Fusion of Five Satellite-Derived Products Using Extremely Randomized Trees to Estimate Terrestrial Latent Heat Flux over Europe

An accurate estimation of spatially and temporally continuous latent heat flux (LE) is essential in the assessment of surface water and energy balance. Various satellite-derived LE products have been generated to enhance the simulation of terrestrial LE, yet each individual LE product shows large discrepancies and uncertainties. Our study used Extremely Randomized Trees (ETR) to fuse five satellite-derived terrestrial LE products to reduce uncertainties from the individual products and improve terrestrial LE estimations over Europe. The validation results demonstrated that the estimation using the ETR fusion method increased the R2 of five individual LE products (ranging from 0.53 to 0.61) to 0.97 and decreased the RMSE (ranging from 26.37 to 33.17 W/m2) to 5.85 W/m2. Compared with three other machine learning fusion models, Gradient Boosting Regression Tree (GBRT), Random Forest (RF), and Gaussian Process Regression (GPR), ETR exhibited the best performance in terms of both training and validation accuracy. We also applied the ETR fusion method to implement the mapping of average annual terrestrial LE over Europe at a resolution of 0.05 ◦ in the period from 2002 to 2005. When compared with global LE products such as the Global Land Surface Satellite (GLASS) and the Moderate Resolution Imaging Spectroradiometer (MODIS), the fusion LE using ETR exhibited a relatively small gap, which confirmed that it is reasonable and reliable for the estimation of the terrestrial LE over Europe.

[1]  S. Liang,et al.  Improving global terrestrial evapotranspiration estimation using support vector machine by integrating three process-based algorithms. , 2017 .

[2]  Jeffrey P. Walker,et al.  THE GLOBAL LAND DATA ASSIMILATION SYSTEM , 2004 .

[3]  T. Foken.  The energy balance closure problem: an overview. , 2008, Ecological applications : a publication of the Ecological Society of America.

[4]  R. Dickinson,et al.  A review of global terrestrial evapotranspiration: Observation, modeling, climatology, and climatic variability , 2011 .

[5]  D. Fernández-Prieto,et al.  Exploring the merging of the global land evaporation WACMOS-ET products based on local tower measurements , 2018, Hydrology and Earth System Sciences.

[6]  Jia Xu,et al.  MODIS-Based Estimation of Terrestrial Latent Heat Flux over North America Using Three Machine Learning Algorithms , 2017, Remote. Sens..

[7]  S. Seneviratne,et al.  Global intercomparison of 12 land surface heat flux estimates , 2011 .

[8]  Chunlin Huang,et al.  Multi‐model ensemble prediction of terrestrial evapotranspiration across north China using Bayesian model averaging , 2016 .

[9]  Chenghu Zhou,et al.  A Review of Current Methodologies for Regional Evapotranspiration Estimation from Remotely Sensed Data , 2009, Sensors.

[10]  Norman J. Rosenberg,et al.  A Resistance Model to Predict Evapotranspiration and Its Application to a Sugar Beet Field1 , 1973 .

[11]  Xiaotong Zhang,et al.  Estimation of surface downward shortwave radiation over China from AVHRR data based on four machine learning methods , 2019, Solar Energy.

[12]  Shunlin Liang,et al.  An Empirical Orthogonal Function-Based Algorithm for Estimating Terrestrial Latent Heat Flux from Eddy Covariance, Meteorological and Satellite Observations , 2016, PloS one.

[13]  Youngryel Ryu,et al.  Multi-scale evaluation of global gross primary productivity and evapotranspiration products derived from Breathing Earth System Simulator (BESS) , 2016 .

[14]  Maosheng Zhao,et al.  Development of a global evapotranspiration algorithm based on MODIS and global meteorology data , 2007 .

[15]  S. Liang,et al.  A satellite-based hybrid algorithm to determine the Priestley–Taylor parameter for global terrestrial latent heat flux estimation across multiple biomes , 2015 .

[16]  Yadvinder Malhi,et al.  A Re-Evaluation of Long-Term Flux Measurement Techniques Part I: Averaging and Coordinate Rotation , 2003 .

[17]  Shaomin Liu,et al.  Measurements of evapotranspiration from eddy-covariance systems and large aperture scintillometers in the Hai River Basin, China , 2013 .

[18]  J. Monteith.  Evaporation and environment. , 1965, Symposia of the Society for Experimental Biology.

[19]  Markus Reichstein,et al.  Upscaled diurnal cycles of land–atmosphere fluxes: a new global half-hourly data product , 2018, Earth System Science Data.

[20]  Tong Zhang,et al.  Learning Nonlinear Functions Using Regularized Greedy Forest , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  William P. Kustas,et al.  A two‐source approach for estimating turbulent fluxes using multiple angle thermal infrared observations , 1997 .

[22]  R. Monson,et al.  Gap-filling missing data in eddy covariance measurements using multiple imputation (MI) for annual estimations , 2004 .

[23]  Lisheng Song,et al.  Evaluating Different Machine Learning Methods for Upscaling Evapotranspiration from Flux Towers to the Regional Scale , 2018, Journal of Geophysical Research: Atmospheres.

[24]  S. Liang,et al.  A simple temperature domain two‐source model for estimating agricultural field surface energy fluxes from Landsat images , 2017 .

[25]  Massimo Menenti,et al.  S-SEBI: A simple remote sensing algorithm to estimate the surface energy balance , 2000 .

