Mohcine Chraibi
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
Mohcine Chraibi has a total of 146 co-authors. Here are the top co-authors by number of shared publications:
- Armin Seyfried
Forschungszentrum Jülich
36 shared publications - Antoine Tordeux
University of Wuppertal
18 shared publications - Andreas Schadschneider
Institute for Theoretical Physics, University of Cologne, 50937 Köln, Germany
17 shared publications Andreas Schadschneider
Institut fuer Theoretische Physik, Albertus-Magnus-Universitat zu Koln, Koeln, GERMANY
8 shared publications- Mohammed Maree
Arab American University
8 shared publications - Ahmed Alia
Institute for Advanced Simulation (IAS-7), Forschungszentrum Jülich, 52425, Jülich, Germany.
6 shared publications
Latest Publications
- Open Access
- 3 November 2026
- Published by Elsevier in Safety Science
- Vol. 207
Crowd dynamics in historical perspective: Reframing the Amritsar massacre through agent-based modelling and social psychology
- 3 November 2026
- Published by Elsevier in Safety Science
- Vol. 207
Open AccessCrowd dynamics in historical perspective: Reframing the Amritsar massacre through agent-based modelling and social psychology
- Open Access
Social LSTM with Dynamic Occupancy Modeling for Realistic Pedestrian Trajectory Prediction
In dynamic and crowded environments, realistic pedestrian trajectory prediction remains a challenging task due to the complex nature of human motion and the mutual influences among individuals. Deep learning models have recently achieved promising results by implicitly learning such patterns from 2D trajectory data. However, most approaches treat pedestrians as point entities, ignoring the physical space that each person occupies. To address these limitations, this paper proposes a novel deep learning model that enhances the Social LSTM with a new Dynamic Occupied Space loss function. This loss function guides Social LSTM in learning to avoid realistic collisions without increasing displacement error across different crowd densities, ranging from low to high, in both homogeneous and heterogeneous density settings. Such a function achieves this by combining the average displacement error with a new collision penalty that is sensitive to scene density and individual spatial occupancy. For efficient training and evaluation, five datasets were generated from real pedestrian trajectories recorded during the Festival of Lights in Lyon 2022. Four datasets represent homogeneous crowd conditions -- low, medium, high, and very high density -- while the fifth corresponds to a heterogeneous density distribution. The experimental findings indicate that the proposed model not only lowers collision rates but also enhances displacement prediction accuracy in each dataset. Specifically, the model achieves up to a 31% reduction in the collision rate and reduces the average displacement error and the final displacement error by 5% and 6%, respectively, on average across all datasets compared to the baseline. Moreover, the proposed model consistently outperforms several state-of-the-art deep learning models across most test sets.
Open AccessSocial LSTM with Dynamic Occupancy Modeling for Realistic Pedestrian Trajectory Prediction
In dynamic and crowded environments, realistic pedestrian trajectory prediction remains a challenging task due to the complex nature of human motion and the mutual influences among individuals. Deep learning models have recently achieved promising results by implicitly learning such patterns from 2D trajectory data. However, most approaches treat pedestrians as point entities, ignoring the physical space that each person occupies. To address these limitations, this paper proposes a novel deep learning model that enhances the Social LSTM with a new Dynamic Occupied Space loss function. This loss function guides Social LSTM in learning to avoid realistic collisions without increasing displacement error across different crowd densities, ranging from low to high, in both homogeneous and heterogeneous density settings. Such a function achieves this by combining the average displacement error with a new collision penalty that is sensitive to scene density and individual spatial occupancy. For efficient training and evaluation, five datasets were generated from real pedestrian trajectories recorded during the Festival of Lights in Lyon 2022. Four datasets represent homogeneous crowd conditions -- low, medium, high, and very high density -- while the fifth corresponds to a heterogeneous density distribution. The experimental findings indicate that the proposed model not only lowers collision rates but also enhances displacement prediction accuracy in each dataset. Specifically, the model achieves up to a 31% reduction in the collision rate and reduces the average displacement error and the final displacement error by 5% and 6%, respectively, on average across all datasets compared to the baseline. Moreover, the proposed model consistently outperforms several state-of-the-art deep learning models across most test sets.
- 26 July 2025
- Published by Springer Nature
- p. 9-36
Exploring Dense Crowd Dynamics: State of the Art and Emerging Paradigms
- 26 July 2025
- Published by Springer Nature
- p. 9-36
Exploring Dense Crowd Dynamics: State of the Art and Emerging Paradigms
- Open Access
- 28 May 2025
- Published by Springer Nature in Fire Technology
- Vol. 61 (6) , 4253-4260
EXIT89: A Foundational Evacuation Model in the High-Rise Fire Safety Landscape
EXIT89 is a pioneering evacuation model developed for high-rise building emergencies, integrating network modeling to simulate occupant movement during crises. This short communication examines its development by Dr. Rita F. Fahy, its applications in critical case studies, and its influence on fire safety codes. The impact of EXIT89 on evacuation modeling and high-rise fire safety is considered, especially in terms of how it laid foundational groundwork for contemporary models.
