Modeling Greenhouse Cucumber Evapotranspiration Using Machine Learning: A Random Forest Approach Versus Traditional and Non-linear Crop Coefficients

Document Type : Research/Original/Regular Article

Authors

1 PhD Student in Irrigation and Drainage Engineering, Department of Irrigation and Reclamation Engineering, Faculty of Agricultural, College of Agriculture and Natural Recourses, University of Tehran, Karaj, Iran

2 Associate Professor of Soil and Water Research Institute, Agricultural Research Education and Extension Organization (AREEO), Karaj, Iran.

Abstract

Extended Abstract

Introduction

Accurate estimation of crop evapotranspiration (ETc) is fundamental for the development of efficient irrigation strategies in greenhouse systems, where environmental conditions differ significantly from open-field farming. In Iran, greenhouse agriculture, particularly for cucumbers (Cucumis sativus L.), has expanded considerably, making irrigation optimization a critical priority. The specific microclimate within greenhouses, including controlled humidity, temperature, and solar radiation levels, affects plant water needs, requiring tailored approaches to predict ETc. Traditional models, like the FAO 56 crop coefficient (Kc) method, provide a standardized way to estimate ETc but are generally suited to field crops under variable outdoor conditions. The limitations of fixed Kc values in capturing the complexity of greenhouse environments have prompted the exploration of alternative models. In recent years, machine learning (ML) techniques, especially ensemble methods like the Random Forest (RF) algorithm, have emerged as promising tools for ETc modeling due to their capacity to manage non-linear interactions among meteorological variables and enhance model flexibility. This study evaluates the performance of three ETc estimation approaches for greenhouse-grown cucumber: the conventional FAO 56 Kc method, a non-linear Kc model using a third-degree polynomial, and direct ETc prediction through the RF algorithm. These methods are assessed across two growth cycles, autumn-winter (A-W) and spring-summer (S-S), to capture seasonal differences in crop water requirements.

Materials and Methods

The study was conducted in a research greenhouse located at the College of Agriculture and Natural Recourses, University of Tehran, focusing on daily ETc of cucumber over two distinct growth periods. Environmental parameters were measured both inside and outside the greenhouse, including maximum, minimum, and average temperatures, relative humidity, and solar radiation. Reference evapotranspiration inside the greenhouse (EToG) was derived using a micro-lysimeter installed with a turfgrass surface, while daily ETc was measured using a soil water balance method, where soil moisture content was monitored daily across three experimental plots to ensure precision. ETc calculations were performed through three modeling approaches. In the first approach, the FAO 56 Kc model estimated ETc by applying fixed crop coefficients and multiplying them by EToG. Although this method has been widely applied in field conditions, its applicability to greenhouses is limited due to fixed Kc assumptions. In the second approach, a non-linear Kc model was developed using third-degree polynomial regression on Kc values calculated as the ratio of ETc to EToG, capturing growth-stage specific variations. In the final approach, the RF model directly predicted ETc based on a broad range of meteorological inputs. To optimize the RF model, hyperparameters were tuned using Python’s GridSearchCV tool, and data were split into training (70%) and testing (30%) sets to validate model performance. After initial RF modeling, a feature selection process using Permutation Feature Importance (PFI) was applied to identify the most influential variables, refining the RF model to the top four parameters.

Results and Discussion

The results highlighted seasonal variability in cumulative ETc, with the S-S period exhibiting nearly double the ETc of the A-W period due to higher ambient temperature and increased solar radiation. These findings underscore the necessity of dynamic ETc models that can accommodate seasonal and environmental variations. The FAO 56 Kc method produced a mean RMSE of 0.915 mm/day across both growth cycles, demonstrating limitations in fixed Kc approaches under greenhouse conditions. The non-linear Kc model, with an average RMSE of 0.64 mm/day, provided improved accuracy by adjusting Kc values across different growth stages, especially during mid-growth when water demand peaks. This improvement aligns with the premise that non-linear models can better capture the ETc variability within controlled environments. The RF algorithm demonstrated superior accuracy and flexibility, outperforming both Kc-based models with R² values of 0.96 for the A-W period and 0.94 for the S-S period in training datasets, and with respective RMSE values of 0.365 mm/day and 0.57 mm/day in testing datasets. These results illustrate the RF model’s capacity to accurately model ETc by capturing complex, non-linear interactions among variables such as maxTG (maximum temperature inside the greenhouse), meanRHG (average relative humidity inside the greenhouse), and RadiationG (solar radiation inside the greenhouse) during the A-W period, with RadiationG and EToG emerging as key variables during the S-S period. By emphasizing critical seasonal drivers of ETc, the RF model offers a robust alternative that adjusts to environmental changes without relying on static Kc values. This adaptability supports RF’s potential as a powerful tool for ETc estimation, accurately reflecting seasonal influences on greenhouse crop water needs.

