Perbandingan Kinerja LSTM, Bi-LSTM, dan Prophet untuk Prediksi Kekeringan berdasarkan SPEI (Standardized Precipitation-Evapotranspiration Index)
- Hana Amalina Universitas Stikubank, Semarang, Indonesia
-
Eri Zuliarso
*
Universitas Stikubank, Semarang,
Indonesia
(*) Corresponding Author
Abstract
Drought is a natural disaster with widespread impacts on agriculture and water availability, particularly in the Gajah Mungkur Reservoir area of Wonogiri Regency, Indonesia. Rainfall instability driven by global climate change and local climate variability is the primary cause of this disaster. Accurate drought prediction is essential for formulating sustainable mitigation strategies. This study aims to analyze drought characteristics in the Gajah Mungkur Reservoir, Wonogiri Regency, using the Standardized Precipitation Evapotranspiration Index (SPEI) and to compare the performance of three prediction models: Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), and Prophet in predicting SPEI. The dataset includes monthly rainfall and air temperature data from 1995 to 2024. The analysis reveals that longer SPEI time scales tend to show more temporally concentrated drought patterns. At the 6-month SPEI scale, which represents long-term drought, a total of 55 drought months were detected between 1995 and 2024, with major drought episodes occurring in 1996–1997, 2000–2007, 2019, and 2023–2024. Model performance evaluation shows a numerical trend in which Bi-LSTM outperforms others for 1-month SPEI prediction, while LSTM performs better at the 3- and 6-month scales. However, statistical significance testing indicates that the performance differences among the three models are not significant (p > 0,05), suggesting that other factors such as computational efficiency may be important considerations in practical applications.
Downloads
References
B. Zahraie, M. Nasseri, and F. Nematizadeh, “Exploring Spatiotemporal Meteorological Correlations for Basin Scale Meteorological Drought Forecasting using Data Mining Methods,” Arab. J. Geosci., vol. 10, no. 19, p. 419, Oct. 2017, doi: 10.1007/s12517-017-3211-x.
C. R. Schwalm et al., “Global Patterns of Drought Recovery,” Nature, vol. 548, no. 7666, pp. 202–205, Aug. 2017, doi: 10.1038/nature23021.
S. M. Vicente-Serrano, G. Van der Schrier, S. Beguería, C. Azorin-Molina, and J.-I. Lopez-Moreno, “Contribution of Precipitation and Reference Evapotranspiration to Drought Indices under Different Climates,” J. Hydrol., vol. 526, pp. 42–54, Jul. 2015, doi: 10.1016/j.jhydrol.2014.11.025.
N. Khan, D. A. Sachindra, S. Shahid, K. Ahmed, M. S. Shiru, and N. Nawaz, “Prediction of Droughts over Pakistan using Machine Learning Algorithms,” Adv. Water Resour., vol. 139, p. 103562, May 2020, doi: 10.1016/j.advwatres.2020.103562.
M. C. Anderson et al., “The Evaporative Stress Index as an Indicator of Agricultural Drought in Brazil: An Assessment based on Crop Yield Impacts,” Remote Sens. Environ., vol. 174, pp. 82–99, Mar. 2016, doi: 10.1016/j.rse.2015.11.034.
L. Xu, N. Chen, X. Zhang, and Z. Chen, “An Evaluation of Statistical, NMME and Hybrid Models for Drought Prediction in China,” J. Hydrol., vol. 566, pp. 235–249, Nov. 2018, doi: 10.1016/j.jhydrol.2018.09.020.
N. Khan, S. Shahid, E.-S. Chung, S. Kim, and R. Ali, “Influence of Surface Water Bodies on the Land Surface Temperature of Bangladesh,” Sustainability, vol. 11, no. 23, p. 6754, Nov. 2019, doi: 10.3390/su11236754.
R. G. Gavilan, J. Caro-Castro, and J. Trinanes, “A New Generation of Real-Time Environmental Monitoring Systems to Study the Impact of El Niño on Disease Dynamics,” Curr. Opin. Biotechnol., vol. 81, p. 102924, Jun. 2023, doi: 10.1016/J.COPBIO.2023.102924.
