The supply sector is subject to ever increasing demands for service and optimization. The large amount of data collected in the sector entails a great opportunity for utilization of machine learning and data science in order to meet these demands. This industrial PhD project aims at investigating how machine learning can create value in the water sector. Furthermore, the goal of the project is to develop three specific machine learning solutions for the water sector, using different machine learning approaches. The three solutions aimed for in this project are within sewer deterioration, anomaly detection and aeration control.
“Prediction of the Methane Production in Biogas Plants Using a Combined Gompertz and Machine Learning Model”
Hansen, B. D., Tamouk, J., Tidmarsh, C. A., Johansen, R., Moeslund, T. B. & Jensen, D. G., 1 okt. 2020, ICCSA 2020, LNCS 12249, pp. 734–745, 2020. Springer
“Sewer Deterioration Modeling: The Effect of Training a Random Forest Model on Logically Selected Data-groups”
Hansen, B. D., Rasmussen, S. H., Moeslund, T. B., Uggerby, M. & Jensen, D. G., 2020, Knowledge-Based and Intelligent Information & Engineering Systems: Proceedings of the 24th International Conference KES2020. Elsevier, Bind 176. s. 291-299 9 s.
“General Sewer Deterioration Model Using Random Forest”
Hansen, B. D., Jensen, D. G., Rasmussen, S. H., Tamouk, J., Uggerby, M. & Moeslund, T. B., 2019, IEEE Symposium on Computational Intelligence for Engineering Solutions (IEEE CIES). IEEE, 8 s.
The project is funded by EnviDan A/S and Innovation Fund Denmark.
PhD-Student: Bolette Dybkjær Hansen
Supervisor: Thomas B. Moeslund