Downscaling of MODIS One Kilometer Evapotranspiration Using Landsat-8 Data and Machine Learning Approaches

This study presented a MODIS 8-day 1 km evapotranspiration (ET) downscaling method based on Landsat 8 data (30 m) and machine learning approaches. Eleven indicators including albedo, land surface temperature (LST), and vegetation indices (VIs) derived from Landsat 8 data were first upscaled to 1 km resolution. Machine learning algorithms including Support Vector Regression (SVR), Cubist, and Random Forest (RF) were used to model the relationship between the Landsat indicators and MODIS 8-day 1 km ET. The models were then used to predict 30 m ET based on Landsat 8 indicators. A total of thirty-two pairs of Landsat 8 images/MODIS ET data were evaluated at four study sites including two in United States and two in South Korea. Among the three models, RF produced the lowest error, with relative Root Mean Square Error (rRMSE) less than 20%. Vegetation greenness related indicators such as Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Soil Adjusted Vegetation Index (SAVI), and vegetation moisture related indicators such as Normalized Difference Infrared Index—Landsat 8 OLI band 7 (NDIIb7) and Normalized Difference Water Index (NDWI) were the five most important features used in RF model. Temperature-based indicators were less important than vegetation greenness and moisture-related indicators because LST could have considerable variation during each 8-day period. The predicted Landsat downscaled ET had good overall agreement with MODIS ET (average rRMSE = 22%) and showed a similar temporal trend as MODIS ET. Compared to the MODIS ET product, the downscaled product demonstrated more spatial details, and had better agreement with in situ ET observations (R2 = 0.56). However, we found that the accuracy of MODIS ET was the main control factor of the accuracy of the downscaled product. Improved coarse-resolution ET estimation would result in better finer-resolution estimation. This study proved the potential of using machine learning approaches for ET downscaling considering their effectiveness and ease of implementation. Future research includes development of the spatial-temporal fusion models of Landsat data and MODIS ET in order to increase temporal resolution of downscaled ET.

[1]  Terry A. Howell,et al.  A review of potential image fusion methods for remote sensing-based irrigation management: part II , 2012, Irrigation Science.

[2]  Jungho Im,et al.  Downscaling of AMSR-E soil moisture with MODIS products using machine learning approaches , 2016, Environmental Earth Sciences.

[3]  Aiko M. Hormann,et al.  Programs for Machine Learning. Part I , 1962, Inf. Control..

[4]  J. Norman,et al.  Remote sensing of surface energy fluxes at 101‐m pixel resolutions , 2003 .

[5]  I. Sandholt,et al.  A simple interpretation of the surface temperature/vegetation index space for assessment of surface moisture status , 2002 .

[6]  Lindi J. Quackenbush,et al.  The MODIS ice surface temperature product as an indicator of sea ice minimum over the Arctic Ocean , 2014 .

[7]  Lindi J. Quackenbush,et al.  Impervious surface quantification using a synthesis of artificial immune networks and decision/regression trees from multi-sensor data , 2012 .

[8]  Jungho Im,et al.  Hyperspectral remote sensing analysis of short rotation woody crops grown with controlled nutrient and irrigation treatments , 2009 .

[9]  S. Running,et al.  Regional evaporation estimates from flux tower and MODIS satellite data , 2007 .

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

[11]  Luis A. Bastidas,et al.  Downscaling and Assimilation of Surface Soil Moisture Using Ground Truth Measurements , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Kenton Lee,et al.  Landsat 8 Operational Land Imager On-Orbit Geometric Calibration and Performance , 2014, Remote. Sens..

[13]  Zhe Zhu,et al.  Object-based cloud and cloud shadow detection in Landsat imagery , 2012 .

[14]  Jungho Im,et al.  Landfast sea ice monitoring using multisensor fusion in the Antarctic , 2015 .

[15]  B. Rock,et al.  Detection of changes in leaf water content using Near- and Middle-Infrared reflectances , 1989 .

