Predictive Modeling and Comparative Analysis of Reference Evapotranspiration with Machine Learning Algorithms

Venkatesh Gaddikeri

ICAR-IARI, New Delhi-110012, India.

Malkhan Singh Jatav

ICAR-IARI, New Delhi-110012, India.

Siddharam

Kelappaji College of Agricultural Engineering and Technology, KAU, Tavanur, India.

K. R. Asha *

College of Agricultural Engineering, PJTSAU, Kandi, India.

L. Aiswarya

Kelappaji College of Agricultural Engineering and Technology, KAU, Tavanur, India.

Preeti

Department of Renewable Energy Engineering, CAET, Dr. BSKKV, Dapoli (MS), India.

Bandi Nageswar

College of Agricultural Engineering, PJTSAU, Kandi, India.

*Author to whom correspondence should be addressed.


Abstract

Accurate estimation of reference evapotranspiration (ET0) is crucial for a multitude of applications, encompassing drought detection, irrigation scheduling, water resource management, and disaster risk reduction. This investigation utilized the FAO-PM equation for ET0 estimation and subsequently incorporated meteorological variables as input variables with machine learning (ML) models to enhance ET0 predictions. The dataset was bifurcated into training and testing data segments. Four distinct machine learning models were deployed in this study, namely Random Forest (RF), Support Vector Machine (SVM), Gradient Boosting Machine (GBM), and Linear Regression (LR). The performance of these models was evaluated using various statistical indices, including Mean Absolute Error (MAE), Mean Sum of Error (MSE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and the coefficient of determination (R2), to pinpoint the most efficacious ML algorithm. After conducting a comprehensive analysis involving both training and testing data, the results unequivocally identify GBM with MAE values of 0.054 and 0.077, MSE values of 0.005 and 0.011, MAPE values of 0.014 and 0.022, RMSE values of 0.072 and 0.107, and an R2 value of 0.096 and 0.092 during training and testing, respectively. This model has been selected as the optimal choice for precise ET0 estimation within the study region. Subsequently, SVM, RF, and LR follow as alternatives in terms of performance, in descending order.

Keywords: Evapotranspiration, machine learning, random forest, support vector machine, gradient boosting trees, linear regression


How to Cite

Gaddikeri , V., Jatav , M. S., Siddharam, Asha, K. R., Aiswarya , L., Preeti, & Nageswar , B. (2023). Predictive Modeling and Comparative Analysis of Reference Evapotranspiration with Machine Learning Algorithms. International Journal of Environment and Climate Change, 13(11), 1623–1634. https://doi.org/10.9734/ijecc/2023/v13i113317

Downloads

Download data is not yet available.

References

United Nations (UN), Department of Economic and Social Affairs, Population Division (2019). World Population Prospects. 2019; Highlights (ST/ESA/SER.A/423).

Press Information Bureau (PIB). Per Capita Availability of Water; 2020. Available:https://pib.gov.in/PressReleasePage.asp PRID=1604871#:~:text=The%20average%20annual%20per%20capita,years%202021%20and%202031%20respectively

Arti Kumari, Ashutosh Upadhyaya, Pawan Jeet, Nadhir Al-Ansari, Jitendra Rajput, Alban Kuriqi, et al. Estimation of Actual Evapotranspiration and Crop Coefficient of Transplanted Puddled Rice using Modified Non-weighing paddy Lysimeter. Agronomy. 2022;12(11):2850. Available:https://doi.org/10.3390/agronomy12112850

Gaddikeri V, Sarangi A, Singh DK, Bandyopadhyay KK, Chakrabarti B, Sarkar SK. Comparative evaluation of reference evapotranspiration estimation models in New Bhupania Minor Command, Jhajjar, Haryana, India. Current Science (00113891). 2023;124(10).

Feng Y, Peng Y, Cui N, Gong D, Zhang K. Modeling reference evapotranspiration using extreme learning machine and generalized regression neural network only with temperature data. Computers and Electronics in Agriculture. 2017;136:71-78.

Chia MY, Huang YF, Koo CH. Swarm-based optimization as stochastic training strategy for estimation of reference evapotranspiration using extreme learning machine. Agriculture Water Management. 2021;243:106447.

Available:https://doi.org/10.1016/j.agwat.2020

Chia MY, Huang YF, Koo CH, Fung KF. Recent advances in evapotranspiration estimation using artificial intelligence approaches with a focus on hybridization techniques – a review. Agronomy 2020b; 10 (1):101. Available:https://doi.org/10.3390/agronomy10010101

Duhan D, Singh D, Arya S. Effect of projected climate change on potential evapotranspiration in the semiarid region of central India. Journal of Water and Climate Change. 2021;12(5):1854–1870.

Jitendra Rajput, Man Singh, Lal K, Manoj Khanna, Sarangi A, Mukherjee J, Shrawan Singh. Performance Evaluation of Soft Computing Techniques for Forecasting Daily Reference Evapotranspiration. Journal of Water and Climate Change. 2022;14(1):350–368. DOI: https://doi.org/10.2166/wcc.2022.385

Jitendra Rajput, Man Singh, Lal K, Manoj Khanna, Sarangi A, Mukherjee J, Shrawan Singh. Selection of Alternate Reference Evapotranspiration Models based on Multi-Criteria Decision Ranking for Semi-Arid Climate. Journal of Environment, Development and Sustainability; 2023. Available:https://doi.org/10.1007/s10668-023-03234-9

Keshtegar B, Kisi O, Arab HG, Zounemat-Kermani M. Subset modeling basis ANFIS for prediction of the reference evapotranspiration. Water Resources Management. 2018;32(3):1101–1116.

