skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Upscaling instantaneous to daily evapotranspiration using modelled daily shortwave radiation for remote sensing applications: An artificial neural network approach

Abstract

Upscaling instantaneous evapotranspiration retrieved at any specific time-of-day (ET i) to daily evapotranspiration (ET d) is a key challenge in mapping regional ET using polar orbiting sensors. Various studies have unanimously cited the shortwave incoming radiation ( R S) to be the most robust reference variable explaining the ratio between ET d and ET i. This study aims to contribute in ET i upscaling for global studies using the ratio between daily and instantaneous incoming shortwave radiation ( R Sd/ R Si) as a factor for converting ET i to ET d. This paper proposes an artificial neural network (ANN) machine-learning algorithm first to predict R Sd from R Si followed by using the R Sd/ R Si ratio to convert ET i to ET d across different terrestrial ecosystems. Using R Si and R Sd observations from multiple sub-networks of the FLUXNET database spread across different climates and biomes (to represent inputs that would typically be obtainable from remote sensors during the overpass time) in conjunction with some astronomical variables (e.g. solar zenith angle, day length, exoatmospheric shortwave radiation), we developed the ANN model for reproducing R Sd and further used it to upscale ET i to ET d.more » The efficiency of the ANN is evaluated for different morning and afternoon times of day, under varying sky conditions, and also at different geographic locations. R S-based upscaled ET d produced a significant linear relation ( R 2 = 0.65 to 0.69), low bias (-0.31 to -0.56 MJ m -2 d -1; approx. 4 %), and good agreement (RMSE 1.55 to 1.86 MJ m -2 d -1; approx. 10 %) with the observed ET d, although a systematic overestimation of ET d was also noted under persistent cloudy sky conditions. Inclusion of soil moisture and rainfall information in ANN training reduced the systematic overestimation tendency in predominantly overcast days. An intercomparison with existing upscaling method at daily, 8-day, monthly, and yearly temporal resolution revealed a robust performance of the ANN-driven R S-based ET i upscaling method and was found to produce lowest RMSE under cloudy conditions. Sensitivity analysis revealed variable sensitivity of the method to biome selection and high ET d prediction errors in forest ecosystems are primarily associated with greater rainfall and cloudiness. As a result, the overall methodology appears to be promising and has substantial potential for upscaling ET i to ET d for field and regional-scale evapotranspiration mapping studies using polar orbiting satellites.« less

Authors:
ORCiD logo [1];  [2];  [3];  [4];  [5]; ORCiD logo [6]
  1. Luxembourg Institute of Science and Technology, Belvaux (Luxembourg); Univ. of Twente, Enschede (The Netherlands)
  2. Luxembourg Institute of Science and Technology, Belvaux (Luxembourg)
  3. Univ. College Cork, Cork (Ireland)
  4. CIRAD, Montpellier (France); Centro Agronomico Tropical de Investigacion y Ensenanza, Cartago (Costa Rica)
  5. Swedish Univ. of Agricultural Sciences, Umea (Sweden)
  6. Consiglio Nazionale delle Ricerche, Naples (Italy)
Publication Date:
Research Org.:
Oregon State Univ., Corvallis, OR (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Biological and Environmental Research (BER) (SC-23)
OSTI Identifier:
1362030
Grant/Contract Number:
FG02-04ER63917; FG02-04ER63911
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
Hydrology and Earth System Sciences (Online)
Additional Journal Information:
Journal Name: Hydrology and Earth System Sciences (Online); Journal Volume: 21; Journal Issue: 1; Journal ID: ISSN 1607-7938
Publisher:
European Geosciences Union (EGU)
Country of Publication:
United States
Language:
English
Subject:
54 ENVIRONMENTAL SCIENCES; 97 MATHEMATICS AND COMPUTING

