Evaluation of spline and bezier interpolation functions in reference evapotranspiration modeling using satellite image data

Document Type : Research/Original/Regular Article

Authors

1 P.hD. student, Department of Water Engineering, Faculty of Agriculture, University of Tabriz, Tabriz, Iran

2 Assoc. Professor, Department of Water Engineering, Faculty of Agriculture, University of Tabriz

3 Professor, Department of Water Engineering, Faculty of Agriculture, University of Tabriz, Tabriz, Iran

Abstract

Introduction

Reference evapotranspiration is one of the important processes in the water cycle that has a great impact on water resources and agriculture. Climate change can affect this process and requires accurate spatial-temporal analysis. The standard method for calculating reference evapotranspiration is the FAO-56 Penman-Monteith method that requires meteorological data. But in some areas, there is not enough data and therefore other methods such as machine learning and remote sensing are used. These methods can estimate reference evapotranspiration with high accuracy using different variables such as vegetation indices, temperature, humidity, and wind speed. Some of these methods are random forest, support vector regression, generalized regression neural network, and gene expression programming. These methods can also help in assessing the importance of predictor variables and their uncertainties.

Materials and Methods

The aim of this article is to model daily reference evapotranspiration (ET0) using data collected from meteorological and satellite sources and implementing random forest (RF) algorithm. The standard FAO-Penman-Monteith method, which is based on the Penman-Monteith equation that integrates radiometric and aerodynamic parameters, was adopted as the base method for calculating ET0 of a reference crop. However, this method demands a large amount of meteorological data such as solar radiation, relative humidity, wind speed, and maximum/minimum temperature, which can be challenging to obtain. To overcome this limitation, satellite images from Google Earth Engine system for the years 2001 to 2021 were processed using Landsat and MODIS sensors to extract parameters such as land surface temperature (LST), enhanced vegetation index (EVI), leaf area index (LAI), and normalized difference vegetation index (NDVI). These parameters can be used to estimate effective evapotranspiration continuously in the short term by applying models and interpolations. One of the problems of planning and management based on satellite image data is the lack of daily images of the study area. One of the ways of time microscaling of this valuable information is interpolation. In other words, interpolation is a mathematical process that estimates unknown data at other points using data available at specific points. This process is used to fill in gaps, increase resolution, or create continuous maps from satellite data. The importance of satellite data interpolation is that it can help improve the quality and accuracy of data and use them to study and predict various meteorological, agricultural, geological, etc. phenomena. In this research, LST (8 days) and vegetation cover data (16 days) were converted into daily data using spline and cubic spline interpolation functions. This work has been done using spline and Bezier interpolation functions and for days without data with equal intervals by coding in Mathematica programming environment.

Results and Discussion

This research used satellite and meteorological data and the random forest machine learning method to estimate the ET0 at Tabriz and Ardabil stations. The results showed that the saturation vapor pressure and the land surface temperature at night and day had the highest correlation and coefficient of determination with the ET0. The highest accuracy of ET0 estimation at Tabriz was in scenario 10 with error of 0.364 and at Ardabil in scenario 12 with error of 0.430. The best model was the combination of meteorological and satellite parameters. The spline interpolation method provided a better modeling than the bezier method. Additionally, increasing the parameters involved in machine learning and the LAI parameter reduced the accuracy.

Douna et al. (2021) investigated the ability of the RF method to predict daily ET0 in three regions in Australia from 2010 to 2014, using satellite data of LAI and LST and regional meteorological parameters. They stated that the LAI is the most important variable, and they also obtained satisfactory performance in three regions, with RMSE errors of about 1 mm per day. At the same time, for Tabriz and Ardabil stations, the LST values were more important than the LAI and more correlated with ET0. Therefore, by combining meteorological and satellite data, the amount of RMSE errors was reduced to 0.364 and 0.430 mm in Spline and Bezier intyerpolation functions.

