Evaluación de los productos de evapotranspiración disponibles en Climate Engine y del algoritmo Support Vector Machine Regression con datos NASA Power

María Florencia Degano; Raúl Eduardo Rivas

doi:10.59069/24225703ee005

Authors

María Florencia Degano Consejo Nacional de Investigaciones Científicas y Técnicas, Argentina. Instituto de Hidrología de Llanuras, Tandil, Buenos Aires, Argentina https://orcid.org/0000-0002-8365-6085
Raúl Eduardo Rivas Instituto de Hidrología de Llanuras, Tandil, Buenos Aires, Argentina. Comisión de Investigaciones Científicas de la provincia de Buenos Aires, Argentina https://orcid.org/0000-0002-3027-5529

DOI:

https://doi.org/10.59069/24225703ee005

Keywords:

artificial intelligence , reanalysis products , satellite products

Abstract

The hydrological country management depends, on the knowledge of the existing basins, their potential and to adequately manage water surpluses. In this sense, the study and analysis of reference (ET₀), actual and potential (ETp) evapotranspiration (ET) is to vital importance. Therefore, it is essential to evaluate the behavior of the different ET products that are freely available for use. Therefore, the main work objective is to analyze the data of the existing models in the Climate Engine platform (TerraClimate, ERA 5, MERRA-2 and MOD16A2), which has data at different temporal and spatial scales. In addition, to evaluate the artificial intelligence Support Vector Machine Regression (SVR) algorithm, determined with parameters obtained from NASA Power, with local data in the Argentinean Pampean region (APR). In general, errors between 0.5 and 1.2 mm d-1 and Nash-Sutcliffe Efficiency Index (NSE) values between 0.6 and 0.9 (ET₀); between 0.4 and 0.7 for actual ET and between 0.6 and 0.9 for ETp were obtained. Likewise, it is demonstrated that the most favorable model for the calculation of ET₀ as real ET is SVR, while for ETp it is ERA 5.

References

Abatzoglou, J. T., Dobrowski, S. Z., Parks, S. A. y Hegewisch, K. C. (2018). TerraClimate, a high-resolution global dataset of monthly climate and climatic water balance from 1958-2015. Scientific Data, 5,170191. https://doi.org/10.1038/sdata.2017.191

Allen, R. G., Pereira, L. S., Raes, D. y Smith, M. (1998). Crop evapotranspiration-Guidelines for computing crop water requirements. FAO Irrigation and drainage paper Nº56. FAO.

Allen, R., Pereira, L., Howell, T. y Jensen, M. (2011). Evapotranspiration information reporting: I. Factors governing measurement accuracy. Agricultural Water Management, 98(6), 899-920. https://doi.org/10.1016/j.agwat.2010.12.015

Basualdo, A. (2011). Balance hídrico como herramienta de decisión. En S. Occhiuzzi, P. Mercuri y C. Pascale (Coords.), Herramientas para la evaluación y gestión del riesgo climático en el sector agropecuario (pp. 55-63). (1ª ed.). Ministerio de Agricultura, Ganadería y Pesca de la Nación.

Castañeda Calatayud, F. (2020). Análisis del potencial eólico en la Región de Aysén a partir del modelo ERA 5 REANALYSIS. Tesis de grado. Facultad de Ciencias Agronómicas, Universidad de Chile. https://repositorio.uchile.cl/handle/2250/183486

Chia, M. Y., Huang, Y. F., Koo, C. H. y Fung, K. F. (2020a). Recent advances in evapotranspiration estimation using artificial intelligence approaches with a focus on hybridization techniques—a review. Agronomy, 10(1), 101. https://doi.org/10.3390/agronomy10010101.

