Improvement of reference evapotranspiration by considering time lag effect in back propagation neural network model

Jialiang Huang, Yuhong Guo, Xiyu Zuo, Xin Wang, Yifei Yao, Zhitao Zhang, Youzhen Xiang, Junying Chen

Abstract


Abstract: Accurate estimation of reference evapotranspiration (ET0) is of great significance for agriculture and climate irrigation systems.  However, the accuracy of estimated reference evapotranspiration using traditional methods are not ideal due to the presence of complicated nonlinear relationship between meteorological factors and reference evapotranspiration.  Given that, three pre-processed techniques including Pearson, Kendall and Spearman were performed to explore time lag effect between meteorological factors and reference evapotranspiration.  An imputation model for ET0 was proposed in the context of time-lag effect using modeling method of network (BP) and multiple linear regression (MLR).  Then, its estimation accuracy was compared with that from traditional model without considering time-lag effect to confirm influence of time-lag effect to estimated reference evapotranspiration.  The results showed that (1) ET0 lags behind the solar radiation (RS) for 10~20 minutes, but in advance in the air temperature (Ta) 120~150 minutes, relative humidity (RH) 90~140 minutes and wind speed (u2) 10~50 minutes; (2) In the estimated monthly ET0 BP model (R2 = 0.91) is better than MLR model (R2 = 0.86); (3) By considering time lag effect, MLR model and BP model can effectively be improved ET0 simulation accuracy, increasing 4% to 6% and 16% to 22%, but BP model is more preferable.  All our preliminary results throw light on time lag effect is one of the important variables of the application model simulation reference evapotranspiration.

Keywords: reference evapotranspiration; meteorological factors; back propagation neural network model; time lag effect

DOI: 10.33440/j.ijpaa.20220501.188

 

Citation: Huang J L, Guo Y H, Zuo X Y, Wang X, Yao Y F, Zhang Z T, Xiang Y Z, Chen J Y.  Improvement of reference evapotranspiration by considering time lag effect in back propagation neural network model.  Int J Precis Agric Aviat, 2022; 5(1): 10–20.


Full Text:

PDF

References


McCabe M F, Wood E F. Scale influences on the remote estimation of evapotranspiration using multiple satellite sensors. Remote Sensing of Environment, 2006, 105(4): 271–285. DOI: 10.1016/j.rse.2006.07.006.

Wang K, Dickinson R E. A review of global terrestrial evapotranspiration: Observation, modeling, climatology, and climatic variability. Reviews of Geophysics, 2012, 50(2). DOI: 10.1016/j.rse.2006.07.006.

Stöckle C O, Kjelgaard J, Bellocchi G. Evaluation of estimated weather data for calculating Penman-Monteith reference crop evapotranspiration. Irrigation science, 2004, 23(1): 39–46. DOI: 10.1007/s00271-004-0091-0.

Tabari H. Evaluation of reference crop evapotranspiration equations in various climates. Water resources management, 2010, 24(10): 2311–2337. DOI: 10.1007/s11269-009-9553-8.

Masoner J R, Stannard D I, Christenson S C. Differences in evaporation between a floating pan and class a pan on land 1. JAWRA Journal of the American Water Resources Association, 2008, 44(3): 552–561.

Yang C, Zhu Z, Tan L, et al. Analysis on evapotranspiration of maize field measured by Lysimeters in Huailai. Plateau Meteorol, 2015, 34(4): 1095–1106.

Drexler J Z, Snyder R L, Spano D, et al. A review of models and micrometeorological methods used to estimate wetland evapotranspiration. Hydrological processes, 2004, 18(11): 2071–2101. DOI: 10.1002/hyp.1462.

Allen R G, Pereira L S, Raes D, et al. Crop evapotranspiration-Guidelines for computing crop water requirements-FAO Irrigation and drainage paper 56. Fao, Rome, 1998, 300(9): D05109.

Jabloun M, Sahli A. Evaluation of FAO-56 methodology for estimating reference evapotranspiration using limited climatic data: Application to Tunisia. Agricultural water management, 2008, 95(6): 707–715. DOI: 10.1016/j.agwat.2010.09.005.

Valiantzas J D. Simple ET0 forms of Penman’s equation without wind

and/or humidity data. II: Comparisons with reduced set-FAO and other methodologies. Journal of Irrigation and Drainage Engineering, 2013, 139(1): 9–19.

Droogers P, Allen R G. Estimating reference evapotranspiration under inaccurate data conditions. Irrigation and drainage systems, 2002, 16(1): 33–45. DOI: 10.1023/A:1015508322413.