Conclusion

The results of the research showed that 1) at Tabriz station, among all meteorological parameters, saturation vapor pressure and among satellite parameters, land surface temperature at night had the highest correlation with daily ET0. 2) At Ardabil station, in the same time period, saturation vapor pressure also had the highest correlation of 0.887, but among satellite parameters, land surface temperature at day had the highest correlation of 0.737 with daily ET0. 3) The highest accuracy of daily ET0 estimation at Tabriz was in spline and random forest methods in scenario 10 with error of 0.364 and in bezier methods in scenarios 14 and 16 with error of 0.380. 4) At Ardabil station, both spline and bezier methods had the highest accuracy in scenario 12 with errors of 0.430 and 0.453, respectively. 5) In both spline and bezier interpolation methods, the most accurate model was the combination of meteorological and satellite parameters. 6) In general, spline interpolation method provided a better modeling than bezier. Increasing the parameters involved in machine learning, which were calculated using the available data, had no positive effect on the accuracy of the model. 7) Adding the LAI parameter, which was calculated using the EVI data, to the machine learning model, reduced the accuracy in spline method.

Keywords

Main Subjects


منابع
ابراهیمی‌پاک، نیازعلی، تافته، آرش، اگدرنژاد، اصلان، و اسدی کپورچال، صفورا (1397). تعیین ضرایب تبخیر تعرق ماهانه گندم زمستانه با استفاده از روش‌های مختلف تخمین تبخیر تعرق و تشت تبخیر در دشت قزوین. مهندسی آبیاری و آب، 32، 119-105.
احمدپری، هدیه، صفوی گردینی، مریم، و ابراهیمی، محبوبه (1398). انتخاب روش مناسب برآورد تبخیر تعرق مرجع در شرایط کمبود داده‌های هواشناسی (مطالعه موردی شهرستان خرمبید در استان فارس). مدیریت اراضی، 7(2)، 231-223. doi:10.22092/lmj.2019.120559.
خاری، دانیال، اگدرنژاد، اصلان و ابراهیمی پاک، نیازعلی. (1402). مقایسه مدل‌های هوش مصنوعی و مدل‌های تجربی در برآورد تبخیر و تعرق مرجع (مطالعه موردی: ایستگاه سینوپتیک رامهرمز). مدل‌سازی و مدیریت آب و خاک، 3(2)، 112-124. doi:10.22098/mmws.2022.11293.1117.
طالبی، حامد، صمدیان فرد، سعید و ولیزاده کامران، خلیل. (1402). روش جدید مبتنی بر تصاویر ماهواره لندست 8 و سنجنده مادیس برای تخمین تبخیر و تعرق مرجع ماهانه در دو اقلیم خشک و نیمه‌خشک. مدل‌سازی و مدیریت آب و خاک، 3(3)، 180-195. doi:10.22098/mmws.2023.12048.1198.
محمودی‌نژاد، وفا، هنربخش، افشین، عبدالهی، خدایار، و دیکارو، ماریو. (1403). ارزیابی روابط بین پارامترهای هواشناسی و تبخیر و تعرق واقعی با استفاده از رگرسیون و خوشه‏بندی سلسله مراتبی (مطالعه موردی: کستلوترانو ایتالیا). مدل‌سازی و مدیریت آب و خاک، 4(3)، 159-172. doi:10.22098/mmws.2023.12941.1289
 
