Evapotranspiration (ET) is an important component of the Earth’s energy and water cycle via the interaction between the atmosphere and the land surface. The reference evapotranspiration (ET₀) is particularly important in the croplands because it is a convenient and reasonable method for calculating the actual evapotranspiration (AET) that represents the loss of water in the croplands through the soil evaporation and vegetation transpiration. To date, many efforts have been made to retrieve ET₀ on a spatially continuous grid. In particular, the Moderate Resolution Imaging Spectroradiometer (MODIS) product is provided with a reasonable spatial resolution of 500 m and a temporal resolution of 8 days. However, the applicability to the local-scale variabilities due to complex and heterogeneous land surfaces in countries like South Korea is not sufficiently validated. Meanwhile, the AI approaches showed a useful functionality for the ET₀ retrieval on the local scale but have rarely demonstrated a substantial product for a spatially continuous grid. This paper presented a retrieval of the daily reference evapotranspiration (ET₀) over a 500 m grid for croplands in South Korea using machine learning (ML) with satellite images and numerical weather prediction data. In a blind test for 2013–2019, the ML-based ET₀ model produced the accuracy statistics with a root mean square error of 1.038 mm/day and a correlation coefficient of 0.870. The results of the blind test were stable irrespective of location, year, and month. This outcome is presumably because the input data of the ML-based ET₀ model were suitably arranged spatially and temporally, and the optimization of the model was appropriate. We found that the relative humidity and land surface temperature were the most influential variables for the ML-based ET₀ model, but the variables with lower importance were also necessary to consider the nonlinearity between the variables. Using the daily ET₀ data produced over the 500 m grid, we conducted a case study to examine agrometeorological characteristics of the croplands in South Korea during the period when heatwave and drought events occurred. Through the experiments, the feasibility of the ML-based ET₀ retrieval was validated, especially for local agrometeorological applications in regions with heterogeneous land surfaces, such as South Korea.

Cloud detection is an essential and important process in remote sensing when surface information is required for various fields. For this reason, we developed a daytime cloud detection algorithm for GEOstationary KOrea Multi-Purpose SATellite 2A (GEO-KOMPSAT-2A, GK-2A) imagery. For each pixel, the filtering technique using angular variance, which denotes the change in top of atmosphere (TOA) reflectance over time, was applied, and filtering technique by using the minimum TOA reflectance was used to remove remaining cloud pixels. Furthermore, near-infrared (NIR) and normalized difference vegetation index (NDVI) images were applied with dynamic thresholds to improve the accuracy of the cloud detection results. The quantitative results showed that the overall accuracy of proposed cloud detection was 0.88 and 0.92 with Visible Infrared Imaging Radiometer Suite (VIIRS) and Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO), respectively, and indicated that the proposed algorithm has good performance in detecting clouds.

Evapotranspiration (ET) is a fundamental factor in energy and hydrologic cycles. Although highly precise in-situ ET monitoring is possible, such data are not always available due to the high spatiotemporal variability in ET. This study estimates daily potential ET (PET) in real-time for the Korean Peninsula, via an artificial neural network (ANN), using data from the GEO-KOMPSAT 2A satellite, which is equipped with an Advanced Meteorological Imager (GK2A/AMI). We also used passive microwave data, numerical weather prediction (NWP) model data, and static data. The ANN-based PET model was trained using data for the period 25 July 2019 to 24 July 2020, and was tested by comparing with in-situ PET for the period 25 July 2020 to 31 July 2021. In terms of accuracy, the PET model performed well, with root-mean-square error (RMSE), bias, and Pearson’s correlation coefficient (R) of 0.649 mm day⁻¹, −0.134 mm day⁻¹, and 0.954, respectively. To examine the efficiency of the GK2A/AMI-derived PET data, we compared it with in-situ ET measured at flux towers and with MODIS PET data. The accuracy of the GK2A/AMI-derived PET, in comparison with the flux tower-measured ET, showed RMSE, bias, and Pearson’s R of 1.730 mm day⁻¹, 1.212 mm day⁻¹, and 0.809, respectively. In comparison with the in-situ PET, the ANN model produced more accurate estimates than the MODIS data, indicating that it is more locally optimized for the Korean Peninsula than MODIS. This study advances the field by applying an ANN approach using GK2A/AMI data and could play an important role in examining hydrologic energy for air-land interactions.

A combined algorithm comprising multiple dust detection methods was developed using infrared (IR) channels onboard the GEOstationary Korea Multi-Purpose SATellite 2A equipped with the Advanced Meteorological Imager (GK2A/AMI). Six cloud tests using brightness temperature difference (BTD) were utilized to reduce errors caused by clouds. For detecting dust storms, three standard BTD tests (i.e., $${BT}_{12.3}-{BT}_{10.5}$$ , $${BT}_{8.7}-{BT}_{10.5}$$ , and $${BT}_{11.2}-{BT}_{10.5}$$ ) were combined with the polarized optical depth index (PODI). The combined algorithm normalizes the indices for cloud and dust detection, and adopts weighted combinations of dust tests depending on the observation time (day/night) and surface type (land/sea). The dust detection results were produced as quantitative confidence factors and displayed as false color imagery, applying a dynamic enhancement background reduction algorithm (DEBRA). The combined dust detection algorithm was qualitatively assessed by comparing it with dust RGB imageries and ground-based lidar data. The combined algorithm especially improved the discontinuity in weak dust advection to the sea and considerably reduced false alarms as compared to previous dust monitoring methods. For quantitative validation, we used aerosol optical thickness (AOT) and fine mode fraction (FMF) derived from low Earth orbit (LEO) satellites in daytime. For both severe and weakened dust cases, the probability of detection (POD) ranged from 0.667 to 0.850 and it indicated that the combined algorithm detects more potential dust pixels than other satellites. In particular, the combined algorithm was advantageous in detecting weak dust storms passing over the warm and humid Yellow Sea with low dust height and small AOT.