Volume 10, Issue 3 (2022)
ECOPERSIA 2022, 10(3): 231-243 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Ahmadinezhad Baghban F, Moosavi V. Convolutional Neural Networks (CNN)-Signal Processing Combination for Daily Runoff Forecasting. ECOPERSIA 2022; 10 (3) :231-243
URL: http://ecopersia.modares.ac.ir/article-24-60974-en.html
URL: http://ecopersia.modares.ac.ir/article-24-60974-en.html
1- Department of Watershed Management Engineering, Faculty of Natural Resources and Marine Sciences, Tarbiat Modares University, Iran.
2- Department of Watershed Management Engineering, Faculty of Natural Resources and Marine Sciences, Tarbiat Modares University, Iran. ,v.moosavi@modares.ac.ir
2- Department of Watershed Management Engineering, Faculty of Natural Resources and Marine Sciences, Tarbiat Modares University, Iran. ,
Abstract: (1280 Views)
Aim: The main aim of this study was to assess the efficacy of two important signal processing approaches i.e., wavelet transform and ensemble empirical mode decomposition (EEMD) on the performance of convolutional neural network (CNN).
Materials & Methods: The study was performed in two watersheds i.e., Kasilian and Bar-Erieh watersheds. In the first step, the CNN based runoff modeling was done in its single form i.e., using the original data as input. In the next step the input data was decomposed into several different sub-components i.e., approximation and details using Wavelet transform and Intrinsic Mode Functions (IMFs) using EEMD. Then the decomposed data were imported to the CNN model as input and combined Wavelet-CNN and EEMD-CNN models were provided.
Findings: The results showed that CNN in its single form could not estimate the one day ahead runoff with an acceptable accuracy. CNN in its original form had a moderate performance (with NRMSE of 83 and 66%). However, application of Wavelet transform and EEMD in combination with CNN produced acceptable results. It was shown that Wavelet transform had a higher impact (with NRMSE of 48 and 26%) on the performance of CNN in comparison to EEMD (with NRMSE of 52 and 61%).
Conclusion: This study showed that signal processing approaches can enhance the ability of deep learning methods such as CNN in predicting runoff values for one day ahead. However, the impact of signal processing methods on the performance of deep learning methods are not equal.
Materials & Methods: The study was performed in two watersheds i.e., Kasilian and Bar-Erieh watersheds. In the first step, the CNN based runoff modeling was done in its single form i.e., using the original data as input. In the next step the input data was decomposed into several different sub-components i.e., approximation and details using Wavelet transform and Intrinsic Mode Functions (IMFs) using EEMD. Then the decomposed data were imported to the CNN model as input and combined Wavelet-CNN and EEMD-CNN models were provided.
Findings: The results showed that CNN in its single form could not estimate the one day ahead runoff with an acceptable accuracy. CNN in its original form had a moderate performance (with NRMSE of 83 and 66%). However, application of Wavelet transform and EEMD in combination with CNN produced acceptable results. It was shown that Wavelet transform had a higher impact (with NRMSE of 48 and 26%) on the performance of CNN in comparison to EEMD (with NRMSE of 52 and 61%).
Conclusion: This study showed that signal processing approaches can enhance the ability of deep learning methods such as CNN in predicting runoff values for one day ahead. However, the impact of signal processing methods on the performance of deep learning methods are not equal.
Article Type: Original Research |
Subject:
Water Management
Received: 2022/04/18 | Accepted: 2022/07/15 | Published: 2022/10/18
Received: 2022/04/18 | Accepted: 2022/07/15 | Published: 2022/10/18
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |