Search

The prediction of combined sewer overflow (CSO) operation in urban environments presents a challenging task for water utilities. The operation of CSOs (most often in heavy rainfall conditions) prevents houses and businesses from flooding. However, sometimes, CSOs do not operate as they should, potentially bringing environmental pollution risks. Therefore, CSOs should be appropriately managed by water utilities, highlighting the need for adapted decision support systems. This paper proposes an automated CSO predictive model construction methodology using field monitoring data, as a substitute for the commonly established hydrological-hydraulic modeling approach for time-series prediction of CSO statuses. It is a systematic methodology factoring in all monitored field variables to construct time-series dependencies for CSO statuses. The model construction process is largely automated with little human intervention, and the pertinent variables together with their associated time lags for every CSO are holistically and automatically generated. A fast least absolute shrinkage and selection operator solution generating scheme is proposed to expedite the model construction process, where matrix inversions are effectively eliminated. The whole algorithm works in a stepwise manner, invoking either an incremental or decremental movement for including or excluding one model regressor into, or from, the predictive model at every step. The computational complexity is thereby analyzed with the pseudo code provided. Actual experimental results from both single-step ahead (i.e., 15 min) and multistep ahead predictions are finally produced and analyzed on a U.K. pilot area with various types of monitoring data made available, demonstrating the efficiency and effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Currently available risk prediction methods are limited in their ability to deal with complex, heterogeneous, and longitudinal data such as that available in primary care records, or in their ability to deal with multiple competing risks. This paper develops a novel deep learning approach that is able to successfully address current limitations of standard statistical approaches such as landmarking and joint modeling. Our approach, which we call Dynamic-DeepHit, flexibly incorporates the available longitudinal data comprising various repeated measurements (rather than only the last available measurements) in order to issue dynamically updated survival predictions for one or multiple competing risk(s). Dynamic-DeepHit learns the time-to-event distributions without the need to make any assumptions about the underlying stochastic models for the longitudinal and the time-to-event processes. Thus, unlike existing works in statistics, our method is able to learn data-driven associations between the longitudinal data and the various associated risks without underlying model specifications. We demonstrate the power of our approach by applying it to a real-world longitudinal dataset from the U.K. Cystic Fibrosis Registry, which includes a heterogeneous cohort of 5883 adult patients with annual follow-ups between 2009 to 2015. The results show that Dynamic-DeepHit provides a drastic improvement in discriminating individual risks of different forms of failures due to cystic fibrosis. Furthermore, our analysis utilizes post-processing statistics that provide clinical insight by measuring the influence of each covariate on risk predictions and the temporal importance of longitudinal measurements, thereby enabling us to identify covariates that are influential for different competing risks. [ABSTRACT FROM AUTHOR]

Recent long term planning studies have demonstrated the important role of variable renewables (VRE) in decarbonising our energy system. However, cost-optimising models do not capture the visual impact of VREs on the landscape which can act to undermine their public acceptability. Here, we use crowd-sourced scenicness data to derive spatially explicit wind energy capacity potentials for three scenarios of public sensitivity to this visual impact. We then use these scenarios in a cost-optimising model of Great Britain's power system to assess their impact on the cost and design of the electricity system in 2050. Our results show that total system costs can increase by up to 14.2% when public sensitivity to visual impact is high compared to low. It is thus essential for policy makers to consider these cost implications and to find mechanisms to ameliorate the visual impact of onshore wind in local communities. [ABSTRACT FROM AUTHOR]

In this article, we introduce the work of the Massively Parallel Particle Hydrodynamics working group, part of the U.K.'s ExCALIBUR software initiative. The aim of the group is to develop extensible software suitable for simulating complex hydrodynamics problems on exascale computing facilities using a Lagrangian particle-based approach. These methods complement mesh-based approaches, and are particularly suited to problems with a large and fluid dynamic range or that involve free surfaces. The code we are developing uses fine-grained task parallelism to achieve a good load balance, when the workload varies greatly from fluid element to element. We describe how components from astrophysics and engineering are being brought together to further develop this interesting approach, and outline some of the challenges, such as enabling task execution on graphics processing units, that the working group will need to solve in order to extract the full potential of exascale systems. [ABSTRACT FROM AUTHOR]

Any reliable model for scheduling optical space-to-ground communication must factor in cloud cover conditions due to attenuation of the laser beam by water droplets in the clouds. In this article, we provide two alternative models of uncertainty for cloud cover predictions: a robust optimization model with a polyhedral uncertainty set and a distributionally robust optimization model with a moment-based ambiguity set. We computationally analyze their performance over a realistic communication system with one satellite and a network of ground stations located in the U.K. The models are solved to schedule satellite operations for six months utilizing cloud cover predictions from official weather forecasts. We found that the presented formulations with the treatment of uncertainty outperform in the long-term models, in which uncertainty is ignored. Both treatments of uncertainty exhibit similar performance. Nonetheless, the novel variant with the polyhedral uncertainty set is considerably faster to solve. [ABSTRACT FROM AUTHOR]