Graph Neural Networks for Multivariate Time Series Regression with Application to Seismic Data
Tilburg University（蒂尔堡大学）；Jheronimus Academy of Data Science（赫罗尼姆斯数据科学学院）；Istituto Nazionale di Geofisica e Vulcanologia（意大利国家地球物理与火山学研究所）；Università degli Studi Roma Tre（罗马第三大学）；Swiss Seismological Service (SED) at ETH Zurich（苏黎世联邦理工学院瑞士地震服务中心）；Osnabrück University（奥斯纳布吕克大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）
Stefan Bloemheuvel, Jurgen van den Hoogen, Dario Jozinović, Alberto Michelini, Martin Atzmueller
备注：
18 pages, LaTeX; final revision; published in: International Journal of Data Science and Analytics, pages 1-16, 2022
Machine learning, with its advances in deep learning has shown great potential in analyzing time series. In many scenarios, however, additional information that can potentially improve the predictions is available. This is crucial for data that arise from e.g., sensor networks that contain information about sensor locations. Then, such spatial information can be exploited by modeling it via graph structures, along with the sequential (time series) information. Recent advances in adapting deep learning to graphs have shown potential in various tasks. However, these methods have not been adapted for time series tasks to a great extent. Most attempts have essentially consolidated around time series forecasting with small sequence lengths. Generally, these architectures are not well suited for regression or classification tasks where the value to be predicted is not strictly depending on the most recent values, but rather on the whole length of the time series. We propose TISER-GCN, a novel graph neural network architecture for processing, in particular, these long time series in a multivariate regression task. Our proposed model is tested on two seismic datasets containing earthquake waveforms, where the goal is to predict maximum intensity measurements of ground shaking at each seismic station. Our findings demonstrate promising results of our approach -- with an average MSE reduction of 16.3% - compared to the best performing baselines. In addition, our approach matches the baseline scores by needing only half the input size. The results are discussed in depth with an additional ablation study.
CoGameReg: Cooperative-Game-Based Collaborative Semi-Supervised Regression for Seismic Reservoir Property Prediction
School of Mathematics, Jilin University（吉林大学数学学院）；AI for Science and Engineering Center, Shenzhen Loop Area Institute（深圳循环区研究院科学与工程人工智能中心）；BGP Inc., China National Petroleum Corporation（中国石油天然气集团公司东方地球物理公司）；National Engineering Research Center of Oil & Gas Exploration Computer Software（油气勘探计算机软件国家工程研究中心）
Calibrated Multivariate Distributional Regression with Pre-Rank Regularization
Department of Statistics and Data Science, Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE（统计与数据科学系，Mohamed Bin Zayed人工智能大学，阿布扎比，阿联酋）
Multivariate Time Series Clustering for Environmental State Characterization of Ground-Based Gravitational-Wave Detectors
Computer Science \& Engineering University of California, Riverside Riverside, CA, USA；Physics University of Dallas Dallas, TX, USA；Physics \& Astronomy University of California, Riverside Riverside, CA, USA；LIGO Laboratory LIGO Livingston Observatory Livingston, LA, USA
Prediction of geophysical properties of rocks on rare well data and attributes of seismic waves by machine learning methods on the example of the Achimov formation
An Efficient Minimax Optimal Estimator For Multivariate Convex Regression
Electrical Engineering and Computer Science, Massachusetts Institute of Technology（麻省理工学院电气工程与计算机科学系）；Department of Mathematics, Tel Aviv University（特拉维夫大学数学系）
Multivariate Regression with Grossly Corrupted Observations: A Robust Approach and its Applications
Bioinformatics Institute, A*STAR（新加坡科技研究局生物信息研究所）；Institute of Psychology, Chinese Academy of Sciences（中国科学院心理研究所）；School of Computing, National University of Singapore（新加坡国立大学计算学院）
FKreg: A MATLAB toolbox for fast Multivariate Kernel Regression
The Clinical Hospital of Chengdu Brain Science Institute（成都脑科学研究院临床医院）；University of Electronic Science and Technology of China（电子科技大学）；Cuban Center for Neuroscience（古巴神经科学中心）
核平滑是数据密度和回归估计的最基本技术。然而，直接评价$N$样本的核光滑性需要进行${O}\left( {{N}^{2}} \right)$运算，这就给实际应用带来了很大的困难。人们已经开发了快速平滑算法，使用的思想，分箱与FFT。不幸的是，准确性是不可控的，和实现多变量和它的带宽选择的快速方法是不可用的。为此，本文提出了一种新的基于非均匀FFT（NUFFT）思想的快速多元核回归MATLAB工具箱，实现了具有${O}\left( N+M\log M \right)$复杂度和精度可控性的$M$网格点算法。带宽选择问题利用快速蒙特卡罗算法来估计自由度（DF），当数据共享相同的网格空间进行多元回归时，可以更好地节省大量的交叉验证时间。到目前为止，这是第一个用于快速合并高维核回归的工具箱。此外，局部多项式回归的估计，异方差模型的条件方差，以及复值数据集也在这个工具箱中实现。通过仿真和在定量脑电信号上的应用，证明了该方法的性能。