Reis MM, daSilva AJ, Zullo Junior J, TuffiSantos LD, Azevedo AM, Lopes ÉMG. Empirical and learning machine approaches to estimating reference evapotranspiration based on temperature data. Computers and Electronics in Agriculture. 2019;165:104937.

Jatav MS, Sarangi A, Singh DK, Sahoo RN, Varghese C. Advanced machine learning-based kharif maize evapotranspiration estimation in semi-arid climate. Water Science & Technology. 2023;88(4):991-1014.

Seifi A, Riahi H. Estimating daily reference evapotranspiration using hybrid gamma test-least square support vector machine, gamma test-ANN, and gamma test-ANFIS models in an arid area of Iran. Journal of Water and Climate Change. 2020;11(1): 217–240

Bachour R, Maslova I, Ticlavilca AM, Walker WR, McKee M. Wavelet-multivariate relevance vector machine hybrid model for forecasting daily evapotranspiration. Stochastic Environmental Research and Risk Assessment. 2016;30(1):103–117. Available:https://doi.org/10.1007/s00477-015-1039-z.

Mehdizadeh S, Behmanesh J, Khalili K. Using MARS, SVM, GEP and empirical equations for estimation of monthly mean reference evapotranspiration. Computers and Electronics in Agriculture. 2017; 139:103–114.

Available:https://doi.org/10.1016/j.compag.2017.05.00.

Dimple, Pradeep Kumar Singh, Jitendra Rajput, Dheeraj Kumar, Venkatesh Gaddikeri, Ahmed Elbeltagi. Combination of discretization regression with data-driven algorithms for modeling irrigation water quality indices. Journal of Ecological Informatics. Available:https://doi.org/10.1016/j.ecoinf.2023.102093

Jitendra Rajput, Man Singh, Lal K, Manoj Khanna, Sarangi A, Mukherjee J, Shrawan Singh. Assessment of Data Intelligence Algorithms in Modeling Daily Reference Evapotranspiration under Input Data Limitation Scenarios in Semi-Arid Climatic Condition. Journal of Water Science and Technology. 2023;87(10):2504–2528 DOI: https://doi.org/10.2166/wst.2023.137

Allen RG, Pereira LS, Raes D, Smith M. Crop evapotranspiration – Guidelines for computing crop water requirements. FAO Irrigation and Drainage Paper, No. 56, FAO, Rome; 1998.

Breiman L. Random Forests. Mach. Learn. 2001;45:5–32.

Misra S, Li H. Chapter 9—Noninvasive Fracture Characterization Based on the Classification of Sonic Wave Travel Times. In Machine Learning for Subsurface Characterization; Misra, S., Li, H., He, J., Eds.; Gulf Professional Publishing: Houston, TX, USA. 2020;243–287.

ISBN 978-0-12-817736-5.

Vapnik V. The Nature of Statistical Learning Theory; Springer: New York, NY, USA; 1995.

Geigy R, Jenni L, Kauffmann M, Onyango RJ, Weiss N. Identification of T. brucei-subgroup strains isolated from game. Acta Tropica. 1975;32(3):190-205.

Jensen ME, Walter IA, Allen RG, Elliott R, Itenfisu D, Mecham B, et al. ASCE’s Standardized Reference Evapotranspiration Equation. 2012;1-11. Available:https://doi.org/10.1061/40499(2000)126

Blaney HF. Determining water requirements in irrigated areas from climatological and irrigation data; 1952.

Naganna SR, Beyaztas BH, Bokde N, Armanuos AM. On the evaluation of the gradient tree boosting model for groundwater level forecasting. Knowledge-Based Engineering and Sciences. 2020; 1(1):48–57.

Available:https://doi.org/10.51526/kbes.2020.1.01.48-57

Bhagat SK, Tiyasha T, Tung TM, Mostafa RR, Yaseen ZM. Manganese (Mn) removal prediction using extreme gradient model. Ecotoxicology and Environmental Safety. 2020;204:111059.

Bhagat SK, Tung TM, Yaseen Z. M. Heavy metal contamination prediction using ensemble model: Case study of Bay sedimentation, Australia. Journal of Hazardous Materials. 2021;403:123492. Available:https://doi.org/10.1016/j.jhazmat.2020.123492

Nagelkerke NJD. A note on a general definition of the coefficient of determination. Biometrika. 1991;78(3): 691–692.

Huffman GJ. Estimates of root-mean-square random error for finite samples of estimated precipitation. Journal of Applied Meteorology and Climatology. 1997;36 (9):1191–1201.

Wu L, Peng Y, Fan J, Wang Y. Machine learning models for the estimation of monthly mean daily reference evapotranspiration based on cross-station and synthetic data. Hydrology Research. 2019;0(6):1730-1750.