Modeling risk of mangroves to tropical cyclones: A case study of Hurricane Irma

Abstract Mangrove forests are productive ecosystems but are vulnerable to tropical cyclones. In this study, we quantified the damage of mangroves from Hurricane Irma at a large-scale using Landsat data, and modeled the risk of mangroves to hurricanes using three internal/physical metrics (a vegetation index, canopy height, and distance to open ocean) and two external/hurricane-related metrics (hurricane track and storm surge inundation). Four machine learning techniques including Artificial Neural Network (ANN), Support Vector Machine (SVM), Random Forest (RF), and k-Nearest Neighbor (k-NN) were examined and compared with the Multiple Linear Regression (MLR) method to identify the best risk model for damage projection from future hurricanes. The models were calibrated and validated using data before and after Hurricane Irma. Machine learning algorithms had a better performance than the linear model, and RF achieved the best result with a correlation coefficient (r) of 0.84 in predicting mangrove damages. The model also produced an encouraging result to hindcast mangrove damages from Hurricane Wilma. We applied object-based modeling and mapping techniques and produced mangrove damage maps from Irma and a worst-case scenario hurricane with an intensity of Category 5 and a track along the mangrove distribution. A total of 332 km2 of mangroves were severely damaged from Irma, and 635 km2 would be devastated from the modeled scenario. The techniques developed here can be used for other mangrove forests exposed to tropical cyclones.

[1]  T. J. Smith,et al.  Hurricane Wilma’s impact on overall soil elevation and zones within the soil profile in a mangrove forest , 2009, Wetlands.

[2]  M. Kampel,et al.  Simulating Sea-Level Rise Impacts on Mangrove Ecosystem adjacent to Anthropic Areas: the case of Maranhão Island, Brazilian Northeast , 2014 .

[3]  Improved modelling of the impacts of sea level rise on coastal wetland plant communities , 2016, Hydrobiologia.

[4]  Hannah M. Cooper,et al.  Quantification of sawgrass marsh aboveground biomass in the coastal Everglades using object-based ensemble analysis and Landsat data , 2018 .

[5]  Petya K. E. Campbell,et al.  Estimating major ion and nutrient concentrations in mangrove estuaries in Everglades National Park using leaf and satellite reflectance , 2014 .

[6]  Thomas Blaschke,et al.  Object based image analysis for remote sensing , 2010 .

[7]  Chandra Giri,et al.  Damage and recovery assessment of the Philippines' mangroves following Super Typhoon Haiyan. , 2016, Marine pollution bulletin.

[8]  S. Hamilton,et al.  Creation of a high spatio-temporal resolution global database of continuous mangrove forest cover for the 21st century (CGMFC-21) , 2014, 1412.0722.

[9]  C. Justice,et al.  The Harmonized Landsat and Sentinel-2 surface reflectance data set , 2018, Remote Sensing of Environment.

[10]  Brian Johnson,et al.  Unsupervised image segmentation evaluation and refinement using a multi-scale approach , 2011 .

[11]  J. Sah,et al.  Early post-hurricane stand development in Fringe mangrove forests of contrasting productivity , 2006, Plant Ecology.

[12]  D. Cahoon,et al.  The vulnerability of Indo-Pacific mangrove forests to sea-level rise , 2015, Nature.

[13]  Lawrence A. Corp,et al.  NASA Goddard's LiDAR, Hyperspectral and Thermal (G-LiHT) Airborne Imager , 2013, Remote. Sens..

[14]  C. Lovelock,et al.  Mangrove mortality in a changing climate: An overview , 2018, Estuarine, Coastal and Shelf Science.

[15]  T. J. Smith,et al.  Wind damage effects of Hurricane Andrew on mangrove communities along the southwest coast of Florida, USA , 1995 .

[16]  James A. Westfall,et al.  NACP Aboveground Biomass and Carbon Baseline Data, V.2 (NBCD 2000), U.S.A., 2000 , 2013 .

[17]  Chaoyang Fang,et al.  Applying time series Landsat data for vegetation change analysis in the Florida Everglades Water Conservation Area 2A during 1996-2016 , 2017, Int. J. Appl. Earth Obs. Geoinformation.

