Abstract
Acquiring river flow records is the primary precondition for providing optimal water resource management practices and preserving the ecohydrological balance. In Turkey, some river gauging stations go intermittently out of service due to some technical problems or unexpected difficulties. Consequently, river flow records are lost, and this is especially true in the rural and remote areas of the nation. In this regard, we investigated the ability of recurrent neural networks (RNN) as a supportive approach for retrieving daily river flow data for some stations, namely, Akçaşehir and Dağgüney located on the Susurluk basin in Bursa, Turkey. To meet the study goal, flow records from nearby stations were collected. In addition, a RNN with two hidden layers was developed. Initially, the model was trained and validated; then, we tried to predict missing records. The findings showed the potential of RNN in providing good predictions during low and mid flows with acceptable uncertainties rate (less than 30%) even with limited number of input data. Moreover, we discussed the current challenges and opportunities of this issue in remote areas of Turkey. Overall, our findings suggested that RNN may be considered as a practical method to predict the likely periods of floods and droughts in remote areas and interpolate missing records instead of using classical approaches.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Availability of data and materials
Runoff data used in this study are openly available on General Directorate of State Water Affairs DSI website.
References
Abbasi, M., Farokhnia, A., Bahreinimotlagh, M., & Roozbahani, R. (2020). A hybrid of Random Forest and Deep Auto-Encoder with support vector regression methods for accuracy improvement and uncertainty reduction of long-term streamflow prediction. Journal of Hydrology. https://doi.org/10.1016/j.jhydrol.2020.125717
Al Sawaf, M. B., Kawanisi, K., & Xiao, C. (2020). Measuring low flowrates of a shallow mountainous river within restricted site conditions and the characteristics of acoustic arrival times within low flows. Water Resources Management, 34(10), 3059–3078. https://doi.org/10.1007/s11269-020-02557-w
Beck, A., Flad, D., & Munz, C. D. (2019). Deep neural networks for data-driven LES closure models. Journal of Computational Physics. https://doi.org/10.1016/j.jcp.2019.108910
Di Baldassarre, G., & Montanari, A. (2009). Uncertainty in river discharge observations: A quantitative analysis. Hydrology and Earth System Sciences, 13(6), 913–921. https://doi.org/10.5194/hess-13-913-2009
Feng, J., Yan, L., & Hang, T. (2019). Stream-flow forecasting based on dynamic spatio-temporal attention. https://ieeexplore.ieee.org/abstract/document/8839786/. Accessed 20 April 2021
Graeff, T., Zehe, E., Reusser, D., Lück, E., Schröder, B., Wenk, G., et al. (2009). Process identification through rejection of model structures in a mid-mountainous rural catchment: Observations of rainfall-runoff response, geophysical conditions and model inter-comparison. Hydrological Processes, 23(5), 702–718. https://doi.org/10.1002/hyp.7171
Hitokoto, M., Sakuraba, M., & Sei, Y. (2017). Development of the real-time river stage prediction method using deep learning. Journal of JSCE, 5(1), 422–429. https://doi.org/10.2208/journalofjsce.5.1_422
Kawanisi, K., Bahreinimotlagh, M., Al Sawaf, M. B., & Razaz, M. (2016). High-frequency streamflow acquisition and bed level/flow angle estimates in a mountainous river using shallow-water acoustic tomography. Hydrological Processes, 30(13), 2247–2254. https://doi.org/10.1002/hyp.10796
Kim, K., Kim, D. K., Noh, J., & Kim, M. (2018). Stable forecasting of environmental time series via long short term memory recurrent neural network. IEEE Access, 6, 75216–75228. https://doi.org/10.1109/ACCESS.2018.2884827
Kratzert, F., Klotz, D., Brenner, C., Schulz, K., & Herrnegger, M. (2018). Rainfall–runoff modelling using long short-term memory (LSTM) networks. Hydrology and Earth System Sciences, 22(11), 6005–6022. https://doi.org/10.5194/hess-22-6005-2018
Lee, C. (2016). Image caption generation using recurrent neural network. Journal of KIISE, 43(8), 878–882. https://doi.org/10.5626/jok.2016.43.8.878
McMillan, H., Freer, J., Pappenberger, F., Krueger, T., & Clark, M. (2010). Impacts of uncertain river flow data on rainfall-runoff model calibration and discharge predictions. Hydrological Processes. https://doi.org/10.1002/hyp.7587
McMillan, H., Seibert, J., Petersen-Overleir, A., Lang, M., White, P., Snelder, T., et al. (2017). How uncertainty analysis of streamflow data can reduce costs and promote robust decisions in water management applications. Water Resources Research, 53(7), 5220–5228. https://doi.org/10.1002/2016WR020328
Mihailović, D. T., Nikolić-Dorić, E., Drešković, N., & Mimić, G. (2014). Complexity analysis of the turbulent environmental fluid flow time series. Physica A: Statistical Mechanics and Its Applications. https://doi.org/10.1016/j.physa.2013.09.062
Ranzato, M., Chopra, S., Auli, M., & Zaremba, W. (2016). Sequence level training with recurrent neural networks. In 4th International Conference on Learning Representations, ICLR 2016 - Conference Track Proceedings. International Conference on Learning Representations, ICLR.
