Modelling of Reference Evapotranspiration using Neural Network and Regression Approaches for Semi-humid Region of Sikkim

G. T. Patle; B. P. Mandal; M. Kumar; D. Jhajharia

doi:10.52151/jae2023602.1808

Authors

G. T. Patle Assistant Professor, College of Agricultural Engineering and Post Harvest Technology, Central Agricultural University, Gangtok, Sikkim, India- 737135 Author
B. P. Mandal M.Tech. Scholar, College of Agricultural Engineering and Post Harvest Technology, Central Agricultural University, Gangtok, Sikkim, India- 737135 Author
M. Kumar Assistant Professor, Government College, Bahadurgarh, Haryana, India. Author
D. Jhajharia Professor, College of Agricultural Engineering and Post Harvest Technology, Central Agricultural University, Gangtok, Sikkim, India- 737135 Author

DOI:

https://doi.org/10.52151/jae2023602.1808

Keywords:

Artificial neural network, evapotranspiration, FAO-56 Penman Monteith equation, multiple linear regression, Sikkim, statistical indices

Abstract

This study compared the applicability of multiple linear regression (MLR) and artificial neural network (ANN) approaches for estimating the weekly reference evapotranspiration (ET0) in a semi-humid area of Tadong in Gangtok district of Sikkim state in India. Daily meteorological data (1991 - 2020) were used for developing MLR and ANN model using various combinations of meteorological data. Predicted ET0 values were compared with the FAO-56 Penman Monteith (PM) equation estimated ET0. The coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), and Nash Sutcliffe efficiency (NSE) were used to assess the performance of MLR and ANN models. For ANN model, one hidden layer and four neurons was found as the best ANN architecture. ANN-4 model with inputs parameters of maximum air temperature (Tmax), minimum air temperature (Tmin), maximum relative humidity (RHmax), minimum relative humidity (RHmin), and sunshine hours (SSH) had the smallest RMSE (0.609 mm.day-1 and 0.880 mm.day-1), MAE (0.473 mm.day-1 and 0.551mm.day-1) and the highest R2 (0.752 and 0.657) and NSE (0.782 and 0.696) during training and testing phases, respectively. The MLR-4 model with same combination of input parameters (Tmax, Tmin, RHmax, RHmin, SSH) resulted in smallest RMSE (0.704 mm.day-1 and 0.714 mm.day-1), MAE (0.562 mm.day-1and 0.583 mm.day-1); and the highest R2 (0.679 and 0.602) and NSE (0.708 and 0.597) during training and testing phase, respectively. Study also showed increase in model performance of ANN and MLR models with increase in number of meteorological parameters. All the ANN models gave comparable results, but ANN 4 model resulted in higher prediction accuracy for the sub-humid region of Tadong in Gangtok district of North-east India. The developed ANN-4 model could be helpful for preparing irrigation schedules and planning, and management of water resources in the data scarce northeast region of India and other identical climatic regions.

References

Ahmad L; Parvaze S; Parvaze S; Kanth R H. 2017. Reference evapotranspiration and crop water requirement of apple (Malus Pumila) in Kashmir Valley. J. Agrometeorol., 19 (3), 262-264.

Allen R G; Pereira L S; Raes D; Smith M. 1998. Crop evapotranspiration (guidelines for computing irrigation crop water requirement). Irrigation and Drainage paper no. 56, Food and Agriculture Organization, Rome, pp: 300.

Ayaz A; Rajesh M; Singh S K; Rehana S. 2021. Estimation of reference evapotranspiration using machine learning models with limited data. AIMS Geosci., 7(3), 268-290.

Chakravarti A; Joshi N; Panjiar H. 2015. Rainfall runoff analysis using artificial neural network. Indian J. Sci. Technol., 8(14), 54370. doi: 10.17485/ijst/2015/v8i14/54370.

Chouaib E H; Salwa B; Saïd K; Abdelghani C. 2022. Early estimation of daily reference evapotranspiration using machine learning techniques for efficient management of irrigation water. J. Phys. Conf. Ser., 2224 012006, 1-9. doi:10.1088/1742-6596/2224/1/012006.

