Estimasi Evapotranspirasi Potensial Menggunakan Algoritma Random Forest
Abstract
Abstrak
Besaran nilai Evapotranspirasi Potensial (ETp) sangat diperlukan untuk perencanaan distribusi air dan pola tanam. Umumnya, perhitungan ETp diperoleh dari perhitungan model empiris, seperti model Penman Monteith (PM) yang direkomendasikan oleh Food and Agriculture Organization (FAO). Namun, penerapan model ini memerlukan variabel cuaca yang banyak dan ketersediaan data cuaca yang tidak memadai. Tujuan penelitian ini adalah menghasilkan model estimasi ETp dengan algoritma Random Forest (RF). Variabel cuaca yang digunakan pada penelitian ini yang dijadikan input dalam pemodelan ETp yaitu radiasi matahari (Rs); suhu udara (T); kelembaban udara (RH); dan kombinasi Rs dan T. Data variabel cuaca diperoleh dari automatic weather station (AWS) di Daerah Irigasi (DI) Tungkub, Mengwi, Bali. Pada kalibrasi model terdapat tiga metrik evaluasi untuk mengevaluasi kinerja model yaitu R2, MSE, dan RMSE. Sementara pada validasi model menggunakan tiga teknik yaitu prediction error plot, residuals plot, dan k-fold CV. Hasil penelitian menunjukkan nilai estimasi ETp rata-rata dengan skenario masukan Rs menggunakan algoritma RF di DI Tungkub 0,14 mm/jam (R2 = 1,00, MSE = 0,00, RMSE = 0,01). Sementara itu, nilai rata-rata ETp PM yaitu 0,15 mm/jam. Skenario masukan Rs menggunakan algoritma RF menunjukan nilai estimasi yang mendekati nilai ETp PM.
Abstract
The estimation of Potential Evapotranspiration (ETp) is crucial for water distribution planning and cropping patterns. Generally, ETp calculation is obtained from empirical models such as the Penman-Monteith (PM) model recommended by the Food and Agriculture Organization (FAO). However, implementing this model requires numerous weather variables and adequate weather data availability. This research aims to develop an ETp estimation model using the Random Forest (RF) algorithm The weather variables used in this research as inputs for ETp modeling are solar radiation (Rs); air temperature (T); air humidity (RH); and a combination of Rs and T. Weather variable data were obtained from an automatic weather station (AWS) in the Tungkub Irrigation Area, Mengwi, Bali. In model calibration, three evaluation metrics were used to assess model performance, R2, MSE, and RMSE. Meanwhile, for model validation, three techniques were employed, prediction error plot, residuals plot, and k-fold cross-validation. The research results indicate that the average ETp estimation value with the scenario of input Rs using the RF algorithm in the Tungkub Irrigation Area is 0,14 mm/hour (R2 = 1,00, MSE = 0,00, RMSE = 0,01). Meanwhile, the average ETp PM value is 0,15 mm/hour. The scenario of input Rs using the RF algorithm shows estimation values close to the PM ETp value.
Downloads
References
Adib, A., Kalantarzadeh, S. S. O., Shoushtari, M. M., Lotfirad, M., Liaghat, A., & Oulapour, M. (2023). Sensitive analysis of meteorological data and selecting appropriate machine learning model for estimation of reference evapotranspiration. Applied Water Science, 13(3), 1–17. https://doi.org/10.1007/s13201-023-01895-5
Ajjur, S. B., & Al-Ghamdi, S. G. (2021). Evapotranspiration and water availability response to climate change in the Middle East and North Africa. Climatic Change, 166(3–4), 1–18. https://doi.org/10.1007/s10584-021-03122-z
Allen, R. G., Pereira, L. S., Raes, D., & Smith, M. (1998). Crop Evapotranspiration - Guidelines for computing crop water requirements - FAO Irrigation and Drainage Paper 56. https://www.fao.org/3/X0490E/x0490e00.htm#Contents
Arif, C., Setiawan, B. I., & Sofiyuddin, H. A. (2020). Analisis evapotranspirasi potensial pada berbagai model empiris dan jaringan syaraf tiruan dengan data cuaca terbatas. Jurnal Irigasi, 15(2), 71–84. https://doi.org/10.31028/ji.v15.i2.71-84
Bayram, S., & Çıtakoğlu, H. (2023). Modeling monthly reference evapotranspiration process in Turkey: application of machine learning methods. Environmental Monitoring and Assessment, 195(1). https://doi.org/10.1007/s10661-022-10662-z
Bengfort, B., & Bilbro, R. (2019). Yellowbrick: Visualizing the Scikit-Learn Model Selection Process. Journal of Open Source Software, 4(35), 1075. https://doi.org/10.21105/joss.01075
Dinpashoh, Y., Jahanbakhsh-Asl, S., Rasouli, A. A., Foroughi, M., & Singh, V. P. (2019). Impact of climate change on potential evapotranspiration (case study: west and NW of Iran). Theoretical and Applied Climatology, 136(1–2), 185–201. https://doi.org/10.1007/s00704-018-2462-0
Dou, X., & Yang, Y. (2018). Evapotranspiration estimation using four different machine learning approaches in different terrestrial ecosystems. Computers and Electronics in Agriculture, 148(February), 95–106. https://doi.org/10.1016/j.compag.2018.03.010
Fereres, E., & Villalobos, F. J. (2016). Agriculture and Agricultural Systems BT - Principles of Agronomy for Sustainable Agriculture (F. J. Villalobos & E. Fereres (eds.); pp. 1–12). Springer International Publishing. https://doi.org/10.1007/978-3-319-46116-8_1
Gad, H. E. (2010). the Effect of Solar Radiation on Animals. Medical Journal of Australia, 2(23), 795–795. https://doi.org/10.5694/j.1326-5377.1936.tb103240.x
Gao, Z., He, J., Dong, K., & Li, X. (2017). Trends in reference evapotranspiration and their causative factors in the West Liao River basin, China. Agricultural and Forest Meteorology, 232, 106–117. https://doi.org/10.1016/j.agrformet.2016.08.006
Ge, J., Zhao, L., Yu, Z., Liu, H., Zhang, L., Gong, X., & Sun, H. (2022). Prediction of Greenhouse Tomato Crop Evapotranspiration Using XGBoost Machine Learning Model. Plants, 11(15), 1–17. https://doi.org/10.3390/plants11151923
Granata, F. (2019). Evapotranspiration evaluation models based on machine learning algorithms—A comparative study. Agricultural Water Management, 217(March), 303–315. https://doi.org/10.1016/j.agwat.2019.03.015
Hair, J. F., Black, W. C., Babin, B. J., & Anderson, R. E. (2011). Multivariate Data Analysis (Fifth Edit).
