Evaluación de redes neuronales convolucionales para la corrección de sesgos en estimaciones satelitales de precipitación

Autores/as

DOI:

https://doi.org/10.24215/1850468Xe050

Palabras clave:

estimación cuantitativa de precipitación, sensoramiento remoto, aprendizaje autom´atico

Resumen

La precipitación es altamente variable espacial y temporalmente, por lo cual su monitoreo es particularmente desafiante. Debido a la escasez de datos observados in-situ, se recurre a sensores remotos para poder estimar su valor. Sin embargo, dichas estimaciones, presentan sesgos que afectan su calidad. En este trabajo, se propone el uso de un modelo de redes neuronales convolucionales profundas de arquitectura U-Net, para corregir parcialmente los sesgos del algoritmo de estimación de precipitación del satélite GOES-16 en escalas de tiempo diezminutales y con resoluciones espaciales del orden del kilómetro. La red se entrena utilizando datos del radar meteorológico a bordo del satélite GPM. En particular, se evalúa el desempeño de las redes entrenadas con tres funciones de costo diferentes: el error cuadrático medio (ECM) y dos variaciones del ECM que buscan dar más relevancia a los eventos extremos. Los modelos basados en U-Net se comparan con la regresión por cuantiles PDF-Matching, que es una técnica ampliamente utilizada en la corrección de sesgos y con estimaciones de precipitación proveniente del producto PDIR-Now. El desempeño de todos los productos es evaluado con observaciones de estaciones pluviométricas automáticas en escalas subdiarias y diarias. La aplicación de los modelos U-Net sobre el GOES-RRQPE mejora aspectos de representación de valores extremos de precipitación, reduciendo el nivel de falsas alarmas. Sin embargo, comparado con estaciones meteorológicas automáticas, la representación de extremos es a expensas del detrimento en la precisión y generación de sesgos sistemáticos de sobreestimación.

Referencias

Alharbi, R., K. Hsu, y S. Sorooshian, 2018: Bias adjustment of satellite-based precipitation estimation using artificial neural networks-cloud classification system over Saudi Arabia. Arab. J. Geosci., 11, 508, https://doi.org/10.1007/s12517-018-3860-4

Andelsman, F., S. Masuelli, y F. Tamarit, 2023: Detection and classification of rainfall in South America using satellite images and machine learning techniques. Pap. Phys., 15, 150006-150006, https://doi.org/10.4279/pip.150006

Arkin, P. A., y B. N. Meisner, 1987: The Relationship between Large-Scale Convective Rainfall and Cold Cloud over the Western Hemisphere during 1982-84. Mon. Weather Rev., 115, 51-74, https://doi.org/10.1175/1520-0493(1987)115%3C0051:TRBLSC%3E2.0.CO;2

Catalini, C. G., A. F. Rico, C. M. Dasso, M. E. Capone, y N. Mortarino, 2016: Sistema de gestión de alertas. INA- CIRSA. http://hdl.handle.net/11086/553397

Colladon, L., y E. Vélez, 2011: Sistema de monitoreo automático de ríos en las Sierras de Córdoba. https://repositorio.ina.gob.ar/handle/123456789/206

Díaz, G. M., M. Vita, M. P. Hobouchian, L. J. Ferreira, y L. Giordano, 2021: Expansión de la red del SMN empleando los datos de precipitación de las estaciones meteorológicas automáticas de terceros. https://repositorio.smn.gob.ar/handle/20.500.12160/1541

Doswell, C. A., H. E. Brooks, y R. A. Maddox, 1996: Flash Flood Forecasting: An Ingredients-Based Methodology. Weather Forecast., 11, 560-581, https://doi.org/10.1175/1520-0434(1996)011%3C0560:FFFAIB%3E2.0.CO;2

Ebert, E. E., M. J. Manton, P. A. Arkin, R. J. Allam, G. E. Holpin, y A. Gruber, 1996: Results from the GPCP Algorithm Intercomparison Programme. Bull. Am. Meteorol. Soc., 77, 2875-2888, https://doi.org/10.1175/1520-0477(1996)077%3C2875:RFTGAI%3E2.0.CO;2

Ebert-Uphoff, I., R. Lagerquist, K. Hilburn, Y. Lee, K. Haynes, J. Stock, C. Kumler, y J. Q. Stewart, 2021: CIRA Guide to Custom Loss Functions for Neural Networks in Environmental Sciences -- Version 1. https://doi.org/10.48550/arXiv.2106.09757

