Prediction of daily reference evapotranspiration with M5P, Gaussian process regression and Support vector regression methods

Authors

Department of Water Engineering, Faculty of Agriculture, University of Tabriz

Abstract

Background and Objectives: Indiscriminate use of water resources and the occurrence of drought in recent years have caused many problems in the country's water resources. The increasing shortage of water resources and high irrigation costs require developing new irrigation methods for optimal water consumption, which can minimize the amount of water used to produce yields. Evapotranspiration is one of the most important parameters needed to estimate the water balance in any ecosystem. Evapotranspiration is an essential parameter in the hydrological cycle process in natural ecosystems, which links the water and energy balance of the earth's surface with the atmosphere. Reference evapotranspiration (ET0) plays an important role in the availability of water resources and stimulating the hydrological effect of climate change. Accurate estimation of ET0 is necessary for forecasting climate changes, predicting and monitoring droughts, assessing the lack of availability of water resources, assessing crop water needs, and planning irrigation. FAO's Penman-Monteith method is known as a standard reference method for estimating ET0. However, this model and, in general, water balance-based assessment methods require accurate and long-term meteorological data, which are not always and everywhere available. Therefore, alternative methods for predicting ET0 at different temporal and spatial scales should be developed, which are easily applied and require fewer input data without compromising the estimation accuracy. Also, due to the high rate of evapotranspiration in the coastal and central stations of the country, so far, few studies have predicted the ET0 parameter. Therefore, this study was carried out to predict daily reference evapotranspiration in Isfahan and Astara stations.
Methodology: The current study is forecasting daily reference evapotranspiration in two stations of Astara and Isfahan using Gaussian Process Regression (GPR), Support Vector Regression (SVR), M5P tree model, and M5Rules linear regression. For this purpose, the daily meteorological data of the stations including average temperature, minimum temperature, maximum temperature, average relative humidity, minimum relative humidity, maximum relative humidity, wind speed, and sunshine hours during the period of 1990-2021 as inputs to the models was used. Also, to evaluate the effectiveness of the models, the evaluation criteria of determination coefficient (R2), root mean square error (RMSE), Nash-Sutcliffe coefficient (NS), and Wilmott's index of agreement (WI) were used.
Findings: The evaluation of the results of different scenarios of the GPR model in Astara station showed that the fifth scenario was recognized as the best scenario of this model due to having a lower error value (RMSE=1.52 mm day-1). For the M5Rules model, the fifth scenario has performed better than the other scenarios of the M5Rules model due to having fewer inputs and similar errors compared to the sixth to eighth scenarios (RMSE=1.42 mm day-1). In the M5P model, the fifth scenario has a higher accuracy than the other scenarios due to having a lower error value (RMSE=1.42 mm day-1). For the SVR model, the sixth scenario with the least error (RMSE=1.58 mm day-1) was selected as the best scenario compared to other scenarios of the SVR model. For the Isfahan station, for the GPR model, the fifth scenario has performed better than the other scenarios due to having fewer inputs. The comparison of M5Rules model scenarios also showed that the eighth scenario with RMSE=1.85 (mm day-1), had higher accuracy than other scenarios. The seventh scenario of the M5P model has performed better than other scenarios due to its RMSE=1.86 (mm day-1). Finally, the evaluation of SVR model scenarios showed that the eighth scenario with RMSE=1.88 (mm day-1) had a better performance than other scenarios.
Conclusion: The comparison of the models used to predict daily reference evapotranspiration in Astara station showed that the fifth scenario of M5P and M5Rules models having evaluation criteria of R2=0.76, RMSE=1.42 (mm day-1), NS=0.7 and WI=0.89 had the highest accuracy compared to other models and showed the best performance. Also, the evaluation of the results of the models in Isfahan station showed that the eighth scenario of the M5Rules model, having the evaluation criteria of R2=0.8, RMSE=1.85 (mm day-1), NS=0.8 and WI=0.94 had the best performance compared to other models and the M5Rules model was selected as the best model. Also, the seventh scenario of the M5P model had almost the same performance as the eighth scenario of the M5Rules model and showed a good performance. Therefore, M5P and M5Rules models successfully predicted reference evapotranspiration. One of the limitations of the present study is the lack of access to dew point temperature and solar radiation data. Therefore, the use of these parameters is suggested for further studies.