Citation Formats

Wandera, Loise, Mallick, Kaniska, Kiely, Gerard, Roupsard, Olivier, Peichl, Matthias, and Magliulo, Vincenzo. Upscaling instantaneous to daily evapotranspiration using modelled daily shortwave radiation for remote sensing applications: An artificial neural network approach. United States: N. p., 2017. Web. doi:10.5194/hess-21-197-2017.
Wandera, Loise, Mallick, Kaniska, Kiely, Gerard, Roupsard, Olivier, Peichl, Matthias, & Magliulo, Vincenzo. Upscaling instantaneous to daily evapotranspiration using modelled daily shortwave radiation for remote sensing applications: An artificial neural network approach. United States. doi:10.5194/hess-21-197-2017.
Wandera, Loise, Mallick, Kaniska, Kiely, Gerard, Roupsard, Olivier, Peichl, Matthias, and Magliulo, Vincenzo. Wed . "Upscaling instantaneous to daily evapotranspiration using modelled daily shortwave radiation for remote sensing applications: An artificial neural network approach". United States. doi:10.5194/hess-21-197-2017. https://www.osti.gov/servlets/purl/1362030.
@article{osti_1362030,
title = {Upscaling instantaneous to daily evapotranspiration using modelled daily shortwave radiation for remote sensing applications: An artificial neural network approach},
author = {Wandera, Loise and Mallick, Kaniska and Kiely, Gerard and Roupsard, Olivier and Peichl, Matthias and Magliulo, Vincenzo},
abstractNote = {Upscaling instantaneous evapotranspiration retrieved at any specific time-of-day (ETi) to daily evapotranspiration (ETd) is a key challenge in mapping regional ET using polar orbiting sensors. Various studies have unanimously cited the shortwave incoming radiation (RS) to be the most robust reference variable explaining the ratio between ETd and ETi. This study aims to contribute in ETi upscaling for global studies using the ratio between daily and instantaneous incoming shortwave radiation (RSd/RSi) as a factor for converting ETi to ETd. This paper proposes an artificial neural network (ANN) machine-learning algorithm first to predict RSd from RSi followed by using the RSd/RSi ratio to convert ETi to ETd across different terrestrial ecosystems. Using RSi and RSd observations from multiple sub-networks of the FLUXNET database spread across different climates and biomes (to represent inputs that would typically be obtainable from remote sensors during the overpass time) in conjunction with some astronomical variables (e.g. solar zenith angle, day length, exoatmospheric shortwave radiation), we developed the ANN model for reproducing RSd and further used it to upscale ETi to ETd. The efficiency of the ANN is evaluated for different morning and afternoon times of day, under varying sky conditions, and also at different geographic locations. RS-based upscaled ETd produced a significant linear relation (R2 = 0.65 to 0.69), low bias (-0.31 to -0.56 MJ m-2 d-1; approx. 4 %), and good agreement (RMSE 1.55 to 1.86 MJ m-2 d-1; approx. 10 %) with the observed ETd, although a systematic overestimation of ETd was also noted under persistent cloudy sky conditions. Inclusion of soil moisture and rainfall information in ANN training reduced the systematic overestimation tendency in predominantly overcast days. An intercomparison with existing upscaling method at daily, 8-day, monthly, and yearly temporal resolution revealed a robust performance of the ANN-driven RS-based ETi upscaling method and was found to produce lowest RMSE under cloudy conditions. Sensitivity analysis revealed variable sensitivity of the method to biome selection and high ETd prediction errors in forest ecosystems are primarily associated with greater rainfall and cloudiness. As a result, the overall methodology appears to be promising and has substantial potential for upscaling ETi to ETd for field and regional-scale evapotranspiration mapping studies using polar orbiting satellites.},
doi = {10.5194/hess-21-197-2017},
journal = {Hydrology and Earth System Sciences (Online)},
number = 1,
volume = 21,
place = {United States},
year = {Wed Jan 11 00:00:00 EST 2017},
month = {Wed Jan 11 00:00:00 EST 2017}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Save / Share:
  • The main objective of present study is to predict daily global solar radiation (GSR) on a horizontal surface, based on meteorological variables, using different artificial neural network (ANN) techniques. Daily mean air temperature, relative humidity, sunshine hours, evaporation, and wind speed values between 2002 and 2006 for Dezful city in Iran (32 16'N, 48 25'E), are used in this study. In order to consider the effect of each meteorological variable on daily GSR prediction, six following combinations of input variables are considered: (I)Day of the year, daily mean air temperature and relative humidity as inputs and daily GSR as output.more » (II)Day of the year, daily mean air temperature and sunshine hours as inputs and daily GSR as output. (III)Day of the year, daily mean air temperature, relative humidity and sunshine hours as inputs and daily GSR as output. (IV)Day of the year, daily mean air temperature, relative humidity, sunshine hours and evaporation as inputs and daily GSR as output. (V)Day of the year, daily mean air temperature, relative humidity, sunshine hours and wind speed as inputs and daily GSR as output. (VI)Day of the year, daily mean air temperature, relative humidity, sunshine hours, evaporation and wind speed as inputs and daily GSR as output. Multi-layer perceptron (MLP) and radial basis function (RBF) neural networks are applied for daily GSR modeling based on six proposed combinations. The measured data between 2002 and 2005 are used to train the neural networks while the data for 214 days from 2006 are used as testing data. The comparison of obtained results from ANNs and different conventional GSR prediction (CGSRP) models shows very good improvements (i.e. the predicted values of best ANN model (MLP-V) has a mean absolute percentage error (MAPE) about 5.21% versus 10.02% for best CGSRP model (CGSRP 5)). (author)« less
  • An unfolding procedure is proposed which aims at obtaining spectral information of a neutron radiation field by the analysis of the response of a multi-element system consisting of converter type semiconductors. For the unfolding procedure an artificial neural network (feed forward network), trained by the back-propagation method, was used. The response functions of the single elements to neutron radiation were calculated by application of a computational model for an energy range from 10{sup {minus}2} eV to 10 MeV. The training of the artificial neural network was based on the computation of responses of a six-element system for a set ofmore » 300 neutron spectra and the application of the back-propagation method. The validation was performed by the unfolding of 100 computed responses. Two unfolding examples were pointed out for the determination of the neutron spectra. The spectra resulting from the unfolding procedure agree well with the original spectra used for the response computation.« less
  • Remote sensing data from the NOAA-11 AVHRR satellite were collected over the USDA-Agricultural Research Service Walnut Gulch Experimental Watershed in southeastern Arizona during the MONSOON 90 field campaigns. An energy balance model which relies primarily on remotely sensed inputs was used to extrapolate evapotranspiration (ET) estimates from one location containing near-surface meteorological data to other areas in the basin. Satisfactory results were obtained under a wide range of environmental conditions. However, the ET values are essentially instantaneous and therefore do not necessarily provide reliable estimates of daytime or daily ET fluxes required for many hydrological and resource management applications. Anmore » operational technique was developed to extrapolate one time of day ET estimates to daytime averages using the evaporative fraction concept and empirical methods for converting midday available energy to daytime average values. Model derived daytime average ET fluxes were in reasonable agreement with local ground-based measurements. The technique also was used to estimate daily ET at the basin scale.« less