Rodolfo Jaffé, Carrie Paul-Gorsline, Molly McDermott, Shannon Fluharty, Ismail Al-Shaikh, Sabrina L. Skeat, Umarfarooq A. Abdulwahab, Lis Nelis, Benjamin D. Jaffe
{"title":"Using habitat suitability modeling to integrate ecosystem-based approaches for mangrove restoration site selection","authors":"Rodolfo Jaffé, Carrie Paul-Gorsline, Molly McDermott, Shannon Fluharty, Ismail Al-Shaikh, Sabrina L. Skeat, Umarfarooq A. Abdulwahab, Lis Nelis, Benjamin D. Jaffe","doi":"10.1002/ecs2.70222","DOIUrl":null,"url":null,"abstract":"<p>Mangrove forest restoration can improve services and functions across associated coastal ecosystems. However, the effectiveness of mangrove restoration efforts is highly dependent on knowing the locations and habitat requirements of target species within the landscape of interest. Habitat suitability models are powerful tools that identify suitable environmental conditions and reduce the risk of poor site selection. When coupled with information on potential future climate conditions, land-use conflicts, and co-benefits (e.g., biodiversity), these models can be used to identify and prioritize areas that meet multiple stakeholder objectives and help implement a broader ecosystem-based approach to restoration. In this study, we coupled habitat suitability models with machine learning to assess present and future habitat suitability of mangrove forests across the Arabian Gulf. We then incorporated land-use and marine habitat data from Qatar to prioritize areas for mangrove restoration in a country where mangroves constitute the only type of forest. All the tested machine learning models (artificial neural networks, boosted regression trees, random forest, Maxent, and Maxnet) showed high predictive performance, but the percentage of contributions of each environmental predictor differed across the models. Important predictors of mangrove habitat suitability in Qatar included elevation, slope, distance to coastline, temperature, and precipitation. While most models predicted a future reduction in suitable habitat for mangrove forests in the country and across the region, there were suitable sites in Qatar located within currently protected areas. We identified several potential areas of high restoration impact (i.e., high present and future suitability, far from urban areas, and closest to live coral areas) across the northwest side of Qatar. These results demonstrate that habitat suitability modeling can be paired with information on land-use restrictions, proximity to infrastructure, and other ecosystems to integrate an ecosystem-based approach to guide restoration site selection.</p>","PeriodicalId":48930,"journal":{"name":"Ecosphere","volume":"16 3","pages":""},"PeriodicalIF":2.7000,"publicationDate":"2025-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ecs2.70222","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ecosphere","FirstCategoryId":"93","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/ecs2.70222","RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ECOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Mangrove forest restoration can improve services and functions across associated coastal ecosystems. However, the effectiveness of mangrove restoration efforts is highly dependent on knowing the locations and habitat requirements of target species within the landscape of interest. Habitat suitability models are powerful tools that identify suitable environmental conditions and reduce the risk of poor site selection. When coupled with information on potential future climate conditions, land-use conflicts, and co-benefits (e.g., biodiversity), these models can be used to identify and prioritize areas that meet multiple stakeholder objectives and help implement a broader ecosystem-based approach to restoration. In this study, we coupled habitat suitability models with machine learning to assess present and future habitat suitability of mangrove forests across the Arabian Gulf. We then incorporated land-use and marine habitat data from Qatar to prioritize areas for mangrove restoration in a country where mangroves constitute the only type of forest. All the tested machine learning models (artificial neural networks, boosted regression trees, random forest, Maxent, and Maxnet) showed high predictive performance, but the percentage of contributions of each environmental predictor differed across the models. Important predictors of mangrove habitat suitability in Qatar included elevation, slope, distance to coastline, temperature, and precipitation. While most models predicted a future reduction in suitable habitat for mangrove forests in the country and across the region, there were suitable sites in Qatar located within currently protected areas. We identified several potential areas of high restoration impact (i.e., high present and future suitability, far from urban areas, and closest to live coral areas) across the northwest side of Qatar. These results demonstrate that habitat suitability modeling can be paired with information on land-use restrictions, proximity to infrastructure, and other ecosystems to integrate an ecosystem-based approach to guide restoration site selection.
期刊介绍:
The scope of Ecosphere is as broad as the science of ecology itself. The journal welcomes submissions from all sub-disciplines of ecological science, as well as interdisciplinary studies relating to ecology. The journal''s goal is to provide a rapid-publication, online-only, open-access alternative to ESA''s other journals, while maintaining the rigorous standards of peer review for which ESA publications are renowned.