Fusing Multisource Data to Estimate the Effects of Urbanization, Sea Level Rise, and Hurricane Impacts on Long-Term Wetland Change Dynamics

Abstract

Wetlands are endangered ecosystems that provide vital habitats for flora and fauna worldwide. They serve as water and carbon storage units regulating the global climate and water cycle, and act as natural barriers against storm-surge among other benefits. Long-term analyses are crucial to identify wetland cover change and support wetland protection/restoration programs. However, such analyses deal with insufficient validation data that limit land cover classification and pattern recognition tasks. Here, we analyze wetland dynamics associated with urbanization, sea level rise, and hurricane impacts in the Mobile Bay watershed, AL since 1984. For this, we develop a land cover classification model with convolutional neural networks (CNNs) and data fusion (DF) framework. The classification model achieves the highest overall accuracy (0.93), and f1-scores in woody (0.90) and emergent wetland class (0.99) when those datasets are fused in the framework. Long-term trends indicate that the wetland area is decreasing at a rate of -1106 m 2 /yr with sharp fluctuations exacerbated by hurricane impacts. We further discuss the effects of DF alternatives on classification accuracy, and show that the CNN & DF framework outperforms machine/deep learning models trained only with single input datasets. Index Terms-Data fusion, deep learning, hurricane impacts, Mobile Bay, sea level rise, urban development, wetland loss. I. INTRODUCTION ETLANDS are defined as lands transitional between terrestrial and aquatic ecosystems [1] that provide valuable services to society [2]. Among those services, wetlands improve water quality due to their capacity for nutrient and pollutant removal [3], [4]. Wetlands regulate the global climate through carbon sequestration and methane emissions [5]-[7], and also contribute to maintaining Manuscript submitted for peer-review on October 12, 2020. This study is partially funded by the National Science Foundation INFEWS Program (award EAR-1856054).

Ditching Nutrients: Roadside Drainage Networks are Hotspots for Microbial Nitrogen Removal

“…A limitation of the study was that land use types were not replicated across the region, so we could not definitively separate land use type from differences in underlying geology between the east and west sides of Mobile Bay (Montiel et al., 2019). However, urbanization and agricultural land use in the study watersheds have impacted water quality and wetland persistence (Lehrter, 2006; Muñoz et al., 2021), indicating that land use effects may be greater than regional differences in natural systems. Regardless of location, our study demonstrates that roadside ditches have significant capacity for N‐removal in the landscape.…”

A Multivariate Scaling System Is Essential to Characterize the Tropical Cyclones' Risk

“…Tropical cyclones (TCs) are among the most devastating natural disasters in the world. Despite the tremendous national governments' protection efforts, they still result in loss of lives and properties ( Karimiziarani et al., 2022; Klotzbach et al., 2018; Munoz et al., 2021; Sebastian et al., 2017; Song et al., 2022; Tennant & Gilmore, 2020). Tropical Cyclones are compound hazards, during which a combination of climate processes and hazards (i.e., torrential rainfall, intense winds, and abnormal surge) lead to significant societal impacts greater than the impacts each can produce in isolation (de Ruiter et al., 2020; Leonard et al., 2014; Zscheischler et al., 2018).…”

Compound Effects of Flood Drivers, Sea Level Rise, and Dredging Protocols on Vessel Navigability and Wetland Inundation Dynamics

“…Also, the nonlinear interactions among SLR, terrestrial and coastal flood drivers, and anthropogenic activities can exacerbate the impacts of CF hazards, escalate flood risks in coastal communities, and cause wetland loss (Eilander et al, 2020;Rezaie et al, 2020;Nasr et al, 2021). In that regard, Muñoz et al (2021) analyzed the effects of SLR, urbanization, and hurricane impacts on long-term wetland change dynamics in Mobile Bay (MB), AL. The authors leveraged multisource satellite imagery and state-of-the-art deep learning techniques to track such wetland dynamics.…”