M. D. Setiawati et al., “Climate Change and Anthropogenic Pressure on Bintan Islands, Indonesia: An Assessment of the Policies Proposed by Local Authorities,” Reg. Stud. Mar. Sci., vol. 66, p. 103123, 2023, doi: https://doi.org/10.1016/j.rsma.2023.103123.
M. Z. Ramdhani, F. Arifianto, and G. Giarno, “Perbandingan Standardized Precipitation Index dan Standardized Anomaly Index untuk Penentuan Tingkat Kekeringan di Kabupaten Sragen, Jawa Tengah,” Semesta Tek., vol. 26, no. 1, pp. 86–96, 2023, doi: 10.18196/st.v26i1.16310.
Y. Zhang, H. Yang, H. Cui, and Q. Chen, “Comparison of the Ability of ARIMA, WNN and SVM Models for Drought Forecasting in the Sanjiang Plain, China,” Nat. Resour. Res., vol. 29, no. 2, pp. 1447–1464, Apr. 2020, doi: 10.1007/s11053-019-09512-6.
Z. Tarawneh and Y. Khalayleh, “Improved Estimate of Multiyear Drought for Water Resources Management Studies,” J. Water Clim. Chang., vol. 7, no. 4, pp. 721–730, Dec. 2016, doi: 10.2166/wcc.2016.151.
S. M. Vicente-Serrano, S. Beguería, and J. I. López-Moreno, “A Multiscalar Drought Index Sensitive to Global Warming: The Standardized Precipitation Evapotranspiration Index,” J. Clim., vol. 23, no. 7, pp. 1696–1718, Apr. 2010, doi: 10.1175/2009JCLI2909.1.
J. Das, A. Gayen, P. Saha, and S. K. Bhattacharya, “Meteorological Drought Analysis Using Standardized Precipitation Index over Luni River Basin in Rajasthan, India,” SN Appl. Sci., vol. 2, no. 9, p. 1530, Sep. 2020, doi: 10.1007/s42452-020-03321-w.
S. Beguería, S. M. Vicente-Serrano, F. Reig, and B. Latorre, “Standardized Precipitation Evapotranspiration Index (SPEI) Revisited: Parameter Fitting, Evapotranspiration Models, Tools, Datasets and Drought Monitoring,” Int. J. Climatol., vol. 34, no. 10, pp. 3001–3023, Aug. 2014, doi: 10.1002/joc.3887.
B. Y. Tam, A. J. Cannon, and B. R. Bonsal, “Standardized Precipitation Evapotranspiration Index (SPEI) for Canada: Assessment of Probability Distributions,” Can. Water Resour. J. / Rev. Can. des ressources hydriques, vol. 48, no. 3, pp. 283–299, Jul. 2023, doi: 10.1080/07011784.2023.2183143.
K. Pyarali, J. Peng, M. Disse, and Y. Tuo, “Development and Application of High Resolution SPEI Drought Dataset for Central Asia,” Sci. Data, vol. 9, no. 1, p. 172, Apr. 2022, doi: 10.1038/s41597-022-01279-5.
M. F. U. Moazzam, G. Rahman, S. Munawar, N. Farid, and B. G. Lee, “Spatiotemporal Rainfall Variability and Drought Assessment during Past Five Decades in South Korea Using SPI and SPEI,” Atmosphere (Basel)., vol. 13, no. 2, p. 292, Feb. 2022, doi: 10.3390/atmos13020292.
S. Ali et al., “The Role of Climate Change and Its Sensitivity on Long-Term Standardized Precipitation Evapotranspiration Index, Vegetation and Drought Changing Trends over East Asia,” Plants, vol. 13, no. 3, p. 399, Jan. 2024, doi: 10.3390/plants13030399.
