Bathymetric Inversion and Uncertainty Estimation from Synthetic Surf-Zone Imagery with Machine Learning
Adam Collins,Katherine L. Brodie,Andrew Spicer Bak,Tyler Hesser,Matthew W. Farthing,Jonghyun Lee,Joseph W. Long +6 more
TLDR
This work explored what types of coastal imagery can be best utilized in a 2-dimensional fully convolutional neural network to directly estimate nearshore bathymetry from optical expressions of wave kinematics to provide additional actionable information about the spatial reliability of each bathymetric prediction.Abstract:
Resolving surf-zone bathymetry from high-resolution imagery typically involves measuring wave speeds and performing a physics-based inversion process using linear wave theory, or data assimilation techniques which combine multiple remotely sensed parameters with numerical models. In this work, we explored what types of coastal imagery can be best utilized in a 2-dimensional fully convolutional neural network to directly estimate nearshore bathymetry from optical expressions of wave kinematics. Specifically, we explored utilizing time-averaged images (timex) of the surf-zone, which can be used as a proxy for wave dissipation, as well as including a single-frame image input, which has visible patterns of wave refraction and instantaneous expressions of wave breaking. Our results show both types of imagery can be used to estimate nearshore bathymetry. However, the single-frame imagery provides more complete information across the domain, decreasing the error over the test set by approximately 10% relative to using timex imagery alone. A network incorporating both inputs had the best performance, with an overall root-mean-squared-error of 0.39 m. Activation maps demonstrate the additional information provided by the single-frame imagery in non-breaking wave areas which aid in prediction. Uncertainty in model predictions is explored through three techniques (Monte Carlo (MC) dropout, infer-transformation, and infer-noise) to provide additional actionable information about the spatial reliability of each bathymetric prediction.read more
Citations
More filters
Journal ArticleDOI
Modeling the Morphodynamics of Coastal Responses to Extreme Events: What Shape Are We In?
TL;DR: In this paper , a review of recent advances in process-based numerical models of the impact of extreme storms on sandy coasts is presented, focusing on wave-induced flows and sediment transport under shoaling waves.
Posted Content
Application of deep learning to large scale riverine flow velocity estimation
Mojtaba Forghani,Yizhou Qian,Jonghyun Lee,Matthew W. Farthing,Tyler Hesser,Peter K. Kitanidis,Eric Darve +6 more
TL;DR: This work uses three different forward solvers referred to as principal component analysis-deep neural network, supervised encoder, and supervised variational encoder to obtain a fast solver of the SWEs, given augmented realizations from the posterior bathymetry distribution and the prescribed range of potential BCs.
Journal ArticleDOI
The future of coastal monitoring through satellite remote sensing
TL;DR: In this paper , a fleet of Earth-observing satellites has enabled multiscale monitoring of beaches, for the very first time, by providing imagery with global coverage and up to daily frequency.
Journal ArticleDOI
Deep learning universal crater detection using Segment Anything Model (SAM)
TL;DR: In this article , the authors presented a universal crater detection scheme based on the recently proposed Segment Anything Model (SAM) from META AI, which is a promptable segmentation system with zero-shot generalization to unfamiliar objects and images without the need for additional training.
Journal ArticleDOI
Prediction of flexible pavement 3-D finite element responses using Bayesian neural networks
Egemen Okte,Imad L. Al-Qadi +1 more
TL;DR: In this paper, a 3D finite element (FE) model is used to model the interaction of tire-pavement interactions, including complex viscoelastic or stress-dependent materia.
References
More filters
Journal Article
Dropout: a simple way to prevent neural networks from overfitting
TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
Proceedings Article
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.
Posted Content
U-Net: Convolutional Networks for Biomedical Image Segmentation
TL;DR: It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Automatic differentiation in PyTorch
Adam Paszke,Sam Gross,Soumith Chintala,Gregory Chanan,Edward Z. Yang,Zachary DeVito,Zeming Lin,Alban Desmaison,Luca Antiga,Adam Lerer +9 more
TL;DR: An automatic differentiation module of PyTorch is described — a library designed to enable rapid research on machine learning models that focuses on differentiation of purely imperative programs, with a focus on extensibility and low overhead.
Proceedings ArticleDOI
TensorFlow: a system for large-scale machine learning
Martín Abadi,Paul Barham,Jianmin Chen,Zhifeng Chen,Andy Davis,Jeffrey Dean,Matthieu Devin,Sanjay Ghemawat,Geoffrey Irving,Michael Isard,Manjunath Kudlur,Josh Levenberg,Rajat Monga,Sherry Moore,Derek G. Murray,Benoit Steiner,Paul A. Tucker,Vijay K. Vasudevan,Pete Warden,Martin Wicke,Yuan Yu,Xiaoqiang Zheng +21 more
TL;DR: TensorFlow as mentioned in this paper is a machine learning system that operates at large scale and in heterogeneous environments, using dataflow graphs to represent computation, shared state, and the operations that mutate that state.