SOIL MOISTURE PREDICTION USING LSTM AND GRU: UNIVARIATE AND MULTIVARIATE DEEP LEARNING APPROACHES
Abstract
Soil moisture is an important indicator in the management of water resources, precision agriculture, and disaster mitigation, such as drought and land fires. Fluctuations in soil moisture are influenced by various climate variables, requiring a reliable predictive approach essential. This research develops a daily soil moisture prediction model using Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) algorithms with univariate and multivariate approaches. Soil moisture data were obtained from Google Earth Engine, while climate data were collected from 10 BMKG stations in East Java for the period 2019–2024. Data preprocessing includes cubic spline interpolation to handle missing values and Min-Max normalization to achieve uniform feature scaling. Models were built using a direct forecasting approach for horizons to and five evaluation metrics: MAE, MSE, RMSE, MAPE, and R². The results show that the multivariate GRU model performs best at horizon with MAE = 0.05455, MSE = 0.00604, RMSE = 0.07539, MAPE = 0.19280, and R² = starting from 0.9626 on day 1 (t), then decreasing to 0.8075 on day 10 The univariate LSTM model excelled in training time efficiency (<400 seconds) at most stations. The multivariate GRU model demonstrates the highest accuracy and stability, making it suitable for medium- to long-term forecasting, while the univariate LSTM excels in training speed, making it effective for daily predictions. The model’s performance remains limited to the dataset's spatial and temporal scope. Therefore, future research should test the model in other regions and under extreme climate conditions, as well as apply transfer learning in data-scarce areas. The novelty of this study lies in comparing LSTM and GRU performance for daily soil moisture prediction in both univariate and multivariate scenarios, using complete climate variables from multiple stations.
Downloads
References
KEMENTAN Keputusan Menteri Pertanian, RENCANA STRATEGIS KEMENTRIAN PERTANIAN TAHUN 2020-2024. Jakarta: Kementan, 2021.
N. Pareek, “CLIMATE CHANGE IMPACT ON SOILS: ADAPTATION AND MITIGATION,” MOJ Ecol. Environ. Sci., vol. 2, no. 3, pp. 136–139, 2017, doi: https://doi.org/10.15406/mojes.2017.02.00026.
M. T. Taye, E. Dyer, F. A. Hirpa, and K. Charles, “CLIMATE CHANGE IMPACT ON WATER RESOURCES IN THE AWASH BASIN, ETHIOPIA,” Water (Switzerland), vol. 10, no. 11, pp. 1–16, 2018, doi: https://doi.org/10.3390/w10111560.
S. M. Mostafa, O. Wahed, W. Y. El-Nashar, S. M. El-Marsafawy, M. Zelenáková, and H. F. Abd-Elhamid, “ERRATUM TO: POTENTIAL CLIMATE CHANGE IMPACTS ON WATER RESOURCES IN EGYPT (WATER 2021, 13, 1715),” Water (Switzerland), vol. 13, no. 14, 2021, doi: https://doi.org/10.3390/w13141919.
G. S. Malhi, M. Kaur, and P. Kaushik, “IMPACT OF CLIMATE CHANGE ON AGRICULTURE AND ITS MITIGATION STRATEGIES: A REVIEW,” Sustain., vol. 13, no. 3, pp. 1–21, 2021, doi: https://doi.org/10.3390/su13031318.
S. Fawzy, A. I. Osman, J. Doran, and D. W. Rooney, “STRATEGIES FOR MITIGATION OF CLIMATE CHANGE: A REVIEW,” Environ. Chem. Lett., vol. 18, no. 6, pp. 2069–2094, 2020, doi: https://doi.org/10.1007/s10311-020-01059-w.
L. Myeni, M. E. Moeletsi, and A. D. Clulow, “PRESENT STATUS OF SOIL MOISTURE ESTIMATION OVER THE AFRICAN CONTINENT,” J. Hydrol. Reg. Stud., vol. 21, no. December 2018, pp. 14–24, 2019, doi: https://doi.org/10.1016/j.ejrh.2018.11.004.
S. J. Sutanto et al., “THE ROLE OF SOIL MOISTURE INFORMATION IN DEVELOPING ROBUST CLIMATE SERVICES FOR SMALLHOLDER FARMERS: EVIDENCE FROM GHANA,” Agronomy, vol. 12, no. 2, 2022, doi: https://doi.org/10.3390/agronomy12020541.
