Using Google Earth Engine to Assess Temporal and Spatial Changes in River Geomorphology and Riparian Vegetation

Abstract

We developed a new approach using a cloud‐based remote sensing and geospatial analysis platform, Google Earth Engine, to quantify temporal changes in river channel location and adjacent riparian vegetation extent and fraction. Our new method uses publicly available 1 m aerial images and eliminates manual processing need by incorporating an automatic image classification algorithm. Classification of riparian vegetation is enhanced by increasing the temporal resolution to monthly and by mapping vegetation at high spatial resolution. We illustrate the application of our method by characterizing temporal and spatial trends in riparian vegetation and river channel position for the mainstem of the Genesee River, New York, from 2006 to 2015. Annual change in riparian vegetation extent along the Genesee River ranged from a loss of 17% to a gain of 13%, and 64 km (28%) of the river demonstrated channel migration across consecutive aerial images. Our method also successfully distinguished differences between sections of the river above and below a dam. The enhanced capacity to map vegetation monthly allowed us to identify that seasonal active vegetation fractions along the Genesee River peaked at 75% in the summer and remained lower than 25% in winter. Our method allows stakeholders and managers to process remotely sensed imagery and investigate trends in river channel and riparian vegetation dynamics over time, while reducing the costs of data processing and storage.

Identifying Factors That Influence Accuracy of Riparian Vegetation Classification and River Channel Delineation Mapped Using 1 m Data

“…We sought to address the lack of published studies [5] that map both river channels and riparian vegetation at high spatial resolution (1 m or higher) over large extents. We used Google Earth Engine to efficiently classify riparian vegetation [25] and integrated geospatial data (e.g., NHD) to improve delineation accuracy.…”

“…Based on prior experimentation, we used 200 trees, set variables per split to 1, minimum leaf population to 1, and bag fraction to 0.5; further details of the classification process are available in Pu et al [5]. We used aerial images because they have been applied for riparian vegetation delineation since the 1930s and provide high quality riparian vegetation coverage information [36].…”

“…Riparian monitoring and evaluation using field-based techniques or manual digitization often demands substantial operational resources with an associated high cost. Over the last few decades, the increased availability of imagery with a range of spatial resolutions, as well as derived land cover mapping products (e.g., the National Land Cover Dataset), have enhanced the capacity to detect and delineate riparian vegetation coverage, species, and communities over large extents [5][6][7][8][9]. Yet, despite these advancements, we still lack comprehensive maps of the location and condition of riparian plant communities [10].…”

Trends in post‐1950 riparian vegetation recovery in coastal catchments of NSW Australia: Implications for remote sensing analysis, forecasting and river management

“…Where they do exist, they tend to focus on target sections of channel and single reaches (e.g., Duro et al, 2012;Fernandes et al, 2014;Gar ofano-G omez et al, 2013;Pu et al, 2021;Tonolla et al, 2020) Landsat images have a coarser resolution (30 m) and extend back to 1987 for our study area. However, for this study, it is essential that we take the time series back further, to at least the 1950s and 1960s when we know, from extensive research in these catchments, that the landscape and rivers were in their poorest vegetative and geomorphic condition (Brooks et al, 2003;Erskine, 1986;Erskine & Melville, 2008;Fryirs et al, 2018).…”

Introduction to Featured Collection on Use of NASA and Other Earth Observations Data, Assets, and Tools to Support Water Management — Part 1

“…Finally, Pu et al (2021) also used Google Earth Engine with multiple freely available EO products, to quantify temporal changes in river channel location for the Genessee River, New York for 2006-2015. The new method uses publicly available 1-m aerial images processed using an automatic image classification algorithm.…”