Cai J, Liu Y, Lei T, et al. Estimating reference evapotranspiration with the FAO Penman–Monteith equation using daily weather forecast messages. Agricultural and Forest Meteorology, 2007, 145(1-2): 22–35. DOI: 10.1016/j.agrformet.2007.04.012.

Allen R G, Pereira L S, Howell T A, et al. Evapotranspiration information reporting: I. Factors governing measurement accuracy. Agricultural Water Management, 2011, 98(6): 899–920. DOI: 10.1016/j.agwat.2010.12.015.

Zhang Q, Manzoni S, Katul G, et al. The hysteretic evapotranspiration—Vapor pressure deficit relation. Journal of Geophysical Research: Biogeosciences, 2014, 119(2): 125–140. DOI: 10.1002/2013jg002484.

Guo X, Shi J. Progress and trend of evapotranspiration research at home and abroad. Geological Review, 2019, 65(06): 1473–1486. DOI: 10.16509/j.georeview.2019.06.014. (in Chinese)

Doorenbos J. Guidelines for predicting crop water requirements. Food and Agriculture organization. Rome, Irrig. Drainage pap., 1975, 24.

Sabziparvar A A, Mirmasoudi S H, Tabari H, et al. ENSO teleconnection impacts on reference evapotranspiration variability in some warm climates of Iran. International Journal of Climatology, 2011, 31(11): 1710–1723. DOI: 10.1002/joc.2187.

Pearson K. Notes on the history of correlation. Biometrika, 1920, 13(1): 25–45.

Kendall M G. A new measure of rank correlation. Biometrika, 1938, 30(1/2): 81–93.

Spearman C. The proof and measurement of association between two things, 1961.

Draper N R, Smith H. Applied regression analysis. John Wiley & Sons, 1998.

Cui K, Jing X. Research on prediction model of geotechnical parameters based on BP neural network. Neural Computing and Applications, 2019,

(12): 8205–8215. DOI: 10.1007/s00521-018-3902-6.

Luo Z, Yang Y, Yang Shi. Spatial-temporal Characteristics of Reference Crop Evapotranspiration and Climatic Influence Factors in Chongqing. Water Saving Irrigation, 2012(10): 5–9. (in Chinese)

Zhang D, Liu X, Hong H. Assessing the effect of climate change on reference evapotranspiration in China. Stochastic Environmental Research and Risk Assessment, 2013, 27(8): 1871–1881. DOI: 10.1007/s00477-013-0723-0.

Zhao J, Xia H, Yue Q, et al. Spatiotemporal variation in reference evapotranspiration and its contributing climatic factors in China under future scenarios. International Journal of Climatology, 2020, 40(8): 3813–3831. DOI: 10.1002/joc.6429.

Di S, De-xin G, Feng-hui Y, et al. Time lag effect between poplar's sap flow velocity and microclimate factors in agroforestry system in west Liaoning Province. Yingyong Shengtai Xuebao, 2010, 21(11). DOI: 10.13287/j.1001-9332.2010.0426. (in Chinese)

Oguntunde P G, Van de Giesen N C, Vlek P L G, et al. Water flux in a cashew orchard during a wet-to-dry transition period: analysis of sap flow and eddy correlation measurements Earth Interactions, 2004, 8(15): 1–17. DOI: 10.1175/1087-3562(2004)8.

Bo X, Du T, Ding R, et al. Time lag characteristics of sap flow in seed-maize and their implications for modeling transpiration in an arid region of Northwest China. Journal of Arid Land, 2017, 9(4): 515–529. DOI: 10.1007/s40333-017-0024-4.

Liu X, Kang S, Li F. Simulation of artificial neural network model for trunk sap flow of Pyrus pyrifolia and its comparison with multiple-linear regression. Agricultural Water Management, 2009, 96(6): 939–945. DOI: 10.1016/j.agwat.2009.01.003.

Kisi O. The potential of different ANN techniques in evapotranspiration modeling. Hydrological Processes: An International Journal, 2008, 22(14): 2449–2460. DOI: 10.1002/hyp.6837.

Granata F. Evapotranspiration evaluation models based on machine learning algorithms—A comparative study. Agricultural Water Management, 2019, 217: 303–315. DOI: 10.1016/j.agwat.2019.03.015.

Fehrman B, Gess B, Jentzen A. Convergence rates for the stochastic gradient descent method for non-convex objective functions. Journal of Machine Learning Research, 2020, 21: 136.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.