In the last years, many European countries have experienced the effects of climate change, in the form of a scarcity of drinking water resources, prolonged periods of drought, and extremely heavy rainfall, with unprecedented dramatic environmental, economic, and social costs. Therefore, understanding, modelling, and predicting the movement and distribution of water on Earth, and effectively managing water resources is of paramount importance. Unfortunately, hydrology involves atmospheric, surface, and underground water systems, which are difficult to model on their own, and even more so when considered as a whole. As a result, modern hydrology often relies on a number of mathematical and empirical models that focus on isolated portions of the whole water cycle, thus providing only partial, defective and oftentimes inconsistent information. Furthermore, such models are either based on complex physical theories that involve a large number of variables, which are often difficult to observe in practice, or empirically obtained from observations, thus lacking generality, adaptability and interpretability.
The ultimate goal of ANDROMEDA is to leverage cutting-edge ICT methodologies to push the research frontier in the science of hydrology beyond its current limits by: (i) enriching models’ input data sets by means of new sensing technologies combined with suitable data processing algorithms; (ii) applying unsupervised deep learning techniques to find the most informative data and reduce the complexity of current hydrologic models; (iii) combining model-based and data-driven techniques to better predict the spatio-temporal dynamics of water subsystems; (iv) devising comprehensive and powerful models of the whole water cycle, capable of providing more accurate prediction of extreme-yet-critical events; and (v) developing augmented and virtual reality tools to visually report the outcome of the hydrological models, so as to increase their usability by different stakeholders.
The project is strongly Interdisciplinary, featuring experts in hydrology (UPM), environmental monitoring (UNIPD), artificial intelligence (UNIPD, UOU) and 3D visual modelling of geomorphic landscapes (UNIPD). Furthermore, the project is high risk because of the complexity of developing a general framework for a comprehensive hydrologic model, but can provide high returns if successful, given the disruptive potential of a model capable of accurately predicting water fluxes on Earth and extreme events.