HSHedieh Soltanpour

Hedieh Soltanpour

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hedieh Soltanpour has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Multi-hazard susceptibility mapping in a karst context using a machine-learning method (MaxEnt)

    by Hedieh Soltanpour, Kamal Serrhini, Joel C. Gill, Sven Fuchs, Solmaz Mohadjer

    In this study, we extend the application of the Maximum Entropy model (MaxEnt), traditionally applied to ecological research and less explored in natural hazard studies, to a novel context by characterising a multi-hazard scenario (i.e., flood-triggered sinkholes) in the Orléans karst region (Val d'Orléans) of France. Many regions of the world exhibit complex hazard landscapes where networks of multi-hazard interrelationships (cascades) pose challenges due to the potential interactions between hazards and the different temporal and spatial scales of hazard events. While mountainous, coastal and volcanic regions have been recognised as multi-hazard forming zones, karst terrains have received little attention despite being prone to multi-hazard events due to their distinct geology, geomorphology, hydrogeology and other environmental characteristics. Incorporating karst-specific multi-hazard scenarios into resilience planning processes supports disaster risk reduction efforts by raising the awareness of citizens, protecting elements at risk and facilitating decisions on disaster prevention. To support this aim, we developed a multi-hazard susceptibility map for the karst region of Val d'Orléans that characterises flood-triggered sinkholes. We applied MaxEnt, a machine learning method, to forecast the spatial probability distribution of flood-triggered sinkholes. Model inputs included the location of past sinkhole occurrences and geo-environmental factors contributing to sinkhole formation (e.g., topography, local geology, hydrology and flood hazard). We validated the performance of the model by initially using 70 % of the sinkhole inventory data and keeping the remaining 30 % for testing. This validation process assessed the model's performance using the Area Under the Curve of the Receiver Operating Characteristic (AUC-ROC). The resulting map reveals areas located up to 1 km south of the Loire River and areas with lowest elevation with highest susceptibility to flood-triggered sinkholes. We conclude that our approach to producing this type of multi-hazard scenario and map is useful for identifying flood-triggered sinkholes in Val d'Orléans and other karst areas around the globe, supporting effective land use planning.


  • Évaluation de la susceptibilité multi-aléas dans les zones karstiques : étude de cas dans la région d'Orléans, France

    by Hedieh Soltanpour

    L'objectif principal de cette thèse est de contribuer à l'amélioration de la gestion des risques multi-aléas dans le contexte des terrains karstiques, en développant et en évaluant une carte intégrée de susceptibilité multi-aléas pour deux dangers interconnectés (dolines déclenchées par des inondations), en utilisant un algorithme d'apprentissage automatique moins exploré (Maximum Entropy). L'efficacité de la carte produite est également évaluée grâce aux retours d'experts locaux recueillis via un sondage en ligne. Cette thèse intègre donc deux composantes de recherche : la modélisation d'une carte de susceptibilité multi-aléas et l'engagement des parties prenantes pour son évaluation. Cette recherche est motivée par une lacune mondiale dans la perception des terrains karstiques comme zones à risques multiples et par le besoin d'évaluations multi-aléas dans la planification de la réduction des risques de catastrophes en France. Cette thèse s'appuie sur des études existantes sur les dolines, adoptant une perspective multi-aléas. Les résultats confirment que la gestion future de la réduction des risques dans l’étude de cas doit être abordée sous l’angle d’une approche multi-aléas. Elle plaide en faveur d’une évaluation multi-aléas dans les zones karstiques, plutôt que de considérer les aléas pertinents de manière isolée. Cette approche permet une utilisation plus efficace des ressources en identifiant et en atténuant les zones de chevauchement où les aléas interconnectés se superposent, comme dans les communes de Bou, Darvoy, Saint-Denis-en-Val et Chécy. Notre carte de susceptibilité multi-aléas intègre les occurrences historiques d'effondrements, ainsi que des facteurs hydrologiques, géologiques, topographiques et les zones à risque d'inondation. Les résultats révèlent que les zones de basse altitude, dans un contexte karstique et de plaine inondable, sont les plus exposées. Cette recherche soutient la révision des règles institutionnelles et administratives pour adopter une approche multi-aléas, particulièrement dans les environnements karstiques.