L. Zhang et al., “IN SITU OBSERVATION-CONSTRAINED GLOBAL SURFACE SOIL MOISTURE USING RANDOM FOREST MODEL,” Remote Sens., vol. 13, no. 23, pp. 1–25, 2021, doi: https://doi.org/10.3390/rs13234893.
L. Gałęzewski et al., “ANALYSIS OF THE NEED FOR SOIL MOISTURE, SALINITY AND TEMPERATURE SENSING IN AGRICULTURE: A CASE STUDY IN POLAND,” Sci. Rep., vol. 11, no. 1, 2021, doi: https://doi.org/10.1038/s41598-021-96182-1.
N. Sazib, J. D. Bolten, and I. E. Mladenova, “LEVERAGING NASA SOIL MOISTURE ACTIVE PASSIVE FOR ASSESSING FIRE SUSCEPTIBILITY AND POTENTIAL IMPACTS OVER AUSTRALIA AND CALIFORNIA,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 15, no. June, pp. 779–787, 2022, doi: https://doi.org/10.1109/JSTARS.2021.3136756.
S. H. Noh, “ANALYSIS OF GRADIENT VANISHING OF RNNS AND PERFORMANCE COMPARISON,” Inf., vol. 12, no. 11, 2021, doi: https://doi.org/10.3390/info12110442.
S. Hochreiter and J. Schmidhuber, “LONG SHORT-TERM MEMORY,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, 1997, doi: https://doi.org/10.1162/neco.1997.9.8.1735.
J. Chung, C. Gulcehre, K. Cho, and Y. Bengio, “EMPIRICAL EVALUATION OF GATED RECURRENT NEURAL NETWORKS ON SEQUENCE MODELING,” pp. 1–9, 2014, [Online]. Available: http://arxiv.org/abs/1412.3555
K. E. ArunKumar, D. V. Kalaga, C. Mohan Sai Kumar, M. Kawaji, and T. M. Brenza, “COMPARATIVE ANALYSIS OF GATED RECURRENT UNITS (GRU), LONG SHORT-TERM MEMORY (LSTM) CELLS, AUTOREGRESSIVE INTEGRATED MOVING AVERAGE (ARIMA), SEASONAL AUTOREGRESSIVE INTEGRATED MOVING AVERAGE (SARIMA) FOR FORECASTING COVID-19 TRENDS,” Alexandria Eng. J., vol. 61, no. 10, pp. 7585–7603, 2022, doi: https://doi.org/10.1016/j.aej.2022.01.011.
Y. Chen et al., “CONVOLUTIONAL NEURAL NETWORK MODEL FOR SOIL MOISTURE PREDICTION AND ITS TRANSFERABILITY ANALYSIS BASED ON LABORATORY VIS-NIR SPECTRAL DATA,” Int. J. Appl. Earth Obs. Geoinf., vol. 104, no. September, p. 102550, 2021, doi: https://doi.org/10.1016/j.jag.2021.102550.
N. Filipović, S. Brdar, G. Mimić, O. Marko, and V. Crnojević, “REGIONAL SOIL MOISTURE PREDICTION SYSTEM BASED ON LONG SHORT-TERM MEMORY NETWORK,” Biosyst. Eng., vol. 213, pp. 30–38, 2022, doi: https://doi.org/10.1016/j.biosystemseng.2021.11.019.
M. F. Celik, M. S. Isik, O. Yuzugullu, N. Fajraoui, and E. Erten, “SOIL MOISTURE PREDICTION FROM REMOTE SENSING IMAGES COUPLED WITH CLIMATE, SOIL TEXTURE AND TOPOGRAPHY VIA DEEP LEARNING,” Remote Sens., vol. 14, no. 21, pp. 1–24, 2022, doi: https://doi.org/10.3390/rs14215584.
M. Haikal, “PENGEMBANGAN MODEL PRAPROSES DATA DAN MODEL PREDIKSI TINGGI MUKA AIR TANAH GAMBUT DENGAN ALGORITMA LSTM [TESIS],” IPB University, 2023.
