Traditional shoreline protection and stabilization measures (like breakwaters) and nature-based solutions (like vegetation and oyster reefs) are adopted in coastal management strategies worldwide. By leveraging machine learning, coastal engineers and scientists can harness vast datasets sourced from numerical simulations, and laboratory experiments, to in-situ measurements, to develop robust predictive data-driven models to facilitate the evaluation of these coastal protection solutions and provide informed decision-making for sustainable coastal management. Moreover, the fusion of established physics-based numerical models and machine learning (ML) techniques, such as neural networks and genetic algorithms, offer innovative solutions to challenges in modeling the coastal dynamics around these structures and nutrient biogeochemistry and planktonic ecosystem dynamics in estuary systems and optimize the design for enhanced resilience against natural hazards.
The primary goal of this research topic is to apply ML and data-driven techniques to assess the effectiveness of traditional and nature-based solutions for coastal and estuarine protection and their impacts on coastal dynamics and sediment stabilization. It is challenging to develop ML-enabled models with certain degrees of generalization and physical interpretability to simulate the coastal dynamics around these structures and nutrient biogeochemistry and planktonic ecosystem dynamics in estuary systems.
The scope of this research topic encompasses studies focusing on the applications of ML and data-driven techniques in modeling the coastal processes around traditional and nature-based solutions and assessing the effectiveness of these solutions for coastal protection. We invite contributions that explore various themes, including but not limited to:
- Methods to integrate the knowledge of physics with machine learning approaches for modeling wave dynamics around and interactions with traditional and nature-based shoreline protection and stabilization solutions;
- ML applications in modeling nutrient biogeochemistry and planktonic ecosystem dynamics in estuary systems;
- Datasets and machine learning methods that enable the discovery of equations for critical parameters involved in traditional and nature-based solutions, such as the transmission coefficient, and vegetation drag coefficients;
- Intelligent data generation, exploration, and curation;
- Applications of ML-empowered techniques for data collection, monitoring, and synthesis;
- Adaptive management strategies informed by ML for enhancing coastal resilience against climate change and sea-level rise;
- Risk assessment and mitigation planning using ML to predict extreme events and assess vulnerabilities.
Keywords:
machine learning, neural networks, equation discovery, nature-based solutions, numerical modeling, data-driven modeling, living shorelines, oyster reefs, coastal wetlands, coastal protection, flood mitigation
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
Traditional shoreline protection and stabilization measures (like breakwaters) and nature-based solutions (like vegetation and oyster reefs) are adopted in coastal management strategies worldwide. By leveraging machine learning, coastal engineers and scientists can harness vast datasets sourced from numerical simulations, and laboratory experiments, to in-situ measurements, to develop robust predictive data-driven models to facilitate the evaluation of these coastal protection solutions and provide informed decision-making for sustainable coastal management. Moreover, the fusion of established physics-based numerical models and machine learning (ML) techniques, such as neural networks and genetic algorithms, offer innovative solutions to challenges in modeling the coastal dynamics around these structures and nutrient biogeochemistry and planktonic ecosystem dynamics in estuary systems and optimize the design for enhanced resilience against natural hazards.
The primary goal of this research topic is to apply ML and data-driven techniques to assess the effectiveness of traditional and nature-based solutions for coastal and estuarine protection and their impacts on coastal dynamics and sediment stabilization. It is challenging to develop ML-enabled models with certain degrees of generalization and physical interpretability to simulate the coastal dynamics around these structures and nutrient biogeochemistry and planktonic ecosystem dynamics in estuary systems.
The scope of this research topic encompasses studies focusing on the applications of ML and data-driven techniques in modeling the coastal processes around traditional and nature-based solutions and assessing the effectiveness of these solutions for coastal protection. We invite contributions that explore various themes, including but not limited to:
- Methods to integrate the knowledge of physics with machine learning approaches for modeling wave dynamics around and interactions with traditional and nature-based shoreline protection and stabilization solutions;
- ML applications in modeling nutrient biogeochemistry and planktonic ecosystem dynamics in estuary systems;
- Datasets and machine learning methods that enable the discovery of equations for critical parameters involved in traditional and nature-based solutions, such as the transmission coefficient, and vegetation drag coefficients;
- Intelligent data generation, exploration, and curation;
- Applications of ML-empowered techniques for data collection, monitoring, and synthesis;
- Adaptive management strategies informed by ML for enhancing coastal resilience against climate change and sea-level rise;
- Risk assessment and mitigation planning using ML to predict extreme events and assess vulnerabilities.
Keywords:
machine learning, neural networks, equation discovery, nature-based solutions, numerical modeling, data-driven modeling, living shorelines, oyster reefs, coastal wetlands, coastal protection, flood mitigation
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.