Abstract
The metabolism and growth of vegetation are highly dependent on the changes in soil water content. Irrigation scheduling and application of water at the right time and rate are a key aspect for precision irrigation. In this study, the Long Short-Term Memory (LSTM) Neural Network model was studied to predict irrigation prescriptions for 1, 3, 6, 12 and 24 h in advance. Training data for LSTM were collected from a precision irrigation study conducted in Alabama, USA. The prediction estimation of irrigation prescription used soil matric potential data measured within two contrasting soil types. Performance of the LSTM models were evaluated by comparing neural network parameters and prediction capability by soil type. The optimal learning algorithm for each case was also determined. The LSTM Neural Network showed good prediction capabilities for both soil types, with \(R^{2}\) ranging between 0.82 and 0.98 for one hour ahead prescription and getting smaller as prediction time increases. The irrigation rate prediction was verified by actual observations that demonstrate the suitability of the machine learning technique as a decision-support tool for irrigation scheduling.
Similar content being viewed by others
References
Adewale, A., Bamidele, A., & Lateef, U. (2018). Predictive modelling and analysis of academic performance of secondary school students: ANN approach. International Journal of Science and Technology Education Research, 9(1), 1–8. https://doi.org/10.5897/IJSTER2017.0415.
Adeyemi, O., Grove, I., Peets, S., Domun, Y., & Norton, T. (2018). Dynamic neural network modelling of soil moisture content for predictive irrigation scheduling. Sensors, 18(10), 3408. https://doi.org/10.3390/s18103408.
Beysolow, T., II. (2017). Introduction to deep learning using R: A step-by-step guide to learning and implementing deep learning models using R. Berkeley, CA: Apress.
Bondesan, L., Ortiz, B. V., Morata, G. T., Damianidis, D., Jimenez, A. F., et al. (2019). Evaluating and improving soil sensor-based variable irrigation scheduling on farmers' fields in Alabama. In Precision agriculture’19 (pp. 713–720). Wageningen Academic Publishers. https://doi.org/10.3920/978-90-8686-888-9.
Gonzalez, J., & Yu, W. (2018). Non-linear system modeling using LSTM neural networks. IFAC-PapersOnLine, 51(13), 485–489. https://doi.org/10.1016/j.ifacol.2018.07.326.
González-Esquiva, J. M., García-Mateos, G., Escarabajal-Henarejos, D., Hernández-Hernández, J. L., Ruiz-Canales, A., et al. (2017). A new model for water balance estimation on lettuce crops using effective diameter obtained with image analysis. Agricultural Water Management, 183, 116–122. https://doi.org/10.1016/j.agwat.2016.11.019.
Goodfellow, I., Bengio, Y., Courville, A., & Bengio, Y. (2016). Deep learning (Vol. 1). Cambridge: MIT Press.
Gutzler, C., Helming, K., Balla, D., Dannowski, R., Deumlich, D., et al. (2015). Agricultural land use changes scenario-based sustainability impact assessment for Brandenburg, Germany. Ecological Indicators, 48, 505–517. https://doi.org/10.1016/j.ecolind.2014.09.004.
Hochreiter, S. (1998). The vanishing gradient problem during learning RNN and problem solutions. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 6(02), 107–116.
Kumar, N. (2018). Deep learning with applications using python. Chatbots and face, object, and speech recognition with TensorFlow and Keras. Berkeley, CA: Apress.
Levidow, L., Zaccaria, D., Maia, R., Vivas, E., Todorovic, M., et al. (2014). Improving water-efficient irrigation: Prospects and difficulties of innovative practices. Agricultural Water Management, 146, 84–94. https://doi.org/10.1016/j.agwat.2014.07.012.
Lu, Z., Chai, L., Ye, Q., & Zhang, T. (2015). Reconstruction of time-series soil moisture from AMSR2 and SMOS data by using recurrent nonlinear autoregressive neural networks. In Geoscience and remote sensing symposium (IGARSS), IEEE international (pp. 980–983). https://doi.org/10.1109/IGARSS.2015.7325932.
Mashayekhi, P., Ghorbani, S., Mosaddeghi, M., Shirani, H., & Nodoushan, A. (2016). Different scenarios for inverse estimation of soil hydraulic parameters from double-ring infiltrometer data using HYDRUS-2D/3D. International Agrophysics, 30(2), 203–210. https://doi.org/10.1515/intag-2015-0087.
NRCS. (2019). Soil texture calculator. Retrieved June 25, 2019, from https://www.nrcs.usda.gov/wps/portal/nrcs/detail/soils/survey/?cid=nrcs142p2_054167.
Pandey, V., & Pandey, P. (2010). Spatial and temporal variability of soil moisture. International Journal of Geosciences, 1(02), 87. https://doi.org/10.4236/ijg.2010.12012.
Qi, Y., Huo, Z., Feng, S., Adeloye, A., & Dai, X. (2018). Prediction of consumptive use under different soil moisture content and soil salinity conditions using artificial neural network models. Irrigation and Drainage, 67(4), 615–624. https://doi.org/10.1002/ird.2270.
Seidel, S., Werisch, S., Barfus, K., Wagner, M., Schütze, N., et al. (2016). Field evaluation of irrigation scheduling strategies using a mechanistic crop growth model. Irrigation and drainage, 65(2), 214–223. https://doi.org/10.1002/ird.1942.
Skansi, S. (2018). Introduction to deep learning: From logical calculus to artificial intelligence. Cham: Springer.
Vellidis, G., Liakos, V., Porter, W., Tucker, M., & Liang, X. (2016). A dynamic variable rate irrigation control system. St. Louis, Missouri: Academic Publishers.
Wang, X., Liu, Y., Chengjie, S.U.N., Wang, B., & Wang, X. (2015). Predicting polarities of tweets by composing word embeddings with long short-term memory. In Proc. 53rd annual meeting of the association of computing linguistics and 7th int. joint conference on natural language process (Vol. 1, pp. 1343–1353). https://doi.org/10.3115/v1/p15-1130.
Zhang, J., Zhu, Y., Zhang, X., Ye, M., & Yang, J. (2018). Developing a LSTM based model for predicting water table depth in agricultural areas. Journal of Hydrology, 561, 918–929. https://doi.org/10.1016/j.jhydrol.2018.04.065.
Acknowledgements
We want to acknowledge the farmer Jim Lewey for his collaboration. Funding for this project was provided by the Natural Resources Conservation Service - Alabama Soil and Water Conservation Committee, the Alabama Association of Conservation Districts and the Alabama Agricultural Experimental Station. A-F. Jimenez expresses his gratitude to the Department of Boyacá and Minciencias – Colombia for the support through the scholarship program No. 733 - 2015 for the Ph.D. at the Universidad Nacional de Colombia and also to the Universidad de Los Llanos, Villavicencio, Colombia.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
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
Jimenez, AF., Ortiz, B.V., Bondesan, L. et al. Long Short-Term Memory Neural Network for irrigation management: a case study from Southern Alabama, USA. Precision Agric 22, 475–492 (2021). https://doi.org/10.1007/s11119-020-09753-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11119-020-09753-z