Gao, J., G. Tang, y Y. Hong, 2017: Similarities and Improvements of GPM Dual-Frequency Precipitation Radar (DPR) upon TRMM Precipitation Radar (PR) in Global Precipitation Rate Estimation, Type Classification and Vertical Profiling. Remote Sens., 9, 1142, https://doi.org/10.3390/rs9111142

Gao, Y., T. Wu, J. Wang, y S. Tang, 2021: Evaluation of GPM Dual-Frequency Precipitation Radar (DPR) Rainfall Products Using the Rain Gauge Network over China. J. Hydrometeorol., 22, 547-559, https://doi.org/10.1175/JHM-D-20-0156.1

Gao, Y., J. Guan, F. Zhang, X. Wang, y Z. Long, 2022: Attention-Unet-Based Near-Real-Time Precipitation Estimation from Fengyun-4A Satellite Imageries. Remote Sens., 14, 2925, https://doi.org/10.3390/rs14122925

Gonzales, R. C., y B. A. Fittes, 1977: Gray-level transformations for interactive image enhancement. Mech. Mach. Theory, 12, 111-122, https://doi.org/10.1016/0094-114X(77)90062-3

Gorooh, V. A., A. A. Asanjan, P. Nguyen, K. Hsu, y S. Sorooshian, 2022: Deep Neural Network High Spatiotemporal Resolution Precipitation Estimation (Deep-STEP) Using Passive Microwave and Infrared Data. J. Hydrometeorol., 23, 597-617, https://doi.org/10.1175/JHM-D-21-0194.1

Guglielmetti, I., 2025: Diseño e implementación de controles de calidad para registros de lluvia de alta frecuencia de estaciones meteorológicas automáticas. Universidad de Buenos Aires. https://hdl.handle.net/20.500.12110/seminario_nATM000029_Guglielmetti

Hapuarachchi, H. a. P., Q. J. Wang, y T. C. Pagano, 2011: A review of advances in flash flood forecasting. Hydrol. Process., 25, 2771-2784, https://doi.org/10.1002/hyp.8040

Hobouchian, M. P., y otros, 2021: Ajuste de la estimación de precipitación satelital IMERG con observaciones pluviométricas en Argentina. https://repositorio.smn.gob.ar/handle/20.500.12160/1694

Hsu, K.-L., N. Karbalee, y D. Braithwaite, 2020: Improving PERSIANN-CCS Using Passive Microwave Rainfall Estimation. Satellite Precipitation Measurement: Volume 1, V. Levizzani, C. Kidd, D.B. Kirschbaum, C.D. Kummerow, K. Nakamura, y F.J. Turk, Eds., Springer International Publishing, pp. 375-391, https://doi.org/10.1007/978-3-030-24568-9_21

Huffman, G. J., y otros, 2020: NASA Global Precipitation Measurement (GPM) Integrated Multi-satellitE Retrievals for GPM (IMERG). Algorithm Theoretical Basis Document, version 06. https://gpm.nasa.gov/resources/documents/gpm-integrated-multi-satellite-retrievals-gpm-imerg-algorithm-theoretical-basis-

Hunt, K. M. R., 2025: Stop using root-mean-square error as a precipitation target!, https://doi.org/10.48550/arXiv.2509.08369

Ji, X., X. Song, A. Guo, K. Liu, H. Cao, y T. Feng, 2024: Oceanic Precipitation Nowcasting Using a UNet-Based Residual and Attention Network and Real-Time Himawari-8 Images. Remote Sens., 16, 2871, https://doi.org/10.3390/rs16162871

Katiraie-Boroujerdy, P.-S., M. Rahnamay Naeini, A. Akbari Asanjan, A. Chavoshian, K. Hsu, y S. Sorooshian, 2020: Bias Correction of Satellite-Based Precipitation Estimations Using Quantile Mapping Approach in Different Climate Regions of Iran. Remote Sens., 12, 2102, https://doi.org/10.3390/rs12132102

Kidd, C., D. R. Kniveton, M. C. Todd, y T. J. Bellerby, 2003: Satellite Rainfall Estimation Using Combined Passive Microwave and Infrared Algorithms. J. Hydrometeorol., 4, 1088-1104, https://doi.org/10.1175/1525-7541(2003)004%3C1088:SREUCP%3E2.0.CO;2