Conclusion

The findings from this study demonstrate that the RF algorithm, when applied to ETc modeling in greenhouse conditions, provides a flexible, high-accuracy alternative to traditional Kc methods. Unlike the FAO 56 Kc and non-linear Kc models, which rely on predefined or growth-stage specific coefficients, the RF approach enables direct ETc prediction using real-time meteorological data. By optimizing input variables through feature selection, RF efficiently reduced the model complexity, focusing on the top four influential parameters while retaining high predictive accuracy. This reduction not only streamlines data collection requirements but also enhances the model's applicability in practical greenhouse operations. The results indicate that RF's capacity to model complex relationships among variables makes it especially suited for greenhouse environments, where precision irrigation is crucial for sustainable water management. Ultimately, this research underscores the importance of integrating machine learning techniques in ETc estimation, providing greenhouse operators with adaptive, resource-efficient tools for managing water use in controlled agricultural settings.

Keywords

Main Subjects

References

منابع
ایرجی، مریم، موحدی نائینی، سید علیرضا، کمکی، چوقی بایرام، ابراهیمی، سهیلا و یغمایی، بامشاد (1403). ارزیابی پارامترهای مؤثر جهت پیش‌بینی عیار پتاسیم شورابه با استفاده از الگوریتم‌های ماشین بردار پشتیبان و جنگل تصادفی (مطالعه موردی: پلایای شهرستان خور و بیابانک، استان اصفهان). تحقیقات آب‌ و خاک ایران، 55(1)، 161-145. doi: 10.22059/ijswr.2023.368909.669610
جعفری نجف‌آبادی، محمد سعید، تافته، آرش و ابراهیمی پاک، نیازعلی (1401). تعیین نیاز آبی و آب کاربردی فلفل دلمه‌ای در گلخانه و مقایسه آن با نتایج سامانه نیاز آب. تحقیقات آب و خاک ایران، 53(8)، 1831-1848. doi: 10.22059/ijswr.2022.345968.669321
رضوانی، سید معین‌الدین، زارعی، قاسم و سالمی، حمیدرضا (1401). تبخیر-تعرق و ضریب گیاهی خیار گلخانه‌ای در منطقه همدان. نشریه آبیاری و زهکشی ایران، 16(5)، 916-904. dor: 20.1001.1.20087942.1401.16.5.2.7
صداقت، آزاده، ابراهیمی پاک، نیازعلی، تافته، آرش و حسینی، سید نرگس (1401). ارزیابی سه روش داده‌کاوی برای تخمین تبخیرتعرق مرجع در استان زنجان. تحقیقات آب و خاک ایران، 53(12)، 2739-2757. doi: 10.22059/ijswr.2023.352890.669419
صداقت، آزاده، تافته، آرش، ابراهیمی پاک، نیازعلی و حسینی، سید نرگس (1402). مقایسه برآوردهای تبخیرتعرق مرجع روزانه با روش‌های داده‌کاوی و سامانه نیاز آبی گیاهان در استان البرز. هواشناسی کشاورزی، 11(2)، 28-16.
doi: 10.22125/agmj.2023.336962.1134
 
