RESUMEN

The reduction of water leakage is essential for ensuring sustainable and resilient water supply systems. Despite recent investments in sensing technologies, pipe leakage remains a significant challenge for the water sector, particularly in developed nations like the UK, which suffer from aging water infrastructure. Conventional models and analytical methods for detecting pipe leakage often face reliability issues and are generally limited to detecting leaks during nighttime hours. Moreover, leakages are frequently detected by the customers rather than the water companies. To achieve substantial reductions in leakage and enhance public confidence in water supply and management, adopting an intelligent detection method is crucial. Such a method should effectively leverage existing sensor data for reliable leakage identification across the network. This not only helps in minimizing water loss and the associated energy costs of water treatment but also aids in steering the water sector towards a more sustainable and resilient future. As a step towards 'self-healing' water infrastructure systems, this study presents a novel framework for rapidly identifying potential leakages at the district meter area (DMA) level. The framework involves training a domain-informed variational autoencoder (VAE) for real-time dimensionality reduction of water flow time series data and developing a two-dimensional surrogate latent variable (LV) mapping which sufficiently and efficiently captures the distinct characteristics of leakage and regular (non-leakage) flow. The domain-informed training employs a novel loss function that ensures a distinct but regulated LV space for the two classes of flow groupings (i.e., leakage and non-leakage). Subsquently, a binary SVM classifier is used to provide a hyperplane for separating the two classes of LVs corresponding to the flow groupings. Hence, the proposed framework can be efficiently utilised to classify the incoming flow as leakage or non-leakage based on the encoded surrogates LVs of the flow time series using the trained VAE encoder. The framework is trained and tested on a dataset of over 2000 DMAs in North Yorkshire, UK, containing water flow time series recorded at 15-minute intervals over one year. The framework performs exceptionally well for both regular and leakage water flow groupings with a classification accuracy of over 98 % on the unobserved test dataset.

Asunto(s)

RESUMEN

The appraisal of appropriate levels of investment for devising flooding mitigation and to support recovery interventions is a complex and challenging task. Evaluation must account for social, political, environmental and other conditions, such as flood state expectations and local priorities. The evaluation method should be able to quickly identify evolving investment needs as the incidence and magnitude of flood events continue to grow. Quantification is essential and must consider multiple direct and indirect effects on flood related outcomes. The method proposed is this study is a Bayesian network, which may be used ex-post for evaluation, but also ex-ante for future assessment, and near real-time for the reallocation of investment into interventions. The particular case we study is the effect of flood interventions upon mental health, which is a gap in current investment analyses. Natural events such as floods expose people to negative mental health disorders including anxiety, distress and post-traumatic stress disorder. Such outcomes can be mitigated or exacerbated not only by state funded interventions, but by individual and community skills and experience. Success is also dampened when vulnerable and previously exposed victims are affected. Current measures evaluate solely the effectiveness of interventions to reduce physical damage to people and assets. This paper contributes a design for a Bayesian network that exposes causal pathways and conditional probabilities between interventions and mental health outcomes as well as providing a tool that can readily indicate the level of investment needed in alternative interventions based on desired mental health outcomes.

Asunto(s)

RESUMEN

Controlling bovine tuberculosis (bTB) disease in cattle farms in England is seen as a challenge for farmers, animal health, environment and policy-makers. The difficulty in diagnosis and controlling bTB comes from a variety of factors: the lack of an accurate diagnostic test which is higher in specificity than the currently available skin test; isolation periods for purchased cattle; and the density of active badgers, especially in high-risk areas. In this paper, to enable the complex evaluation of bTB disease, a dynamic Bayesian network (DBN) is designed with the help of domain experts and available historical data. A significant advantage of this approach is that it represents bTB as a dynamic process that evolves periodically, capturing the actual experience of testing and infection over time. Moreover, the model demonstrates the influence of particular risk factors upon the risk of bTB breakdown in cattle farms.

Asunto(s)

RESUMEN

Many critical infrastructure systems have network structures and are under stress. Despite their national importance, the complexity of large-scale transport networks means that we do not fully understand their vulnerabilities to cascade failures. The research conducted through this paper examines the interdependent rail networks in Greater London and surrounding commuter area. We focus on the morning commuter hours, where the system is under the most demand stress. There is increasing evidence that the topological shape of the network plays an important role in dynamic cascades. Here, we examine whether the different topological measures of resilience (stability) or robustness (failure) are more appropriate for understanding poor railway performance. The results show that resilience, not robustness, has a strong correlation with the consumer experience statistics. Our results are a way of describing the complexity of cascade dynamics on networks without the involvement of detailed agent-based models, showing that cascade effects are more responsible for poor performance than failures. The network science analysis hints at pathways towards making the network structure more resilient by reducing feedback loops.

Asunto(s)

RESUMEN

If epistemology is about what we know and how we know what we know (what is inside) and ontology is about what there is to know (what is outside) then the most fundamental challenge that complexity makes is that these can no longer be considered as separable. Traditional science was based on the idea that there was an objective reality outside, and that we could study it and do experiments on it that allowed us to build, cumulatively, an increasingly accurate picture of that reality. Whilst for simple physical problems, and for planetary motion, this was a reasonable working hypothesis, for biological and social systems this has always been a problem. Experiments are not repeatable or transferable, and situations are historically evolved involving local, co-evolving contexts, and therefore can potentially all be unique and lacking in any generic behaviours or laws. Complexity science brings us face to face with this elusive reality, and tells us that we must accept uncertainty, and admit that our cognition, our descriptions and our models are necessarily incomplete and temporary props to our current functioning. They help us make some sense of the past and the present, and are all we have to help us in taking steps into the future. Examples of these ideas will be given for ecological, social and economic systems, showing that models, despite their necessary incompleteness, can still be useful in clarifying and living with some of the real uncertainties we have, and in this way can help us explore possible futures. However, complexity also tells us that we need not limit our explorations to those suggested by our models, since they are necessarily incomplete, and that we should also indulge in "creative actions" in order to find out more about what might happen, and in this way both increase our possible choices of action, and also improve the scope of our models.

Asunto(s)