In recent years, climate change has been responsible for unusual weather patterns on a global scale. Droughts, natural disasters triggered by insufficient rainfall, can inflict significant social and economic consequences on the entire agricultural sector due to their widespread occurrence and the challenge in accurately predicting their onset. The frequency of drought occurrences in South Korea has been rapidly increasing since 2000, with notably severe droughts hitting regions such as Incheon, Gyeonggi, Gangwon, Chungbuk, and Gyeongbuk in 2015, resulting in significant agricultural and social damage. To prepare for future drought occurrences resulting from climate change, it is essential to develop long-term drought predictions and implement corresponding measures for areas prone to drought. The Intergovernmental Panel on Climate Change (IPCC) Sixth Assessment Report outlines a climate change scenario under the Shared Socioeconomic Pathways (SSPs), which integrates projected future socio-economic changes and climate change mitigation efforts derived from the Coupled Model Intercomparison Project 6 (CMIP6). SSPs encompass a range of factors including demographics, economic development, ecosystems, institutions, technological advancements, and policy frameworks. In this study, various drought indices were calculated using SSP scenarios derived from 18 CMIP6 global climate models. The SSP5-8.5 scenario was employed as the climate change scenario, and meteorological drought indices such as the Standardized Precipitation Index (SPI), Self-Calibrating Effective Drought Index (scEDI), and Standardized Precipitation Evapotranspiration Index (SPEI) were utilized to analyze the prediction and variability of future drought occurrences in South Korea.

This study aimed to design and build a web-based decision support system for wheat cultivation management. The system is designed to collect and measure the weather environment at the growth stage on a daily basis and predict the soil moisture content. Based on this, APSIM, one of the process-based crop models, was used to predict the potential yield of wheat cultivation in real time by making decisions at each stage. The decision-making system for wheat crop management was designed to provide information through a web-based dashboard in consideration of user convenience and to comprehensively evaluate wheat yield potential according to past, present, and future weather conditions. Based on the APSIM model, the system estimates the current yield using past and present weather data and predicts future weather using the past 40 years of weather data to estimate the potential yield at harvest. This system is expected to be developed into a decision support system for farmers to prescribe irrigation and fertilizer in order to increase domestic wheat production and quality by enhancing the yield estimation model by adding influence factors that can contribute to improving wheat yield.

Soil texture is determined by the proportions of sand, silt, and clay within the soil, which influence characteristics such as porosity, water retention capacity, electrical conductivity (EC), and pH. Traditional classification of soil texture requires significant sample preparation including oven drying to remove organic matter and moisture, a process that is both time-consuming and costly. This study aims to explore an alternative method by developing an AI model capable of predicting soil texture from images of pre-sorted soil samples using computer vision and deep learning technologies. Soil samples collected from agricultural fields were pre-processed using sieve analysis and the images of each sample were acquired in a controlled studio environment using a smartphone camera. Color distribution ratios based on RGB values of the images were analyzed using the OpenCV library in Python. A convolutional neural network (CNN) model, built on PyTorch, was enhanced using Digital Image Processing (DIP) techniques and then trained across nine distinct conditions to evaluate its robustness and accuracy. The model has achieved an accuracy of over 80% in classifying the images of pre-sorted soil samples, as validated by the components of the confusion matrix and measurements of the F1 score, demonstrating its potential to replace traditional experimental methods for soil texture classification. By utilizing an easily accessible tool, significant time and cost savings can be expected compared to traditional methods.

Precipitation is an important component of the hydrological cycle and a key input parameter for many applications in hydrology, climatology, meteorology, and weather forecasting research. Grid-based satellite rainfall products with wide spatial coverage and easy accessibility are well recognized as a supplement to ground-based observations for various hydrological applications. The error properties of satellite rainfall products vary as a function of rainfall intensity, climate region, altitude, and land surface conditions. Therefore, this study aims to evaluate the commonly used new global grid-based satellite rainfall product, Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS), using data collected at different spatial and temporal scales. Additionally, in this study, grid-based CHIRPS satellite precipitation data were used to evaluate the 2022 extreme drought. CHIRPS provides high-resolution precipitation data at 5 km and offers reliable global data through the correction of ground-based observations. A frequency analysis was performed to determine the precipitation deficit in 2022. As a result of comparing droughts in 2015, 2017, and 2022, it was found that May 2022 had a drought frequency of more than 500 years. The 1-month SPI in May 2022 indicated a severe drought with an average value of -1.8, while the 3-month SPI showed a moderate drought with an average value of 0.6. The extreme drought experienced in South Korea in 2022 was evident in the 1-month SPI. Both CHIRPS precipitation data and observations from weather stations depicted similar trends. Based on these results, it is concluded that CHIRPS can be used as fundamental data for drought evaluation and monitoring in unmeasured areas of precipitation.

This study was conducted on how to simulate runoff, which was done using existing physical models, using an LSTM (Long Short-Term Memory) model based on deep learning. Tancheon, the first tributary of the Han River, was selected as the target area for the model application. To apply the model, one water level observatory and four rainfall observatories were selected, and hourly data from 2020 to 2023 were collected to apply the model. River water level of the outlet of the Tancheon basin was simulated by inputting precipitation data from four rainfall observation stations in the basin and average preceding 72-hour precipitation data for each hour. As a result of water level simulation using 2021 to 2023 data for learning and testing with 2020 data, it was confirmed that reliable simulation results were produced through appropriate learning steps, reaching a certain mean absolute error in a short period time. Despite the short data period, it was found that the mean absolute percentage error was 0.5544~0.6226%, showing an accuracy of over 99.4%. As a result of comparing the simulated and observed values of the rapidly changing river water level during a specific heavy rain period, the coefficient of determination was found to be 0.9754 and 0.9884. It was determined that the performance of LSTM, which aims to simulate river water levels, could be improved by including preceding precipitation in the input data and using precipitation data from various rainfall observation stations within the basin.