University of Florida Homepage

Machine learning insights of anthropogenic and natural influences on riverbed deformation in a large lowland river

Thee maps are shown. The primary map shows the thirty miles of the upper Apalachicola River south of the Jim Woodruff Dam. The river and its streams are shown in blue. Red lines along the river are the dikes. The green, yellow, and brown shading indicate the elevation near the river from nine to ninety-four meters. The river's floodplain boundary is uniformly a light green-blue color with a black border. The inset map on the top left shows the southeast United States including Florida, Georgia, Alabama, and South Carolina. All the rivers in the Apalachicola, Chattahoochee, Flint river basin are shown. A red rectangle indicates the area where the primary map is located. The second inset map on the right is a zoomed in view of just three miles along the thirty mile stretch of river in the primary map. It provides a closer view of several dikes in that stretch of river. A black rectangle in the primary map indicate the location of this inset map.
Study area showing the dam, widening valley, where the river impinges on the valley walls, and the distribution of dikes along the upper Apalachicola River. The Apalachicola-Chattahoochee-Flint basin, the floodplain boundary from River Mile 106 to 76, and a zoomed view of some dikes between River Mile 92 and 89 are shown.

AMANAMBU, MOSSAMachine learning insights of anthropogenic and natural influences on riverbed deformation in a large lowland river

Amobichukwu C. Amanambu, Joann Mossa

Article first published online: 28 November 2023

DOI: https://doi.org/10.1016/j.geomorph.2023.108986

ABSTRACT: As escalating environmental pressures threaten the world’s river systems, understanding the driving factors influencing their geomorphological changes is of critical global importance. This study illuminates the complex interaction between natural and anthropogenic factors that drove geomorphological changes along the upper Apalachicola River (UAR) from 1960 to 2010. This study utilized LiDAR point cloud data and hydrographic surveys conducted between 1960 and 2010 to identify the primary factors driving riverbed changes. A triangular irregular network (TIN) was used to convert the combined datasets from each survey, following coordinate transformation, into a 1.5 m-resolution digital elevation model (DEM) raster. The DEM of difference (DEMoD) was computed by subtracting the 1960 DEM from that of 2010, and the total sediment loss and gain were then determined by multiplying the DEMoD by the DEM resolution. A random forest (RF) regression model was used to determine the most influential factors contributing to riverbed deformation. The results revealed substantial differences in sediment loss and gain across the river. The UAR, divided into three segments, experienced sediment loss of about −6.56 × 106 m3 between 1960 and 2010, with the farthest upstream section (RM 106 to 98) losing −3.14 × 106 m3, which is ~48 % of the sediment losses in the study area. Some sections of the channel have deepened significantly, with a pronounced depth difference of −17.20 m between RM 92 and 94, potentially caused by the presence of limestone and the enlargement of a sinkhole or spring on the riverbed. The RF model identified the dam (>28 %) as the most crucial anthropogenic factor in riverbed deformation, followed by the presence of dikes (~17—18 %), then historical dredging (~7—8 %), highlighting the substantial impact of artificial structures on riverbed deformation. In contrast, rock removal, while potentially impactful in certain locations, had negligible effects (>0.5 %) at the system scale. This study highlights the interaction of natural and anthropogenic factors in river geomorphology and the potential for machine learning to identify these dynamics and inform data-driven river management and conservation strategies.

Read the full publication in Geomorphology.