[26]  A. Huete,et al.  Overview of the radiometric and biophysical performance of the MODIS vegetation indices , 2002 .

[27]  T. Holmes,et al.  Global land-surface evaporation estimated from satellite-based observations , 2010 .

[28]  A. Holtslag,et al.  A remote sensing surface energy balance algorithm for land (SEBAL)-1. Formulation , 1998 .

[29]  Massimo Menenti,et al.  Comparison of MOD16 and LSA-SAF MSG evapotranspiration products over Europe for 2011 , 2015 .

[30]  Roger A. Pielke,et al.  Land–atmosphere energy exchange in Arctic tundra and boreal forest: available data and feedbacks to climate , 2000, Global change biology.

[31]  Md Taufeeq Uddin,et al.  Human activity recognition from wearable sensors using extremely randomized trees , 2015, 2015 International Conference on Electrical Engineering and Information Communication Technology (ICEEICT).

[32]  J. Norman,et al.  Correcting eddy-covariance flux underestimates over a grassland , 2000 .

[33]  Alan K. Betts,et al.  Land‐Surface‐Atmosphere Coupling in Observations and Models , 2009 .

[34]  Jonas Ardö,et al.  Estimation of high-resolution terrestrial evapotranspiration from Landsat data using a simple Taylor skill fusion method , 2017 .

[35]  L. Aragão,et al.  Assessment of the MODIS global evapotranspiration algorithm using eddy covariance measurements and hydrological modelling in the Rio Grande basin , 2013 .

[36]  Pierre Geurts,et al.  Extremely randomized trees , 2006, Machine Learning.

[37]  Li Jia,et al.  Monitoring of Evapotranspiration in a Semi-Arid Inland River Basin by Combining Microwave and Optical Remote Sensing Observations , 2015, Remote. Sens..

[38]  Sujay V. Kumar,et al.  Land information system: An interoperable framework for high resolution land surface modeling , 2006, Environ. Model. Softw..

[39]  C. Priestley,et al.  On the Assessment of Surface Heat Flux and Evaporation Using Large-Scale Parameters , 1972 .

[40]  J. Wallace,et al.  Evaporation from sparse crops‐an energy combination theory , 2007 .

[41]  S. Liang,et al.  MODIS-driven estimation of terrestrial latent heat flux in China based on a modified Priestley-Taylor algorithm , 2013 .

[42]  Z. Su.  The Surface Energy Balance System (SEBS) for estimation of turbulent heat fluxes , 2002 .

[43]  Maosheng Zhao,et al.  Improvements to a MODIS global terrestrial evapotranspiration algorithm , 2011 .

[44]  J. Norman,et al.  Evaluation of soil and vegetation heat flux predictions using a simple two-source model with radiometric temperatures for partial canopy cover , 1999 .

[45]  Jiyuan Liu,et al.  The Performances of MODIS-GPP and -ET Products in China and Their Sensitivity to Input Data (FPAR/LAI) , 2014, Remote. Sens..

[46]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[47]  Li Jing,et al.  Estimation of daily evapotranspiration using a two‐layer remote sensing model , 2005 .

[48]  F. Aires.  Combining Datasets of Satellite-Retrieved Products. Part I: Methodology and Water Budget Closure , 2014 .

[49]  Martha C. Anderson,et al.  A Two-Source Time-Integrated Model for Estimating Surface Fluxes Using Thermal Infrared Remote Sensing , 1997 .

[50]  Maosheng Zhao,et al.  Sensitivity of Moderate Resolution Imaging Spectroradiometer (MODIS) terrestrial primary production to the accuracy of meteorological reanalyses , 2006 .

[51]  S. Schubert,et al.  MERRA: NASA’s Modern-Era Retrospective Analysis for Research and Applications , 2011 .

[52]  M. Mccabe,et al.  Estimating Land Surface Evaporation: A Review of Methods Using Remotely Sensed Surface Temperature Data , 2008 .

[53]  Farid Melgani,et al.  Gaussian Process Regression for Estimating Chlorophyll Concentration in Subsurface Waters From Remote Sensing Data , 2010, IEEE Geoscience and Remote Sensing Letters.

[54]  D. Baldocchi,et al.  Global estimates of the land–atmosphere water flux based on monthly AVHRR and ISLSCP-II data, validated at 16 FLUXNET sites , 2008 .

[55]  Renaud Mathieu,et al.  Validation of Global Evapotranspiration Product (MOD16) using Flux Tower Data in the African Savanna, South Africa , 2014, Remote. Sens..

[56]  Xin Niu,et al.  A mobile recommendation system based on logistic regression and Gradient Boosting Decision Trees , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[57]  Jing M. Chen,et al.  Evaluating spatial and temporal patterns of MODIS GPP over the conterminous U.S. against flux measurements and a process model , 2012 .

[58]  Markus Reichstein,et al.  Benchmark products for land evapotranspiration: LandFlux-EVAL multi-data set synthesis , 2013 .

[59]  J. Norman,et al.  Source approach for estimating soil and vegetation energy fluxes in observations of directional radiometric surface temperature , 1995 .

[60]  Rafal Kulik,et al.  Bootstrap , 2020, Heavy-Tailed Time Series.

[61]  R. Dickinson,et al.  Evidence for decadal variation in global terrestrial evapotranspiration between 1982 and 2002: 1. Model development , 2010 .

[62]  S. Liang,et al.  Bayesian multimodel estimation of global terrestrial latent heat flux from eddy covariance, meteorological, and satellite observations , 2014 .