- 28 May 2025
- Published by Springer Nature in Fire Technology
- Vol. 61 (6) , 4253-4260
Open AccessEXIT89: A Foundational Evacuation Model in the High-Rise Fire Safety Landscape
EXIT89 is a pioneering evacuation model developed for high-rise building emergencies, integrating network modeling to simulate occupant movement during crises. This short communication examines its development by Dr. Rita F. Fahy, its applications in critical case studies, and its influence on fire safety codes. The impact of EXIT89 on evacuation modeling and high-rise fire safety is considered, especially in terms of how it laid foundational groundwork for contemporary models.
- Open Access
- 30 April 2025
- Published by Springer Nature in Scientific Data
- Vol. 12 (1) , 1-10
Dense Crowd Dynamics and Pedestrian Trajectories: A Multiscale Field Dataset from the Festival of Lights in Lyon
The dynamics of dense crowds have received considerable attention from researchers seeking fundamental understanding or aiming to develop data-driven algorithms to predict pedestrian trajectories. However, current research mainly relies on data collected in controlled settings. We present one of the first comprehensive field datasets describing dense pedestrian dynamics at different scales, from contextualized macroscopic crowd flows over hundreds of meters to microscopic trajectories (around 7000 individual trajectories). In addition, a sample of GPS traces, some statistics of contacts and pushes, and a list of non-standard crowd phenomena observed in the video recordings are provided. The data were collected during the 2022 Festival of Lights in Lyon, France, as part of the French-German MADRAS project and cover densities up to 4 pedestrians per square meter. We suggest using this extensive dataset, acquired in complex real-world settings, to benchmark models of pedestrian dynamics.
- 30 April 2025
- Published by Springer Nature in Scientific Data
- Vol. 12 (1) , 1-10
Open AccessDense Crowd Dynamics and Pedestrian Trajectories: A Multiscale Field Dataset from the Festival of Lights in Lyon
The dynamics of dense crowds have received considerable attention from researchers seeking fundamental understanding or aiming to develop data-driven algorithms to predict pedestrian trajectories. However, current research mainly relies on data collected in controlled settings. We present one of the first comprehensive field datasets describing dense pedestrian dynamics at different scales, from contextualized macroscopic crowd flows over hundreds of meters to microscopic trajectories (around 7000 individual trajectories). In addition, a sample of GPS traces, some statistics of contacts and pushes, and a list of non-standard crowd phenomena observed in the video recordings are provided. The data were collected during the 2022 Festival of Lights in Lyon, France, as part of the French-German MADRAS project and cover densities up to 4 pedestrians per square meter. We suggest using this extensive dataset, acquired in complex real-world settings, to benchmark models of pedestrian dynamics.
- Open Access
- 17 February 2025
- Published by Elsevier in Developments in the Built Environment
- Vol. 21, 100626
Multi-scale analysis of fire and evacuation drill in a multi-functional university high-rise building
- 17 February 2025
- Published by Elsevier in Developments in the Built Environment
- Vol. 21, 100626
Open AccessMulti-scale analysis of fire and evacuation drill in a multi-functional university high-rise building
- Open Access
Hybrid Machine Learning and Physics-based Modelling of Pedestrian Pushing Behaviours at Bottlenecks
In high-density crowds, close proximity between pedestrians makes the steady state highly vulnerable to disruption by pushing behaviours, potentially leading to serious accidents. However, the scarcity of experimental data has hindered systematic studies of its mechanisms and accurate modelling. Using behavioural data from bottleneck experiments, we investigate pedestrian heterogeneity in pushing tendencies, showing that pedestrians tend to push under high-motivation and in wider corridors. We introduce a spatial discretization method to encode neighbour states into feature vectors, serving together with pedestrian pushing tendencies as inputs to a random forest model for predicting pushing behaviours. Through comparing speed-headway relationships, we reveal that pushing behaviours correspond to an aggressive space-utilization movement strategy. Consequently, we propose a hybrid machine learning and physics-based model integrating pushing tendencies heterogeneity, pushing behaviours prediction, and dynamic movement strategies adjustment. Validations show that the hybrid model effectively reproduces experimental crowd dynamics and fits to incorporate additional behaviours.
