in Kenya hinder socioeconomic development and challenge progress toward the Vision 2030 goals. This study addresses spatial inequality in transport provision by developing a transport network need index (TNNI) based on socioeconomic indicators and comparing it with existing road network density, termed transport network provision (TNP). The difference between TNNI and TNP yields the index of disparity between needs and provision (IDNP), identifying counties that are over- or under-served relative to their development needs. Machine learning models are employed to predict road density based on socioeconomic features, with the best-performing model selected through accuracy metrics. Shapley additive explanations (SHAP) are used to interpret the model and determine the empirical importance of each input feature. These SHAP-based weights are compared with literature-based weights used in TNNI to assess disparities in factor prioritization. Results highlight critical spatial disparities, with counties such as Turkana, Wajir, and Mandera falling into the most under-served category (IDNP >0.8). SHAP analysis reveals that population density is the dominant driver of current road provision (56.8% weight), while poverty and unemployment, despite their policy relevance, are underrepresented in actual infrastructure allocation. This twofold analysis—identifying both regional service gaps through IDNP and mismatches in factor prioritization—provides critical insights for policymakers. By pinpointing under-served regions and highlighting which socioeconomic drivers are being overlooked, the study offers a robust, data-driven framework for guiding equitable infrastructure investments, advancing transport justice, and supporting diversity and inclusion in Kenya’s road transport planning.
- 27 September 2025
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2680 (1) , 748-763
Assessing Disparities in Road Transport Services in Kenya: Geographic Information System and Machine Learning Approach
Regional disparities in road infrastructure access in Kenya hinder socioeconomic development and challenge progress toward the Vision 2030 goals. This study addresses spatial inequality in transport provision by developing a transport network need index (TNNI) based on socioeconomic indicators and comparing it with existing road network density, termed transport network provision (TNP). The difference between TNNI and TNP yields the index of disparity between needs and provision (IDNP), identifying counties that are over- or under-served relative to their development needs. Machine learning models are employed to predict road density based on socioeconomic features, with the best-performing model selected through accuracy metrics. Shapley additive explanations (SHAP) are used to interpret the model and determine the empirical importance of each input feature. These SHAP-based weights are compared with literature-based weights used in TNNI to assess disparities in factor prioritization. Results highlight critical spatial disparities, with counties such as Turkana, Wajir, and Mandera falling into the most under-served category (IDNP >0.8). SHAP analysis reveals that population density is the dominant driver of current road provision (56.8% weight), while poverty and unemployment, despite their policy relevance, are underrepresented in actual infrastructure allocation. This twofold analysis—identifying both regional service gaps through IDNP and mismatches in factor prioritization—provides critical insights for policymakers. By pinpointing under-served regions and highlighting which socioeconomic drivers are being overlooked, the study offers a robust, data-driven framework for guiding equitable infrastructure investments, advancing transport justice, and supporting diversity and inclusion in Kenya’s road transport planning.
- Open Access
- 4 November 2024
- Published by Springer Nature in Research Square
AI-Enhanced Data-Driven Approach to Model the Mechanical Behavior of Sustainable Geopolymer Concrete
The increasing environmental concerns associated with Ordinary Portland Cement (OPC) production have driven research towards alternative, sustainable construction materials. Geopolymer concrete (GPC) has emerged as a promising eco-friendly substitute, offering reduced carbon emissions and improved mechanical properties. However, accurately predicting the compressive strength of GPC remains a complex task due to the numerous variables influencing its performance, such as material properties, mix proportions, and curing conditions. This study develops an interpretable machine learning (ML) model to predict the compressive strength of geopolymer concrete, leveraging various ML techniques, including linear regression, decision trees (DT), gradient boosting, support vector regression (SVR), artificial neural networks (ANN), and random forests (RF). To enhance prediction accuracy, a super learner model is employed, integrating these individual techniques. The model's performance is evaluated using metrics such as the coefficient of determination (R²), mean absolute percentage error (MAPE), mean square error (MSE), and root mean square error (RMSE). Additionally, SHAP values and sensitivity analysis are conducted to quantify the impact of each input parameter on the predictions, ensuring the model's transparency and reliability. The proposed approach provides a robust framework for accurately forecasting the compressive strength of geopolymer concrete, thereby contributing to the advancement of sustainable construction practices.
- 4 November 2024
- Published by Springer Nature in Research Square
Open AccessAI-Enhanced Data-Driven Approach to Model the Mechanical Behavior of Sustainable Geopolymer Concrete
The increasing environmental concerns associated with Ordinary Portland Cement (OPC) production have driven research towards alternative, sustainable construction materials. Geopolymer concrete (GPC) has emerged as a promising eco-friendly substitute, offering reduced carbon emissions and improved mechanical properties. However, accurately predicting the compressive strength of GPC remains a complex task due to the numerous variables influencing its performance, such as material properties, mix proportions, and curing conditions. This study develops an interpretable machine learning (ML) model to predict the compressive strength of geopolymer concrete, leveraging various ML techniques, including linear regression, decision trees (DT), gradient boosting, support vector regression (SVR), artificial neural networks (ANN), and random forests (RF). To enhance prediction accuracy, a super learner model is employed, integrating these individual techniques. The model's performance is evaluated using metrics such as the coefficient of determination (R²), mean absolute percentage error (MAPE), mean square error (MSE), and root mean square error (RMSE). Additionally, SHAP values and sensitivity analysis are conducted to quantify the impact of each input parameter on the predictions, ensuring the model's transparency and reliability. The proposed approach provides a robust framework for accurately forecasting the compressive strength of geopolymer concrete, thereby contributing to the advancement of sustainable construction practices.