Horvitz, E., & Mulligan, D. (2015). Machine learning: Trends,perspectives, and prospects. Science, 349(6245), 253–255.
Iannelli, M., Rahman, M. R., Choi, N., & Wang, L. (2020). Applying machine learning to end-to-end slice SLA decomposition. Proceedings of the 2020 IEEE Conference on Network Softwarization: Bridging the Gap Between AI and Network Softwarization, NetSoft 2020, 92–99. https://doi.org/10.1109/NetSoft48620.2020.9165317
Jha, S. B., Babiceanu, R. F., Pandey, V., & Jha, R. K. (2020). Housing Market Prediction Problem using Different Machine Learning Algorithms: A Case Study. http://arxiv.org/abs/2006.10092
Liu, J., Yu, K., Li, P., Jia, L., Zhang, X., Yang, Z., & Zhao, Y. (2022). Estimation of Potential Evapotranspiration in the Yellow River Basin Using Machine Learning Models. Atmosphere, 13(9). https://doi.org/10.3390/atmos13091467
Lotfi, M., Kamali, G. A., Meshkatee, A. H., & Varshavian, V. (2020). Study on the impact of climate change on evapotranspiration in west of Iran. Arabian Journal of Geosciences, 13(15). https://doi.org/10.1007/s12517-020-05715-x
Nur, N., Wajidi, F., Sulfayanti, S., & Wildayani, W. (2023). Implementasi Algoritma Random Forest Regression untuk Memprediksi Hasil Panen Padi di Desa Minanga. Jurnal Komputer Terapan, 9(1), 58–64. https://doi.org/10.35143/jkt.v9i1.5917
Orji, U., & Ukwandu, E. (2024). Machine learning for an explainable cost prediction of medical insurance. Machine Learning with Applications, 15(July 2023), 100516. https://doi.org/10.1016/j.mlwa.2023.100516
Pino-Vargas, E., Taya-Acosta, E., Ingol-Blanco, E., & Torres-Rúa, A. (2022). Deep Machine Learning for Forecasting Daily Potential Evapotranspiration in Arid Regions, Case: Atacama Desert Header. Agriculture (Switzerland), 12(12). https://doi.org/10.3390/agriculture12121971
Runtunuwu, E., H. Syahbuddin, & A. Pramudia. (2008). Validasi Model Pendugaan Evapotranspirasi: Upaya Melengkapi Sistem Database Iklim Nasional. Jurnal Tanah Dan Iklim, 27, 1–12.
Saidah, H., Sulistyono, H., & Budianto, M. B. (2020). Kalibrasi Persamaan Thornthwaite Dan Evaporasi Panci Untuk Memprediksi Evapotranspirasi Potensial Pada Daerah Dengan Data Cuaca Terbatas. Jurnal Sains Teknologi & Lingkungan, 6(1), 72–84. https://doi.org/10.29303/jstl.v6i1.155
Sofos, F., & Karakasidis, T. E. (2021). Nanoscale slip length prediction with machine learning tools. Scientific Reports, 11(1), 1–10. https://doi.org/10.1038/s41598-021-91885-x
Sua, L. S., Wang, H., Ortiz, J., Sua, L. S., Wang, H., Ortiz, J., Huang, J., & Alidaee, B. (2023). Predicting renewable energy production outputs from climate factors : A machine learning approach Predicting renewable energy production outputs from climate factors : A machine learning approach. 0–14.
Supangat, A. B. (2016). Analisis perubahan nilai pendugaan evapotranspirasi potensial akibat perubahan iklim di kawasan hutan tanaman eucalyptus pellita. Balai Penelitian Dan Pengembangan Teknologi Pengelolaan DAS, 112–122.
Tanny, J. (2022). Evapotranspiration Measurements and Modeling. Water (Switzerland), 14(16), 16–18. https://doi.org/10.3390/w14162474
Wang, Y., Meili, N., & Fatichi, S. (2024). Ecohydrological responses to solar radiation changes. March, 1–24.
Yong, S. L. S., Ng, J. L., Huang, Y. F., & Ang, C. K. (2023). Estimation of Reference Crop Evapotranspiration with Three Different Machine Learning Models and Limited Meteorological Variables. Agronomy, 13(4). https://doi.org/10.3390/agronomy13041048
Jurnal BETA (Biosistem dan Teknik Pertanian)
