Data driven hydrological modelling for railway water management

当铁路排水基础设施发生故障时，由此产生的洪水可能会导致乘客延误和生命危险，并对网络铁路(NR)造成惩罚性成本，但也可能导致其他严重故障，如最近在苏格兰东北部发生的严重脱轨事件。最近，NR与谢菲尔德大学(UoS)的合作开始揭示排水资产的表现和退化，以及由此对母公司资产的影响。然而，这种理解取决于对从周围集水区进入铁路系统的水量的准确和可靠的了解。目前的水文模型是大规模运行的，用于预测大范围的洪水区域，而不是开发用于在与个别铁路资产相关的尺度上准确模拟水流路径。数字地形模型的分辨率通常有限，可以省略较小比例的排水功能，例如可以显著改变小集水区的路边沟渠。模型还受到入渗率、存储容量和径流路线等因素的严重不确定性。这个项目将使用数据驱动的方法来解决从降雨到铁路的水路运输过程中的不确定性，从而能够更准确地预测个别铁路资产水平的到达流量。该项目将由Nichols博士和Tait教授与Network Rail的合作伙伴合作监督。Network Rail将提供对行业的关注，并使成功的申请者能够在行业和学术界之间工作，并在大学和公司花费大量时间

When railway drainage infrastructure fails, resulting flooding can cause delay and risk to life for passengers, and penalty costs for Network Rail (NR), but can also cause other severe failures such as land slips, as seen in the recent serious derailment event in North-East Scotland.Recent collaboration between NR and The University of Sheffield (UoS) has begun to shed light on the performance and degradation of drainage assets, and the resulting impacts on parent assets. However, this understanding is contingent on accurate and reliable knowledge of the volume of water entering the railway system from the surrounding catchment.Current hydrological models operate at large scale to predict broad areas of flooding, and are not developed for accurate modelling of flow paths at scales relevant to individual railway assets. Digital terrain models are typically limited in resolution and can omit smaller scale drainage features such as roadside ditches that can substantially alter a small catchment. Models also suffer from deep uncertainty in factors such as infiltration rate, storage capacities and flow routing. This project will use a data-driven approach to address the uncertainty in water transport processes from rainfall to railway, enabling more accurate prediction of arrival flow volumes at the individual railway asset level.The project will be supervised by Dr Nichols and Professor Tait in collaboration with partners from Network Rail. Network Rail will provide industrial focus and enable the successful applicant to work at the interface between industry and academia, with substantial time spent both at the university and the company