References
Allen, R. G., Pereira, L. S., Raes, D., Smith, M., & others. (1998). Crop evapotranspiration-Guidelines for computing crop water requirements-FAO Irrigation and drainage paper 56. Fao, Rome, 300(9), D05109.
Blanco, F. F., & Folegatti, M. V. (2003). Evapotranspiration and crop coefficient of cucumber in greenhouse. Revista Brasileira de Engenharia Agrícola e Ambiental, 7(2), 285–291. doi: 10.1590/S141543662003000200017
Borg, H., & Grimes, D. W. (1986). Depth Development of Roots with Time: An Empirical Description. Transactions of the ASAE, 29(1), 194–197. doi: 10.13031/2013.30125
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
doi: 10.1023/A:1010933404324/METRICS
Chen, H., Huang, J. J., & McBean, E. (2020). Partitioning of daily evapotranspiration using a modified shuttleworth-wallace model, random Forest and support vector regression, for a cabbage farmland. Agricultural Water Management, 228, 105923.
doi: 10.1016/J.AGWAT.2019.105923
Ding, R., Kang, S., Li, F., Zhang, Y., & Tong, L. (2013). Evapotranspiration measurement and estimation using modified Priestley–Taylor model in an irrigated maize field with mulching. Agricultural and Forest Meteorology, 168, 140–148. doi: 10.1016/J.AGRFORMET.2012.08.003
Fernández, M. D., Bonachela, S., Orgaz, F., Thompson, R., López, J. C., Granados, M. R., Gallardo, M., & Fereres, E. (2010). Measurement and estimation of plastic greenhouse reference evapotranspiration in a Mediterranean climate. Irrigation Science, 28(6), 497–509.
doi: 10.1007/S00271-010-0210-Z
Gallardo, M., Thompson, R. B., & Fernández, M. D. (2013). Water requirements and irrigation management in Mediterranean greenhouses: the case of the southeast coast of Spain. Good Agricultural Practices for Greenhouse Vegetable Crops; Plant Production and Protection Paper, 217, 109–136.
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 2022, Vol. 11, Page 1923, 11(15), 1923.
doi: 10.3390/PLANTS11151923
Gong, X., Liu, H., Sun, J., Gao, Y., Zhang, X., Jha, S. K., Zhang, H., Ma, X., & Wang, W. (2017). A proposed surface resistance model for the Penman-Monteith formula to estimate evapotranspiration in a solar greenhouse. Journal of Arid Land, 9(4), 530–546.
doi: 10.1007/S40333-017-0020-8/METRICS
Gong, X., Qiu, R., Ge, J., Bo, G., Ping, Y., Xin, Q., & Wang, S. (2021). Evapotranspiration partitioning of greenhouse grown tomato using a modified Priestley–Taylor model. Agricultural Water Management, 247, 106709. doi: 10.1016/J.AGWAT.2020.106709
Gong, X., Wang, S., Xu, C., Zhang, H., & Ge, J. (2020). Evaluation of Several Reference Evapotranspiration Models and Determination of Crop Water Requirement for Tomato in a Solar Greenhouse. HortScience, 55(2), 244–250. doi: 10.21273/HORTSCI14514-19
Gu, C., Ma, J., Zhu, G., Yang, H., Zhang, K., Wang, Y., & Gu, C. (2018). Partitioning evapotranspiration using an optimized satellite-based ET model across biomes. Agricultural and Forest Meteorology, 259, 355–363.
doi: 10.1016/J.AGRFORMET.2018.05.023
Harris, J. R., & Grunsky, E. C. (2015). Predictive lithological mapping of Canada’s North using Random Forest classification applied to geophysical and geochemical data. Computers & Geosciences, 80, 9–25. doi: 10.1016/J.CAGEO.2015.03.013
Huang, S., Yan, H., Zhang, C., Wang, G., Acquah, S. J., Yu, J., Li, L., Ma, J., & Opoku Darko, R. (2020). Modeling evapotranspiration for cucumber plants based on the Shuttleworth-Wallace model in a Venlo-type greenhouse. Agricultural Water Management, 228, 105861. doi: 10.1016/j.agwat.2019.105861
Ignatenko, V., Surkov, A., & Koltcov, S. (2024). Random forests with parametric entropy-based information gains for classification and regression problems. PeerJ Computer Science, 10, e1775. doi: 10.7717/PEERJ-CS.1775