Kidd C., A. Becker, G. J. Huffman, C. L. Muller, P. Joe, G. Skofronick-Jackson, y D. B. Kirschbaum, 2017: So, How Much of the Earth’s Surface Is Covered by Rain Gauges? Bull. Am. Meteorol. Soc., 98, 69-78, https://doi.org/10.1175/BAMS-D-14-00283.1

Ko, J., K. Lee, H. Hwang, S.-G. Oh, S.-W. Son, y K. Shin, 2022: Effective Training Strategies for Deep-learning-based Precipitation Nowcasting and Estimation. Comput. Geosci., 161, 105072, https://doi.org/10.1016/j.cageo.2022.105072

Koenker, R., y G. Bassett, 1978: Regression Quantiles. Econometrica, 46, 33-50, https://doi.org/10.2307/1913643

Kuligowski, R. J., 2020: GOES-R Advanced Baseline Imager (ABI) Algorithm Theoretical Basis Document For Rainfall Rate (QPE). https://www.star.nesdis.noaa.gov/goesr/documents/ATBDs/Enterprise/ATBD_Enterprise_Rainfall_Rate_v3_2020-07-10.pdf

Lasser, M., S. O, y U. Foelsche, 2019: Evaluation of GPM-DPR precipitation estimates with WegenerNet gauge data. Atmospheric Meas. Tech., 12, 5055-5070, https://doi.org/10.5194/amt-12-5055-2019

Lebedev, V., y otros, 2019: Precipitation Nowcasting with Satellite Imagery. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2680-2688, https://doi.org/10.1145/3292500.3330762

Li, X., y otros, 2021: Leveraging machine learning for quantitative precipitation estimation from Fengyun-4 geostationary observations and ground meteorological measurements. Atmospheric Meas. Tech., 14, 7007-7023, https://doi.org/10.5194/amt-14-7007-2021

Mega, T., T. Ushio, M. Takahiro, T. Kubota, M. Kachi, y R. Oki, 2019: Gauge-Adjusted Global Satellite Mapping of Precipitation. IEEE Trans. Geosci. Remote Sens., 57, 1928-1935, https://doi.org/10.1109/TGRS.2018.2870199

Negri, P., A. Silvarrey, S. Gonzalez, J. Ruiz, y L. Vidal, 2025: Remote-Sensing Based Precipitation Detection Using Conditional GAN and Recurrent Neural Networks. Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, R. Hernández-García, R.J. Barrientos, y S.A. Velastin, Eds., Cham, Springer Nature Switzerland, 135-150, https://doi.org/10.1007/978-3-031-76604-6_10

Negri, P., D. Acevedo, J. Ruiz, S. Gonzalez, L. Vidal, A. Silvarrey, y M. G. Nicora, 2026: Enhancing precipitation detection: A multi-sensor approach using conditional GANs and recurrent networks. Pattern Recognit. Lett., 200, 150-157, https://doi.org/10.1016/j.patrec.2025.05.022

Nguyen, P., y otros, 2020: PERSIANN Dynamic Infrared–Rain Rate (PDIR-Now): A Near-Real-Time, Quasi-Global Satellite Precipitation Dataset. J. Hydrometeorol., 21, 2893-2906, https://doi.org/10.1175/JHM-D-20-0177.1

Petracca, M., L. P. D’Adderio, F. Porcù, G. Vulpiani, S. Sebastianelli, y S. Puca, 2018: Validation of GPM Dual-Frequency Precipitation Radar (DPR) Rainfall Products over Italy. J. Hydrometeorol., 19, 907-925, https://doi.org/10.1175/JHM-D-17-0144.1

Pfreundschuh, S., I. Ingemarsson, P. Eriksson, D. A. Vila, y A. J. P. Calheiros, 2022: An improved near-real-time precipitation retrieval for Brazil. Atmospheric Meas. Tech., 15, 6907-6933, https://doi.org/10.5194/amt-15-6907-2022

Qi, D., y A. J. Majda, 2020: Using machine learning to predict extreme events in complex systems. Proc. Natl. Acad. Sci., 117, 52-59, https://doi.org/10.1073/pnas.1917285117

Roberts, N. M., y H. W. Lean, 2008: Scale-Selective Verification of Rainfall Accumulations from High-Resolution Forecasts of Convective Events. Mon. Weather Rev., 136, 78-97, https://doi.org/10.1175/2007MWR2123.1

Romatschke, U., y R. A. Houze, 2010: Extreme Summer Convection in South America. J. Clim., 23, 3761-3791, https://doi.org/10.1175/2010JCLI3465.1

