Abstract
As streamflow quantity and drought problem become increasingly severe, it’s imperative than ever to seek next generation machine learning models and learning algorithms which can provide accurate prediction. Reliable prediction of drought variables such as precipitation, soil moisture, and streamflow has been a significant challenge for water resources professionals and water management districts due to their random and nonlinear nature. This paper proposes a long short-term memory networks (LSTM) based deep learning method to predict the historical monthly soil moisture time series data based on the MERRA-Land from 1980 to 2012. The proposed LSTM model learns to predict the value of the next time step at each time step of the time sequence. We also compare the predication accuracy when the network state is updated with the observed values and when the network state is updated with the predicted values. We find that the predictions are more accurate when updating the network state with the observed values instead of the predicted values. In addition, it demonstrated that the proposed method has much lower MSE than the autoregressive integrated moving average model (ARIMA) model and autoregressive model (AR) model.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Water Supply Outlook and Status, Interstate Commission on the Potomac River Basin. https://www.potomacriver.org
Hao, Z., AghaKouchak, A., Nakhjiri, N., Farahmand, A.: Global integrated drought monitoring and prediction system. Sci. Data 1(140001), 1–10 (2014)
Agana, N.A., Homaifar, A.: A deep learning based approach for long-term drought prediction. In: SoutheastCon 2017, Charlotte, USA, 30 March–2 April, pp. 1–8 (2017)
Fu, M., Fan, T., Ding, Z., Salih, S.Q., Al-Ansari, N., Yaseen, Z.M.: Deep learning data-intelligence model based on adjusted forecasting window scale: application in daily streamflow simulation. IEEE Access 8, 32632–32651 (2020)
Filik, Ü.B., Filik, T.: Wind speed prediction using artificial neural networks based on multiple local measurements in eskisehir. Energy Procedia 107, 264–269 (2017)
Goodfellow, I.: Deep Learning. MIT Press, Cambridge (2016)
Rochac, J.F.R., Zhang, N., Xiong, J.: A spectral feature based CNN long short-term memory approach for classification. In: The Tenth International Conference on Intelligent Control and Information Processing (ICICIP), Marrakesh, Morocco, 14–19 December (2019)
Ehsan, M.A., Shahirinia, A., Zhang, N., Oladunni, T.: Interpretation of deep learning on wind speed prediction and visualization. In: The 10th International Conference on Information Science and Technology (ICIST), Bath, London, and Plymouth, United Kingdom, 9–15 September (2020)
Rochac, J.F.R., Zhang, N., Xiong, J, Zhong, J., Oladunni, T.: Data augmentation for mixed spectral signatures coupled with convolutional neural networks. In: The 9th International Conference on Information Science and Technology (ICIST 2019), Hulunbuir, Inner Mongolia, China, 2–5 August (2019)
Koster, R.D., De Lannoy, G.J.M., Forman, B.A., Liu, Q., Mahanama, S.P.P., Touré, A.: Assessment and enhancement of MERRA land surface hydrology estimates. J. Clim. 24, 6322–6338 (2011)
Acknowledgment
This work was supported in part by the National Science Foundation (NSF) grants #1505509 and #2011927, DoD grants #W911NF1810475 and #W911NF2010274, NIH grant #1R25AG067896-01, and USGS grant #2020DC142B, and in part by the Foundation of Chongqing Municipal Key Laboratory of Institutions of Higher Education ([2017]3), Foundation of Chongqing Development and Reform Commission (2017[1007]), Scientific and Technological Research Program of Chongqing Municipal Education Commission (Grant Nos. KJQN201901218 and KJQN201901203), Natural Science Foundation of Chongqing (Grant No. cstc2019jcyj-bshX0101), Foundation of Chongqing Three Gorges University.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, N., Dai, X., Ehsan, M.A., Deksissa, T. (2020). Development of a Drought Prediction System Based on Long Short-Term Memory Networks (LSTM). In: Han, M., Qin, S., Zhang, N. (eds) Advances in Neural Networks – ISNN 2020. ISNN 2020. Lecture Notes in Computer Science(), vol 12557. Springer, Cham. https://doi.org/10.1007/978-3-030-64221-1_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-64221-1_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-64220-4
Online ISBN: 978-3-030-64221-1
eBook Packages: Computer ScienceComputer Science (R0)