Incrocci, L., Thompson, R. B., Fernandez-Fernandez, M. D., De Pascale, S., Pardossi, A., Stanghellini, C., Rouphael, Y., & Gallardo, M. (2020). Irrigation management of European greenhouse vegetable crops. Agricultural Water Management, 242, 106393.
doi: 10.1016/j.agwat.2020.106393
Iraji, M., Movahedi naeini, S. A., Komaki, C. B., Ebrahimi, S., & Yaghmaei, B. (2024). Evaluation of effective parameters for predicting the potassium grade of saline water by using support vector machine and random forest algorithms (case study: playa of Khoor and Biabank area city, Isfahan province). Iranian Journal of Soil and Water Research, 55(1), 145–161.
doi: 10.22059/ijswr.2023.368909.669610 [In Persian]
Jafari najafabadi, M. S., Tafteh, A., & Ebrahimipak, N. (2022). Determining the Water Requirement and Applied Water of Bell Pepper in the Greenhouse and Comparing It with the Results of the Water Requirement System. Iranian Journal of Soil and Water Research, 53(8), 1831–1848. doi: 10.22059/ijswr.2022.345968.669321 [In Persian]
James, L. (1988). Principles of farm irrigation systems design.
https://www.cabidigitallibrary.org/doi/full/10.5555/19891934086
Jamieson, P. D., Porter, J. R., & Wilson, D. R. (1991). A test of the computer simulation model ARCWHEAT1 on wheat crops grown in New Zealand. Field Crops Research, 27(4), 337–350. doi: 10.1016/0378-4290(91)90040-3
Kisi, O., Karahan, M. E., & Şen, Z. (2006). River suspended sediment modelling using a fuzzy logic approach. Hydrological Processes, 20(20), 4351–4362. doi: 10.1002/hyp.6166
Kramer, O. (2016). Scikit-Learn. Studies in Big Data, 20, 45–53.
doi: 10.1007/978-3-319-33383-0_5
Li, L., Chen, S., Yang, C., Meng, F., & Sigrimis, N. (2020). Prediction of plant transpiration from environmental parameters and relative leaf area index using the random forest regression algorithm. Journal of Cleaner Production, 261, 121136. doi: 10.1016/J.JCLEPRO.2020.121136
Marcoulides, K. M., & Raykov, T. (2018). Evaluation of Variance Inflation Factors in Regression Models Using Latent Variable Modeling Methods. Educational and Psychological Measurement, 79(5), 874.
      doi: 10.1177/0013164418817803
Medrano, E., Lorenzo, P., Sánchez-Guerrero, M. C., & Montero, J. I. (2005). Evaluation and modelling of greenhouse cucumber-crop transpiration under high and low radiation conditions. Scientia Horticulturae, 105(2), 163–175. doi: 10.1016/J.SCIENTA.2005.01.024
Merrill, S. D., Tanaka, D. L., & Hanson, J. D. (2002). Root Length Growth of Eight Crop Species in Haplustoll Soils. Soil Science Society of America Journal, 66(3), 913–923.
doi: 10.2136/SSSAJ2002.9130
Moriasi, D. N., Arnold, J. G., Liew, M. W. Van, Bingner, R. L., Harmel, R. D., & Veith, T. L. (2007). Model Evaluation Guidelines for Systematic Quantification of Accuracy in Watershed Simulations. Transactions of the ASABE, 50(3), 885–900.
      doi: 10.13031/2013.23153
Mushab, F. S. (2020). Forecasting Crop Coefficient Values for Cucumber Plant (Cucumis sativus). Solid State Technology, 63(6), 9085–9092. https://www.solidstatetechnology.us/index.php/JSST/article/view/5304
Nikolaou, G., Neocleous, D., Christou, A., Polycarpou, P., Kitta, E., & Katsoulas, N. (2021). Energy and Water Related Parameters in Tomato and Cucumber Greenhouse Crops in Semiarid Mediterranean Regions. A Review, Part I: Increasing Energy Efficiency. Horticulturae 2021, Vol. 7, Page 521, 7(12), 521.
doi: 10.3390/HORTICULTURAE7120521
Nikolaou, G., Neocleous, D., Kitta, E., & Katsoulas, N. (2023). Assessment of the Priestley-Taylor coefficient and a modified potential evapotranspiration model. Smart Agricultural Technology, 3, 100075.
doi: 10.1016/J.ATECH.2022.100075