S. McKinley and M. Levine, “CUBIC SPLINE INTERPOLATION,” Methods Shape-Preserving Spline Approx., vol. 3, no. 2, pp. 37–59, 1998, doi: https://doi.org/10.1142/9789812813381_0003.
C. Biele, J. Kacprzyk, W. Kopeć, J. W. Owsiński, A. Romanowski, and M. Sikorski, DIGITAL INTERACTION AND MACHINE INTELLIGENCE, Volume 440. Warsaw, Poland: Springer, 2021. [Online]. Available: https://link.springer.com/bookseries/15179
N. Mahesh, J. J. Babu, K. Nithya, and S. A. Arunmozhi, “WATER QUALITY PREDICTION USING LSTM WITH COMBINED NORMALIZER FOR EFFICIENT WATER MANAGEMENT,” Desalin. Water Treat., vol. 317, no. January, p. 100183, 2024, doi: https://doi.org/10.5772/intechopen.72352.
B. Vrigazova, “THE PROPORTION FOR SPLITTING DATA INTO TRAINING AND TEST SET FOR THE BOOTSTRAP IN CLASSIFICATION PROBLEMS,” Bus. Syst. Res., vol. 12, no. 1, pp. 228–242, 2021, doi: https://doi.org/10.2478/bsrj-2021-0015.
A. Gholamy, V. Kreinovich, and O. Kosheleva, “WHY 70/30 OR 80/20 RELATION BETWEEN TRAINING AND TESTING SETS : A PEDAGOGICAL EXPLANATION,” Dep. Tech. Reports, vol. 1209, pp. 1–6, 2018.
S. Kervanci and M. F. Akay, “LSTM HYPERPARAMETERS OPTIMIZATION WITH HPARAM PARAMETERS FOR BITCOIN PRICE PREDICTION,” 2023, doi: https://doi.org/10.35377/saucis...1172027.
Z. C. Lipton, J. Berkowitz, and C. Elkan, “A CRITICAL REVIEW OF RECURRENT NEURAL NETWORKS FOR SEQUENCE LEARNING,” pp. 1–38, 2015, [Online]. Available: http://arxiv.org/abs/1506.00019
J. Luo, L. Zhu, K. Zhang, C. Zhao, and Z. Liu, “FORECASTING THE 10.7-CM SOLAR RADIO FLUX USING DEEP CNN-LSTM NEURAL NETWORKS,” Processes, vol. 10, no. 2, pp. 1–11, 2022, doi: https://doi.org/10.3390/pr10020262.
S. Mohsen, “RECOGNITION OF HUMAN ACTIVITY USING GRU DEEP LEARNING ALGORITHM,” Multimed. Tools Appl., vol. 82, no. 30, pp. 47733–47749, 2023, doi: https://doi.org/10.1007/s11042-023-15571-y.
D. Chicco, M. J. Warrens, and G. Jurman, “THE COEFFICIENT OF DETERMINATION R-SQUARED IS MORE INFORMATIVE THAN SMAPE, MAE, MAPE, MSE AND RMSE IN REGRESSION ANALYSIS EVALUATION,” PeerJ Comput. Sci., vol. 7, pp. 1–24, 2021, doi: https://doi.org/10.7717/PEERJ-CS.623.
I. A. Zulfauzi, N. Y. Dahlan, H. Sintuya, and W. Setthapun, “ANOMALY DETECTION USING K-MEANS AND LONG-SHORT TERM MEMORY FOR PREDICTIVE MAINTENANCE OF LARGE-SCALE SOLAR (LSS) PHOTOVOLTAIC PLANT,” Energy Reports, vol. 9, no. S12, pp. 154–158, 2023, doi: https://doi.org/10.1016/j.egyr.2023.09.159.
Copyright (c) 2026 Jemsri Stenli Batlajery, Agus Buono, Mushthofa -Mushthofa
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this Journal agree to the following terms:
- Author retain copyright and grant the journal right of first publication with the work simultaneously licensed under a creative commons attribution license that allow others to share the work within an acknowledgement of the work’s authorship and initial publication of this journal.
- Authors are able to enter into separate, additional contractual arrangement for the non-exclusive distribution of the journal’s published version of the work (e.g. acknowledgement of its initial publication in this journal).
- Authors are permitted and encouraged to post their work online (e.g. in institutional repositories or on their websites) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published works.
1.gif)
