遇见数据集

Processed dataset used for developing tsunami inundation emulators(Part-II Test Dataset)

收藏
Zenodo2024-12-05 更新2026-05-26 收录
官方服务:

资源简介:

This dataset is related to the main Zenodo repository: https://doi.org/10.5281/zenodo.13738078 This dataset contains some of the processed datasets covering testing datasets covering tsunami inputs and outputs (for parameters of offshore waveforms, local deformation fields and inundation depths) used in the evaluation of machine learning emulator discussed in the preprint article - "Towards Using Machine Learning Emulation for Probabilistic Inundation Mapping: Multiple Earthquake Sources and Near-field Effect with project repo - https://github.com/naveenragur/ML4SicilyTsunami/tree/ptha_emulators. The post-processed (numpy) files for the two test locations of Catania(CT) and Siracusa(SR) are provided in compressed gzip files(.gz) typically stored in data/processed: -test_dZ.tar.gz (local deformation files) -test_d.tar.gz (inundation depth files) -test_t.tar.gz (offshore waveform files) The filename follow nomenclature as below d_CT_0.dat, dZ_CT_0.dat, dflat_CT_0.dat, dZflat_CT_0.dat, t_CT_0.dat,lat_lon_idx_CT_892.npy where the file names represent {parameter}_{site}_{size} The first var represent parameter of the file. d - 2 dimensional file for inundation depth (events x m x n) dZ - 2 dimensional file for local deformation( events x m x n) dflat - 1 dimensional flat file for inundation ( events x locations) dZflat - 1 dimensional flat file for local deformation( events x locations) t - 3 dimension offshore waveform for (events x gauges x timesteps) lat_lon_idx - index file for matching lat long coordinate with location indices(locations x lat x lon) The second var represents site of the file. CT - Catania SR - Siracusa The third var represents number of events in the file or the selection size. 0,1,2,3 - represent the approx 50000 test events divided into 4 splits More information on the attached readme, see project structure and code is available at: https://github.com/naveenragur/ML4SicilyTsunami/tree/ptha_emulators

本数据集关联的Zenodo主仓库地址为:https://doi.org/10.5281/zenodo.13738078。 本数据集包含部分经过预处理的数据集,用于预印本论文《面向概率海啸淹没制图的机器学习仿真:多震源与近场效应》中讨论的机器学习模拟器的评估,这些数据集涵盖了海啸输入与输出的测试集(涵盖近海波形、局地形变场与淹没深度参数),该预印本的项目仓库地址为:https://github.com/naveenragur/ML4SicilyTsunami/tree/ptha_emulators。 针对卡塔尼亚(CT)与锡拉库扎(SR)两个测试点位的后处理numpy(Numerical Python)格式文件以压缩gzip格式(.gz)存储,通常存放于data/processed路径下,具体包括: - test_d.tar.gz(淹没深度文件) - test_dZ.tar.gz(局地形变文件) - test_t.tar.gz(近海波形文件) 文件名遵循如下命名规范:d_CT_0.dat、dZ_CT_0.dat、dflat_CT_0.dat、dZflat_CT_0.dat、t_CT_0.dat、lat_lon_idx_CT_892.npy,其命名格式为{参数}_{点位}_{样本规模}。 各字段含义如下: 1. 第一个字段代表文件的参数类型: - d:二维淹没深度文件,维度为(事件数×m×n) - dZ:二维局地形变文件,维度为(事件数×m×n) - dflat:一维扁平化淹没数据文件,维度为(事件数×监测点位数量) - dZflat:一维扁平化局地形变数据文件,维度为(事件数×监测点位数量) - t:三维近海波形文件,维度为(事件数×测站数×时间步长数) - lat_lon_idx:用于匹配经纬度坐标与点位索引的索引文件,维度为(监测点位数量×纬度×经度) 2. 第二个字段代表文件对应的监测点位: - CT:卡塔尼亚(Catania) - SR:锡拉库扎(Siracusa) 3. 第三个字段代表文件中的事件总数或划分的样本子集编号: 0、1、2、3代表将约50000个测试事件划分为4个拆分子集的编号。 更多信息可参阅附带的README文件,项目结构与代码可访问以下仓库:https://github.com/naveenragur/ML4SicilyTsunami/tree/ptha_emulators

提供机构:
Zenodo
创建时间:
2024-12-02
二维码
社区交流群
二维码
科研交流群
商业服务