A Temporal Fusion Transformer Model to Forecast Overflow from Sewer Manholes during Pluvial Flash Flood Events
This study employs a temporal fusion transformer (TFT) for predicting overflow from sewer manholes during heavy rainfall events. The TFT utilised is capable of forecasting overflow hydrographs at the manhole level and was tested on a sewer network with 975 manholes. As part of the investigations, th...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Hydrology |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5338/11/3/41 |
| _version_ | 1827306025443655680 |
|---|---|
| author | Benjamin Burrichter Juliana Koltermann da Silva Andre Niemann Markus Quirmbach |
| author_facet | Benjamin Burrichter Juliana Koltermann da Silva Andre Niemann Markus Quirmbach |
| author_sort | Benjamin Burrichter |
| collection | DOAJ |
| description | This study employs a temporal fusion transformer (TFT) for predicting overflow from sewer manholes during heavy rainfall events. The TFT utilised is capable of forecasting overflow hydrographs at the manhole level and was tested on a sewer network with 975 manholes. As part of the investigations, the TFT was compared to other deep learning architectures to evaluate its predictive performance. In addition to precipitation measurements and forecasts, the issue of how the additional consideration of measurements in the sewer network as model inputs impacts forecast accuracy was investigated. A varying number of sensors and different measurement signals were compared. The results indicate high performance for the TFT compared to other model architectures like a long short-term memory (LSTM) network or a dual-stage attention-based recurrent neural network (DA-RNN). Additionally, results suggest that considering a single measuring point at the outlet of the sewer network instead of an entire measuring network yields better forecasts. One possible explanation is the high correlation between measurements, which increases model and training complexity without adding much value. |
| first_indexed | 2024-04-24T18:12:08Z |
| format | Article |
| id | doaj.art-311b2720b4a34d6fbe4f67c0dd38374a |
| institution | Directory Open Access Journal |
| issn | 2306-5338 |
| language | English |
| last_indexed | 2024-04-24T18:12:08Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Hydrology |
| spelling | doaj.art-311b2720b4a34d6fbe4f67c0dd38374a2024-03-27T13:44:43ZengMDPI AGHydrology2306-53382024-03-011134110.3390/hydrology11030041A Temporal Fusion Transformer Model to Forecast Overflow from Sewer Manholes during Pluvial Flash Flood EventsBenjamin Burrichter0Juliana Koltermann da Silva1Andre Niemann2Markus Quirmbach3Institute of Civil Engineering, University of Applied Sciences Ruhr West, 45479 Mülheim an der Ruhr, GermanyInstitute of Civil Engineering, University of Applied Sciences Ruhr West, 45479 Mülheim an der Ruhr, GermanyInstitute of Hydraulic Engineering and Water Resources Management, University of Duisburg-Essen, 45141 Essen, GermanyInstitute of Civil Engineering, University of Applied Sciences Ruhr West, 45479 Mülheim an der Ruhr, GermanyThis study employs a temporal fusion transformer (TFT) for predicting overflow from sewer manholes during heavy rainfall events. The TFT utilised is capable of forecasting overflow hydrographs at the manhole level and was tested on a sewer network with 975 manholes. As part of the investigations, the TFT was compared to other deep learning architectures to evaluate its predictive performance. In addition to precipitation measurements and forecasts, the issue of how the additional consideration of measurements in the sewer network as model inputs impacts forecast accuracy was investigated. A varying number of sensors and different measurement signals were compared. The results indicate high performance for the TFT compared to other model architectures like a long short-term memory (LSTM) network or a dual-stage attention-based recurrent neural network (DA-RNN). Additionally, results suggest that considering a single measuring point at the outlet of the sewer network instead of an entire measuring network yields better forecasts. One possible explanation is the high correlation between measurements, which increases model and training complexity without adding much value.https://www.mdpi.com/2306-5338/11/3/41deep learningtemporal fusion transformerurban pluvial floodingurban drainage systemreal-time flood forecastingmanhole overflow |
| spellingShingle | Benjamin Burrichter Juliana Koltermann da Silva Andre Niemann Markus Quirmbach A Temporal Fusion Transformer Model to Forecast Overflow from Sewer Manholes during Pluvial Flash Flood Events Hydrology deep learning temporal fusion transformer urban pluvial flooding urban drainage system real-time flood forecasting manhole overflow |
| title | A Temporal Fusion Transformer Model to Forecast Overflow from Sewer Manholes during Pluvial Flash Flood Events |
| title_full | A Temporal Fusion Transformer Model to Forecast Overflow from Sewer Manholes during Pluvial Flash Flood Events |
| title_fullStr | A Temporal Fusion Transformer Model to Forecast Overflow from Sewer Manholes during Pluvial Flash Flood Events |
| title_full_unstemmed | A Temporal Fusion Transformer Model to Forecast Overflow from Sewer Manholes during Pluvial Flash Flood Events |
| title_short | A Temporal Fusion Transformer Model to Forecast Overflow from Sewer Manholes during Pluvial Flash Flood Events |
| title_sort | temporal fusion transformer model to forecast overflow from sewer manholes during pluvial flash flood events |
| topic | deep learning temporal fusion transformer urban pluvial flooding urban drainage system real-time flood forecasting manhole overflow |
| url | https://www.mdpi.com/2306-5338/11/3/41 |
| work_keys_str_mv | AT benjaminburrichter atemporalfusiontransformermodeltoforecastoverflowfromsewermanholesduringpluvialflashfloodevents AT julianakoltermanndasilva atemporalfusiontransformermodeltoforecastoverflowfromsewermanholesduringpluvialflashfloodevents AT andreniemann atemporalfusiontransformermodeltoforecastoverflowfromsewermanholesduringpluvialflashfloodevents AT markusquirmbach atemporalfusiontransformermodeltoforecastoverflowfromsewermanholesduringpluvialflashfloodevents AT benjaminburrichter temporalfusiontransformermodeltoforecastoverflowfromsewermanholesduringpluvialflashfloodevents AT julianakoltermanndasilva temporalfusiontransformermodeltoforecastoverflowfromsewermanholesduringpluvialflashfloodevents AT andreniemann temporalfusiontransformermodeltoforecastoverflowfromsewermanholesduringpluvialflashfloodevents AT markusquirmbach temporalfusiontransformermodeltoforecastoverflowfromsewermanholesduringpluvialflashfloodevents |