five

Processed dataset used for developing tsunami inundation emulators(Part-III Simulation and Emulation Dataset)

收藏
NIAID Data Ecosystem2026-05-02 收录
下载链接:
https://zenodo.org/record/13741057
下载链接
链接失效反馈
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 tsunami inundation depths using simulation results and emulation results discussed in the article - "Towards Using Machine Learning Emulation for Probabilistic Inundation Mapping: Multiple Earthquake Sources and Near-field Effectwith 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): Processed inundation depth files from simulation and emulation typically stored in model/CT/ptha or model/SR/ptha     -pthaSR.tar.gz - max inundation depth1d(eve x m) for true(simulation and pred(emulation of different models))     -pthaCT.tar.gz - max inundation depth1d(eve x m) for true(simulation and pred(emulation of different models)) The filename follows the nomenclature with: -true - simulation results -pred - emulator with pretraining -pred_direct - emulator without pretraining -pred_nodeform - emulator without pertaining and deformation input More information on the attached readme, see project structure and code is available at: https://github.com/naveenragur/ML4SicilyTsunami/tree/ptha_emulators

本数据集关联的官方Zenodo仓库地址为:https://doi.org/10.5281/zenodo.13738078 本数据集包含经后处理的部分数据集,其基于论文《面向机器学习仿真开展概率淹没制图:多地震源与近场效应》(英文原标题:Towards Using Machine Learning Emulation for Probabilistic Inundation Mapping: Multiple Earthquake Sources and Near-field Effect)中讨论的模拟结果与仿真结果,用于提取海啸淹没深度数据,项目仓库地址为:https://github.com/naveenragur/ML4SicilyTsunami/tree/ptha_emulators 针对卡塔尼亚(Catania,缩写CT)与锡拉库扎(Siracusa,缩写SR)这两个测试点位的经后处理numpy格式文件,均以gzip压缩文件(后缀为.gz)形式发布。 模拟与仿真得到的淹没深度处理文件通常存储于model/CT/ptha或model/SR/ptha路径下: - pthaSR.tar.gz:包含全事件×网格点维度的最大淹没深度数据,涵盖真实模拟结果(true)与不同模型的仿真预测结果(pred); - pthaCT.tar.gz:包含全事件×网格点维度的最大淹没深度数据,涵盖真实模拟结果与不同模型的仿真预测结果。 文件命名遵循以下规范: - true:模拟计算得到的真实结果; - pred:经过预训练的仿真器预测结果; - pred_direct:未经过预训练的仿真器直接预测结果; - pred_nodeform:未经过预训练且未输入形变参数的仿真器预测结果。 更多细节可参阅随附的自述文件,项目结构与代码可访问以下仓库地址获取:https://github.com/naveenragur/ML4SicilyTsunami/tree/ptha_emulators
创建时间:
2024-12-05
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作