Keywords

References

Abedi-Koupai J, Dorafshan MM, Javadi A and Ostad-Ali-Askari K, 2022. Estimating potential reference
evapotranspiration using time series models (Case study: synoptic station of Tabriz in northwestern Iran).
Applied Water Science 12(9): 212-224.
Abeysiriwardana HD, Muttil N and Rathnayake U, 2022. A Comparative study of potential evapotranspiration
estimation by three methods with FAO Penman–Monteith method across Sri Lanka. Hydrology 9(11):
206-218.
Al-Dosary NMN, Maray SA, Al-Hamed SA and Aboukarima AM, 2023. Employing data mining algorithms
and mathematical empirical models for predicting wind drift and evaporation losses of a sprinkler
irrigation method. Water 15(5): 922-939.
AL–Janabi MAHJ, 2017. Modeling of monthly pan evaporation using M5P machine learning technique.
Journal of Kufa-Physics 9(1): 21-38.
Ayaz Y, Kocamaz AF and Karakoç MB, 2015. Modeling of compressive strength and UPV of high-volume
mineral-admixtured concrete using rule-based M5 rule and tree model M5P classifiers. Construction and
Building Materials 94: 235-240.
Baydaroğlu Ö and Koçak K, 2014. SVR-based prediction of evaporation combined with chaotic approach.
Journal of Hydrology 508: 356-363.
Breiman L, Friedman JH, Olshen RA and Stone CJ, 1984. Classification and Regression Trees. Taylor &
Francis, New York.
Cortes C and Vapnik V, 1995. Support-vector networks. Machine Learning 20: 273-297.
175صمدیان فردو همکاراننشریه دانش آب و خاک / جلد34شماره2/ سال1403
Cui Y, Song L and Fan W, 2021. Generation of spatio-temporally continuous evapotranspiration and its
components by coupling a two-source energy balance model and a deep neural network over the Heihe
River Basin. Journal of Hydrology 597: 126-139.
Deo RC and Samui P, 2017. Forecasting evaporative loss by least-square support-vector regression and
evaluation with genetic programming, Gaussian process, and minimax probability machine regression:
case study of Brisbane City. Journal of Hydrologic Engineering 22(6): 50-64.
El-Nashar W and Elyamany A, 2023. Adapting irrigation strategies to mitigate climate change impacts: a value
engineering approach. Water Resources Management 37(6-7): 2369-2386.
Frank E and Witten IH, 1998. Generating accurate rule sets without global optimization. 1-18.
Gisolo D, Previati M, Bevilacqua I, Canone D, Boetti M, Dematteis N, Balocco J, Ferrari S, Gentile A and
N'sassila M, 2022. A calibration free radiation driven model for estimating actual evapotranspiration of
mountain grasslands (CLIME-MG). Journal of Hydrology 610: 127-138.
Koepernik P and Pfaff F, 2021. Consistency of Gaussian process regression in metric spaces. The Journal of
Machine Learning Research 22(1): 11066-11092.
Marin FR, Angelocci LR, Nassif DS, Costa LG, Vianna MS and Carvalho KS, 2016. Crop coefficient changes
with reference evapotranspiration for highly canopy-atmosphere coupled crops. Agricultural Water
Management 163: 139-145.
Mirdashtvan M, Najafinejad A, Malekian A and Sa’doddin A, 2021. Sustainable water supply and demand
management in semi-arid regions: optimizing water resources allocation based on RCPs scenarios. Water
Resources Management 35: 5307-5324.
Mirhashemi S, Panahi M and Zareei L, 2020. Evaluation of M5P algorithm for estimation of potential
evapotranspiration, minimum and maximum temperature (Case study: Sari Weather Station). Journal of
Meteorology and Atmospheric Science 2(4): 287-295.
Nhu VH, Shahabi H, Nohani E, Shirzadi A, Al-Ansari N, Bahrami S, Miraki S, Geertsema M and Nguyen H,
2020. Daily water level prediction of Zrebar Lake (Iran): a comparison between M5P, random forest,
random tree and reduced error pruning trees algorithms. ISPRS International Journal of Geo-Information
9(8): 479-491.
Pham BT, Ly H-B, Al-Ansari N and Ho LS, 2021. A comparison of Gaussian process and M5P for prediction
