arXiv subjects

David R Johnson

Publications and source records attributed to David R Johnson.

3 recordsLinked to original sources

arXiv2025

Surrogate Models to Predict Wave Hydrodynamics on Evolving Landscapes

Coastal planners using probabilistic risk assessments to evaluate structural flood risk reduction projects may wish to simulate the hydrodynamics associated with large suites of tropical cyclones in large ensembles of landscapes: with and without projects' implementation; over decades of their useful lifetimes; and under multiple scenarios reflecting uncertainty about sea level rise, land subsidence, and other factors. Wave action can be a substantial contributor to flood losses and overtopping of structural features like levees and floodwalls, but numerical methods solving for wave dynamics are computationally expensive, potentially limiting budget-constrained planning efforts. In this study, we present and evaluate the performance of deep learning-based surrogate models for predicting peak significant wave heights under a variety of relevant use cases: predicting waves with or without modeled peak storm surge as a feature, predicting wave heights while simultaneously predicting peak storm surge, or using storm surge predicted by another surrogate model as an input feature. All models incorporate landscape morphological elements (e.g., elevation, roughness, canopy) and global boundary conditions (e.g., sea level) in addition to tropical cyclone characteristics as predictive features to improve accuracy as landscapes evolve over time. Using simulations from Louisiana's 2023 Coastal Master Plan as a case study, we demonstrate suitable accuracy of surrogate models for planning-level studies, with a two-sided Kolmogorov-Smirnov test indicating no significant difference between significant wave heights generated by the Simulating Waves Nearshore model and those predicted by our surrogate models in approximately 89% of grid cells and landscapes evaluated in the study, with performance varying by landscape and model. On average, the models produced a root mean squared error of 0.05-0.06 m.

stat.AP↗

arXiv2025

HiPoNet: A Multi-View Simplicial Complex Network for High Dimensional Point-Cloud and Single-Cell Data

In this paper, we propose HiPoNet, an end-to-end differentiable neural network for regression, classification, and representation learning on high-dimensional point clouds. Our work is motivated by single-cell data which can have very high-dimensionality --exceeding the capabilities of existing methods for point clouds which are mostly tailored for 3D data. Moreover, modern single-cell and spatial experiments now yield entire cohorts of datasets (i.e., one data set for every patient), necessitating models that can process large, high-dimensional point-clouds at scale. Most current approaches build a single nearest-neighbor graph, discarding important geometric and topological information. In contrast, HiPoNet models the point-cloud as a set of higher-order simplicial complexes, with each particular complex being created using a reweighting of features. This method thus generates multiple constructs corresponding to different views of high-dimensional data, which in biology offers the possibility of disentangling distinct cellular processes. It then employs simplicial wavelet transforms to extract multiscale features, capturing both local and global topology from each view. We show that geometric and topological information is preserved in this framework both theoretically and empirically. We showcase the utility of HiPoNet on point-cloud level tasks, involving classification and regression of entire point-clouds in data cohorts. Experimentally, we find that HiPoNet outperforms other point-cloud and graph-based models on single-cell data. We also apply HiPoNet to spatial transcriptomics datasets using spatial coordinates as one of the views. Overall, HiPoNet offers a robust and scalable solution for high-dimensional data analysis.

cs.LG↗

arXiv2023

Prediction of storm surge on evolving landscapes under climate change

Planners who wish to manage coastal flood risk with long-lived infrastructure (e.g., levees, floodwalls) under a constrained computational budget face a tradeoff. Simulating a large number of future time periods or scenarios with different assumptions about land subsidence, sea level rise, land accretion, imposes a limit on how many storm simulations can be run in each scenario and time period. Machine learning approaches have been developed to reduce the computational burden of predicting storm surge from many tropical cyclone events, but prior efforts focus on predicting surge as a function of storm parameters on a single landscape. In this analysis, we present a deep learning model that also incorporates landscape characteristics and boundary conditions (e.g., mean sea level). The model is informed by a dataset of peak surge elevations from Advanced Circulation (ADCIRC) hydrodynamic simulations of coastal Louisiana in eleven scenarios: a 2020 baseline and decadal time slices from 2030 to 2070 under two scenarios varying land subsidence and sea level rise rates. Training on ten scenarios to make predictions on the eleventh yields a grand RMSE of 0.086 m and grand MAE of 0.050 m over 90 storms per scenario and over 94,000 geospatial locations. We also aggregated the 90 storms in each scenario to generate an annual exceedance probability distribution; a two-sided Kolmogorov-Smirnov test comparing AEP estimates from the model predictions to the original ADCIRC simulations rejected the null hypothesis that the predictions and ADCIRC AEP values were drawn from the same distribution only 1.1% of the time.

physics.ao-ph↗