[16]  R. Bingner,et al.  Evaluation of the use of remotely sensed evapotranspiration estimates into AnnAGNPS pollution model , 2011 .

[17]  Jungho Im,et al.  Forest Biomass and Carbon Stock Quantification Using Airborne LiDAR Data: A Case Study Over Huntington Wildlife Forest in the Adirondack Park , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[18]  D. Lu,et al.  A comparative analysis of approaches for successional vegetation classification in the Brazilian Amazon , 2014 .

[19]  Lucy Marshall,et al.  Object-oriented crop classification using multitemporal ETM+ SLC-off imagery and random forest , 2013 .

[20]  S. K. McFeeters.  The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features , 1996 .

[21]  L. S. Galvão,et al.  Potential of multispectral and hyperspectral data to detect saline-exposed soils in Brazil , 2015 .

[22]  Subimal Ghosh,et al.  Statistical downscaling of GCM simulations to streamflow using relevance vector machine , 2008 .

[23]  S. Sader,et al.  Detection of forest harvest type using multiple dates of Landsat TM imagery , 2002 .

[24]  David R. Miller,et al.  Sensitivity Analysis of the Surface Energy Balance Algorithm for Land (SEBAL) , 2009 .

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

[26]  D. Hughes,et al.  Satellite earth observation as a tool to conceptualize hydrogeological fluxes in the Sandveld, South Africa , 2013, Hydrogeology Journal.

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

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

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

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

[31]  Michael E. Schaepman,et al.  Algorithm theoretical basis document , 2009 .

[32]  B. Rudolf,et al.  World Map of the Köppen-Geiger climate classification updated , 2006 .

[33]  A. Huete,et al.  A Modified Soil Adjusted Vegetation Index , 1994 .

[34]  N. McDowell,et al.  Numerical Terradynamic Simulation Group 1-2013 A Remotely Sensed Global Terrestrial Drought Severity Index , 2017 .

[35]  柯樱海.  Characteristics of Landsat 8 OLI-derived NDVI by comparison with multiple satellite sensors and in-situ observations , 2015 .

[36]  James P. Verdin,et al.  On the Downscaling of Actual Evapotranspiration Maps Based on Combination of MODIS and Landsat-Based Actual Evapotranspiration Estimates , 2014, Remote. Sens..

[37]  A. Senthil Kumar,et al.  Expansion of LISS III swath using AWiFS wider swath data and contourlet coefficients learning , 2015 .

[38]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[39]  S. Ha,et al.  Machine learning approaches to coastal water quality monitoring using GOCI satellite data , 2014 .

[40]  C. Tucker.  Red and photographic infrared linear combinations for monitoring vegetation , 1979 .

[41]  Yujiu Xiong,et al.  Estimation of evapotranspiration and its partition based on an extended three-temperature model and MODIS products , 2013 .

[42]  Martha C. Anderson,et al.  Use of Landsat thermal imagery in monitoring evapotranspiration and managing water resources , 2012 .

[43]  Terry A. Howell,et al.  A review of downscaling methods for remote sensing-based irrigation management: part I , 2012, Irrigation Science.

[44]  Jan M. H. Hendrickx,et al.  Down-scaling of SEBAL derived evapotranspiration maps from MODIS (250 m) to Landsat (30 m) scales , 2011 .

[45]  S. Liang,et al.  Calculating environmental moisture for per-field discrimination of rice crops , 2003 .

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

[47]  T. Tadesse,et al.  The Vegetation Outlook (VegOut): A New Method for Predicting Vegetation Seasonal Greenness , 2010 .

[48]  K. Moffett,et al.  Remote Sens , 2015 .

[49]  Martha C. Anderson,et al.  Monitoring daily evapotranspiration over two California vineyards using Landsat 8 in a multi-sensor data fusion approach , 2016 .

