Machine learning methods operate on formal representations of the data at hand and the models or patterns induced from the data. They also assume a suitable formalization of the learning task itself (e.g., as a classification problem), including a specification of the objective in terms of a suitable performance metric, and sometimes other criteria the induced model is supposed to meet. Different representations or problem formalizations may be more or less appropriate to address a particular task and to deal with the type of training information available. The goal of LEMUR is to create a novel branch of machine learning we call Learning with Multiple Representations. We aim to develop the theoretical foundations and a first set of algorithms for this new paradigma. Moreover, corresponding applications are to demonstrate the usefulness of the new family of approaches. We regard LEMUR as very timely, as LMR algorithms will allow to flexible representations (e.g., suitable for explainability, fairness) with diverse target functions (e.g., incorporating environmental or even social impact) so as to make the induced models abide by the Green Charter and trustworthy AI criteria by design. We will focus on learning with weak supervision because it addresses one of the major flaws of modern ML approaches, i.e., their data hunger, by means of weaker sources of labelling for training data. The outcome of the DN will be a set of 10 experts trained to implement the third and subsequent waves of AI in Europe. The highly interdisciplinary and intersectoral context in which they will be trained will provide them with research-related and transferable competences relevant to successful careers in central AI areas.

Water is a vital natural resource, delivering essential services to our societies and economies, and thereby playing a key role in European productivity and security. Excessive leakage and excessive consumption, especially in areas like Cyprus, where there is water scarcity and drought, have a direct negative impact on the EU citizens’ health and on the economy. Therefore, the need for developing and introducing advanced innovative metering and smart water data management technologies is more evident than ever before. The SME SignalGeneriX in collaboration with the University of Cyprus and the Limassol Water Board proposes a revolutionary IoT-based system for intelligent real-time water management and leakage detection with unique functionalities and data privacy management. The TAMIT project aims to significantly improve current technologies developed by SignalGeneriX (US patent pending) and introduce additional novel technologies, so as to develop a new product able to disrupt with its innovations the smart water management market and beyond. Some of the innovative technologies and components that will be included in the TAMIT product are: 1) A novel low-powered, low-cost, universal automatic water metering add-on device that can provide water consumption readings in real-time and communicate these to the cloud 2) Innovative signal processing algorithms and processes embedded in the device to provide robust water metering readings 3) A cloud-based platform able to store a vast number of water meter readings and provide water management interfaces and visualisation to utilities and consumers 4) Innovative water utility big data analytics algorithms and processes for intelligent water management embedded in the cloud platform 5) Innovative algorithms and AI based processes for data privacy vulnerability management 6) Robust water leakage detection and early alerting processes 7) A mobile platform and application for enabling personalized water management

Exposure of citizens to potential disasters has led to vulnerable societies that require risk reduction measures. Drinking water is one main source of risk when its safety and security is not ensured. aqua3S combines novel technologies in water safety and security, aiming to standardise existing sensor technologies complemented by state-of-the-art detection mechanisms. On the one hand sensor networks are deployed in water supply networks and sources, supported by complex sensors for enhanced detection; on the other hand sensor measurements are supported by videos from Unmanned Aerial Vehicles (UAVs), satellite images and social media observations from the citizens that report low-quality water in their area (e.g. by colorisation), creating also social awareness and an interactive knowledge transfer. Semantic representation and data fusion provides intelligent DSS alerts and messages to the public through first responders’ mediums. The proposed technical solution is designed to offer a very effective detection system, taking into account the cost of the aqua3S platform and targets at very high return over investment ratio. A strategy for the insertion of aqua3S solution into the market is designed towards the standardisation of the proposed technologies and the aqua3S secure platform.

Delivering water of good quality is a crucial societal function. Problems can occur due to pathogen contamination, accidental injections of sewage water/industrial chemicals, etc. Moreover, new challenges appear, such as the so-called “forever chemicals”, causing cancer in the long-term. Water contaminants may infiltrate naturally or maliciously into a drinking water system. Currently, water utilities typically depend on manual samplings, consumers’ feedback and very few water quality sensors to detect events and decide on response measures. The current scene with regards to water quality monitoring and control demonstrates that a high-quality product in the water quality monitoring and contamination risk management domain would be valuable. The core DigiWATER vision is to make continuous online water quality monitoring accessible to all water system operators, enabling them to effectively respond to the recent EU Directive’s set of minimum quality standards. The consortium plans to build on top of WaterAnalytics Platform, offering an innovative, low-cost intelligent “Digital Water Twin” software, designed to meet the needs of water system operators to comply with legislation and continuously monitor the quality of water in their distribution networks, evaluate the risk of contamination incidents and isolate their possible locations and magnitude asap. This will assist water utilities in reducing personnel workload, contamination detection & response time, risk of deaths, decontamination, liability & insurance costs and fines. The project is compatible with the RESTART Programme and the Call objectives, such as the development of an innovative product, to improve the competitiveness of PHOEBE in EU and internationally in the smart water market, the enhancement of the research capacity of PHOEBE, through its collaboration with the KIOS CoE, the creation of a link between PHOEBE and WBL, that might result into the use of PHOEBE’s innovative products in WBL’s day-to-day operations and more.