 
References
Ahmadpari, H., Safavi Gerdini, M., & Ebrahimi, M. (2019) .An appropriate method for estimating potential evapotranspiration in the absence of meteorological data. Land Management Journal, 7(2), 223-231. doi:10.22092/lmj.2019.120559 [In Persian].
Allen, R., Pereira, L., Raes, D., & Smith. M. (1998). Crop evapotranspiration-Guidelines for computing crop water requirements-FAO Irrigation and drainage paper 56, FAO, Rome, 300: D05109.
Amirzehni, P., Samadianfard, S., Nazemi, A., & Sadraddini, A. (2023). Evaluating capabilities of the spline and cubic spline interpolation functions in reference evapotranspiration estimation implementing satellite image data. Earth Science Informatics, 1-17. doi:10.1007/s12145-023-01127-z.
Asadzadeh Sh., Raouf, H. & Mahmoudi Fard, G. (2015). Comparison of different methods of estimating evaporation and transpiration of the reference plant in Ardabil plain. The Second National Conference on the Protection of Natural Resources and Environment, University of Mohaghegh Ardabili.
Beu, T.A. (2015). Introduction to Numerical Programming. A Pratical Guide for Scientists and Engineers Using Python and C/C++, CRC Press, Taylor and Francis Group, Boca Raton, FL, USA.
Bhattarai N, Mallick K, Stuart J, Vishwakarma, B.D., Niraula, R., Sen S., & Jain, M. (2019). An automated multi-model evapotranspiration mapping framework using remotely sensed and reanalysis data. Remote Sensing of Environment, 229, 69-92. doi:10.1016/j.rse.2019.04.026.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32. doi:10.1023/a:1010933404324.
Cai, Y., Guan, K., Lobell, D., Potgieter, A., Wang, S., Peng, J., Xu, T., Asseng, S., Zhang, Y., You L. & Peng, B. (2019). Integrating satellite and climate data to predict wheat yield in Australia using machine learning approaches. Agricultural and Forest Meteorology, 274, 144-159. doi:10.1016/j.agrformet.2019.03.010.
Choi, J., Gu, B. & Chin, S. (2020). Machine learning predictive model based on national data for fatal accidents of construction workers. Automation in Construction, 110, 102974. doi:10.1016/j.autcon.2019.102974.
De Caceres, M., Martin-StPaul, N., Turco, M., Cabon, A. & Granda, V. (2018). Estimating daily meteorological data and downscaling climate models over landscapes. Environmental Modelling and Software, 108,186-196, doi:10.1016/j.envsoft.2018.08.003.
Dou, X. & Yang, Y. (2018). Evapotranspiration estimation using four different machine learning approaches in different terrestrial ecosystems. Computers and Electronics in Agriculture, 148, 95-106, doi:10.1016/j.compag.2018.03.010.
Douna V., Barraza, V., Grings, F., Huete, A., Restrepo-Coupe, N.& Beringer, J. (2021). Towards a remote sensing data based evapotranspiration estimation in Northern Australia using a simple random forest approach. Journal of Arid Environments, 191, 104513, doi:10.1016/j.jaridenv.2021.104513
Ebrahimipak, A., Tafteh, A., Egdarnejad, A., & Asadi Kapourchal, S. (2019). Determination of monthly evapotranspiration coefficients of winter wheat by different methods of estimating evapotranspiration and evaporation pan in Qazvin plain. Irrigation and Water Engineering, 32, 105-119. [In Persian]
Eslamian, S., Khordadi, M.J., & Abedi-Koupai, J. (2011). Effects of variations in climatic parameters on evapotranspiration in the arid and semi-arid regions. Global and Planetary Change, 78(3-4), 188-194. doi:10.1016/j.gloplacha.2011.07.001.
Fan, J., Wu, L., Zhang, F., Xiang, Y., & Zheng, J. (2016). Climate change effects on reference crop evapotranspiration across different climatic zones of China during 1956–2015. Journal of Hydrology, 542, 923-937. doi:10.1016/j.jhydrol.2016.09.060.
Fawzy, H. E.D., Sakr, A., El-Enany, M., & Moghazy, H.M. (2021). Spatiotemporal assessment of actual evapotranspiration using satellite remote sensing technique in the Nile Delta, Egypt. Alexandria Engineering Journal, 60(1), 1421-1432, doi:10.1016/j.aej.2020.11.001.
