Deep reinforcement learning challenges and opportunities for urban water systems.

The efficient and sustainable supply and transport of water is a key component to any functioning civilisation making the role of urban water systems (UWS) inherently crucial to the wellbeing of its customers. However, managing water is not a simple task. Whether it is ageing infrastructure, transient flows, air cavities or low pressures; water can be lost as a result of many issues that face UWSs. The complexity of those networks grows with the high urbanisation trends and climate change making water companies and regulatory bodies in need of new solutions. So, it comes as no surprise that many researchers are invested in innovating within the water industry to ensure that the future of our water is safe. Deep reinforcement learning (DRL) has the potential to tackle complexities that used to be very challenging as it relies on deep neural networks for function approximation and representation. This technology has conquered many fields due to its impressive results and can effectively revolutionise UWS. In this article, we explain the background of DRL and the milestones of this field using a novel taxonomy of the DRL algorithms. This will be followed by with a novel review of DRL applications in the UWS which focus on water distribution networks and stormwater systems. The review will be concluded with critical insights on how DRL can benefit different aspects of urban water systems.

Tidal range electricity generation: A comparison between estuarine barrages and coastal lagoons.

The potential power from coastal tidal range is becoming better appreciated due to the need to mitigate global warming. Great Britain (GB) is ideally situated to exploit tidal power but currently has no operational systems. Historically, estuaries have been proposed as sites for barrages, but more recently coastal lagoons are favoured due to a lower environment impact. To contrast the differences between barrages and lagoons two potential schemes are analysed using the Lancaster 0-D Tidal Range Model. Both schemes were analysed with a range of turbine numbers and generator ratings. The schemes are compared in terms of energy generation, flood protection, navigation, and selected environmental impacts. The analysis indicates that the schemes are not categorically different, characterised by the shape and alignment of the impoundment. Barrages impoundments across estuaries are generally shorter than lagoons impounding similar volumes, with lower civil engineering costs. Whilst estuaries tend to have slightly higher tidal ranges, they also create unique ecological conditions with diverse natural ecosystems that are increasingly valued. The analysis shows that 2-way generation and pumping can match the full tidal range and help preserve inter-tidal areas.

Dataset on the solid-liquid separation of anaerobic digestate by means of wood ash-based treatment.

Wood bottom and fly ashes were added to the anaerobic digestate using sulfuric, hydrochloric, nitric, and lactic acids, as pH conditioners and sorption activating agents. Minimum (pH of zero-point charge), mild, and severe acidification of the samples were tested. The solid-liquid separation achieved was accounted visually and with the measurement of the masses of water-soluble extract and water-insoluble material isolated. The average mass of the blend was 36.61 ± 0.68 g, including the extractant agent that was prepared with the commercial acids and ultrapure milli-QⓇ water. During the 144-h incubation of the mixtures at 20 °C and 0.17 x g, the shares of the solid and liquid were determined by centrifugation of the destructive samples at 3,130.40 x g for 5 minutes and 3-µm filtration of the supernatant. Before weighing the water-insoluble material, both the pellet that remained in the tube and the filter cake were dried at 70 °C until reaching constant weight. There was a significant increase in the amount of water-insoluble phase of the wood bottom ash due to the activation with lactic and sulfuric acids. The treatment of the wood fly ash and the agrowaste digestate with the hydrochloric acid showed an increase in the formation of water-soluble extract, in direct relation with the acidic pH of the blend. The characterization of the pH of the WS extract was performed with a Mettler ToledoⓇ Seven CompactTM S220 pH/Ion meter. The conditions of this process can be further optimized and each of the fractions can be characterized, in terms of nutrient content, to confirm the efficiency of the separation. More complex and ambitious processes can be designed for combining the wood ash and the anaerobic digestate. The performance of this treatment involving wood ashes and commercial acids can be extrapolated to other type of organic manures with a moisture content of approximately 95%, to improve their management in terms of reducing the cost of storage and transportation for land application below £5 per tonne.

Investigating pipeline and state of the art blood glucose biosensors to formulate next steps.

Ten years on from a review in the twentieth issue of this journal, this contribution assess the direction research in the field of glucose sensing for diabetes is headed and various technologies to be seen in the future. The emphasis of this review was placed on the home blood glucose testing market. After an introduction to diabetes and glucose sensing, this review analyses state of the art and pipeline devices; in particular their user friendliness and technological advancement. This review complements conventional reviews based on scholarly published papers in journals.