DiTEC-WDN
收藏资源简介:
DiTEC-WDN是一个大规模的水力情景数据集,由荷兰格罗宁根大学伯努利学院和阿姆斯特丹大学信息学院共同创建。该数据集包含36,000个独特的模拟场景,覆盖短期(24小时)和长期(1年)周期。通过自动化的管道优化关键参数,生成228百万个基于规则验证和事后分析的离散、合成但水力现实的网络状态。该数据集支持多种机器学习任务,如图级、节点级和链接级回归以及时间序列预测,为水 distribution 网络领域的研究提供了一个大型基准数据集。
DiTEC-WDN is a large-scale hydraulic scenario dataset jointly created by the Bernoulli Institute of the University of Groningen and the School of Informatics of the University of Amsterdam, the Netherlands. This dataset contains 36,000 unique simulation scenarios covering both short-term (24-hour) and long-term (1-year) cycles. Through automated, pipeline-based optimization of critical parameters, it generates 228 million discrete, synthetic yet hydraulically realistic network states validated via rule-based verification and post-hoc analysis. This dataset supports a variety of machine learning tasks including graph-level, node-level, link-level regression and time series forecasting, providing a large-scale benchmark dataset for research in the field of water distribution networks.