  • Open Access

    Reply on RC1

    by Hedieh Soltanpour, Kamal Serrhini, Joel C. Gill, Sven Fuchs, Solmaz Mohadjer

    In this study, we extend the application of the Maximum Entropy model (MaxEnt), traditionally applied to ecological research and less explored in natural hazard studies, to a novel context by characterising a multi-hazard scenario (i.e., flood-triggered sinkholes) in the Orléans karst region (Val d'Orléans) of France. Many regions of the world exhibit complex hazard landscapes where networks of multi-hazard interrelationships (cascades) pose challenges due to the potential interactions between hazards and the different temporal and spatial scales of hazard events. While mountainous, coastal and volcanic regions have been recognised as multi-hazard forming zones, karst terrains have received little attention despite being prone to multi-hazard events due to their distinct geology, geomorphology, hydrogeology and other environmental characteristics. Incorporating karst-specific multi-hazard scenarios supports disaster risk reduction efforts by raising the awareness of citizens, protecting elements at risk and facilitating decisions on disaster prevention. To support this aim, we developed a multi-hazard susceptibility map for the karst region of Val d'Orléans that characterises flood-triggered sinkholes. We applied MaxEnt, a machine learning method, to forecast the spatial probability distribution of flood-triggered sinkholes. Model inputs included the location of past sinkhole occurrences and geo-environmental factors contributing to sinkhole formation (e.g., topography, local geology, hydrology and flood hazard). We validated the performance of the model by initially using 70 % of the sinkhole inventory data and keeping the remaining 30 % for testing. This validation process assessed the model's performance using the Area Under the Curve of the Receiver Operating Characteristic (AUC-ROC). The resulting map reveals areas located up to 1 km south of the Loire River and areas with lowest elevation with highest susceptibility to flood-triggered sinkholes. We conclude that our approach to producing this type of multi-hazard scenario and map is useful for identifying flood-triggered sinkholes in Val d'Orléans and other karst areas around the globe, supporting effective land use planning.

  • Open Access

    Reply on RC2

    by Hedieh Soltanpour, Kamal Serrhini, Joel C. Gill, Sven Fuchs, Solmaz Mohadjer

    In this study, we extend the application of the Maximum Entropy model (MaxEnt), traditionally applied to ecological research and less explored in natural hazard studies, to a novel context by characterising a multi-hazard scenario (i.e., flood-triggered sinkholes) in the Orléans karst region (Val d'Orléans) of France. Many regions of the world exhibit complex hazard landscapes where networks of multi-hazard interrelationships (cascades) pose challenges due to the potential interactions between hazards and the different temporal and spatial scales of hazard events. While mountainous, coastal and volcanic regions have been recognised as multi-hazard forming zones, karst terrains have received little attention despite being prone to multi-hazard events due to their distinct geology, geomorphology, hydrogeology and other environmental characteristics. Incorporating karst-specific multi-hazard scenarios supports disaster risk reduction efforts by raising the awareness of citizens, protecting elements at risk and facilitating decisions on disaster prevention. To support this aim, we developed a multi-hazard susceptibility map for the karst region of Val d'Orléans that characterises flood-triggered sinkholes. We applied MaxEnt, a machine learning method, to forecast the spatial probability distribution of flood-triggered sinkholes. Model inputs included the location of past sinkhole occurrences and geo-environmental factors contributing to sinkhole formation (e.g., topography, local geology, hydrology and flood hazard). We validated the performance of the model by initially using 70 % of the sinkhole inventory data and keeping the remaining 30 % for testing. This validation process assessed the model's performance using the Area Under the Curve of the Receiver Operating Characteristic (AUC-ROC). The resulting map reveals areas located up to 1 km south of the Loire River and areas with lowest elevation with highest susceptibility to flood-triggered sinkholes. We conclude that our approach to producing this type of multi-hazard scenario and map is useful for identifying flood-triggered sinkholes in Val d'Orléans and other karst areas around the globe, supporting effective land use planning.