Chia, M. Y., Huang, Y. F. y Koo, C. H. (2020b). Support vector machine enhanced empirical reference evapotranspiration estimation with limited meteorological parameters. Computers and Electronics in Agriculture, 175, 105577. https://doi.org/10.1016/j.compag.2020.105577

Copernicus Climate Change Service (C3S). (2017). ERA5: Fifth generation of ECMWF atmospheric reanalyses of the global climate. Copernicus Climate Change Service Climate Data Store (CDS), date of access. https://cds.climate.copernicus.eu/

Cristianini, N. y Shawe-Taylor, J. (2000). An introduction to support vector machines and other kernel-based learning methods. Cambridge University press.

Degano, M. F., Rivas, R. E. y Bayala, M. I. (2023). Determinación de la evapotranspiración con datos satelitales y de reanálisis utilizando Google Earth Engine. Tecnología y Ciencias del Agua. https://doi.org/10.24850/j-tyca-15-4-4

Degano, M. F., Rivas, R. E., Carmona, F., Faramiñán, A. M. G. y Olivera Rodríguez, P. S. (2021a). Calibración del producto de evapotranspiración potencial “MOD16A2” para la Región Pampeana Argentina. Boletín Geológico y Minero de España, 132(1-2), 167-174. https://doi.org/10.21701/bolgeomin.132.1-2.017

Degano, M. F., Rivas, R. E., Carmona, F., Niclòs, R. y Sánchez, J. M. (2021b). Evaluation of the MOD16A2 evapotranspiration product in an agricultural area of Argentina, the Pampas region. The Egyptian Journal of Remote Sensing and Space Science, 24(2), 319-328. https://doi.org/10.1016/j.ejrs.2020.08.004

Fan, J., Yue, W., Wu, L., Zhang, F., Cai, H., Wang, X., Lu, X. y Xiang, Y. (2018). Evaluation of SVM, ELM and four tree-based ensemble models for predicting daily reference evapotranspiration using limited meteorological data in different climates of China. Agricultural and Forest Meteorology, 263, 225-241. https://doi.org/10.1016/j.agrformet.2018.08.019

Faramiñán A. M. G. (2022). Estudio de la evapotranspiración y su aporte en el desarrollo de modelos por medio de medidas directas e inteligencia artificial. Tesis doctoral. Facultad de Ciencias Exactas, Universidad Nacional del Centro de la provincia de Buenos Aires.

Faramiñán, A. M. G., Carmona, F., Rivas, R. E., Degano, M. F. y Abadie, P. A. (2021a). Monitoreo de la evapotranspiración real horaria por medio del balance energético y un lisímetro de pesada. Boletín Geológico y Minero de España, 132(1-2), 47-56 . http://hdl.handle.net/11336/164282

Faramiñán, A. M., Degano, M. F., Carmona, F. y Rodriguez, P. O. (2021 b). Estimation of actual evapotranspiration using NASA-POWER data and Support Vector Machine. En 2021 XIX Workshop on Information Processing and Control (RPIC) (pp. 1-5). IEEE. http://dx.doi.org/10.1109/RPIC53795.2021.9648425

Gelaro, R., McCarty, W., Suárez, M.J., Todling, R., Molod, A., Takacs, L., Randles, C., Darmenov, A., Bosilovich, M.G., Reichle, R., Wargan, K., Coy, L., Cullather, R., Draper, C., Akella, S., Buchard, V., Conaty, A., da Silva, A., Gu, W., .... y Zhao B. (2017). The modern-era retrospective analysis for research and applications, Version 2 (MERRA-2). Journal of Climate, 30(13), 5419–5454.

Hargreaves, G. H. y Samani, Z. A. (1985). Reference crop evapotranspiration from temperature. Applied Engineering in Agriculture, 1(2): 96-99. http://dx.doi.org/10.13031/2013.26773

Huntington, J. L., Hegewisch, K. C., Daudert, B., Morton, C. G., Abatzoglou, J. T., McEvoy, D. J. y Erickson, T. (2017). Climate engine: Cloud computing and visualization of climate and remote sensing data for advanced natural resource monitoring and process understanding. Bulletin of the American Meteorological Society, 98(11), 2397-2410. http://dx.doi.org/10.1175/BAMS-D-15-00324.1

Juarez, J., Trentin, G. y Heinen, M. (2018). Determinación de evapotranspiración de referencia a partir de modelos de inteligencia artificial. En X Congreso de AgroInformática (CAI)-JAIIO 47 (pp. 160-168). Sociedad Argentina de Informática e Investigación Operativa.

