Abstract
Soil moisture prediction with high quality has important guiding effect on agricultural production. Aiming at the problem that the time series of soil moisture is non-stationary, a prediction method which combine wavelet transform and improved Back Propagation Neural Network (BPNN) is proposed in this paper. First obtained several relatively stable data sequence with different scales by decompose the original time series using the discrete wavelet transform, then use BPNN to predict each sequence respectively, finally reconstruct to obtain final prediction result. Aiming at the problem that BPNN has slow converging speed and easy to fall into the local optimal solution, proposed an optimization method by adjusting the momentum factor and learning rate adaptively in the learning process. The experiment has been carried out in KenLi town, the research region of “BoHai Barn” in ShanDong province, using data from 10 observation stations. We use 3 prediction methods respectively to predict the original time series, experimental results explicit that the proposed method has higher prediction accuracy (compared with the other two methods, increased by 9.5% and 31% respectively) and fewer iterations (compared with the other two methods, increased by 70% and 77% respectively).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Qiu, J., et al.: Comparison of temporal trends from multiple soil moisture data sets and precipitation: the implication of irrigation on regional soil moisture trend. Int. J. Appl. Earth Obs. Geoinformation 48, 17–27 (2016)
Romano, N.: Soil moisture at local scale: measurements and simulations. J. Hydrol. 516, 6–20 (2014)
Sun, Q., Liu, J., Liang, H.: Analysis of regional soil moisture forecasting model in northeast China. J. Natural Res. 29(6), 1065–1075 (2014)
Li, Y., et al.: Research on forecasting method for soil moisture during spring sowing period in Northeast Area of China. Agric. Res. Arid Areas 33(6), 178–183 (2013)
Hui, L., et al.: Comparison of two new ARIMA-ANN and ARIMA-Kalman hybrid methods for wind speed prediction. Appl. Energy 98, 415–424 (2012)
Hui, L., et al.: A hybrid model for wind speed prediction using empirical mode decomposition and artificial neural networks. Renew. Energy, 48, 545–556 (2012)
Bouzgou, H., et al.: Multiple architecture system for wind speed prediction. Appl. Energy 88, 2463–2471 (2011)
Cadenas, E., et al.: Wind speed forecasting in three different regions of Mexico, using a hybrid ARIMA-ANN model. Renew. Energy 35, 2732–2738 (2010)
Shi, H., Yang, J., Ding, M., Wang, J.: A short-term wind power prediction method base on wavelet decomposition and BP neural network. Autom. Electric Power Syst. 35(16), 44–48 (2011)
Liu, L., Ye, W.: Precipitation prediction of time series model based on BP artificial neural network. J. Water Res. Water Eng. 21(5), 156–159 (2010)
Hu, S., Zhang, Z.: Fault prediction for nonlinear time series based on neural network. ACTA Automatica Sinica 33(7), 744–748 (2007)
Hecht-Nielsen, R.: Kolmogorov’s mapping neural network existence theorem. In: Proceedings of the International Conference on Neural Networks, Publishing (1987)
Na, Y.: Prediction of soil moisture from characteristic meteorological elements by BP neural network. Chin. J. Soil Sci. 42(6), 1324–1329 (2011)
Pandhian, S.M., et al.: A comparative analysis and time series forecasting of monthly stream flow data using hybrid model. Jurnal Teknologi 76(13), 67–74 (2015)
Jin, J., et al.: Forecasting natural gas prices using wavelets, time series, and artificial neural networks. Plos One 10(11) (2015)
Qi, L., Wang, X., Xiaolong, X., Dou, W., Li, S.: Privacy-aware cross-platform service recommendation based on enhanced locality-sensitive hashing. IEEE Trans. Network Sci. Eng. (2020a). https://doi.org/10.1109/TNSE.2020.2969489
Wang, X., Yang, L.T., Wang, Y., Ren, L., Deen, M.J.: ADTT: a highly-efficient distributed tensor-train decomposition method for IIoT big data. IEEE Trans. Ind. Inf. (2020). https://doi.org/10.1109/tii.2020.2967768
Qi, L., He, Q., Chen, F., Zhang, X., Dou, W., Ni, Q.: Data-driven web APIs recommendation for building web applications. IEEE Trans. Big Data (2020b). https://doi.org/10.1109/TBDATA.2020.2975587
Zhong, W., Yin, X., Zhang, X., Li, S., Dou, W., Wang, R., Qi, L.: Multi-dimensional quality-driven service recommendation with privacy-preservation in mobile edge environment. Comput. Commun. (2020). https://doi.org/10.1016/j.comcom.2020.04.018
Chi, X., Yan, C., Wang, H., Rafique, W., Qi, L.: Amplified LSH-based recommender systems with privacy protection. Concurrency Comput. Pract. Exp. (2020). https://doi.org/10.1002/CPE.5681
Wang, X., Yang, L.T. Kuang, L., Liu, X., Zhang, Q., Jamal Deen, M.: A tensor-based big data-driven routing recommendation approach for heterogeneous networks. IEEE Network Mag. 33(1), 64–69 (2019)
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
Yang, X., Jia, S., Zhang, C. (2020). A Prediction Method for Soil Moisture Time Series. In: Chen, X., Yan, H., Yan, Q., Zhang, X. (eds) Machine Learning for Cyber Security. ML4CS 2020. Lecture Notes in Computer Science(), vol 12488. Springer, Cham. https://doi.org/10.1007/978-3-030-62463-7_49
Download citation
DOI: https://doi.org/10.1007/978-3-030-62463-7_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-62462-0
Online ISBN: 978-3-030-62463-7
eBook Packages: Computer ScienceComputer Science (R0)