Ronneberger, O., P. Fischer, y T. Brox, 2015: U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, N. Navab, J. Hornegger, W.M. Wells, y A.F. Frangi, Eds., Cham, Springer International Publishing, 234-241, https://doi.org/10.1007/978-3-319-24574-4_28

Sadeghi, M., A. A. Asanjan, M. Faridzad, P. Nguyen, K. Hsu, S. Sorooshian, y D. Braithwaite, 2019: PERSIANN-CNN: Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks–Convolutional Neural Networks. J. Hydrometeorol., 20, 2273-2289, https://doi.org/10.1175/JHM-D-19-0110.1

Sadeghi, M., P. Nguyen, K. Hsu, y S. Sorooshian, 2020: Improving near real-time precipitation estimation using a U-Net convolutional neural network and geographical information. Environ. Model. Softw., 134, 104856, https://doi.org/10.1016/j.envsoft.2020.104856

Salio, P., M. Nicolini, y E. J. Zipser, 2007: Mesoscale Convective Systems over Southeastern South America and Their Relationship with the South American Low-Level Jet. Mon. Weather Rev., 135, 1290-1309, https://doi.org/10.1175/MWR3305.1

Scofield, R. A., y R. J. Kuligowski, 2003: Status and Outlook of Operational Satellite Precipitation Algorithms for Extreme-Precipitation Events. Weather Forecast., 18, 1037-1051, https://doi.org/10.1175/1520-0434(2003)018%3C1037:SAOOOS%3E2.0.CO;2

Seto, S., T. Iguchi, R. Meneghini, J. Awaka, T. Kubota, T. Masaki, y N. Takahashi, 2021: The Precipitation Rate Retrieval Algorithms for the GPM Dual-frequency Precipitation Radar. J. Meteorol. Soc. Jpn. Ser II, 99, 205-237, https://doi.org/10.2151/jmsj.2021-011

Shen, Y., P. Zhao, Y. Pan, y J. Yu, 2014: A high spatiotemporal gauge-satellite merged precipitation analysis over China. J. Geophys. Res. Atmospheres, 119, 3063-3075, https://doi.org/10.1002/2013JD020686

Siqueira, R. A. D., y D. Vila, 2019: Hybrid methodology for precipitation estimation using Hydro-Estimator over Brazil. Int. J. Remote Sens., 40, 4244-4263, https://doi.org/10.1080/01431161.2018.1562262

Uribe, I. M., 2019: Desempeño del algoritmo RRQPE del satélite GOES 16 para la estimación de lluvia en el estado de Nayarit tras el paso del huracán Willa. Ing. Rev. Académica Fac. Ing. Univ. Autónoma Yucatán, 23, 37-51. https://www.redalyc.org/journal/467/46760454004/html/

Wang, C., G. Tang, y P. Gentine, 2021: PrecipGAN: Merging Microwave and Infrared Data for Satellite Precipitation Estimation Using Generative Adversarial Network. Geophys. Res. Lett., 48, e2020GL092032, https://doi.org/10.1029/2020GL092032

Wang, F., D. Tian, y M. Carroll, 2023: Customized deep learning for precipitation bias correction and downscaling. Geosci. Model Dev., 16, 535-556, https://doi.org/10.5194/gmd-16-535-2023

Wilks, D. S., 1990: Maximum Likelihood Estimation for the Gamma Distribution Using Data Containing Zeros. J. Clim., 3, 1495-1501, https://doi.org/10.1175/1520-0442(1990)003%3C1495:MLEFTG%3E2.0.CO;2

Xie, P., y A.-Y. Xiong, 2011: A conceptual model for constructing high-resolution gauge-satellite merged precipitation analyses. J. Geophys. Res. Atmospheres, 116, https://doi.org/10.1029/2011JD016118

Xie, P., R. Joyce, S. Wu, S.-H. Yoo, Y. Yarosh, F. Sun, y R. Lin, 2017: Reprocessed, Bias-Corrected CMORPH Global High-Resolution Precipitation Estimates from 1998. J. Hydrometeorol., 18, 1617-1641, https://doi.org/10.1175/JHM-D-16-0168.1

Descargas

Publicado

07-08-2026

Número

Sección

Artículos

Cómo citar

Gonzalez, S. H., Negri, P. A., Vidal, L., & Ruiz, J. J. (2026). Evaluación de redes neuronales convolucionales para la corrección de sesgos en estimaciones satelitales de precipitación. Meteorologica, e050. https://doi.org/10.24215/1850468Xe050