Genaidy M A. 2020. Estimating of evapotranspiration using artificial neural network. Misr. J. Agric. Eng., 37 (1), 81 – 94. doi: 0.21608/MJAE.2020.94971

Islam A; Ahuja L; Garcia L A; Ma L; Saseendran A S; Trout T J. 2012a. Modeling the impacts of climate change on irrigated corn production in the Central Great Plains. Agric. Water Manage., 110, 94-108. https://doi.org/10.1016/j.agwat.2012.04.004

Islam A; Sikka A K; Saha B; Singh A. 2012b. Streamflow response to climate change in the Brahmani River basin, India. Water Resour. Manage., 26, 1409- 1424. https://doi.org/10.1007/s11269-011-9965-0

Jhajharia D; Dinpashoh Y; Kahya E; Singh V P. 2012. Trends in reference evapotranspiration in the humid region of northeast India. Hydrol. Proc., 26(3), 421 – 435. doi:10.1002/hyp.8140

Jyothi; Reddy G V S; Babu B M; Kulkarni P S; Ananda N. 2020. Artificial neural network models for estimation of potential evapotranspiration in a semi-arid region of Raichur, Karnataka. J. Agric. Eng., (India), 57(2), 172-181. doi: 10.52151/jae2020572.1713

Khan M Y A; Hasan F; Panwar S; Chakrapani G J. 2016. Neural network model for discharge and water-level prediction for Ramganga River catchment of Ganga Basin, India. Hydrol. Sci. J., 61(11), 2084- 2095. doi: 10.1080/02626667.2015.1083650

Khedkar D D; Singh P K; Bhakar S R. 2019. Estimation of evapotranspiration using neural network approach. J. Agrometeorol., 21(2), 233-235.

Kumar P; Sharma M C; Saini R; Singh G K. 2020. Climatic variability at Gangtok and Tadong weather observatories in Sikkim, India, during 1961–2017. Sci Rep 10, 15177. https://doi.org/10.1038/s41598-020-71163-y

Kumar S. 2017. Reference evapotranspiration (ETo) and irrigation water requirement of different crops in Bihar. J. Agrometeorol., 19 (3), 238-241.

Laaboudi A; Mouhouche B; Draoui B. 2012. Neural network approach to reference evapotranspiration modeling from limited climatic data in arid regions. Int. J. Biometeorol., 56(5), 831–841.

Litta A J; Idicula S M; Mohanty U C. 2013. Artificial neural network model in prediction of meteorological parameters during premonsoon thunderstorms. Int. J. Atm. Sci. 2013,, 1-14. https://doi.org/10.1155/2013/525383

Makwana J J; Deora B S; Parmar B S; Patel C K; Saini A K. 2022. Modelling of reference evapotranspiration using artificial neural network in semi-arid region of North Gujarat. J. Agric. Eng. (India), 59(2), 193-200. doi: 10.52151/jae2022592.1775

Mallikarjuna P; Kamasani C R. 2012. Daily reference evapotranspiration estimation using artificial neural networks. Hydrol. J., 35(1, 2), 19-27.

Marti P; Royuela A; Manzano J; Palau-Salvador G. 2010. Generalization of ET0 ANN models through data supplanting. J. Irrig Drain Eng., 136(3),161–174.

Mattar M A. 2018. Using gene expression programming in monthly reference evapotranspiration modelling: A case study in Egypt. Agric. Water Manage., 198, 28–38.

Mehdizadeh S; Mohammadi B; Pham Q B; Duan Z. 2021. Development of boosted machine learning models for estimating daily reference evapotranspiration and comparison with empirical approaches. Water, 13(24), 3489. doi.org/10.3390/w13243489

Nathan S; Saravanane N R; Sundararajan T. 2017. Application of ANN and MLR models on groundwater quality using CWQI at Lawspet, Puducherry in India. J. Geosci. Environ. Protect., 5, 99-124.

Ozgur K; Vahdettin D. 2016. Evapotranspiration estimation using six different multi-layer perception algorithms. Irrig. Drain. Syst. Eng., 5(2),1-6. doi:10.4172/2168-9768.1000164

Pandey P K; Dabral P P; Pandey V. 2016. Evaluation of reference evapotranspiration methods for the northeastern region of India. Int. Soil Water Conserv. Res., 4(1), 52-63. doi.org/10.1016/j.iswcr.2016.02.003

Patle G T; Singh D K. 2015. Sensitivity of annual and seasonal reference crop evapotranspiration to principal climatic variables. J. Earth Syst. Sci., 124(4), 819–828.

Patle G T; Sengdo D; Tapak M. 2020. Trends in major climatic parameters and sensitivity of evapotranspiration to climatic parameters in the eastern Himalayan region of Sikkim. Indian J. Water Clim. Change, 11 (2), 491-502.

