• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.143-143
• /
• 2022

Precipitation plays an essential role in water resources management and disaster prevention. Therefore, the understanding related to spatiotemporal characteristics of rainfall is necessary. Nowadays, highly accurate precipitation is mainly obtained from gauge observation systems. However, the density of gauge stations is a sparse and uneven distribution in mountainous areas. With the proliferation of technology, satellite-based precipitation sources are becoming increasingly common and can provide rainfall information in regions with complex topography. Nevertheless, satellite-based data is that it still remains uncertain. To overcome the above limitation, this study aims to take the strengthens of machine learning to generate a new reanalysis of precipitation data by fusion of multiple satellite precipitation products (SPPs) with gauge observation data. Several machine learning algorithms (i.e., Random Forest, Support Vector Regression, and Artificial Neural Network) have been adopted. To investigate the robustness of the new reanalysis product, observed data were collected to evaluate the accuracy of the products through Kling-Gupta efficiency (KGE), probability of detection (POD), false alarm rate (FAR), and critical success index (CSI). As a result, the new precipitation generated through the machine learning model showed higher accuracy than original satellite rainfall products, and its spatiotemporal variability was better reflected than others. Thus, reanalysis of satellite precipitation product based on machine learning can be useful source input data for hydrological simulations in ungauged river basins.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.134-134
• /
• 2021

Precipitation is a crucial component of water cycle and play a key role in hydrological processes. Traditionally, gauge-based precipitation is the main method to achieve high accuracy of rainfall estimation, but its distribution is sparsely in mountainous areas. Recently, satellite-based precipitation products (SPPs) provide grid-based precipitation with spatio-temporal variability, but SPPs contain a lot of uncertainty in estimated precipitation, and the spatial resolution quite coarse. To overcome these limitations, this study aims to generate new grid-based daily precipitation using Automatic weather system (AWS) in Korea and multiple SPPs(i.e. CHIRPSv2, CMORPH, GSMaP, TRMMv7) during the period of 2003-2017. And this study used a machine learning based Random Forest (RF) model for generating new merging precipitation. In addition, several statistical linear merging methods are used to compare with the results of the RF model. In order to investigate the efficiency of RF, observed data from 64 observed Automated Synoptic Observation System (ASOS) were collected to evaluate the accuracy of the products through Kling-Gupta efficiency (KGE), probability of detection (POD), false alarm rate (FAR), and critical success index (CSI). As a result, the new precipitation generated through the random forest model showed higher accuracy than each satellite rainfall product and spatio-temporal variability was better reflected than other statistical merging methods. Therefore, a random forest-based ensemble satellite precipitation product can be efficiently used for hydrological simulations in ungauged basins such as the Mekong River.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.120-120
• /
• 2020

Spatial precipitation data is one of the essential components in modeling hydrological problems. The estimation of these data has achieved significant achievements own to the recent advances in remote sensing technology. However, there are still gaps between the satellite-derived rainfall data and observed data due to the significant dependence of rainfall on spatial and temporal characteristics. An effective approach based on the Convolutional Neural Network (CNN) model to correct the satellite-derived rainfall data is proposed in this study. The Mekong River basin, one of the largest river system in the world, was selected as a case study. The two gridded precipitation data sets with a spatial resolution of 0.25 degrees used in the CNN model are APHRODITE (Asian Precipitation - Highly-Resolved Observational Data Integration Towards Evaluation) and PERSIANN-CDR (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks). In particular, PERSIANN-CDR data is exploited as satellite-based precipitation data and APHRODITE data is considered as observed rainfall data. In addition to developing a CNN model to correct the satellite-based rain data, another statistical method based on standard deviations for precipitation bias correction was also mentioned in this study. Estimated results indicate that the CNN model illustrates better performance both in spatial and temporal correlation when compared to the standard deviation method. The finding of this study indicated that the CNN model could produce reliable estimates for the gridded precipitation bias correction problem.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.62 no.1
• /
• pp.83-93
• /
• 2020