  • Open Access

    Comment on egusphere-2024-1779

    by Hedieh Soltanpour, Kamal Serrhini, Joel C. Gill, Sven Fuchs, Solmaz Mohadjer

    In this study, we extend the application of the Maximum Entropy model (MaxEnt), traditionally applied to ecological research and less explored in natural hazard studies, to a novel context by characterising a multi-hazard scenario (i.e., flood-triggered sinkholes) in the Orléans karst region (Val d'Orléans) of France. Many regions of the world exhibit complex hazard landscapes where networks of multi-hazard interrelationships (cascades) pose challenges due to the potential interactions between hazards and the different temporal and spatial scales of hazard events. While mountainous, coastal and volcanic regions have been recognised as multi-hazard forming zones, karst terrains have received little attention despite being prone to multi-hazard events due to their distinct geology, geomorphology, hydrogeology and other environmental characteristics. Incorporating karst-specific multi-hazard scenarios supports disaster risk reduction efforts by raising the awareness of citizens, protecting elements at risk and facilitating decisions on disaster prevention. To support this aim, we developed a multi-hazard susceptibility map for the karst region of Val d'Orléans that characterises flood-triggered sinkholes. We applied MaxEnt, a machine learning method, to forecast the spatial probability distribution of flood-triggered sinkholes. Model inputs included the location of past sinkhole occurrences and geo-environmental factors contributing to sinkhole formation (e.g., topography, local geology, hydrology and flood hazard). We validated the performance of the model by initially using 70 % of the sinkhole inventory data and keeping the remaining 30 % for testing. This validation process assessed the model's performance using the Area Under the Curve of the Receiver Operating Characteristic (AUC-ROC). The resulting map reveals areas located up to 1 km south of the Loire River and areas with lowest elevation with highest susceptibility to flood-triggered sinkholes. We conclude that our approach to producing this type of multi-hazard scenario and map is useful for identifying flood-triggered sinkholes in Val d'Orléans and other karst areas around the globe, supporting effective land use planning.

  • Open Access

    Comment on egusphere-2024-1779

    by Hedieh Soltanpour, Kamal Serrhini, Joel C. Gill, Sven Fuchs, Solmaz Mohadjer

    In this study, we extend the application of the Maximum Entropy model (MaxEnt), traditionally applied to ecological research and less explored in natural hazard studies, to a novel context by characterising a multi-hazard scenario (i.e., flood-triggered sinkholes) in the Orléans karst region (Val d'Orléans) of France. Many regions of the world exhibit complex hazard landscapes where networks of multi-hazard interrelationships (cascades) pose challenges due to the potential interactions between hazards and the different temporal and spatial scales of hazard events. While mountainous, coastal and volcanic regions have been recognised as multi-hazard forming zones, karst terrains have received little attention despite being prone to multi-hazard events due to their distinct geology, geomorphology, hydrogeology and other environmental characteristics. Incorporating karst-specific multi-hazard scenarios supports disaster risk reduction efforts by raising the awareness of citizens, protecting elements at risk and facilitating decisions on disaster prevention. To support this aim, we developed a multi-hazard susceptibility map for the karst region of Val d'Orléans that characterises flood-triggered sinkholes. We applied MaxEnt, a machine learning method, to forecast the spatial probability distribution of flood-triggered sinkholes. Model inputs included the location of past sinkhole occurrences and geo-environmental factors contributing to sinkhole formation (e.g., topography, local geology, hydrology and flood hazard). We validated the performance of the model by initially using 70 % of the sinkhole inventory data and keeping the remaining 30 % for testing. This validation process assessed the model's performance using the Area Under the Curve of the Receiver Operating Characteristic (AUC-ROC). The resulting map reveals areas located up to 1 km south of the Loire River and areas with lowest elevation with highest susceptibility to flood-triggered sinkholes. We conclude that our approach to producing this type of multi-hazard scenario and map is useful for identifying flood-triggered sinkholes in Val d'Orléans and other karst areas around the globe, supporting effective land use planning.