Q. He, M. Wang, K. Liu, and B. Wang, “High-resolution Standardized Precipitation Evapotranspiration Index (SPEI) reveals trends in drought and vegetation water availability in China,” Geogr. Sustain., vol. 6, no. 2, p. 100228, Apr. 2025, doi: 10.1016/j.geosus.2024.08.007.
C. Liu, C. Yang, Q. Yang, and J. Wang, “Spatiotemporal Drought Analysis by the Standardized Precipitation Index (SPI) and Standardized Precipitation Evapotranspiration Index (SPEI) in Sichuan Province, China,” Sci. Rep., vol. 11, no. 1, p. 1280, Jan. 2021, doi: 10.1038/s41598-020-80527-3.
X. Shi, Y. Yang, H. Ding, F. Chen, and M. Shi, “Analysis of the Variability Characteristics and Applicability of SPEI in Mainland China from 1985 to 2018,” Atmosphere (Basel)., vol. 14, no. 5, p. 790, Apr. 2023, doi: 10.3390/atmos14050790.
J. Zhao, Q. Liu, H. Lu, Z. Wang, K. Zhang, and P. Wang, “Future Droughts in China Using the Standardized Precipitation Evapotranspiration Index (SPEI) Under Multi-spatial Scales,” Nat. Hazards, vol. 109, no. 1, pp. 615–636, Oct. 2021, doi: 10.1007/s11069-021-04851-1.
H. Zhao, Y. Huang, X. Wang, X. Li, and T. Lei, “The Performance of SPEI Integrated Remote Sensing Data for Monitoring Agricultural Drought in the North China Plain,” F. Crop. Res., vol. 302, p. 109041, Oct. 2023, doi: 10.1016/j.fcr.2023.109041.
L. Wan et al., “Drought Characteristics and Dominant Factors Across China: Insights from High-Resolution Daily SPEI Dataset Between 1979 and 2018,” Sci. Total Environ., vol. 901, p. 166362, Nov. 2023, doi: 10.1016/j.scitotenv.2023.166362.
Z. Wang, Q. Zhang, S. Sun, and P. Wang, “Interdecadal Variation of the Number of Days with Drought in China Based on the Standardized Precipitation Evapotranspiration Index (SPEI),” J. Clim., vol. 35, no. 6, pp. 2003–2018, Mar. 2022, doi: 10.1175/JCLI-D-20-0985.1.
J. Peng et al., “A Pan-African High-Resolution Drought Index Dataset,” Earth Syst. Sci. Data, vol. 12, no. 1, pp. 753–769, Mar. 2020, doi: 10.5194/essd-12-753-2020.
M. A. Worku, “Spatiotemporal Analysis of Drought Severity Using SPI and SPEI: Case Study of Semi-Arid Borana Area, Southern Ethiopia,” Front. Environ. Sci., vol. 12, Mar. 2024, doi: 10.3389/fenvs.2024.1337190.
M. B. Mukhawana, T. Kanyerere, and D. Kahler, “Review of In-Situ and Remote Sensing-Based Indices and Their Applicability for Integrated Drought Monitoring in South Africa,” Water, vol. 15, no. 2, p. 240, Jan. 2023, doi: 10.3390/w15020240.
K. T. Alito, M. S. Kerebih, and D. A. Hailu, “Characterization of Drought Detection With Remote Sensing Based Multiple Indices and SPEI in Northeastern Ethiopian Highland,” Air, Soil Water Res., vol. 18, Mar. 2025, doi: 10.1177/11786221251328833.
Suroso, D. Nadhilah, Ardiansyah, and E. Aldrian, “Drought Detection in Java Island Based on Standardized Precipitation and Evapotranspiration Index (SPEI),” J. Water Clim. Chang., vol. 12, no. 6, pp. 2734–2752, Sep. 2021, doi: 10.2166/wcc.2021.022.
N. Sunusi and N. H. Auliana, “Assessing SPI and SPEI for Drought Forecasting Through the Power Law Process: A Case Study in South Sulawesi, Indonesia,” MethodsX, vol. 14, p. 103235, Jun. 2025, doi: 10.1016/j.mex.2025.103235.