Phad S V; Dakhore K K; Sayyad R S. 2019. Comparison of different methods for estimation of reference evapotranspiration at Parbhani, Maharashtra. J. Agrometeorol., 21(2), 236-238.

Poddar A; Gupta P; Kumar N; Shankar V; Ojha C S P. 2021. Evaluation of reference evapotranspiration methods and sensitivity analysis of climatic parameters for sub-humid sub-tropical locations in western Himalayas (India). ISH J. Hydraul. Eng., 27 (3), 336–346. doi.org/10.1080/09715010.2018.1551731

Rajendra P; Murthy K V N; Subbarao A. 2019. Use of ANN models in the prediction of meteorological data. Mod. Earth Syst. Environ., 5, 1051–1058. https://doi.org/10.1007/s40808-019-00590-2

Rajput J; Singh M; Lal K; Khanna M; Sarangi A; Mukherjee J; Singh S. 2023. Performance evaluation of soft computing techniques for forecasting daily reference evapotranspiration. J. Water Clim. Change, 14(1), 350-368. doi: 10.2166/wcc.2022.385

Ravindran S M; Bhaskaran S K M; Ambat S K N. 2021 A deep neural network architecture to model reference evapotranspiration using a single input meteorological parameter. Environ. Proc., 8 (4), 1567–1599.

Saggi M K; Jain S. 2019. Reference evapotranspiration estimation and modeling of the Punjab Northern India using deep learning. Comput. Electron. Agric., 156, 387–398.

Sharma N; Zakaullah M; Tiwari H. 2015. Runoff and sediment yield modelling using ANN and support vector machines: A case study from Nepal watershed. Model. Earth Syst. Environ., 23,1-8. doi. org/10.1007/s40808-015-0027-0

Singh A; Singh R M; Kumar A R S; Kumar A; Hanwat S; Tripathi V K. 2021. Evaluation of soft computing and regression-based techniques for the estimation of evaporation. J. Water Clim. Change, 12 (1), 32–43.

Singh R K; Mishra A K; Satapathy K K. 2001 Rainfall pattern at mid hills of Sikkim. Indian J. Hill Farming, 14 (2), 17–23.

Smith M; Allen R G; Monteith J L; Pereira L; Segeren A. 1991. Report of the Expert Consultation on Procedures for Revision of FAO Guidelines for Prediction of Crop Water Requirements. UN-FAO, Rome, pp: 60.

Sriram A V; Rashmi C N. 2014. Estimation of potential evapotranspiration by multiple linear regression method. IOSR J. Mech. Civil Eng., 11(2), 65-70.

Tiwari A K; De Maio M; Singh P K; Singh A K. 2016. Hydro geochemical characterization and groundwater quality assessment in a coal mining area, India. Arab. J. Geosci., 9, 1-17. doi.org/10.1007/ s12517-015-2209-5

Tomar A S. 2022. Evaluating the performance of calibrated temperature-based equations as compared to standard FAO-56 Penman Monteith equation in humid climatic condition of Dehradun (India). J. Agric. Eng. (India), 59(4), 386-403. doi: 10.52151/jae2022594.1790

Vyas K N; Subbaiah R. 2016. Application of artificial neural network approach for estimating reference evapotranspiration. Curr. World Environ., 11(2), 637- 647. doi.org/10.12944/CWE.11.2.36

Wu L; Peng Y; Fan J; Wang Y. 2019. Machine learning models for the estimation of monthly mean daily reference evapotranspiration based on cross-station and synthetic data. Hydrol. Res., 50(6), 1730- 1750.

Yassin M A; Alazba A A; Mattar M A. 2016. Artificial neural networks versus gene expression programming for estimating reference evapotranspiration in arid climate. Agric. Water Manage., 163(1), 110-124.

Yohanani E; Frisch A; Lukyanov V; Cohen S; Teite M; Tanny J. 2022. Estimating evapotranspiration of screenhouse banana plantations using artificial neural network and multiple linear regression models. Water, 14(7), 2-21. doi.org/10.3390/ w14071130

Zhao L; Zhao X; Zhou H; Wang X; Xing X. 2021. Prediction model for daily reference crop evapotranspiration based on hybrid algorithm and principal components analysis in Southwest China. Comput. Electron. Agric., 190,1-13. doi.org/10.1016/j.compag.2021.106424