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

Abstract

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 (R 2 = 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.

An NDVI-Based Statistical ET Downscaling Method

“…The downscaled results obtained using the "de-pixelation" method show good agreement with the original ETWatch 1-km dataset in terms of temporal changes. Based on the R 2 values between the ETWatch data and the results of the "de-pixelation" method, which range from 0.98 to 0.82, the accuracy of the fine-scale dataset is mainly determined by the corresponding coarse dataset, similar to the findings of other researchers [26].…”

“…In addition, our future work will concentrate on improvements in temporal resolution using the STARFM downscaling method to extend the model to a daily scale by including information from the MODIS 8-day NDVI product. This method could provide additional temporal detail over crop areas [26,60].…”

Mapping Evapotranspiration Coefficients in a Temperate Maritime Climate Using the METRIC Model and Landsat TM

“…It has been suggested [73][74][75] that is feasible to apply various downscaling methods to combine MODIS and Landsat imagery in order to obtain both high temporal and high spatial ET resolutions. Using a daily temporal resolution like MODIS [75,76] it is easy to exploit new images and apply the model to a new data set, strengthening the applicability of the procedure. Furthermore, introducing hyperspectral data is possible to improve the accuracy of LST computation, while the use of microwave data during the days affected by weather could make an LST estimation feasible.…”

Downscaling GLDAS Soil Moisture Data in East Asia through Fusion of Multi-Sensors by Optimizing Modified Regression Trees

“…Recently, machine learning approaches have been applied in various remote sensing fields, including land cover classification [46][47][48], drought monitoring [49,50], atmospheric process modelling [49,51], polar sea ice characterization [52,53], rainfall rate retrievals [54], and biophysical parameter estimation [55,56]. Ahmad et al [57] estimated soil moisture from the Variable Infiltration Capacity Three Layer (VIC) model, radar backscattering, and incidence angle measurements from Tropical Rainfall Measuring Mission (TRMM) and Normalized Difference Vegetation Index (NDVI) from Advanced Very High Resolution Radiometer (AVHRR) based on the two machine learning approaches; Support Vector Machine (SVM) and Artificial Neural Network (ANN).…”