D. P. Ariyanto, A. Aziz, K. Komariah, S. Sumani, and M. Abara, “Comparing the Accuracy of Estimating Soil Moisture Using the Standardized Precipitation Index (SPI) and the Standardized Precipitation Evapotranspiration Index (SPEI),” SAINS TANAH - J. Soil Sci. Agroclimatol., vol. 17, no. 1, p. 23, Jun. 2020, doi: 10.20961/stjssa.v17i1.41396.
I. Bordi and A. Sutera, “Drought Monitoring and Forecasting at Large Scale,” in Methods and Tools for Drought Analysis and Management, Dordrecht: Springer Netherlands, pp. 3–27. doi: 10.1007/978-1-4020-5924-7_1.
Y. W. Soh, C. H. Koo, Y. F. Huang, and K. F. Fung, “Application of Artificial Intelligence Models for the Prediction of Standardized Precipitation Evapotranspiration Index (SPEI) at Langat River Basin, Malaysia,” Comput. Electron. Agric., vol. 144, pp. 164–173, Jan. 2018, doi: 10.1016/j.compag.2017.12.002.
S. J. Taylor and B. Letham, “Forecasting at Scale,” Am. Stat., vol. 72, no. 1, pp. 37–45, Jan. 2018, doi: 10.1080/00031305.2017.1380080.
A. Basak, A. T. M. S. Rahman, J. Das, T. Hosono, and O. Kisi, “Drought Forecasting Using the Prophet Model in a Semi-Arid Climate Region of Western India,” Hydrol. Sci. J., vol. 67, no. 9, pp. 1397–1417, Jul. 2022, doi: 10.1080/02626667.2022.2082876.
A. T. M. S. Rahman, T. Hosono, O. Kisi, B. Dennis, and A. H. M. R. Imon, “A Minimalistic Approach for Evapotranspiration Estimation Using the Prophet Model,” Hydrol. Sci. J., vol. 65, no. 12, pp. 1994–2006, Sep. 2020, doi: 10.1080/02626667.2020.1787416.
M. A. Hossain, M. M. Rahman, S. S. Hasan, A. Mahmud, and L. Bai, “Analysis and Forecasting of Meteorological Drought Using PROPHET and SARIMA Models Deploying Machine Learning Technique for Southwestern Region of Bangladesh,” Environ. Sustain. Indic., vol. 27, p. 100761, Sep. 2025, doi: 10.1016/j.indic.2025.100761.
A. Dikshit, B. Pradhan, and A. Huete, “An Improved SPEI Drought Forecasting Approach Using the Long Short-Term Memory Neural Network,” J. Environ. Manage., vol. 283, p. 111979, Apr. 2021, doi: 10.1016/j.jenvman.2021.111979.
J. Shang, B. Zhao, H. Hua, J. Wei, G. Qin, and G. Chen, “Application of Informer Model Based on SPEI for Drought Forecasting,” Atmosphere (Basel)., vol. 14, no. 6, p. 951, May 2023, doi: 10.3390/atmos14060951.
J. Dong, L. Xing, N. Cui, L. Zhao, L. Guo, and D. Gong, “Standardized Precipitation Evapotranspiration Index (SPEI) Estimated Using Variant Long Short-Term Memory Network at Four Climatic Zones of China,” Comput. Electron. Agric., vol. 213, p. 108253, Oct. 2023, doi: 10.1016/j.compag.2023.108253.
F. Granata and F. Di Nunno, “Evolving Drought Dynamics in Barcelona: Leveraging a Bayesian Ensemble Algorithm for Insightful Analysis and a Bidirectional Long Short-Term Memory Network for Predictive Modeling,” Stoch. Environ. Res. Risk Assess., vol. 39, no. 4, pp. 1253–1270, Apr. 2025, doi: 10.1007/s00477-024-02900-2.