East Asia, which includes China, Japan, Korea, and Mongolia, is highly impacted by hydroclimate extremes such drought, flood, and typhoon recent year. In 2017, more than 18.5 million hectares of crops have been damaged in China, and Korea has suffered economic losses as a result of severe drought. Satellite-derived rainfall products are becoming more accurate as space and time resolution become increasingly higher, and provide an alternative means of estimating ground-based rainfall. In this study, we verified the availability of rainfall products by comparing widely used satellite images such as Climate Hazards Groups InfraRed Precipitation with Station (CHIRPS), Global Precipitation Climatology Centre (GPCC), and Precipitation Estimation From Remotely Sensed Information Using Artificial Neural Networks-Climate Data Record (PERSIANN-CDR) with ground stations in East Asia. Also, the satellite-based rainfall products were used to calculate the Standardized Precipitation Index (SPI). The temporal resolution is based on monthly images and compared with the past 30 years data from 1989 to 2018. The comparison between rainfall data based on each satellite image products and the data from weather station-based weather data was shown by the coefficient of determination and showed more than 0.9. Each satellite-based rainfall data was used for each grid and applied to East Asia and South Korea. As a result of SPI analysis, the RMSE values of CHIRPS were 0.57, 0.53 and 0.47, and the MAE values of 0.46, 0.43 and 0.37 were better than other satellite products. This satellite-derived rainfall estimates offers important advantages in terms of spatial coverage, timeliness and cost efficiency compared to analysis for drought assessment with ground stations.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.23 no.3
• /
• pp.208-219
• /
• 2020

This study aims to determine the applicability of satellite precipitation to the ungauged or inaccessible areas by comparing the accuracy of satellite precipitation. The accuracy assessment showed that the overall spatial distributions of ground-based rainfall and satellite precipitation were similar in all three events. For one-month precipitation with one-hour temporal resolution, the correlations between ground-based precipitation (ASOS) and satellite precipitation were analyzed to be between 0.42 and 0.46. In the evaluation during the period in which precipitation was concentrated, the correlation coefficients for one-hour temporal resolution data were analyzed as 0.55 to 0.66 for IMERG and 0.56 to 0.67 for GSMAP. According to the total rainfall analysis of each rainfall station for the three events, the correlation coefficients of IMERG and GSMaP were relatively better than CMORPH, and the bias of CMORPH data was relatively better than IMERG and GSMaP. However, all the three satellite precipitation were underestimated compared to the ground-based precipitation. In the future, a study will be carried out to estimate precipitation across the Korean Peninsula, including North Korea, reflecting the results from this study.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.62 no.2
• /
• pp.39-52
• /
• 2020

A high quality, long-term, high-resolution precipitation dataset is an essential in climate analyses and global water cycles. Rainfall data from station observations are inadequate over many parts of the world, especially North Korea, due to non-existent observation networks, or limited reporting of gauge observations. As a result, satellite-based rainfall estimates have been used as an alternative as a supplement to station observations. The Climate Hazards Group Infrared Precipitation (CHIRP) and CHIRP combined with station observations (CHIRPS) are recently produced satellite-based rainfall products with relatively high spatial and temporal resolutions and global coverage. CHIRPS is a global precipitation product and is made available at daily to seasonal time scales with a spatial resolution of 0.05° and a 1981 to near real-time period of record. In this study, we analyze the applicability of CHIRPS data on the Korean Peninsula by supplementing the lack of precipitation data of North Korea. We compared the daily precipitation estimates from CHIRPS with 81 rain gauges across Korea using several statistical metrics in the long-term period of 1981-2017. To summarize the results, the CHIRPS product for the Korean Peninsula was shown an acceptable performance when it is used for hydrological applications based on monthly rainfall amounts. Overall, this study concludes that CHIRPS can be a valuable complement to gauge precipitation data for estimating precipitation and climate, hydrological application, for example, drought monitoring in this region.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.188-188
• /
• 2017

Rainfall is an important input to hydrological models. The accuracy of hydrological studies for water resources and floods management depend primarily on the estimation of rainfall. Thailand is among the countries that have regularly affected by floods. Flood forecasting and warning are necessary to prevent or mitigate loss and damage. Merging near real time satellite-based precipitation estimation with relatively high spatial and temporal resolutions to ground gauged precipitation data could contribute to reducing uncertainty and increasing efficiency for flood forecasting application. This study tested the applicability of satellite-based rainfall for water resources management and flood forecasting. The objectives of the study are to assess uncertainty associated with satellite-based rainfall estimation, to perform bias correction for satellite-based rainfall products, and to evaluate the performance of the bias-corrected rainfall data for the prediction of flood events. This study was conducted using a case study of Thai catchments including the Chao Phraya, northeastern (Chi and Mun catchments), and the eastern catchments for the period of 2006-2015. Data used in the study included daily rainfall from ground gauges, telegauges, and near real time satellite-based rainfall products from TRMM, GSMaP and PERSIANN CCS. Uncertainty in satellite-based precipitation estimation was assessed using a set of indicators describing the capability to detect rainfall event and efficiency to capture rainfall pattern and amount. The results suggested that TRMM, GSMaP and PERSIANN CCS are potentially able to improve flood forecast especially after the process of bias correction. Recommendations for further study include extending the scope of the study from regional to national level, testing the model at finer spatial and temporal resolutions and assessing other bias correction methods.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.35 no.5
• /
• pp.423-430
• /
• 2017

