Interpretable Time Series Models for Wastewater Modeling in Combined Sewer Overflows (2401.02465v1)
Abstract: Climate change poses increasingly complex challenges to our society. Extreme weather events such as floods, wild fires or droughts are becoming more frequent, spontaneous and difficult to foresee or counteract. In this work we specifically address the problem of sewage water polluting surface water bodies after spilling over from rain tanks as a consequence of heavy rain events. We investigate to what extent state-of-the-art interpretable time series models can help predict such critical water level points, so that the excess can promptly be redistributed across the sewage network. Our results indicate that modern time series models can contribute to better waste water management and prevention of environmental pollution from sewer systems. All the code and experiments can be found in our repository: https://github.com/TeodorChiaburu/RIWWER_TimeSeries.
- Tabnet: Attentive interpretable tabular learning. arXiv:1908.07442.
- A spatiotemporal deep learning approach for urban pluvial flood forecasting with multi-source data. Water 15. doi:10.3390/w15091760.
- N-hits: Neural hierarchical interpolation for time series forecasting. arXiv:2201.12886.
- An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929.
- A simplified approach for the hydrological simulation of urban drainage systems with swmm. Journal of Hydrology 623, 129757. doi:10.1016/j.jhydrol.2023.129757.
- Stochastic weight averaging revisited. arXiv:2201.00519.
- Temporal fusion transformers for interpretable multi-horizon time series forecasting. arXiv:1912.09363.
- A Review on Machine Learning, Artificial Intelligence, and Smart Technology in Water Treatment and Monitoring. Water 14, 1384. URL: https://www.mdpi.com/2073-4441/14/9/1384, doi:10.3390/w14091384.
- Reinforcement learning-based particle swarm optimization for sewage treatment control. Springer Link URL: https://doi.org/10.1007/s40747-021-00395-w.
- The bellinge data set: open data and models for community-wide urban drainage systems research. Earth System Science Data 13, 4779–4798. URL: https://essd.copernicus.org/articles/13/4779/2021/, doi:10.5194/essd-13-4779-2021.
- N-beats: Neural basis expansion analysis for interpretable time series forecasting. arXiv:1905.10437.
- Accelerating hydrodynamic simulations of urban drainage systems with physics-guided machine learning. Water Research 223, 118972. URL: https://www.sciencedirect.com/science/article/pii/S0043135422009198, doi:https://doi.org/10.1016/j.watres.2022.118972.
- A threefold rise in widespread extreme rain events over central India. Nature Communications 8, 708. URL: https://doi.org/10.1038/s41467-017-00744-9, doi:10.1038/s41467-017-00744-9.
- Attention is all you need. arXiv:1706.03762.
- A review of the application of machine learning in water quality evaluation. Eco-Environment & Health 1, 107–116. URL: https://linkinghub.elsevier.com/retrieve/pii/S2772985022000163, doi:10.1016/j.eehl.2022.06.001.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
