Application of a Machine Learning Algorithm in Generating an Evapotranspiration Data Product From Coupled Thermal Infrared and Microwave Satellite Observations.

Land surface evapotranspiration (ET) is one of the main energy sources for atmospheric dynamics and a critical component of the local, regional, and global water cycles. Consequently, accurate measurement or estimation of ET is one of the most active topics in hydro-climatology research. With massive and spatially distributed observational data sets of land surface properties and environmental conditions being collected from the ground, airborne or space-borne platforms daily over the past few decades, many research teams have started to use big data science to advance the ET estimation methods. The Geostationary satellite Evapotranspiration and Drought (GET-D) product system was developed at the National Oceanic and Atmospheric Administration (NOAA) in 2016 to generate daily ET and drought maps operationally. The primary inputs of the current GET-D system are the thermal infrared (TIR) observations from NOAA GOES satellite series. Because of the cloud contamination to the TIR observations, the spatial coverage of the daily GET-D ET product has been severely impacted. Based on the most recent advances, we have tested a machine learning algorithm to estimate all-weather land surface temperature (LST) from TIR and microwave (MW) combined satellite observations. With the regression tree machine learning approach, we can combine the high accuracy and high spatial resolution of GOES TIR data with the better spatial coverage of passive microwave observations and LST simulations from a land surface model (LSM). The regression tree model combines the three LST data sources for both clear and cloudy days, which enables the GET-D system to derive an all-weather ET product. This paper reports how the all-weather LST and ET are generated in the upgraded GET-D system and provides an evaluation of these LST and ET estimates with ground measurements. The results demonstrate that the regression tree machine learning method is feasible and effective for generating daily ET under all weather conditions with satisfactory accuracy from the big volume of satellite observations.

The Efficiency of Data Assimilation.

Data assimilation is the application of Bayes' theorem to condition the states of a dynamical systems model on observations. Any real-world application of Bayes' theorem is approximate, and therefore we cannot expect that data assimilation will preserve all of the information available from models and observations. We outline a framework for measuring information in models, observations, and evaluation data in a way that allows us to quantify information loss during (necessarily imperfect) data assimilation. This facilitates quantitative analysis of tradeoffs between improving (usually expensive) remote sensing observing systems vs. improving data assimilation design and implementation. We demonstrate this methodology on a previously published application of the Ensemble Kalman Filter used to assimilate remote sensing soil moisture retrievals from AMSR-E into the Noah land surface model.

An Assessment of the Impact of Land Thermal Infrared Observation on Regional Weather Forecasts Using Two Different Data Assimilation Approaches.

Recent studies have shown the unique value of satellite-observed land surface thermal infrared (TIR) information (e.g., skin temperature) and the feasibility of assimilating land surface temperature (LST) into land surface models (LSMs) to improve the simulation of land-atmosphere water and energy exchanges. In this study, two different types of LST assimilation techniques are implemented and the benefits from the techniques are compared. One of the techniques is to directly assimilate LST using ensemble Kalman filter (EnKF) data assimilation (DA) utilities. The other is to use the Atmosphere-Land Exchange Inversion model (ALEXI) as an "observation operator" that converts LST retrievals into the soil moisture (SM) proxy based on the ratio of actual to potential evapotranspiration (fPET), which is then assimilated into an LSM. While most current studies have shown some success in both directly the assimilating LST and assimilating ALEXI SM proxy into offline LSMs, the potential impact of the assimilation of TIR information through coupled numerical weather prediction (NWP) models is unclear. In this study, a semi-coupled Land Information System (LIS) and Weather Research and Forecast (WRF) system is employed to assess the impact of the two different techniques for assimilating the TIR observations from NOAA GOES satellites on WRF model forecasts. The NASA LIS, equipped with a variety of LSMs and advanced data assimilation tools (e.g., the ensemble Kalman Filter (EnKF)), takes atmospheric forcing data from the WRF model run, generates updated initial land surface conditions with the assimilation of either LST- or TIR-based SM and returns them to WRF for initializing the forecasts. The WRF forecasts using the daily updated initializations with the TIR data assimilation are evaluated against ground weather observations and re-analysis products. It is found that WRF forecasts with the LST-based SM assimilation have better agreement with the ground weather observations than those with the direct LST assimilation or without the land TIR data assimilation.