[18]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[19]  J. Ellison.  Vulnerability assessment of mangroves to climate change and sea-level rise impacts , 2014, Wetlands Ecology and Management.

[20]  E. Gilman,et al.  Threats to mangroves from climate change and adaptation options: A review , 2008 .

[21]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[22]  K. Beurs,et al.  Evaluation of Landsat and MODIS data fusion products for analysis of dryland forest phenology , 2012 .

[23]  B. Zachry,et al.  A National View of Storm Surge Risk and Inundation , 2015 .

[24]  J. L. Rangel-Salazar,et al.  Resilience in a Mexican Pacific Mangrove after Hurricanes: Implications for Conservation Restoration , 2013 .

[25]  P. Atkinson,et al.  Remote sensing of mangrove forest phenology and its environmental drivers , 2018 .

[26]  Timothy A. Warner,et al.  Implementation of machine-learning classification in remote sensing: an applied review , 2018 .

[27]  G. Vecchi,et al.  Modeled Impact of Anthropogenic Warming on the Frequency of Intense Atlantic Hurricanes , 2010, Science.

[28]  Wei Zhao,et al.  Directional Wind-Wave Coupling in Fully Coupled Atmosphere-Wave-Ocean Models: Results from CBLAST-Hurricane , 2013 .

[29]  Neil Saintilan,et al.  How mangrove forests adjust to rising sea level. , 2014, The New phytologist.

[30]  Hans-Martin Füssel,et al.  Vulnerability: A generally applicable conceptual framework for climate change research , 2007 .

[31]  T. J. Smith,et al.  Cumulative impacts of hurricanes on Florida mangrove ecosystems: Sediment deposition, storm surges and vegetation , 2009, Wetlands.

[32]  Keqi Zhang,et al.  The role of mangroves in attenuating storm surges , 2012 .

[33]  Mariana Belgiu,et al.  Random forest in remote sensing: A review of applications and future directions , 2016 .

[34]  Juan J. Flores,et al.  The application of artificial neural networks to the analysis of remotely sensed data , 2008 .

[35]  Gherardo Chirici,et al.  A meta-analysis and review of the literature on the k-Nearest Neighbors technique for forestry applications that use remotely sensed data , 2016 .

[36]  D. Whitman,et al.  Spatial and temporal variability in spectral-based surface energy evapotranspiration measured from Landsat 5TM across two mangrove ecotones , 2015 .

[37]  Daniel A. Friess,et al.  Impacts of climate change on mangrove ecosystems: a region by region overview , 2016 .

[38]  Ashbindu Singh,et al.  Status and distribution of mangrove forests of the world using earth observation satellite data , 2011 .

[39]  T. Doyle,et al.  Modeling mangrove forest migration along the southwest coast of Florida under climate change , 2003 .

[40]  Iryna Dronova,et al.  Object-Based Image Analysis in Wetland Research: A Review , 2015, Remote. Sens..

[41]  R. Lucas,et al.  Aberystwyth University Distribution and Drivers of Global Mangrove Forest Change, 1996-2010 , 2017 .

[42]  Caiyun Zhang,et al.  Mapping salt marsh soil properties using imaging spectroscopy , 2019, ISPRS Journal of Photogrammetry and Remote Sensing.

[43]  R. H. Day,et al.  Water level observations in mangrove swamps during two hurricanes in Florida , 2009, Wetlands.

[44]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[45]  Jungho Im,et al.  ISPRS Journal of Photogrammetry and Remote Sensing , 2022 .

[46]  John R. Jensen,et al.  Introductory Digital Image Processing: A Remote Sensing Perspective , 1986 .

[47]  T. Doyle,et al.  Sea-level rise and landscape change influence mangrove encroachment onto marsh in the Ten Thousand Islands region of Florida, USA , 2011 .

[48]  Keqi Zhang,et al.  Remote sensing of seasonal changes and disturbances in mangrove forest: a case study from South Florida , 2016 .

[49]  Michael B. Robblee,et al.  Mangroves, hurricanes and lightning strikes , 1994 .