Machine learning and in particular deep learning are powerful enabling technologies for the water sector. Both in the water monitoring and modeling fields, we observe a leap in capabilities. For instance, machine learning assists in the acceleration of physically-based models, breaching the gap between operational models and our best representation of the underlying physics. Also, computer vision and remote sensing powered by deep-learning solutions are unlocking the observation of new hydro-environmental processes in the field. These technologies lead to a better understanding of our water systems and a better capacity to actively manage our infrastructure and ecosystems.

Dr. Antonio Moreno-Rodenas is a researcher in environmental hydraulics. He graduated as a civil engineer (hydraulics and energy) at the Polytechnical University of Valencia. In 2019 he defended his Ph.D. at the Delft University of Technology, where he conducted research on the quantification of uncertainties in large-scale water quality models within a Marie Sklodowska-Curie EU program. Since then, he works at the hydraulic engineering unit of Deltares, researching new monitoring-modeling methods for the water industry. This involves the use of computer vision, remote sensing, and machine learning techniques to investigate hydraulic-environmental processes at laboratory and field scales. Currently, he is the coordinator of the Deltares’ Data science program (enabling technologies).