Joann Mossa

Women in Geography have been earning PhDs at a rate comparable to men over the past two decades in the United States (Kaplan and Mapes 2016), and the number of PhD degrees awarded to underrepresent...

Women and other marginalized groups in geography are telling their stories and advocating for change in a discipline where they have historically been underrepresented and overlooked in research an...

Gender is one aspect of faculty diversity that benefits recruitment and retention of faculty and supports the engagement and success of students (Drury et al. 2011; Fox Tree and Vaid 2021). Diverse...

Understanding and predicting bankfull stage is essential for geomorphic analysis, hydraulic modelling and river corridor management, especially regarding floods and connectivity. This study evaluates traditional geomorphic and hydrologic methods and introduces a machine learning (ML) approach to predict bankfull stage along the upper Apalachicola River, Florida, United States. First, we integrated LiDAR point cloud data with a 2010 hydrographic survey through a triangular irregular network (TIN) following coordinate transformation, producing a 1.5‐m resolution digital elevation model (DEM) that captures riverbed elevation. After extracting cross‐sections, we applied two geomorphic methods, Width‐to‐Depth Ratio (WDR) and Hydraulic Mean Depth (HMD), and three (1.1‐, 1.5‐, 2.0‐year) hydrologic return intervals to 344 cross‐sections to determine bankfull stage and assessed their agreement with visual and field‐verified bankfull elevations. A refined HMD method using shape ratio (Rs) and slope inflection corrections improved geomorphic estimates in 131 cross‐sections. Bankfull estimates based on return intervals exhibited substantially lower reliability relative to geomorphic methods, with associated confidence levels falling below 70%. This reduced performance is attributable to stage‐based spatial averaging and limited sensitivity to local topographic variability. By contrast, the geomorphic methods (WDR and HMD) achieved confidence levels exceeding 95%, underscoring their stronger agreement and robustness. To improve accuracy, we developed ML models: Random Forest (RF), Gradient Boosting (GB) and Ensemble model trained on cross‐sectional elevation profiles and engineered features such as cross‐sectional area, top width, maximum depth, symmetry, etc. The GB model outperformed all others ( R ² = 0.94, MSE = 0.21), with feature importance analysis revealing that elevation at the top bank as well as channel area, top width and maximum depth dominated predictions. While this study advances the integration of ML into fluvial systems and provides a replicable framework for large rivers with limited hydrologic data, we recommend that multiple ML models be evaluated across individual reaches to account for the unique geomorphic and hydraulic characteristics of each river reach.

Sloughs are slow‐moving or still water systems that serve as an important ecosystem component connecting rivers and floodplains such as the Apalachicola River in northwest Florida. However, sloughs of the Apalachicola River have become hydrologically disconnected from the mainstem due to the impact of failed navigation projects such as channel incision, disposal of dredge spoils, and reduced flows from upstream. A few hydrologic modeling studies have been undertaken in complex slough systems. To predict the impact of proposed physical interventions to restore more normal slough flow conditions, we conducted a hydrodynamic analysis using the HEC‐RAS model. This analysis compared the observed discharge through the slough from June 2021 to June 2023 with the predicted discharge after implementing two proposed restoration actions, assuming no change in water surface elevation at the slough inlet. Under current/pre‐restoration conditions, measured streamflow declined sharply through Spiders Cut as the main river water level receded, resulting in irregular flows and, eventually, total interruption of flows to the receiving floodplain swamps, often for several months. A post‐restoration scenario involving the excavation of the sediment obstruction at the head of the slough predicts an annual flow increase of ~200%, mostly occurring during conditions of moderate flow. Full restoration and excavation of a defined template through the full length of the impaired channel is predicted to yield a 470% annual increase in flow compared with pre‐restoration conditions. With full restoration, Spiders Cut will maintain continuous water flow throughout the year, providing a constant water supply from the main river water in the mainstem flow of ~300 m³s⁻¹ or greater (below this, slough will not get water) to the swamp ecosystems downstream. This study highlights the value of modeling scenarios in restoration planning. It shows key differences in benefits resulting from restoration scenarios ranging from partial excavation only at the head of the slough to removal of sand blockages along the length of the slough channel in restoring hydrological connectivity to floodplain swamps.