This paper compares different artificial intelligence (AI) models in order to develop the best crop yield prediction model for the Midwestern United States (US). Through experiments to examine the effects of phenology using three different periods, we selected the July–August (JA) database as the best months to predict corn and soybean yields. Six different AI models for crop yield prediction are tested in this research. Then, a comprehensive and objective comparison is conducted between the AI models. Particularly for the deep neural network (DNN) model, we performed an optimization process to ensure the best configurations for the layer structure, cost function, optimizer, activation function, and drop-out ratio. In terms of mean absolute error (MAE), our DNN model with the JA database was approximately 21–33% and 17–22% more accurate for corn and soybean yields, respectively, than the other five AI models. This indicates that corn and soybean yields for a given year can be forecasted in advance, at the beginning of September, approximately a month or more ahead of harvesting time. A combination of the optimized DNN model and spatial statistical methods should be investigated in future work, to mitigate partly clustered errors in some regions.

The worst forest fire in South Korea occurred in April 2000 on the eastern coast. Forest recovery works were conducted until 2005, and the forest has been monitored since the fire. Remote sensing techniques have been used to detect the burned areas and to evaluate the recovery-time point of the post-fire processes during the past 18 years. We used three indices, Normalized Burn Ratio (NBR), Normalized Difference Vegetation Index (NDVI), and Gross Primary Production (GPP), to temporally monitor a burned area in terms of its moisture condition, vegetation biomass, and photosynthetic activity, respectively. The change of those three indices by forest recovery processes was relatively analyzed using an unburned reference area. The selected unburned area had similar characteristics to the burned area prior to the forest fire. The temporal patterns of NBR and NDVI, not only showed the forest recovery process as a result of forest management, but also statistically distinguished the recovery periods at the regions of low, moderate, and high fire severity. The NBR_2.1 for all areas, calculated using 2.1 μm wavelengths, reached the unburned state in 2008. The NDVI for areas with low and moderate fire severity levels became significantly equal to the unburned state in 2009 (p > 0.05), but areas with high severity levels did not reach the unburned state until 2017. This indicated that the surface and vegetation moisture conditions recovered to the unburned state about 8 years after the fire event, while vegetation biomass and health required a longer time to recover, particularly for high severity regions. In the case of GPP, it rapidly recovered after about 3 years. Then, the steady increase in GPP surpassed the GPP of the reference area in 2015 because of the rapid growth and high photosynthetic activity of young forests. Therefore, the concluding scientific message is that, because the recovery-time point for each component of the forest ecosystem is different, using only one satellite-based indicator will not be suitable to understand the post-fire recovery process. NBR, NDVI, and GPP can be combined. Further studies will require more approaches using various terms of indices.

Satellite remote sensing provides significant information for the monitoring of natural disasters. Recently, on a global scale, floods have been increasing both in frequency and in magnitude. In order to map the inundation area, flooding events are investigated using unique RGB composite imagery based on the MODIS surface reflectance (MOD09GA) data obtained from the Terra satellite, which is used to visualize and analyze these events. This study proposes using an RGB combination of MODIS band 6 (1.64 μm), band 5 (1.24 μm), and band 2 (0.86 μm) data from the visible and the near-infrared spectral ranges to map flood events. The flooding events that were investigated in this study occurred on 25 October 2015 along the Pampanga River in the Philippines, and on 28 July 2016 along the Poyang and Dongting Lakes in China. In the case of the Pampanga River, the inundated areas were estimated with surface reflectance (R) thresholds of 0.0 ≤ R₆ ≤ 0.102, 0.0 ≤ R₅ ≤ 0.138, and 0.03 ≤ R₂ ≤ 0.148 for MODIS bands 6, 5, and 2, respectively, which were determined using Otsu’s method. The total inundated area was estimated to be 487.75 km². This estimate was indirectly compared with the results obtained from SENTINEL-1A Synthetic Aperture Radar (SAR) data. The total inundated area on 26 October 2015 for the case of the Pampanga River was estimated to be 486.37 km² using histogram analysis based on Otsu’s method. For the flooding case in China, the total estimated inundated area using MODIS RGB imagery on 28 July 2016 and SAR on 3 August 2016 was 1148.25 km² and 1110.096 km², respectively. In addition, RGB imagery results using MODIS 6-5-2 bands were supported by the refractive index retrieval along the inundation area. A threshold of 1.6 for the real part of the complex refractive index allows for the discrimination between the flooded and non-flooded areas using the Hong and ASH approximations. This study shows that the RGB composite techniques using advanced sensors with more bands and higher spatio-temporal resolutions, and supported by the refractive index retrieval method, are useful for estimating flood events.

