arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2011.09707stat.MLcs.LGstat.AP
收藏

基于深度学习的插值方法在近岸水深测量中的应用

Application of Deep Learning-based Interpolation Methods to Nearshore Bathymetry

Stanford University(斯坦福大学);University of Hawaii at Manoa(夏威夷大学马诺阿分校);US Army Engineer Research and Development Center(美国陆军工程研究与发展中心)

Yizhou Qian, Mojtaba Forghani, Jonghyun Harry Lee, Matthew Farthing, Tyler Hesser, Peter Kitanidis, Eric Darve

摘要:

近岸水深测量,即沿海地区洋底的地形,对于预测碎波带的水动力和规划路线以避开地下特征至关重要。因此,它对于各种应用越来越重要,包括航运运营、沿海管理和风险评估。然而,由于预算限制和后勤限制,很少进行近岸水深的直接高分辨率调查。当只有稀疏观测可用时,另一种选择是使用高斯过程回归(GPR),也称为克里金法。但是探地雷达很难识别具有明显梯度的模式,比如在沙洲和水下物体周围发现的模式,特别是在观测稀疏的情况下。在这项工作中,我们提出了几种基于深度学习的技术,用于通过稀疏的多尺度测量来估计近岸水深。我们提出了一个深度神经网络(DNN)来计算近岸测深的后验估计,以及一个条件生成对抗网络(cGAN),从后验分布中采样。我们根据美国提供的近岸调查生成的合成数据训练我们的神经网络。美国陆军工程兵野战研究所(Army Corps of Engineer Field Research Facility,简称FRF),位于北卡罗来纳州达克市。我们比较我们的方法与克里格真正的调查,以及调查与人工添加的尖锐梯度。结果表明,DNN的直接估计比Kriging在此应用中给出更好的预测。我们使用DNN的Bootstrapping来进行不确定性量化。我们还提出了一种名为DNN-Kriging的方法,该方法将深度学习与Kriging相结合,并进一步改进了后验估计。

英文摘要:

Nearshore bathymetry, the topography of the ocean floor in coastal zones, is vital for predicting the surf zone hydrodynamics and for route planning to avoid subsurface features. Hence, it is increasingly important for a wide variety of applications, including shipping operations, coastal management, and risk assessment. However, direct high resolution surveys of nearshore bathymetry are rarely performed due to budget constraints and logistical restrictions. Another option when only sparse observations are available is to use Gaussian Process regression (GPR), also called Kriging. But GPR has difficulties recognizing patterns with sharp gradients, like those found around sand bars and submerged objects, especially when observations are sparse. In this work, we present several deep learning-based techniques to estimate nearshore bathymetry with sparse, multi-scale measurements. We propose a Deep Neural Network (DNN) to compute posterior estimates of the nearshore bathymetry, as well as a conditional Generative Adversarial Network (cGAN) that samples from the posterior distribution. We train our neural networks based on synthetic data generated from nearshore surveys provided by the U.S.\ Army Corps of Engineer Field Research Facility (FRF) in Duck, North Carolina. We compare our methods with Kriging on real surveys as well as surveys with artificially added sharp gradients. Results show that direct estimation by DNN gives better predictions than Kriging in this application. We use bootstrapping with DNN for uncertainty quantification. We also propose a method, named DNN-Kriging, that combines deep learning with Kriging and shows further improvement of the posterior estimates.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