Assessing biomass of diverse coastal marsh ecosystems using statistical and machine learning models

The importance and vulnerability of coastal marshes necessitate effective ways to closely monitor them. Optical remote sensing is a powerful tool for this task, yet its application to diverse coastal marsh ecosystems consisting of different marsh types is limited. This study samples spectral and biophysical data from freshwater, intermediate, brackish, and saline marshes in Louisiana, and develops statistical and machine learning models to assess the marshes' biomass with combined ground, airborne, and spaceborne remote sensing data. It is found that linear models derived from NDVI and EVI are most favorable for assessing Leaf Area Index (LAI) using multispectral data (R² = 0.7 and 0.67, respectively), and the random forest models are most useful in retrieving LAI and Aboveground Green Biomass (AGB) using hyperspectral data (R² = 0.91 and 0.84, respectively). It is also found that marsh type and plant species significantly impact the linear model development (P < .05 in both cases). Sensors with coarser spatial resolution yield lower LAI values because the fine water networks are not detected and mixed into the vegetation pixels. The Landsat OLI-derived map shows the LAI of coastal mashes in Louisiana mostly ranges from 0 to 5.0, and is highest for freshwater marshes and for marshes in the Atchafalaya Bay delta. The CASI-derived maps show that LAI of saline marshes at Bay Batiste typically ranges from 0.9 to 1.5, and the AGB is mostly less than 900 g/m². This study provides solutions for assessing the biomass of Louisiana's coastal marshes using various optical remote sensing techniques, and highlights the impacts of the marshes' species composition on the model development and the sensors' spatial resolution on biomass mapping, thereby providing useful tools for monitoring the biomass of coastal marshes in Louisiana and diverse coastal marsh ecosystems elsewhere.