Snow Radar Echogram Layer Tracker: Deep Neural Networks for radar data from NASA Operation IceBridge
Snow Radar Echogram Layer Tracker: Deep Neural Networks for radar data from NASA Operation IceBridge
复制标题
DOI：
10.1109/radarconf2351548.2023.10149734
复制
发表时间：
2023-05
期刊：
影响因子：
--
通讯作者：
O. Ibikunle;Hara Madhav Talasila;D. Varshney;J. Paden;Jilu Li;M. Rahnemoonfar
中科院分区：
文献类型：
--
作者：
O. Ibikunle;Hara Madhav Talasila;D. Varshney;J. Paden;Jilu Li;M. Rahnemoonfar
本文介绍了两种深度学习模型的性能，所开发的深度学习模型用于自动跟踪雪地雷达回波中的内层。为了克服雷达数据特有的小训练数据问题，提出了一种新的迭代行块方法，将像素级密集预测问题转化为具有数百万训练数据的多类分类问题。对格陵兰岛干雪区的超声图像，SKIP_MLP和LSTM_PE模型的跟踪精度分别达到81.2%和87.9%。此外，对于两种模型，分别有96.7%和97.3%的误差小于或等于两个像素。跟踪的层被用来估计20年来的年累积，并与区域大气模式(MAR)的估计进行比较，得到的决定系数为0.943，从而验证了该方法。
This paper documents the performance of two deep learning models developed to automatically track internal layers in Snow Radar echograms. A novel iterative RowBlock approach is developed to circumvent the small training-data problem peculiar to radar data by recasting pixel-wise dense prediction problem as a multi-class classification task with millions of training data. The proposed models, Skip_MLP and LSTM_PE, achieved tracking accuracies of 81.2 % and 87.9%, respectively, on echograms from the dry snow zone in Greenland. Moreover, 96.7% and 97.3% of the errors are less than or equal to two pixels for both models respectively. The tracked layers were used to estimate annual accumulation over two decades and compared with Regional Atmosphere Model (MAR) estimates to yield a coefficient of determination of 0.943, thus validating this approach.