Leveraging the Historical Landsat Catalog for a Remote Sensing Model of Wetland Accretion in Coastal Louisiana. Issue 6 (6th June 2022)

• Record Type: Journal Article
• Authors: Jensen, D. J.; Cavanaugh, K. C.; Thompson, D. R.; Fagherazzi, S.; Cortese, L.; Simard, M.
• Is Part Of: Journal of geophysical research. Volume 127:Issue 6(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-06-06
• Subjects: accretion -- wetlands -- Landsat -- machine learning -- Louisiana -- delta‐X; Geobiology -- Periodicals; Biogeochemistry -- Periodicals; Biotic communities -- Periodicals; Geophysics -- Periodicals; 577.14
• DOI: 10.1029/2022JG006794
• Languages: English
• ISSNs: 2169-8953

Abstract

Abstract: A wetland's ability to vertically accrete—capturing sediment and biological matter for soil accumulation—is key for maintaining elevation to counter soil subsidence and sea level rise. Wetland soil accretion is comprised of organic and inorganic components largely governed by net primary productivity and sedimentation. Sea level, land elevation, primary productivity, and sediment accretion are all changing across Louisiana's coastline, destabilizing much of its wetland ecosystems. In coastal Louisiana, analysis from 1984 to 2020 shows an estimated 1940.858 km 2 of total loss at an average rate of 53.913 km 2 /year. Here we hypothesize that remote sensing timeseries data can provide suitable proxies for organic and inorganic accretionary components to estimate local accretion rates. The Landsat catalog offers decades of imagery applicable to tracking land extent changes across coastal Louisiana. This dataset's expansiveness allows it to be combined with the Coastwide Reference Monitoring System's point‐based accretion data. We exported normalized difference vegetation index (NDVI) and red‐band surface reflectance data for every available Landsat 4–8 scene across the coast using Google Earth Engine. Water pixels from the red‐band were transformed into estimates of total suspended solids to represent sediment deposition—the inorganic accretionary component. NDVI values over land pixels were used to estimate bioproductivity—representing accretion's organic component. We then developed a Random Forest regression model that predicts wetland accretion rates ( R 2 = 0.586, MAE = 0.333 cm/year). This model can inform wetland vulnerability assessments and loss predictions, and is to our knowledge the first remote sensing‐based model that directly estimates accretion rates in coastal wetlands. Plain Language Summary: Soil accretion in coastal wetlands—whereby a wetland area builds its surface by capturing sediment and organic matter—helps counter land loss due to the compaction of soil and sea level rise. Coastal Louisiana has seen significant coastal wetland loss due widespread coastal engineering altering the processes that impact accretion. Remote sensing data can represent these processes, including organic matter production and sediment deposition, but they have not before been applied to directly model accretion rates. Here, we use Landsat timeseries data to model accretion based on derived estimates of suspended sediment availability and bioproductivity. These remote sensing inputs represent the primary inorganic and organic accretionary components, respectively. We additionally track changes in Louisiana's coastal wetland extent from 1984 to 2020 for comparison to our estimated accretion rates, estimating a total of 1940.858 km 2 of total loss with a net change accounting for land gain of −1253.130 km 2 at a rate of −34.809 km 2 /year. Our machine learning model results show significant accretion rate declines in coastal regions that experienced the greatest loss over the study period. Our remote sensing‐based model can inform future assessments of wetland vulnerability and loss predictions. Key Points: In Louisiana from 1984 to 2020, we estimated 1940.9 km 2 of wetland loss at a 53.9 km 2 /year rate (net change −1253.1 km 2 and −34.8 km 2 /year) We used machine learning to develop a remote sensing‐based model that directly estimates soil accretion rates in coastal wetlands Accretion rates have significantly declined in the coastal basins that have lost the most wetland area