Abstract
Evapotranspiration (ET) is key to assess crop water balance and optimize water-use efficiency. To attain sustainability in cropping systems, especially in semi-arid ecosystems, it is necessary to improve methodologies of ET estimation. A method to predict ET is by using land surface temperature (LST) from remote sensing data and applying the Operational Simplified Surface Energy Balance Model (SSEBop). However, to date, LST information from Landsat-8 Thermal Infrared Sensor (TIRS) has a coarser resolution (100 m) and longer revisit time than Sentinel-2, which does not have a thermal infrared sensor, which compromises its use in ET models as SSEBop. Therefore, in the present study we set out to use Sentinel-2 data at a higher spatial-temporal resolution (10 m) to predict ET. Three models were trained using TIRS’ images as training data (100 m) and later used to predict LST at 10 m in the western section of the Copiapó Valley (Chile). The models were built on cubist (Cub) and random forest (RF) algorithms, and a sinusoidal model (Sin). The predicted LSTs were compared with three meteorological stations located in olives, vineyards, and pomegranate orchards. RMSE values for the prediction of LST at 10 m were 7.09 K, 3.91 K, and 3.4 K in Cub, RF, and Sin, respectively. ET estimation from LST in spatial-temporal relation showed that RF was the best overall performance (R2 = 0.710) when contrasted with Landsat, followed by the Sin model (R2 = 0.707). Nonetheless, the Sin model had the lowest RMSE (0.45 mm d−1) and showed the best performance at predicting orchards’ ET. In our discussion, we argue that a simplistic sinusoidal model built on NDVI presents advantages over RF and Cub, which are constrained to the spatial relation of predictors at different study areas. Our study shows how it is possible to downscale Landsat-8 TIRS’ images from 100 m to 10 m to predict ET.
Highlights
We evaluated three models to estimate and downscale land surface temperature (LST) using Sentinel2 images and remote sensing indices as predictors, comparing them with Landsat-8 LST
The results of the LST predictions showed that the best model to downscale LST was a sinusoidal model, which showed the lowest root mean square error (RMSE) of 3.97 K at 100 m and 3.4 K in 10 m, and with the highest correlation coefficients
The machine learning analysis showed that the variable with the greatest importance in predicting LST was Sentinel-2 band 9, as it was included in the majority of internal model conditions and prediction rules
Summary
Evapotranspiration has a key role as a component of the hydrological cycle in terrestrial ecosystems [1]. ET has become an element to consider in future climate change effects on the water cycle [2]. Monitoring ET has relevance for assessing the hydrological cycle at different levels, such as irrigation, water resource quantification and use, weather forecast, and drought indexes [3]. Land surface temperature (LST) is an important variable in the energy balance equation of the Earth’s surface and in the estimation of ET [4]. Satellite sensors do not directly measure ET; algorithms or models are developed for ET estimation [5,6]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