  • Open Access

    Maximum Entropy Modeling for Multi-Hazard Spatial Distribution: A Case Study of Flood-Triggered Sinkholes

    by Hedieh Soltanpour, Kamal Serrhini, Joel C Gill, Sven Fuchs, Solmaz Mohadjer

    Recent decades have seen a growing availability of detailed geo-environmental data, coupled with powerful open-access software and machine-learning algorithms, driving significant advancements in natural hazard forecasting. Exploring cutting-edge machine-learning techniques is essential to understanding their strengths and limitations, which vary with factors such as data quality, hazard types, and the complexity of variable relationships. In this study, we extend the application of the Maximum Entropy model (MaxEnt) initially applied to ecological research to a novel context by characterising a common multi-hazard scenario in karst settings (i.e., flood-triggered sinkholes). While MaxEnt has been widely used by ecologists to model species distributions, its application in natural hazard modelling, particularly for hidden hazards like sinkholes in karst regions, remains underexplored.Here, we applied MaxEnt to forecast the spatial probability distribution of flood-triggered sinkholes. Model inputs included past sinkhole occurrence data and geo-environmental factors such as topography, local geology, hydrology, and flood hazard. The model was validated using 70% of the sinkhole inventory for training and the remaining 30% for testing, with performance assessed using the Area Under the Curve of the Receiver Operating Characteristic (AUC-ROC).The resulting susceptibility map highlights areas up to 1 km south of the Loire River and low-elevation zones as most vulnerable to flood-triggered sinkholes. Our findings demonstrate that this multi-hazard scenario mapping approach is a valuable tool for identifying flood-triggered sinkholes in Val d’Orléans and other karst regions worldwide, supporting effective land-use planning. By applying MaxEnt at different spatial scales, we also identified limitations affecting the model’s final accuracy, which provide insights for future improvements.

  • Open Access

    Multi-hazard susceptibility mapping in the karst context using a machine-learning method (MaxEnt)

    by Hedieh Soltanpour, Kamal Serrhini, Joel C. Gill, Sven Fuchs, Solmaz Mohadjer

    In this study, we extend the application of the Maximum Entropy model (MaxEnt), traditionally applied to ecological research and less explored in natural hazard studies, to a novel context by characterising a multi-hazard scenario (i.e., flood-triggered sinkholes) in the Orléans karst region (Val d'Orléans) of France. Many regions of the world exhibit complex hazard landscapes where networks of multi-hazard interrelationships (cascades) pose challenges due to the potential interactions between hazards and the different temporal and spatial scales of hazard events. While mountainous, coastal and volcanic regions have been recognised as multi-hazard forming zones, karst terrains have received little attention despite being prone to multi-hazard events due to their distinct geology, geomorphology, hydrogeology and other environmental characteristics. Incorporating karst-specific multi-hazard scenarios supports disaster risk reduction efforts by raising the awareness of citizens, protecting elements at risk and facilitating decisions on disaster prevention. To support this aim, we developed a multi-hazard susceptibility map for the karst region of Val d'Orléans that characterises flood-triggered sinkholes. We applied MaxEnt, a machine learning method, to forecast the spatial probability distribution of flood-triggered sinkholes. Model inputs included the location of past sinkhole occurrences and geo-environmental factors contributing to sinkhole formation (e.g., topography, local geology, hydrology and flood hazard). We validated the performance of the model by initially using 70 % of the sinkhole inventory data and keeping the remaining 30 % for testing. This validation process assessed the model's performance using the Area Under the Curve of the Receiver Operating Characteristic (AUC-ROC). The resulting map reveals areas located up to 1 km south of the Loire River and areas with lowest elevation with highest susceptibility to flood-triggered sinkholes. We conclude that our approach to producing this type of multi-hazard scenario and map is useful for identifying flood-triggered sinkholes in Val d'Orléans and other karst areas around the globe, supporting effective land use planning.