Feng, Y., Cui, N., Zhao, L., Hu, X., & Gong, D. (2016). Comparison of ELM, GANN, WNN and empirical models for estimating reference evapotranspiration in humid region of Southwest China. Journal of Hydrology, 536, 376-383. doi:10.1016/j.jhydrol.2016.02.053.
Frotan, M., & Salahi, B. (2023). Climatic zoning of Ardabil province using multivariate methods. Journal of Environmental Science Studies8(1), 6238-6247. doi: 10.22034/jess.2022.369206.1903.
Goyal, M.K., Gupta, A.K. & Gupta (Eds.), A. (2022). Hydro-Meteorological extremes and disasters, disaster resilience and green growth. Springer, Singapore.
Hu, X., Zhao, J., Sun, S., Jia, C., Zhang, F., Ma, Y., Wang, K., & Wang, Y. (2023). Evaluation of the temporal reconstruction methods for MODIS-based continuous daily actual evapotranspiration estimation. Agricultural Water Management, 275, 107991, doi: 10.1016/j.agwat.2022.107991.
Huang, G., Wu, L., Ma, X., Zhang, W., Fan, J., Yu, X., & Zhou, H. (2019). Evaluation of CatBoost method for prediction of reference evapotranspiration in humid regions. Journal of Hydrology, 574, 1029-1041. doi:10.1016/j.jhydrol.2019.04.085
Khari, D., Agderneghad, A., Ebrahimi Pak, N. A. (2023). Comparison of artificial intelligence models and empirical models in estimating reference evapotranspiration (case study: Ramhormoz synoptic station). Water and Soil Management and Modeling, 3(2), 112-124. doi:10.22098/mmws.2022.11293.1117 [In Persian]
Kim, N., Kim, K., Lee, S., Cho, J., & Lee, Y. (2020). Retrieval of daily reference evapotranspiration for croplands in South Korea using machine learning with satellite images and numerical weather prediction data. Remote Sensing, 12(21), 364. doi:10.3390/rs12213642.
Landeras, G., Ortiz-Barredo, A., & Javier López, J. (2008). Comparison of artificial neural network models and empirical and semi-empirical equations for daily reference evapotranspiration estimation in the Basque Country (Northern Spain). Agricultural Water Management, 95,553-564. doi:10.1016/j.agwat.2007.12.011.
Ling, X., Zhongqiu, L.an & Binbin, D. (2021). A Method for Predicting the Quality of Slabs Based on GA-RF Algorithm, IEEE 16th Conference on Industrial Electronics and Applications (ICIEA), Chengdu, China, 2021, pp. 1637-1642, doi: 10.1109/ICIEA51954.2021.9516413.
Mahmoudinezhad, V., Honarbakhsh, A., Abdollahi, K., & Decaro, D. (2024). Evaluation of relationships between meteorological parameters and actual evapotranspiration using regression and hierarchical clustering (case study: Castelvetrano, Italy). Water and Soil Management and Modeling, 4(3), 159-172. doi:10.22098/mmws.2023.12941.1289 [In Persian].
Sultan Abdullah, S., Malek, M.A., Sultan Abdullah, N., Kisi, O., & Siah Yap, K. (2015). Extreme Learning Machines: A new approach for prediction of reference evapotranspiration. Journal of Hydrology, 527, 184-195, doi:10.1016/j.jhydrol.2015.04.073.
Talebi, H., Samadianfard, S., & Kamran, K.V. (2023a). Investigating the roles of different extracted parameters from satellite images in improving the accuracy of daily reference evapotranspiration estimation. Applied Water Science, 13(2), 1-11. doi:10.1007/s13201-022-01862-6.
Talebi, H., Samadianfard, S., & Kamran, K.V. (2023b). A novel method based on Landsat 8 and MODIS satellite images to estimate monthly reference evapotranspiration in arid and semi-arid climates. Water and Soil Management and Modeling, 3(3),180-195. doi:10.22098/mmws.2023.12048.1198 [In Persian].
Wang, S., Lian, J., Peng, Y., Hu, B., & Chen, H. (2019). Generalized reference evapotranspiration models with limited climatic data based on random forest and gene expression programming in Guangxi, China. Agricultural Water Management, 221, 220-230. doi:10.1016/j.agwat.2019.03.027.
Yang, L., Feng, Q., Adamowski, J.F., Yin, Z., Wen, X., Wu, M., Jia, B., & Hao, Q. (2020). Spatio-temporal variation of reference evapotranspiration in northwest China based on CORDEX-EA. Atmospheric Research, 238,104868. doi:10.1016/j.atmosres.2020.104868.