Open AccessHybrid Machine Learning and Physics-based Modelling of Pedestrian Pushing Behaviours at Bottlenecks
In high-density crowds, close proximity between pedestrians makes the steady state highly vulnerable to disruption by pushing behaviours, potentially leading to serious accidents. However, the scarcity of experimental data has hindered systematic studies of its mechanisms and accurate modelling. Using behavioural data from bottleneck experiments, we investigate pedestrian heterogeneity in pushing tendencies, showing that pedestrians tend to push under high-motivation and in wider corridors. We introduce a spatial discretization method to encode neighbour states into feature vectors, serving together with pedestrian pushing tendencies as inputs to a random forest model for predicting pushing behaviours. Through comparing speed-headway relationships, we reveal that pushing behaviours correspond to an aggressive space-utilization movement strategy. Consequently, we propose a hybrid machine learning and physics-based model integrating pushing tendencies heterogeneity, pushing behaviours prediction, and dynamic movement strategies adjustment. Validations show that the hybrid model effectively reproduces experimental crowd dynamics and fits to incorporate additional behaviours.
- Open Access
- 22 November 2024
- Published by Elsevier in Safety Science
- Vol. 183
Walk the Line: The role of gender and culture on the movement patterns of pedestrians based on a multicultural study
- 22 November 2024
- Published by Elsevier in Safety Science
- Vol. 183
Open AccessWalk the Line: The role of gender and culture on the movement patterns of pedestrians based on a multicultural study
- Open Access
- 29 October 2024
- Published by Forschungszentrum Julich, Zentralbibliothek in Collective Dynamics
- Vol. 9, 1-47
Comprehensive Review and New Analysis Software for Single-file Pedestrian Experiments
This paper offers a comprehensive examination of single-file experiments within the field of pedestrian dynamics, providing a thorough review from both theoretical and analytical perspectives. It begins by tracing the historical context of single-file movement studies in pedestrian dynamics. Then, the significance of understanding the fundamental relationships among density, speed, and flow in pedestrian dynamics through the lens of simple single-file systems is explored in depth. Furthermore, we investigate various traffic systems involving human or non-human entities such as ants, mice, bicycles, and cars, and provide insights. We explore the types of experimental setups, data collection methods, and influential factors that affect pedestrian movement. We also define and explain the common concepts concerning single-file movement, particularly in experimental research. Finally, we present a Python tool named ``SingleFileMovementAnalysis'' designed for analyzing single-file experimental data, specifically head trajectories. This tool provides a cohesive approach to preparing and calculating movement metrics like speed, density, and headway. The article aims to stimulate further research and underscore the areas where future researchers can contribute to advancing and enhancing single-file studies.
- 29 October 2024
- Published by Forschungszentrum Julich, Zentralbibliothek in Collective Dynamics
- Vol. 9, 1-47
Open AccessComprehensive Review and New Analysis Software for Single-file Pedestrian Experiments
This paper offers a comprehensive examination of single-file experiments within the field of pedestrian dynamics, providing a thorough review from both theoretical and analytical perspectives. It begins by tracing the historical context of single-file movement studies in pedestrian dynamics. Then, the significance of understanding the fundamental relationships among density, speed, and flow in pedestrian dynamics through the lens of simple single-file systems is explored in depth. Furthermore, we investigate various traffic systems involving human or non-human entities such as ants, mice, bicycles, and cars, and provide insights. We explore the types of experimental setups, data collection methods, and influential factors that affect pedestrian movement. We also define and explain the common concepts concerning single-file movement, particularly in experimental research. Finally, we present a Python tool named ``SingleFileMovementAnalysis'' designed for analyzing single-file experimental data, specifically head trajectories. This tool provides a cohesive approach to preparing and calculating movement metrics like speed, density, and headway. The article aims to stimulate further research and underscore the areas where future researchers can contribute to advancing and enhancing single-file studies.
- Open Access
Dense Crowd Dynamics and Pedestrian Trajectories: A Multiscale Field Study at the Fête des Lumières in Lyon
We present one of the first comprehensive field datasets capturing dense pedestrian dynamics across multiple scales, ranging from macroscopic crowd flows over distances of several hundred meters to microscopic individual trajectories, including approximately 7,000 recorded trajectories. The dataset also includes a sample of GPS traces, statistics on contact and push interactions, as well as a catalog of non-standard crowd phenomena observed in video recordings. Data were collected during the 2022 Festival of Lights in Lyon, France, within the framework of the French-German MADRAS project, covering pedestrian densities up to 4 individuals per square meter.
Open AccessDense Crowd Dynamics and Pedestrian Trajectories: A Multiscale Field Study at the Fête des Lumières in Lyon
We present one of the first comprehensive field datasets capturing dense pedestrian dynamics across multiple scales, ranging from macroscopic crowd flows over distances of several hundred meters to microscopic individual trajectories, including approximately 7,000 recorded trajectories. The dataset also includes a sample of GPS traces, statistics on contact and push interactions, as well as a catalog of non-standard crowd phenomena observed in video recordings. Data were collected during the 2022 Festival of Lights in Lyon, France, within the framework of the French-German MADRAS project, covering pedestrian densities up to 4 individuals per square meter.