Shajun Nisha, S., Mohamed Sathik, M., & Nagoor Meeral, M. (2021). Application, algorithm, tools directly related to deep learning. In Handbook of Deep Learning in Biomedical Engineering (pp. 61–84). Elsevier. https://doi.org/10.1016/B978-0-12-823014-5.00007-7
Shin, H. -C., Orton, M., Collins, D. J., Doran, S., & Leach, M. O. (2016). Organ detection using deep learning. In Medical image recognition, segmentation and parsing (pp. 123–153). Elsevier. https://doi.org/10.1016/B978-0-12-802581-9.00007-X
Sun, R. (2019). Optimization for deep learning: Theory and algorithms.
Susurluk Basin Flood Management Plan. (2018). ORMAN VE SU İŞLERİ BAKANLIĞI. https://www.google.com.tr/search?q=SUSURLUK+HAVZASI+TAŞKIN+YÖNETİM+PLANI&source=hp&ei=SPx5YOqoJYHPgwfpgr6IDg&iflsig=AINFCbYAAAAAYHoKWD4ybvjiT0VrU9RrRkqNySgMAJLB&oq=SUSURLUK+HAVZASI+TAŞKIN+YÖNETİM+PLANI&gs_lcp=Cgdnd3Mtd2l6EAMyBggAEBYQHlCVAliVAmDcCWgAcAB4AI
Sutskever, I., Vinyals, O., & Le, Q. V. (2014). Sequence to sequence learning with neural networks. In Advances in Neural Information Processing Systems (Vol. 4, pp. 3104–3112). Neural information processing systems foundation.
Tzeng, A., Ma, F. -Y., Tzeng, F. -Y., & Ma, K. -L. (2005). Opening the black box-data driven visualization of neural networks. https://escholarship.org/uc/item/9dd6f376. Accessed 17 April 2021
Wu, C. L., Chau, K. W., & Li, Y. S. (2009). Predicting monthly streamflow using data-driven models coupled with data-preprocessing techniques. Water Resources Research. https://doi.org/10.1029/2007WR006737
Yerdelen, C., Abdelkader, M., & Eris, E. (2021). Assessment of drought in SPI series using continuous wavelet analysis for Gediz Basin, Turkey. Atmospheric Research, 260, 105687. https://doi.org/10.1016/j.atmosres.2021.105687
Acknowledgements
Insightful comments from the anonymous reviewers to improve the content of the manuscript.
Author information
Authors and Affiliations
Contributions
Yaman AlSavaf: Conceptualization, methodology, software, data curation, and writing — original draft preparation. Arzu Teksoy: Supervision, conceptualization, methodology, reviewing and editing, and validation.
Corresponding author
Ethics declarations
Ethical approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
Not applicable.
Competing interests
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Alsavaf, Y., Teksoy, A. Applicability of recurrent neural networks to retrieve missing runoff records: challenges and opportunities in Turkey. Environ Monit Assess 194, 28 (2022). https://doi.org/10.1007/s10661-021-09681-z
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10661-021-09681-z