Recently, data analysis research has been carried out using the deep learning technique in various fields such as image interpretation and/or classification. Various types of algorithms are being developed for many applications. In this paper, we propose a precipitation prediction algorithm based on deep learning with high accuracy in order to take care of the possible severe damage caused by climate change. Since the geographical and seasonal characteristics of Korea are clearly distinct, the meteorological factors have repetitive patterns in a time series. Since the LSTM (Long Short-Term Memory) is a powerful algorithm for consecutive data, it was used to predict precipitation in this study. For the numerical test, we calculated the PWV (Precipitable Water Vapor) based on the tropospheric delay of the GNSS (Global Navigation Satellite System) signals, and then applied the deep learning technique to the precipitation prediction. The GNSS data was processed by scientific software with the troposphere model of Saastamoinen and the Niell mapping function. The RMSE (Root Mean Squared Error) of the precipitation prediction based on LSTM performs better than that of ANN (Artificial Neural Network). By adding GNSS-based PWV as a feature, the over-fitting that is a latent problem of deep learning was prevented considerably as discussed in this study.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.66 no.3
• /
• pp.25-37
• /
• 2024

Global warming-induced drought inflicts significant socio-economic and environmental damage. In Korea, the persistent drought in the southern region since 2022 has severely affected water supplies, agriculture, forests, and ecosystems due to uneven precipitation distribution. To effectively prepare for and mitigate such impacts, it is imperative to develop proactive measures supported by early monitoring systems. In this study, we analyzed the spatiotemporal changes of multiple evapotranspiration-based drought indices, focusing on the flash drought event in the southern region in 2022. The indices included the Evaporative Demand Drought Index (EDDI), Standardized Precipitation Evapotranspiration Index (SPEI) considering precipitation and temperature, and the Evaporative Stress Index (ESI) based on satellite images. The Standardized Precipitation Index (SPI) and SPEI indices utilized temperature and precipitation data from meteorological observation stations, while the ESI index was based on satellite image data provided by the MODIS sensor on the Terra satellite. Additionally, we utilized the Evaporative Demand Drought Index (EDDI) provided by the North Oceanic and Atmospheric Administration (NOAA) as a supplementary index to ESI, enabling us to perform more effective drought monitoring. We compared the degree and extent of drought in the southern region through four drought indices, and analyzed the causes and effects of drought from various perspectives. Findings indicate that the ESI is more sensitive in detecting the timing and scope of drought, aligning closely with observed drought trends.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.61 no.2
• /
• pp.1-11
• /
• 2019

Remote sensing products have long been used to monitor and forecast natural disasters. Satellite-derived rainfall products are becoming more accurate as space and time resolution improve, and are widely used in areas where measurement is difficult because of the periodic accumulation of images in large areas. In the case of North Korea, there is a limit to the estimation of precipitation for unmeasured areas due to the limited accessibility and quality of statistical data. CHIRPS (Climate Hazards Group InfraRed Precipitation with Stations) is global satellite-derived rainfall data of 0.05 degree grid resolution. It has been available since 1981 from USAID (U.S. Agency for International Development), NASA (National Aeronautics and Space Administration), NOAA (National Oceanic and Atmospheric Administration). This study evaluates the applicability of CHIRPS rainfall products for South Korea and North Korea by comparing CHIRPS data with ground observation data, and analyzing temporal and spatial drought trends using the Standardized Precipitation Index (SPI), a meteorological drought index available through CHIRPS. The results indicate that the data set performed well in assessing drought years (1994, 2000, 2015 and 2017). Overall, this study concludes that CHIRPS is a valuable tool for using data to estimate precipitation and drought monitoring in Korea.