S. Yalçın, M. Eşit, and Ö. Çoban, “A New Deep Learning Method for Meteorological Drought Estimation Based-On Standard Precipitation Evapotranspiration Index,” Eng. Appl. Artif. Intell., vol. 124, p. 106550, Sep. 2023, doi: 10.1016/j.engappai.2023.106550.
Y. LeCun, Y. Bengio, and G. Hinton, “Deep Learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015, doi: 10.1038/nature14539.
A. Graves and J. Schmidhuber, “Framewise Phoneme Classification with Bidirectional LSTM and Other Neural Network Architectures,” Neural Networks, vol. 18, no. 5–6, pp. 602–610, Jul. 2005, doi: 10.1016/j.neunet.2005.06.042.
A. D. H. Bahri, A. K. Mudzakir, and I. Triarso, “Analisis Kinerja Koperasi Unit Desa (KUD) Mina Tirta di Waduk Gajah Mungkur Kabupaten Wonogiri,” J. Fish. Resour. Util. Manag. Technol., vol. 9, no. 3, pp. 1–25, 2020.
BPS, Kabupaten Wonogiri dalam Angka Tahun 2025. Wonogiri: BPS Kabupaten Kabupaten Wonogiri, 2025.
C. W. Thornthwaite, “An Approach Toward a Rational Classification of Climate,” Geogr. Rev., vol. 38, no. 1, p. 55, Jan. 1948, doi: 10.2307/210739.
V. Potop, C. Boroneanţ, M. Možný, P. Štěpánek, and P. Skalák, “Observed Spatiotemporal Characteristics of Drought on Various Time Scales Over the Czech Republic,” Theor. Appl. Climatol., vol. 115, no. 3, pp. 563–581, 2014, doi: 10.1007/s00704-013-0908-y.
A. Shekhar and C. A. Shapiro, “What Do Meteorological Indices Tell Us About a Long-Term Tillage Study?,” Soil Tillage Res., vol. 193, pp. 161–170, Oct. 2019, doi: 10.1016/j.still.2019.06.004.
S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, Nov. 1997, doi: 10.1162/neco.1997.9.8.1735.
F. Friedrichs and C. Igel, “Evolutionary Tuning of Multiple SVM Parameters,” Neurocomputing, vol. 64, pp. 107–117, Mar. 2005, doi: 10.1016/j.neucom.2004.11.022.
P. R. Lorenzo, J. Nalepa, M. Kawulok, L. S. Ramos, and J. R. Pastor, “Particle Swarm Optimization for Hyper-parameter Selection in Deep Neural Networks,” in Proceedings of the Genetic and Evolutionary Computation Conference, New York, NY, USA: ACM, Jul. 2017, pp. 481–488. doi: 10.1145/3071178.3071208.
F. A. Prodhan, J. Zhang, S. S. Hasan, T. P. Pangali Sharma, and H. P. Mohana, “A Review of Machine Learning Methods for Drought Hazard Monitoring and Forecasting: Current Research Trends, Challenges, and Future Research Directions,” Environ. Model. Softw., vol. 149, p. 105327, Mar. 2022, doi: 10.1016/j.envsoft.2022.105327.
T. Chai and R. R. Draxler, “Root Mean Square Error (RMSE) or Mean Absolute Error (MAE)? — Arguments Against Avoiding RMSE in the Literature,” Geosci. Model Dev., vol. 7, no. 3, pp. 1247–1250, Jun. 2014, doi: 10.5194/gmd-7-1247-2014.
J. Demsar, “Statistical Comparisons of Classifiers Over Multiple Data Sets,” J. Mach. Learn. Res., vol. 7, pp. 1–30, 2006.
K. F. Fung, Y. F. Huang, and C. H. Koo, “Assessing drought conditions through temporal pattern, spatial characteristic and operational accuracy indicated by SPI and SPEI: case analysis for Peninsular Malaysia,” Nat. Hazards, vol. 103, no. 2, pp. 2071–2101, 2020, doi: 10.1007/s11069-020-04072-y.
