An analog period method for gap‐filling of latent heat flux measurements

2021 ◽  
Author(s):  
Lucas Emilio B. Hoeltgebaum ◽  
Nelson Luís Dias ◽  
Marcelo Azevedo Costa
Keyword(s):  
Heat Flux ◽  
Latent Heat ◽  
Latent Heat Flux ◽  
Gap Filling ◽  
Flux Measurements

scholarly journals ESTIMATIVA DE FLUXO DE CALOR LATENTE EM RESERVATÓRIOS ATRAVÉS DE UMA REDE NEURAL ARTIFICIAL

2016 ◽  
Vol 38 ◽  
pp. 361
Author(s):  
Dornelles Vissotto Junior ◽  
Lucas Emílio Bernardelli Hoeltgebaum ◽  
Ricardo Carvalho de Almeida
Keyword(s):  
Heat Flux ◽  
Latent Heat ◽  
Latent Heat Flux ◽  
Heat Fluxes ◽  
Transfer Model ◽  
Ann Model ◽  
Gap Filling ◽  
Flux Measurements ◽  
Index Of Agreement ◽  
Artificial Neural Network Ann

Micrometeorology monitoring has been used in reservoirs for latent heat flux measurements by eddy covariance. It is hard to establish long and continuous measurement datasets due to the complexity involved in this monitoring. When fails occur there is necessary a gap filling procedure to keep the continuity of the series. This filling could be performed through statistical techniques and use of model results. In this work we assessed the performance of a backpropagation Artificial Neural Network (ANN) Model to estimatives of latent heat fluxes at Furnas Lake – MG to fill the gaps in 50 days measurement dataset. The ANN was applied using various sets of input parameters, layer structures and trainning time. The performance of ANN estimatives were compared of a classic mass transfer model. The index of agreement are used to evaluate the performance of the models. The ANN Model index of agreement equal to 0.93536 showing better results than transfer model with 0.89681. The results showed that the ANN could be used with great performance to estimate latent heat flux and gap filling.

Carbon dioxide and latent heat flux measurements in a windbreak-sheltered orchard

1993 ◽  
Vol 66 (3-4) ◽  
pp. 193-210 ◽  
Author(s):  
M.J. Judd ◽  
P.T. Prendergast ◽  
K.J. McAneney
Keyword(s):  
Carbon Dioxide ◽  
Heat Flux ◽  
Latent Heat ◽  
Latent Heat Flux ◽  
Flux Measurements

scholarly journals Latent heat flux measurements over complex terrain by airborne water vapour and wind lidars

2011 ◽  
Vol 137 (S1) ◽  
pp. 190-203 ◽  
Author(s):  
Christoph Kiemle ◽  
Martin Wirth ◽  
Andreas Fix ◽  
Stephan Rahm ◽  
Ulrich Corsmeier ◽  
...  
Keyword(s):  
Heat Flux ◽  
Water Vapour ◽  
Latent Heat ◽  
Latent Heat Flux ◽  
Complex Terrain ◽  
Flux Measurements

An attenuated eddy covariance method for latent heat flux measurements

2007 ◽  
Vol 43 (4) ◽  
Author(s):  
Nelson L. Dias ◽  
Henrique F. Duarte ◽  
Selma R. Maggiotto ◽  
Leocádio Grodzki
Keyword(s):  
Heat Flux ◽  
Eddy Covariance ◽  
Latent Heat ◽  
Latent Heat Flux ◽  
Eddy Covariance Method ◽  
Flux Measurements

A comparison of bowen ratio and eddy correlation sensible and latent heat flux measurements above deciduous forest

1994 ◽  
Vol 71 (1-2) ◽  
pp. 21-41 ◽  
Author(s):  
Alan G. Barr ◽  
K. M. King ◽  
T. J. Gillespie ◽  
G. Den Hartog ◽  
H. H. Neumann
Keyword(s):  
Heat Flux ◽  
Latent Heat ◽  
Latent Heat Flux ◽  
Deciduous Forest ◽  
Bowen Ratio ◽  
Eddy Correlation ◽  
Flux Measurements

scholarly journals Gap-Filling Eddy Covariance Latent Heat Flux: Inter-Comparison of Four Machine Learning Model Predictions and Uncertainties in Forest Ecosystem

2021 ◽  
Vol 13 (24) ◽  
pp. 4976
Author(s):  
Muhammad Sarfraz Khan ◽  
Seung Bae Jeon ◽  
Myeong-Hun Jeong
Keyword(s):  
Machine Learning ◽  
Heat Flux ◽  
Eddy Covariance ◽  
Latent Heat ◽  
Latent Heat Flux ◽  
Model Performance ◽  
Support Vector ◽  
Two Dimensional ◽  
Gap Filling

Environmental monitoring using satellite remote sensing is challenging because of data gaps in eddy-covariance (EC)-based in situ flux tower observations. In this study, we obtain the latent heat flux (LE) from an EC station and perform gap filling using two deep learning methods (two-dimensional convolutional neural network (CNN) and long short-term memory (LSTM) neural networks) and two machine learning (ML) models (support vector machine (SVM), and random forest (RF)), and we investigate their accuracies and uncertainties. The average model performance based on ~25 input and hysteresis combinations show that the mean absolute error is in an acceptable range (34.9 to 38.5 Wm−2), which indicates a marginal difference among the performances of the four models. In fact, the model performance is ranked in the following order: SVM > CNN > RF > LSTM. We conduct a robust analysis of variance and post-hoc tests, which yielded statistically insignificant results (p-value ranging from 0.28 to 0.76). This indicates that the distribution of means is equal within groups and among pairs, thereby implying similar performances among the four models. The time-series analysis and Taylor diagram indicate that the improved two-dimensional CNN captures the temporal trend of LE the best, i.e., with a Pearson’s correlation of > 0.87 and a normalized standard deviation of ~0.86, which are similar to those of in situ datasets, thereby demonstrating its superiority over other models. The factor elimination analysis reveals that the CNN performs better when specific meteorological factors are removed from the training stage. Additionally, a strong coupling between the hysteresis time factor and the accuracy of the ML models is observed.

Sign in / Sign up

Export Citation Format

Share Document