Toward Autonomous Detection of Anomalous GNSS Data Via Applied Unsupervised Artificial Intelligence
Toward Autonomous Detection of Anomalous GNSS Data Via Applied Unsupervised Artificial Intelligence
复制标题
DOI：
10.1142/s1793351x22400025
复制
发表时间：
2022-03-01
影响因子：
0.8
通讯作者：
Saria, Elifuraha
中科院分区：
文献类型：
--
作者：
Dye, Mike;Stamps, D. Sarah;Saria, Elifuraha
地球科学领域的人工智能应用变得越来越普遍，但将现有技术应用于地球科学数据集仍然存在许多挑战。火山灾害评估领域的应用显示出应对此类挑战的巨大前景。在这里，我们描述了我们开发的 Jupyter Notebook，它从 EarthCube CHORDS（地球科学云托管实时数据服务）门户 TZVOLCANO 获取实时全球导航卫星系统 (GNSS) 数据流，应用无监督学习算法来执行自动数据质量控制（“降噪”），并探索使用神经网络自动检测异常火山活动。 TZVOLCANO CHORDS 门户以 1 秒的间隔从 TZVOLCANO 网络传输实时 GNSS 定位数据，该网络通过 UNAVCO 的实时 GNSS 数据服务监控坦桑尼亚的 Ol Doinyo Lengai 活火山。 UNAVCO 的实时数据服务提供由 Trimble Pivot 系统处理的近实时位置。定位数据（纬度、经度和高度）以用户定义的时间跨度导入到本文中介绍的 Jupyter Notebook 中。然后，Jupyter Notebook 成组收集定位数据，并进行处理以提取有用的计算变量，为机器学习算法做准备，我们选择其中的向量大小进行进一步处理。然后利用无监督 K 均值和高斯混合机器学习算法来定位和删除可能由噪声引起且与火山信号无关的数据点（“过滤器”）。我们发现 K 均值和高斯混合机器学习算法在识别测试的 GNSS 数据集中的高噪声区域方面表现良好。然后，过滤后的数据用于训练预测火山变形的人工智能神经网络。我们的 Jupyter Notebook 有望用于检测地球表面快速垂直或水平位移形式的潜在危险火山活动。
Artificial intelligence applications within the geosciences are becoming increasingly common, yet there are still many challenges involved in adapting established techniques to geoscience data sets. Applications in the realm of volcanic hazards assessment show great promise for addressing such challenges. Here, we describe a Jupyter Notebook we developed that ingests real-time Global Navigation Satellite System (GNSS) data streams from the EarthCube CHORDS (Cloud-Hosted Real-time Data Services for the geosciences) portal TZVOLCANO, applies unsupervised learning algorithms to perform automated data quality control ("noise reduction"), and explores autonomous detection of unusual volcanic activity using a neural network. The TZVOLCANO CHORDS portal streams real-time GNSS positioning data in 1s intervals from the TZVOLCANO network, which monitors the active volcano Ol Doinyo Lengai in Tanzania, through UNAVCO's real-time GNSS data services. UNAVCO's real-time data services provide near-real-time positions processed by the Trimble Pivot system. The positioning data (latitude, longitude and height) are imported into the Jupyter Notebook presented in this paper in user-defined time spans. The positioning data are then collected in sets by the Jupyter Notebook and processed to extract a useful calculated variable in preparation for the machine learning algorithms, of which we choose the vector magnitude for further processing. Unsupervised K-means and Gaussian Mixture machine learning algorithms are then utilized to locate and remove data points ("filter") that are likely caused by noise and unrelated to volcanic signals. We find that both the K-means and Gaussian Mixture machine learning algorithms perform well at identifying regions of high noise within tested GNSS data sets. The filtered data are then used to train an artificial intelligence neural network that predicts volcanic deformation. Our Jupyter Notebook has promise to be used for detecting potentially hazardous volcanic activity in the form of rapid vertical or horizontal displacement of the Earth's surface.