1 Interoperating Data-driven and Model-driven Techniques for the Automated Development of Intelligent Environmental Decision Support Systems Josep Pascual-Pañach a,b,c , Miquel Àngel Cugueró-Escofet a,b,d , Miquel Sànchez-Marrè c a CCB Serveis Mediambientals, SAU b Consorci Besòs Tordera Av. Sant Julià, 241, 08403 Granollers, Catalonia Email: jpascual@besos-tordera.cat c Knowledge Engineering and Machine Learning Group (KEMLG) Intelligent Data Science and Artificial Intelligence Research Centre (IDEAI-UPC) Universitat Politècnica de Catalunya (UPC) Campus Nord, building OMEGA, C. Jordi Girona 1-3, 08034 Barcelona, Catalonia Email: miquel@cs.upc.edu d Advanced Control Systems Research Group, Universitat Politècnica de Catalunya (UPC- BarcelonaTech), Terrassa Campus, Gaia Research Bldg. Rambla Sant Nebridi, 22, 08222 Terrassa, Barcelona, Catalonia Email: miquel.angel.cuguero@upc.edu Abstract: This paper proposes an Intelligent Decision Support (IDS) methodology based on the integration of data-driven and model-driven techniques for control, supervision and decision support on environmental systems. Design stage of control and decision support tools for environmental systems tend to be somehow ad-hoc regarding to the nature of the processes involved. Hence, an automated approach is proposed here for the sake of scalability to different types and configurations of environmental systems, and the methodology has been designed in a general fashion to allow scalability to further types of systems. The interoperation of a data-driven technique –Case-Based Reasoning (CBR)– and a model-driven technique –Rule-Based Reasoning (RBR)– is considered in this work. The proposed hybrid scheme provides complementarity and supervised redundancy in the set- point generation for the process controllers and actuators, increasing the reliability of the Intelligent Process Control System (IPCS), which is the core component of the IDS methodology. A Decision module selects which reasoning approach to use –i.e. CBR or RBR– depending on a metric quantifying the confidence in the CBR solution. Furthermore, the IDS methodology is flexible and dynamic enough to be able to cope with the dynamic evolution of environmental systems, learning from its relevant experienced situations. The approach presented has been implemented in a real facility within the ambit of a local water administration in the area of Barcelona. Keywords: Case-Based Reasoning; Rule-Based Reasoning; Intelligent Environmental Decision Support System; Intelligent Process Control; Data Mining; Wastewater Treatment Plant. 1 INTRODUCTION 1.1 Background © 2021 Elsevier. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/