Orgaz, F., Fernández, M. D., Bonachela, S., Gallardo, M., & Fereres, E. (2005). Evapotranspiration of horticultural crops in an unheated plastic greenhouse. Agricultural Water Management, 72(2), 81–96.
doi: 10.1016/J.AGWAT.2004.09.010
Pereira, A. R., Villa Nova, N. A., Pereira, A. S., & Barbieri, V. (1995). A model for the class A pan coefficient. Agricultural and Forest Meteorology, 76(2), 75–82.
     doi: 10.1016/0168-1923(94)02224-8
Priestley, C. H. B., & Taylor, R. J. (1972). On the assessment of surface heat flux and evaporation using large-scale parameters. Monthly Weather Review, 100(2), 81–92.
doi: 10.1175/1520-0493(1972)100%3C0081: OTAOSH%3E2.3.CO;2
Rezvani, S., Zarei, G., & Salemi, H. (2022). Evapotranspiration and crop coefficient of greenhouse cucumber in the Hamedan region. Iranian Journal of Irrigation & Drainage, 16(5), 904–916.
    https://idj.iaid.ir/article_159921.html [In Persian]
Ruiz-Aĺvarez, M., Gomariz-Castillo, F., & Alonso-Sarría, F. (2021). Evapotranspiration Response to Climate Change in Semi-Arid Areas: Using Random Forest as Multi-Model Ensemble Method. Water 2021, Vol. 13, Page 222, 13(2), 222. doi: 10.3390/W13020222
Sedaghat, A., Ebrahimipak, N., Tafteh, A., & Hosseini, S. N. (2023). Evaluation of three data mining methods to estimate reference evapotranspiration in Zanjan province. Iranian Journal of Soil and Water Research, 53(12), 2739–2757. doi: 10.22059/ijswr.2023.352890.669419 [In Persian]
Sedaghat, A., Tafteh, A., Ebrahimipak, N., & Hosseini, S. N. (2023). Comparison of the reference evapotranspiration estimations by data mining methods and Crop Water Requirement System project in Alborz province. Journal of Agricultural Meteorology, 11(2), 16–28. doi: 10.22125/agmj.2023.336962.1134 [In Persian]
Snyder, R. L. (1992). Equation for Evaporation Pan to Evapotranspiration Conversions. Journal of Irrigation and Drainage Engineering, 118(6), 977–980. doi: 10.1061/(ASCE)0733-9437(1992)118:6(977)
Stanghellini, C. (1987). Transpiration of greenhouse crops: an aid to climate management. Wageningen University and Research.
Sun, Y., Zhang, J., Wang, H., Wang, L., & Li, H. (2019). Identifying optimal water and nitrogen inputs for high efficiency and low environment impacts of a greenhouse summer cucumber with a model method. Agricultural Water Management, 212, 23–34.
doi: 10.1016/J.AGWAT.2018.08.028
Tabari, H., Grismer, M. E., & Trajkovic, S. (2013). Comparative analysis of 31 reference evapotranspiration methods under humid conditions. Irrigation Science, 31(2), 107–117. doi: 10.1007/S00271-011-0295-Z/TABLES/6
Tafteh, A., & Babazadeh, H. I. (2014). Determine Yield Response Factors of Important Crops by Different Production Functions in Qazvin Plain. https://gnanaganga.inflibnet.ac.in:8443/jspui/handle/123456789/10474
Thom, A. S. (1972). Momentum, mass and heat exchange of vegetation. Quarterly Journal of the Royal Meteorological Society, 98(415), 124–134. doi: 10.1002/QJ.49709841510
Yan, H., Zhao, S., Zhang, C., Zhang, J., Wang, G., Li, M., Deng, S., Liang, S., & Jiang, J. (2024). Calibration and assessment of evapotranspiration methods for cucumber plants in a Venlo-type greenhouse. Irrigation and Drainage, 73(1), 119–135.
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 2023, Vol. 13, Page 1048, 13(4), 1048.
doi: 10.3390/AGRONOMY13041048
Zhang, L., Huettmann, F., Zhang, X., Liu, S., Sun, P., Yu, Z., & Mi, C. (2019). The use of classification and regression algorithms using the random forests method with presence-only data to model species’ distribution. MethodsX, 6, 2281–2292. doi: 10.1016/J.MEX.2019.09.035
Water and Soil Management and Modelling
Volume 5, Issue 2
2025
Pages 69-87

Files

History

  • Receive Date: 10 November 2024
  • Revise Date: 08 December 2024
  • Accept Date: 11 December 2024

Share

How to cite

Statistics