[50]  Xiaolei Yu,et al.  Land Surface Temperature Retrieval from Landsat 8 TIRS - Comparison between Radiative Transfer Equation-Based Method, Split Window Algorithm and Single Channel Method , 2014, Remote. Sens..

[51]  Di Long,et al.  Toward the Use of the MODIS ET Product to Estimate Terrestrial GPP for Nonforest Ecosystems , 2014, IEEE Geoscience and Remote Sensing Letters.

[52]  Steven W. Running,et al.  MODIS Global Terrestrial Evapotranspiration (ET) Product (NASA MOD16A2/A3) Collection 5. NASA Headquarters , 2013 .

[53]  Ranz,et al.  World Map of the Köppen-Geiger climate classification updated — Source link , 2006 .

[54]  W. Buytaert,et al.  Coupling a land-surface model with a crop growth model to improve ET flux estimations in the Upper Ganges basin, India , 2014 .

[55]  J. Rhee,et al.  Relationship between land cover patterns and surface temperature in urban areas , 2014 .

[56]  Suming Jin,et al.  Completion of the 2011 National Land Cover Database for the Conterminous United States – Representing a Decade of Land Cover Change Information , 2015 .

[57]  Martha C. Anderson,et al.  Mapping daily evapotranspiration at field scales over rainfed and irrigated agricultural areas using remote sensing data fusion , 2014 .

[58]  Le Wang,et al.  An object-based SVM method incorporating optimal segmentation scale estimation using Bhattacharyya Distance for mapping salt cedar (Tamarisk spp.) with QuickBird imagery , 2015 .

[59]  Lindi J. Quackenbush,et al.  A simple Landsat–MODIS fusion approach for monitoring seasonal evapotranspiration at 30 m spatial resolution , 2015 .

[60]  Françoise Gellens-Meulenberghs,et al.  Evapotranspiration modelling at large scale using near-real time MSG SEVIRI derived data , 2010 .

[61]  Baharin Bin Ahmad,et al.  SENSITIVITY ANALYSIS OF METRIC–BASED EVAPOTRANSPIRATION ALGORITHM , 2013 .

[62]  Damien Sulla-Menashe,et al.  MODIS Collection 5 global land cover: Algorithm refinements and characterization of new datasets , 2010 .

[63]  T. Andrew Black,et al.  Numerical Terradynamic Simulation Group 8-2015 Comparing Evapotranspiration from Eddy Covariance Measurements , Water Budgets , Remote Sensing , and Land Surface Models over Canada , 2018 .

[64]  W. Bastiaanssen,et al.  A remote sensing surface energy balance algorithm for land (SEBAL). , 1998 .

[65]  James L. Wright,et al.  Satellite-Based Energy Balance for Mapping Evapotranspiration with Internalized Calibration (METRIC)—Applications , 2007 .

[66]  A. Huete.  A soil-adjusted vegetation index (SAVI) , 1988 .

[67]  F. Tsai,et al.  GIS-Based Water Budget Framework for High-Resolution Groundwater Recharge Estimation of Large-Scale Humid Regions , 2014 .

[68]  E. Lokupitiya,et al.  Incorporation of crop phenology in Simple Biosphere Model (SiBcrop) to improve land-atmosphere carbon exchanges from croplands , 2009 .

[69]  Martha C. Anderson,et al.  A data fusion approach for mapping daily evapotranspiration at field scale , 2013 .

[70]  Juan C. Jiménez-Muñoz,et al.  Land Surface Temperature Retrieval Methods From Landsat-8 Thermal Infrared Sensor Data , 2014, IEEE Geoscience and Remote Sensing Letters.

[71]  Jungho Im,et al.  Forest biomass estimation from airborne LiDAR data using machine learning approaches , 2012 .

[72]  R. Allen,et al.  At-Surface Reflectance and Albedo from Satellite for Operational Calculation of Land Surface Energy Balance , 2008 .