B. Bera, P. K. Shit, N. Sengupta, S. Saha, and S. Bhattacharjee, “Trends and Variability of Drought in the Extended Part of Chhota Nagpur Plateau (Singbhum Protocontinent), India Applying SPI and SPEI Indices,” Environ. Challenges, vol. 5, p. 100310, 2021, doi: https://doi.org/10.1016/j.envc.2021.100310.
S. M. Vicente-Serrano et al., “Performance of Drought Indices for Ecological, Agricultural, and Hydrological Applications,” Earth Interact., vol. 16, no. 10, pp. 1–27, 2012.
M. D. Svoboda, B. A. Fuchs, and others, Handbook of Drought Indicators and Indices, vol. 2. World Meteorological Organization Geneva, Switzerland, 2016.
S. M. Vicente-Serrano et al., “A Multiscalar Global Evaluation of the Impact of ENSO on Droughts,” J. Geophys. Res., vol. 116, no. D20, p. D20109, Oct. 2011, doi: 10.1029/2011JD016039.
D. Manatsa, T. Mushore, and A. Lenouo, “Improved predictability of droughts over southern Africa using the standardized precipitation evapotranspiration index and ENSO,” Theor. Appl. Climatol., vol. 127, no. 1–2, pp. 259–274, Jan. 2017, doi: 10.1007/s00704-015-1632-6.
S. Sanjaya, B. Koes Paulina Cantik, and A. Septya Wardaningrum, “Analisis Derajat Bencana Kekeringan di Pulau Jawa Akibat Fenomena El-Nino 2023,” J. Tek. Sumber Daya Air, vol. 4, no. 2, pp. 115–126, 2024, doi: 10.56860/jtsda.v4i2.124.
P. Nguyen, S. Min, and Y. Kim, “Combined Impacts of the El Niño‐Southern Oscillation and Pacific Decadal Oscillation on Global Droughts Assessed Using the Standardized Precipitation Evapotranspiration Index,” Int. J. Climatol., vol. 41, no. S1, Jan. 2021, doi: 10.1002/joc.6796.
M. Schuster and K. K. Paliwal, “Bidirectional Recurrent Neural Networks,” IEEE Trans. Signal Process., vol. 45, no. 11, pp. 2673–2681, 1997, doi: 10.1109/78.650093.
S. S. Band et al., “Evaluation of Time Series Models in Simulating Different Monthly Scales of Drought Index for Improving Their Forecast Accuracy,” Front. Earth Sci., vol. 10, Feb. 2022, doi: 10.3389/feart.2022.839527.
K. Sundararajan et al., “A Contemporary Review on Drought Modeling Using Machine Learning Approaches,” Comput. Model. Eng. Sci., vol. 128, no. 2, pp. 447–487, 2021, doi: 10.32604/cmes.2021.015528.
N. A. Hasan, Y. Dongkai, and F. Al-Shibli, “SPI and SPEI Drought Assessment and Prediction Using TBATS and ARIMA Models, Jordan,” Water, vol. 15, no. 20, p. 3598, Oct. 2023, doi: 10.3390/w15203598.
J. A. Melchor Varela and oseph I. Ramírez Hernández, “Prediction of Hydrological Drought by the Standardized Precipitation Evapotranspiration Index in Chihuahua, Mexico, Using Machine Learning Algorithms,” Atmósfera, vol. 38, Jul. 2024, doi: 10.20937/ATM.53355.
M. Lotfirad, H. Esmaeili-Gisavandani, and A. Adib, “Drought Monitoring and Prediction Using SPI, SPEI, and Random Forest Model in Various Climates of Iran,” J. Water Clim. Chang., vol. 13, no. 2, pp. 383–406, Feb. 2022, doi: 10.2166/wcc.2021.287.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Perbandingan Kinerja LSTM, Bi-LSTM, dan Prophet untuk Prediksi Kekeringan berdasarkan SPEI (Standardized Precipitation-Evapotranspiration Index)
Pages: 1131-1142
Copyright (c) 2025 Hana Amalina, Eri Zuliarso
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment 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 website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
