Preprints
https://doi.org/10.5194/hess-2021-124
https://doi.org/10.5194/hess-2021-124

  10 Mar 2021

10 Mar 2021

Review status: this preprint is currently under review for the journal HESS.

Evaluating different machine learning methods to simulate runoff from extensive green roofs

Elhadi Mohsen Hassan Abdalla1, Vincent Pons1, Virginia Stovin2, Simon De-Ville2, Elizabeth Fassman-Beck3, Knut Alfredsen1, and Tone Merete Muthanna1 Elhadi Mohsen Hassan Abdalla et al.
  • 1Department of Civil and Environmental Engineering, The Norwegian University of Science and Technology, Trondheim, 7031, Norway
  • 2Department of Civil and Structural Engineering, The University of Sheffield, Sheffield, S1 3JD, United Kingdom
  • 3Southern California Coastal Water Research Project, Costa Mesa, California, CA 92626, United States

Abstract. Green roofs are increasingly popular measures to permanently reduce or delay stormwater runoff. Conceptual and physically-based hydrological models are powerful tools to estimate their performance. However, physically-based models are associated with a high level of complexity and computation costs while parameters of conceptual models are more difficult to obtain when measurements are not available for calibration. The main objective of the study was to examine the potential of using machine learning (ML) to simulate runoff from green roofs to estimate their hydrological performance. Four machine learning methods, Artificial Neural Network (ANN), M5 Model tree, Long Short-Term Memory (LSTM) and k-Nearest Neighbour (kNN) were applied to simulate stormwater runoff from sixteen extensive green roofs located in four Norwegian cities across different climatic zones. The potential of these ML methods for estimating green roof retention was assessed by comparing their simulations with a proven conceptual retention model. Furthermore, the transferability of ML models between the different green roofs in the study was tested to investigate the potential of using ML models as a tool for planning and design purposes. The ML models yielded low volumetric errors that were comparable with the conceptual retention models, which indicates good performance in estimating annual retention. The ML models yielded satisfactory modelling results (NSE > 0.5) in both training and validation data which indicates an ability to estimate green roof detention. The variations in ML models' performance between the cities was larger than between the different configurations, which was attributed to the different climatic characteristics between the four cities. Transferred ML models between cities with similar rainfall events characteristics (Bergen–Sandnes, Trondheim–Oslo) could yield satisfactory modelling performance (NSE > 0.5, |PBIAS| < 25 %) in most cases. However, we recommend the use of the conceptual retention model over the transferred ML models, to estimate the retention of new green roofs, as it gives more accurate volume estimates. Follow-up studies are needed to explore the potential of ML models in estimating detention from higher temporal resolution datasets.

Elhadi Mohsen Hassan Abdalla et al.

Status: open (until 12 May 2021)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on hess-2021-124', Anonymous Referee #1, 20 Apr 2021 reply

Elhadi Mohsen Hassan Abdalla et al.

Elhadi Mohsen Hassan Abdalla et al.

Viewed

Total article views: 530 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
433 91 6 530 5 0
  • HTML: 433
  • PDF: 91
  • XML: 6
  • Total: 530
  • BibTeX: 5
  • EndNote: 0
Views and downloads (calculated since 10 Mar 2021)
Cumulative views and downloads (calculated since 10 Mar 2021)

Viewed (geographical distribution)

Total article views: 447 (including HTML, PDF, and XML) Thereof 447 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 09 May 2021