This paper investigates the benefits of integrating coarse resolution satellite-derived precipitation estimates with quasi-point rain gauge data for generating a fine spatial resolution precipitation map product. To integrate the two precipitation data sources, a geostatistical downscaling and integration approach is presented that can account for the differences in spatial resolution between data from different supports and adjusts inherent errors in the coarse resolution precipitation estimates. First, coarse resolution precipitation estimates are downscaled at a fine spatial resolution via area-to-point kriging to allow direct comparison with rain gauge data. Second, the downscaled precipitation estimates are integrated with the rain gauge data by multivariate kriging. In particular, errors in the coarse resolution precipitation estimates are adjusted against rain gauge data during this second stage. In this study, simple kriging with local means (SKLM) and kriging with an external drift (KED) are used as multivariate kriging algorithms. For comparative purposes, conditional merging (CM), a frequently-applied method for integrating rain gauge data and radar precipitation, is also employed. From a case study with Tropical Rainfall Measuring Mission (TRMM) 3B43 monthly precipitation products acquired in South Korea from May–October in 2013, we found that the incorporation of TRMM data with rain gauge data did not improve prediction performance when the number of rain gauge data was relatively large. However, the benefit of integrating TRMM and rain gauge data was most striking, regardless of multivariate kriging algorithms, when a small number of rain gauge data was used. These results indicate that the coarse resolution satellite-derived precipitation product would be a useful source for mapping precipitation at a fine spatial resolution if the geostatistical integration approach is applied to areas with sparse rain gauges.

Weather radars play an important role in in situ rainfall monitoring owing to their ability to measure instantaneous rain rates and rainfall distributions. Currently, the Korea Meteorological Administration (KMA) provides instantaneous radar observation data and predictions based on the McGill algorithm for precipitation nowcasting by Lagrangian extrapolation (MAPLE) for up to 6 h, for short-term forecasting. This study presents a conditional generative adversarial network (CGAN)-based radar rainfall prediction method for very short-range weather forecasts from 10 min to 4 h. The CGAN-predicted model was trained and tested using KMA’s constant altitude plan position indicator (CAPPI) observation data. The qualitative comparison between the radar observation and the CGAN-predicted rain rates displayed high statistical scores, such as the probability of detection (POD) = 0.8442, false alarm ratio (FAR) = 0.2913, and critical success index (CSI) = 0.6268, in the case of a 1-h prediction for rainfall on September 5, 2019, 15:20 KST. This study demonstrates the capability of the CGAN model for short-term rainfall forecasting. Consequently, the CGAN-generated radar-based rainfall prediction could complement the KMA MAPLE system and be useful in various forecasting applications.

Visible (VIS) bands, such as the 0.675 μm band in geostationary satellite remote sensing, have played an important role in monitoring and analyzing weather and climate change during the past few decades with coarse spatial and high temporal resolution. Recently, many deep learning techniques have been developed and applied in a variety of applications and research fields. In this study, we developed a deep-learning-based model to generate non-existent nighttime VIS satellite images using the Conditional Generative Adversarial Nets (CGAN) technique. For our CGAN-based model training and validation, we used the daytime image data sets of reflectance in the Communication, Ocean and Meteorological Satellite / Meteorological Imager (COMS/MI) VIS (0.675 μm) band and radiance in the longwave infrared (10.8 μm) band of the COMS/MI sensor over five years (2012 to 2017). Our results show high accuracy (bias = −2.41 and root mean square error (RMSE) = 36.85 during summer, bias = −0.21 and RMSE = 33.02 during winter) and correlation (correlation coefficient (CC) = 0.88 during summer, CC = 0.89 during winter) of values between the observed images and the CGAN-generated images for the COMS VIS band. Consequently, our CGAN-based model can be effectively used in a variety of meteorological applications, such as cloud, fog, and typhoon analyses during daytime and nighttime.