• Korean Journal of Remote Sensing
• /
• v.38 no.2
• /
• pp.179-188
• /
• 2022

Global warming causes climate change and increases extreme weather events worldwide, and the occurrence of heatwaves and droughts is also increasing in Korea. For the monitoring of extreme weather, various satellite data such as LST (Land Surface Temperature), TCI (Temperature Condition Index), NDVI (Normalized Difference Vegetation Index), VCI (Vegetation Condition Index), and VHI (Vegetation Health Index) have been used. VHI, the combination of TCI and VCI, represents the vegetation stress affected by meteorological factors like precipitation and temperature and is frequently used to assess droughts under climate change. TCI and VCI require historical reference values for the LST and NDVI for each date and location. So, it is complicated to produce the VHI from the recent satellite GK2A (Geostationary Korea Multi-Purpose Satellite-2A). This study examined the retrieval of VHI using GK2A AMI (Advanced Meteorological Imager) by referencing the historical data from VIIRS (Visible Infrared Imaging Radiometer Suite) NDVI and LST as a proxy data. We found a close relationship between GK2A and VIIRS data needed for the retrieval of VHI. We produced the TCI, VCI, and VHI for GK2A during 2020-2021 at intervals of 8 days and carried out the interpretations of recent extreme weather events in Korea. GK2A VHI could express the changes in vegetation stress in 2020 due to various extreme weather events such as heatwaves (in March and June) and low temperatures (in April and July), and heavy rainfall (in August), while NOAA (National Oceanic and Atmospheric Administration) VHI could not well represent such characteristics. The GK2A VHI presented in this study can be utilized to monitor the vegetation stress due to heatwaves and droughts if the historical reference values of LST and NDVI can be adjusted in a more statistically significant way in the future work.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1095-1105
• /
• 2021

The advancement of dam operation is further required due to the upcoming rainy season, typhoons, or torrential rains. Besides, physical models based on specific rules may sometimes have limitations in controlling the release discharge of dam due to inherent uncertainty and complex factors. This study aims to forecast the water level of the nearest station to the dam multi-timestep-ahead and evaluate the availability when it makes a decision for a release discharge of dam based on LSTM (Long Short-Term Memory) of deep learning. The LSTM model was trained and tested on eight data sets with a 1-hour temporal resolution, including primary data used in the dam operation and downstream water level station data about 13 years (2009~2021). The trained model forecasted the water level time series divided by the six lead times: 1, 3, 6, 9, 12, 18-hours, and compared and analyzed with the observed data. As a result, the prediction results of the 1-hour ahead exhibited the best performance for all cases with an average accuracy of MAE of 0.01m, RMSE of 0.015 m, and NSE of 0.99, respectively. In addition, as the lead time increases, the predictive performance of the model tends to decrease slightly. The model may similarly estimate and reliably predicts the temporal pattern of the observed water level. Thus, it is judged that the LSTM model could produce predictive data by extracting the characteristics of complex hydrological non-linear data and can be used to determine the amount of release discharge from the dam when simulating the operation of the dam.