of soil permeability coefficient. Scientific Programming 2021: 1-13.
Quinlan JR, 1987. Simplifying decision trees. International Journal of Man-Machine Studies 27(3): 221-234.
Quinlan JR, 1992. Learning with continuous classes. 5th Australian joint conference on artificial intelligence,
6-18 November, Hobart, Australia.
Quinlan JR, 1993. Combining instance-based and model-based learning. Proceedings of the Tenth International
Conference on Machine Learning.
Rasmussen CE and Williams CK, 2006. Gaussian Processes for Machine Learning. Springer.
Roushangar K and Shahnazi S, 2020. Prediction of sediment transport rates in gravel-bed rivers using Gaussian
process regression. Journal of Hydroinformatics 22(2): 249-262.
Sattari MT and Esmailzadeh B, 2017. Performance assessment of M5 tree model and genetic Programming in
Tabriz station reference evapotranspiration modeling. Journal of Water Resources Engineering 9(31): 11-
20 (In Persian with English abstract).
Sattari MT, Ahmadifar V and Pashapour Kholf Ansar R, 2014. M5 tree model based modeling of evaporation
losses in Eleviyan reservoir and comparison with empirical equations. Journal of Irrigation And Water
Engineering 5(1): 107-121(In Persian with English abstract).
Shafiullah G, Simson S, Thompson A, Wolfs PJ and Ali A. 2008. Forecasting vertical acceleration railway
wagons-A comparative study. 4th International Conference on Data Mining (DMIN'08), 11(2): 290-299.
Shah S, Duan Z, Song X, Li R, Mao H, Liu J, Ma T and Wang M, 2021. Evaluating the added value of multi-
variable calibration of SWAT with remotely sensed evapotranspiration data for improving hydrological
modeling. Journal of Hydrology 603: 127-146.
Sharafatmandrad M and Khosravi Mashizi A, 2021. Temporal and spatial assessment of supply and demand
of the water-yield ecosystem service for water scarcity management in arid to semi-arid ecosystems. Water
Resources Management 35(1): 63-82.
پیش بینیتبخیر-تعرق مرجع روزانه با روشهای مدل.. .176
Sharafi M and Samadian Fard S, 2021. The role of kernel functions in increasing the accuracy of daily
evaporation prediction in wet and dry regions of Iran. Journal of Auifer and Qanat 3(1): 147-157 (In
Persian with English abstract).
Sharafi M, Samadian Fard S and Hashemi S, 2021. Monthly rainfall Forecasting using genetic programming
and support vector machine. Journal of Rainwater Catchment Systems 8(4): 63-71 (In Persian with
English abstract).
Talebmorad H, Abedi-Koupai J, Eslamian S, Mousavi SF, Akhavan S, Ostad-Ali-Askari K and Singh VP, 2021.
Evaluation of the impact of climate change on reference crop evapotranspiration in Hamedan-Bahar plain.
International Journal of Hydrology Science and Technology 11(3): 333-347.
Tejada Jr AT, Ella VB, Lampayan RM and Reaño CE, 2022. Modeling reference crop evapotranspiration using
support vector machine (SVM) and extreme learning machine (ELM) in region IV-A, Philippines. Water
14(5): 754-766.
Tezel G and Buyukyildiz M, 2016. Monthly evaporation forecasting using artificial neural networks and
support vector machines. Theoretical and Applied Climatology 124: 69-80.
Wang WC, Xu DM, Chau KW and Chen S, 2013. Improved annual rainfall-runoff forecasting using PSO–
SVM model based on EEMD. Journal of Hydroinformatics 15(4): 1377-1390.
Wanniarachchi S and Sarukkalige R, 2022. A review on evapotranspiration estimation in agricultural water
management: Past, present, and future. Hydrology 9(7): 123-142.
Xu Y, Xu Y, Wang Y, Wu L, Li G and Song S, 2017. Spatial and temporal trends of reference crop
evapotranspiration and its influential variables in Yangtze River Delta, eastern China. Theoretical and
Applied Climatology 130: 945-958.
Journal of Soil and Plant Science
Volume 34, Issue 2
The articles of this issue have been published in the Journal of Water and Soil Science.
June 2024
Pages 156-176

Files

Share

How to cite

Statistics