  • Open Access

    Vulnérabilité non-structurelle et résilience territoriale en situation de multi-risque. Perception et préférences cartographiques des aléas effondrement et inondation (val d’Orléans, Loiret, France)

    by Kamal Serrhini, Yolaine Moy, Gildas Noury, José Serrano, Hedieh Soltanpour

    En tant qu’élément central de la politique nationale de gestion des risques naturels, le Plan de Prévention du Risque inondation (PPRi) est fondé sur une logique du mono-aléa. Le val d’Orléans (VdO) est concerné par l’interaction entre deux aléas naturels majeurs, les inondations et les effondrements karstiques. L’existence du PPRi impose aux collectivités territoriales concernées (mairies) de développer un Document d’Information Communal sur les RIsques Majeurs (DICRIM). Une rapide analyse de ces dispositifs de communication montre clairement une insuffisance des politiques de prévention des effondrements de cavités karstiques limitant le développement d’une culture du risque ce qui peut aggraver les dommages potentiels et mettre en danger des vies humaines. A l’aide d’une enquête par questionnaire, cette contribution s’intéresse à l’évaluation de la perception du risque karstique par les communes (mairies) et les acteurs majeurs du VdO (Préfecture, DDT, DREAL). Cette publication focalise sur les mesures préventives non-structurelles en termes de communication institutionnelle en situation de multirisque à destination des acteurs locaux dans la perspective d’une meilleure résilience des territoires.


  • Open Access

    A Critical Research Gap Study of Sinkhole Hazard Assessments

    by Hedieh Soltanpour, Kamal Serrhini, Jose Serrano, Gildas Noury

    Karst landscapes are perceived as sensible environments due to soluble rocks (limestone, marble, dolomite, etc.) being the predominant features. The dissolution process in karstic structures poses serious multiple hazards to the communities on which they are built. Sinkholes and ground subsidence are the main geological hazards from these areas causing damage to lives and livelihoods. Meteorological events such as heavy rainfall leading to flooding play an important aggravating factor for these areas which often can collide with the special geological situation resulting in a cascade of hazards (flooding and sinkhole collapse). Consequently, such multi-hazard-forming environments like karst regions present a need to better understand the complex interrelationship of water in the form of flooding and underground cavity collapses. Yet, till the present, our approaches to these hazardous events have been often fragmented and inadequate. Moreover, with climate change having a significant impact on Earth, a change in hydrological processes followed by increasing dissolution of limestone, which may lead to more flooding and sinkhole occurrences, can be predicted in the immediate future. Therefore, research on interrelated hazards will be imperative in order to set priorities for complex natural events. While numerous research works have made attempts to study sinkholes and their contributing factors, to date if not any, few studies have perceived and assessed flooding and sinkhole as a multi-hazard event. Since globally, a shift from single to multi-hazard assessment is being encouraged by international risk communities, the present study is to provide new insight towards flooding and sinkholes assessment emphasising multi-hazard approaches. This critical review aims at understanding the current state of sinkhole-related researches, reviewing grey- and peer-review literature. Afterwards, the studies are classified into seven research themes (Morphology, Flood impacts on karst, Monitoring and prediction, Hazard & risk assessment, Multi-hazard-mapping modelling, Mitigation measure, and Others), demonstrating the more favourite research directions and research gap in the field of sinkhole hazard assessment. The results highlight the importance of the integrated multi-hazard assessment in the areas affected by both flooding and karst hazards and show that so far sinkhole risk assessment (70 articles – 35%) followed by sinkhole morphology (63 articles – 31,5%) have been the most popular research subject within the discipline. This research aids future research to bridge the existing gap towards improving mitigation planning and helping policy and decision-makers in their inclusion of multi-hazard interactions in municipal policies and approaches.