, Volume 7, Issue 1, pp 103-111
Date: 18 Nov 2012

An artificial neural network approach to estimate evapotranspiration from remote sensing and AmeriFlux data

Rent the article at a discount

Rent now

* Final gross prices may vary according to local VAT.

Get Access


A simple and accurate method to estimate evapotranspiration (ET) is essential for dynamic monitoring of the Earth system at a large scale. In this paper, we developed an artificial neural network (ANN) model forced by remote sensing and AmeriFlux data to estimate ET. First, the ANN was trained with ET measurements made at 13 AmeriFlux sites and land surface products derived from satellite remotely sensed data (normalized difference vegetation index, land surface temperature and surface net radiation) for the period 2002–2006. ET estimated with the ANN was then validated by ET observed at five AmeriFlux sites during the same period. The validation sites covered five different vegetation types and were not involved in the ANN training. The coefficient of determination (R 2) value for comparison between estimated and measured ET was 0.77, the root-mean-square error was 0.62 mm/d, and the mean residual was − 0.28. The simple model developed in this paper captured the seasonal and interannual variation features of ET on the whole. However, the accuracy of estimated ET depended on the vegetation types, among which estimated ET showed the best result for deciduous broadleaf forest compared to the other four vegetation types.

Zhuoqi Chen obtained his bachelor degree in 2003 from Beijing Normal University, China and Ph.D. in Cartography and Geographic Information System from Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences in 2009. In 2009, he began to work as a Junior Researcher at College of Global Change and Earth System Science, Beijing Normal University. His research interest include: remote sensing applications in ecological model and hydrometeorology. Dr. Chen published 4 papers as first author or corresponding author.
Runhe Shi is an Associate Professor in the Department of Geography at East China Normal University, China. He is working at the Key Laboratory of Geographic Information Science, Ministry of Education, China, and serves as an Assistant Director. He obtained his B.S. in Geography from East China Normal University in 2001 and Ph.D. in Cartography and Geographic Information System from the Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences in 2006. His primary area of research is quantitative remote sensing including retrieval of plant biochemistry, greenhouse gases and particulate matters in the atmosphere. He has authored more than 50 refereed journal articles and conference papers. He is also the holder of two patents about data processing of remote sensing images.
Shupeng Zhang earned his Ph.D. in applied mathematics from Beijing Normal University, China in 2010. He has been working as a Junior Researcher for the college of global change and earth system science of Beijing Normal University since July 2010. His research fields focus on numerical solutions of partial differential equations, numerical simulations of fluids, atmospheric models and data assimilation.