Convolutional neural networks for estimating spatially distributed evapotranspiration

Angel M. García-Pedrero; Consuelo Gonzalo-Martín; Mario F. Lillo-Saavedra; Dionisio Rodriguéz-Esparragón; Ernestina Menasalvas

doi:10.1117/12.2278321

Translator Disclaimer

4 October 2017 Convolutional neural networks for estimating spatially distributed evapotranspiration

Angel M. García-Pedrero, Consuelo Gonzalo-Martín, Mario F. Lillo-Saavedra, Dionisio Rodriguéz-Esparragón, Ernestina Menasalvas

Author Affiliations +

Proceedings Volume 10427, Image and Signal Processing for Remote Sensing XXIII; 104270P (2017) https://doi.org/10.1117/12.2278321
Event: SPIE Remote Sensing, 2017, Warsaw, Poland

Abstract

Efficient water management in agriculture requires an accurate estimation of evapotranspiration (ET). There are available several balance energy surface models that provide a daily ET estimation (ET_d) spatially and temporarily distributed for different crops over wide areas. These models need infrared thermal spectral band (gathered from remotely sensors) to estimate sensible heat flux from the surface temperature. However, this spectral band is not available for most current operational remote sensors. Even though the good results provided by machine learning (ML) methods in many different areas, few works have applied these approaches for forecasting distributed ET_d on space and time when aforementioned information is missing. However, these methods do not exploit the land surface characteristics and the relationships among land covers producing estimation errors. In this work, we have developed and evaluated a methodology that provides spatial distributed estimates of ET_d without thermal information by means of Convolutional Neural Networks.

Citation Download Citation

Angel M. García-Pedrero, Consuelo Gonzalo-Martín, Mario F. Lillo-Saavedra, Dionisio Rodriguéz-Esparragón, and Ernestina Menasalvas "Convolutional neural networks for estimating spatially distributed evapotranspiration", Proc. SPIE 10427, Image and Signal Processing for Remote Sensing XXIII, 104270P (4 October 2017); https://doi.org/10.1117/12.2278321

ACCESS THE FULL ARTICLE