The impacts of climate change, especially sea-level rise, are an increasing threat to the world’s coastal regions. Following recommendations made by the United Nations about the preservation of mangrove environments, particularly given their potential for effective natural defence against wave-driven hazards, a series of experiments have been conducted to quantify the ability of mangroves to counter climate change impacts. To date, these experiments have been limited by computational cost and inability to model multiple scenarios. With improved data quality and availability, machine learning has enormous potential to supplement, or even replace, existing numerical methods. This article presents both an outline of the importance of protecting mangrove environments and a review of methods currently used to quantify the capacity of mangroves to adapt to climate change impacts. In view of the limitations of existing numerical methods, the article also discusses the potential of machine learning as an efficient and effective alternative.
|Number of pages||14|
|Journal||Environmental Modelling & Software|
|Early online date||25 Feb 2023|
|Publication status||E-pub ahead of print - 25 Feb 2023|
Bibliographical note© 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
FunderThe authors would like to thank Coventry University, United Kingdom for funding this PhD Studentship titled “Enhancing Mangrove Forest Resilience against Coastal Degradation and Climate Change Impacts using Advanced Bayesian Machine Learning Methods”, through the GCRF Scheme.
- Mangrove environments
- Climate change
- Hydro-morphodynamic modelling
- Adaptation policies
- Machine learning
- Data-driven modelling