Liakos, K. G., Busato, P., Moshou, D., Pearson, S. y Bochtis, D. (2018). Machine learning in agriculture: A review. Sensors, 18(8), 2674. https://doi.org/10.3390/s18082674.

Lv, M., Xu, Z. y Lv, M. (2020). Evaluating hydrological processes of the atmosphere–vegetation interaction model and MERRA-2 at global scale. Atmosphere, 12(1), 16.

McCuen, R. H., Knight, Z. y Cutter, A. G. (2006). Evaluation of the Nash–Sutcliffe Efficiency index. Journal of Hydrologic Engineering, 11(6), 597–602. https://doi.org/10.1061/(ASCE)1084-0699(2006)11:6(597)

Monteith J. L. y Unsworth M. H. (1990). Principles of Environmental Physics. (2ª ed.). E. Arnold.

Mu, Q. Z., Zhao y M.S., Running, S. W. (2013). MODIS Global Terrestrial Evapotranspiration (ET) product (NASA MOD16A2/A3). Algorithm Theoretical Basis Document. Collection 5. NASA Headquarters. Numerical Terradynamic Simulation Group, 268. https://scholarworks.umt.edu/ntsg_pubs/268

Orte, F., Lusi, A., Carmona, F., D’Elia, R., Faramiñán, A. y Wolfram, E. (2021,). Comparison of NASA-POWER solar radiation data with ground-based measurements in the south of South America. En 2021 XIX Workshop on Information Processing and Control (RPIC) (pp. 1-4). IEEE. https://doi.org/10.1109/RPIC53795.2021.9648428

Pereyra, F. X. (2003). Ecoregiones de la Argentina. Servicio Geológico Minero Argentino. http://repositorio.segemar.gov.ar/308849217/2953

Ritter, A. y Muñoz-Carpena, R. (2013). Performance evaluation of hydrological models: Statistical significance for reducing subjectivity in goodness-of-fit assessments. Journal of Hydrology, 480, 33–45. https://doi.org/10.1016/j.jhydrol.2012.12.004

Ruhoff, A., de Andrade, B. C., Laipelt, L., Fleischmann, A. S., Siqueira, V. A., Moreira, A. A., Barbedo, R., Cyganski, G.L., Fernandez, G.M.R., Brêda, J.P.L.F., Paiva, R.C.D.d., Meller, A., Teixeira, A.d.A., Araújo, A.A., Fuckner, M.A., Biggs, T. (2022). Global Evapotranspiration Datasets Assessment Using Water Balance in South America. Remote Sensing, 14(11), 2526. https://doi.org/10.3390/rs14112526

Running, S. W., Mu, Q. Z. y Zhao, M. S. (2017). MOD16A2 MODIS/Terra Net Evapotranspiration 8-Day L4 Global 500m SIN Grid V006. NASA EOSDIS Land Processes DAAC, 6. https://doi.org/10.5067/MODIS/MOD16A2.006

Shrestha, N. K. y Shukla, S. (2015). Support vector machine based modeling of evapotranspiration using hydro-climatic variables in a sub-tropical environment. Agricultural and Forest Meteorology, 200, 172-184. https://doi.org/10.1016/j.agrformet.2014.09.025

Weinzettel P. y Usunoff E. (2001). Cálculo de la recarga mediante la aplicación de la ecuación de Darcy en la zona no saturada. En A. Medina, J. Carrera (Eds.), Las caras del agua subterránea. Tomo II (pp. 225–261). IGME.