|Thursday, September 17th|
Piet Seuntjens, VITO
10:00 AM - 10:20 AM
Monitoring the quality of our water resources is essential if we want to make the transition towards smart water management, which will enable us to better adapt to climate change and create smart water systems for cities and regions. The deployment of IoT technologies, using a wireless network of compact, cost-effective and low-power fluid sensors, enables the collection of indicators of water quality data on a large scale and in real time. The government of Flanders has brought together key partners to build a pilot for such an Internet of Water (IoW) that will be scalable for use in other world regions. A characteristic feature of the Internet of Water Flanders project is its full-stack approach. The aim is to build a network of 2500 wireless fluid sensors that permanently measure aspects of the quality of surface water, groundwater and treated domestic wastewater. The dense network of sensors with high temporal resolution will provide unprecedented volumes of data. The sensor measurements are combined with other existing data sources and processed on a cloud data platform. Machine learning algorithms and models will analyse and visualize the data stream, and make predictions of future evolutions (e.g., the coupling of neural network and data assimilation schemes for water quality forecasting). Water management authorities and utilities can rely on these insights to take short- and long-term actions to address challenges such as salt water intrusion in coastal areas, drought planning and water quality management or the impact of sewer overflows or industrial discharges in surface water. The setup of the IoW and the first test results with a small pilot network of sensors will be presented during this talk.
Matthias Maeyens, VITO
10:20 AM - 10:40 AM
In recent years, extended periods of drought have been affecting the water quality and availability in the Flanders region in Belgium. Especially the coastal region experienced increased salinization of the water system during drought periods. The Flemish government therefore decided to invest in a dense IoT water quality monitoring network aiming to deploy 2500 water quality sensors primarily in surface water but also in ground water and sewers. The goal of this "Internet of Water" project is to establish an operational state of the art monitoring and prediction system in support of future water policy in Flanders. Since Flanders is a relatively small region (13,522 km²), placing this many sensors will result in one of the most dense surface water quality sensor networks in the world. Each sensor will continuously measure several indicators of water quality and transmit the data wirelessly. This allows us to continuously monitor the water quality and build a big enough data set to be able to use a more data driven approach to predicting changes in water quality. However, as with any sensor system, the quality of the data can vary in time due to problems with the sensors, incorrect calibration or unforeseen issues. Real-time data quality control is crucial to prevent unsound decisions due to faulty data. This contribution will give a general overview of the network and it’s specifications, but mainly focus on the implementation of the data stream as well as methods that are implemented to guarantee good data quality. More specifically the architecture and setup of a real-time data quality control system is described. Which will add quality control flags to measurements. This system is integrated with the NGSI API introduced by FIWARE, which forces us to make specific design decisions to accommodate to the NGSI API.
Krishna Mohan Botcha, Centurion University, Odisha state, India
10:40 AM - 11:00 AM
Managing water resources is of utmost importance with the increasing uncertainty in rainfall escalating every year with climate change. Innovation in agriculture has accelerated in the recent years with a wide adoption of upcoming technologies like Internet of Things, Edge computing and Machine Learning. This paper proposes a design for a Smart Irrigation Solution SIrS which can be adopted at scale with low cost and high resilience. The high-level design shown below can be implemented with any commercially available databases and cloud services. Machine learning model requires farm or area specific datasets to be trained and applied in solution. Deployments using containers like Docker will enable remote deployments at large-scale.
Tien Do Huu, Vrije Universiteit Brussel, imec
11:00 AM - 11:20 AM
The Internet of Things (IoT) is a rising communication paradigm, allowing the interconnection of microcontroller-integrated devices via the Internet. In an urban context, the adoption of IoT technologies can lead to a better use of public urban resources, offering high-quality services to citizens while reducing the administrative operational cost. In Smart Cities, a plethora of useful ICT-enabled services can be provided to citizens -including waste management, noise monitoring, smart lighting and air quality monitoring. So far, air quality has been monitored in many cities, mostly by deploying fixed stations. Given the high cost of necessary equipment, the number of the fixed stations is limited; this results in low spatial resolution of air quality data. Low-cost sensing technologies overcome this challenge by providing higher spatial monitoring resolution at a lower cost. By deploying air quality sensors on moving vehicles, the spatial monitoring resolution improves without the need of deploying hundreds of fixed sensors. However, the collected air quality measurements often have low temporal resolution at specific locations because of the movement of the vehicles. Furthermore, there are still many locations that are not covered by the vehicles, leaving room for improving the spatial resolution. In this paper, we present an air quality monitoring system capable of real-time collection of air quality measurements from static reference stations and mobile sensors. To address the problem of spatiotemporal resolution, we introduce a method for processing and interpolating air quality data based on deep learning. Experiments with promising results conducted on data collected from the City-of-Things in Antwerp, Belgium show the effectiveness of the proposed method in comparison with state-of-the-art methods.
Remko Uijlenhoet, Wageningen University, Netherlands
11:20 AM - 11:40 AM
Hydrometeorologists have traditionally relied on dedicated measurement equipment to do their business. Such instruments are typically owned and operated by government agencies and regional or local authorities. Installed and maintained according to (inter)national standards, they offer accurate and reliable information about environmental states and fluxes. Such standard instruments are often further developments of novel measurement techniques which have their origins in the research community and have been tested during dedicated field campaigns. One drawback of the operational measurement networks available to the hydrometeorological community today is that they often lack the required coverage and spatial and/or temporal resolution for high-resolution real-time monitoring or short-term forecasting of rapidly responding systems (e.g. urban areas). Another drawback is that dedicated networks are often costly to install and maintain, which makes it a challenge for nations in the developing world to operate them on a continuous basis, for instance. Yet, our world is nowadays full of sensors, often related to the rapid development in wireless communication networks we are currently witnessing (including 5G). Let us try to make use of such opportunistic sensors to do our science and operations. They may not be as accurate or reliable as the dedicated measurement equipment we are used to working with, let alone meet official international standards, but they typically come in large numbers and are accessible online. Hence, in combination with smart retrieval algorithms and statistical treatment, opportunistic sensors may provide a valuable complementary source of information regarding the state of our environment. The presentation will focus on some recent examples of the potential of opportunistic sensing techniques in hydrometeorology, from rainfall monitoring using microwave links from cellular communication networks (in Europe, South America, Africa and Asia), via crowdsourcing urban air temperatures using smartphone battery temperatures to high-resolution urban rainfall monitoring using personal weather stations.