20 research outputs found
Improved Ocean-Fog Monitoring Using Himawari-8 Geostationary Satellite Data Based on Machine Learning With SHAP-Based Model Interpretation
No full textOcean-fog is a type of fog that forms over the ocean and has a visibility of less than 1 km. Ocean-fog frequently causes incidents over oceanic and coastal regions; ocean-fog detection is required regardless of the time of day. Ocean-fog has distinct thermo-optical properties, and spatially and temporally extensive ocean-fog detection methods based on geostationary satellites are typically employed. Infrared (IR) channels of Himawari-8 were used to construct three machine-learning models for the continuous detection of ocean-fog. In contrast, visible channels are valid only during the daytime. As control models, we used fog products from the National Meteorological Satellite Center (NMSC) and machine-learning models trained by adding a visible channel. The extreme gradient boosting model utilizing IR channels corrected ocean-fog perfectly day and night, with the highest F1 score of 97.93% and a proportion correct (PC) of 98.59% throughout the day. In contrast, the NMSC product had a probability of detection of 87.14%, an F1 score of 93.13%, and a PC of 71.9%. As demonstrated by the qualitative evaluation, the NMSC product overestimates clouds over small and coarsely textured ocean-fog regions. In contrast, the proposed model distinguishes between ocean-fog, clear skies, and clouds at the pixel scale. The Shapley additive explanation analysis demonstrated that the difference between channels 14 and 7 was very useful for ocean-fog detection at night, and its extremely low values contributed significantly to distinguishing nonfog during the daytime. Channel 15, affected by water vapor absorption, contributed most to ocean-fog detection among atmospheric window channels. The research findings can be used to improve operational ocean-fog detection and forecasting
An Advanced Operational Approach for Tropical Cyclone Center Estimation Using Geostationary-Satellite-Based Water Vapor and Infrared Channels
No full textTropical cyclones (TCs) are destructive natural disasters. Accurate prediction and monitoring are important to mitigate the effects of natural disasters. Although remarkable efforts have been made to understand TCs, operational monitoring information still depends on the experience and knowledge of forecasters. In this study, a fully automated geostationary-satellite-based TC center estimation approach is proposed. The proposed approach consists of two improved methods: the setting of regions of interest (ROI) using a score matrix (SCM) and a TC center determination method using an enhanced logarithmic spiral band (LSB) and SCM. The former enables prescreening of the regions that may be misidentified as TC centers during the ROI setting step, and the latter contributes to the determination of an accurate TC center, considering the size and length of the TC rainband in relation to its intensity. Two schemes, schemes A and B, were examined depending on whether the forecasting data or real-time observations were used to determine the initial guess of the TC centers. For each scheme, two models were evaluated to discern whether SCM was combined with LSB for TC center determination. The results were investigated based on TC intensity and phase to determine the impact of TC structural characteristics on TC center determination. While both proposed models improved the detection performance over the existing approach, the best-performing model (i.e., LSB combined with SCM) achieved skill scores (SSs) of +17.4% and +20.8% for the two schemes. In particular, the model resulted in a significant improvement for strong TCs (categories 4 and 5), with SSs of +47.8% and +72.8% and +41.2% and +72.3% for schemes A and B, respectively. The research findings provide an improved understanding of the intensity- and phase-wise spatial characteristics of TCs, which contributes to objective TC center estimation
Estimation of Spatially Continuous Near-Surface Relative Humidity Over Japan and South Korea
No full textNear-surface relative humidity (RHns) is an essential meteorological parameter for water, carbon, and climate studies. However, spatially continuous RHns estimation is difficult due to the spatial discontinuity of in situ observations and the cloud contamination of satellite-based data. This article proposed machine learning-based models to estimate spatially continuous daily RHns at 1 km resolution over Japan and South Korea under all sky conditions and examined the spatiotemporal patterns of RHns. All sky estimation of RHns using machine learning has been rarely conducted, and it can be an alternative to the currently available RHns data mostly from numerical models, which have relatively low spatial resolution. We combined two schemes for clear sky conditions (scheme A, which uses satellite and reanalysis data) and cloudy sky conditions (scheme B, which uses reanalysis data solely). The relatively small numbers of data in extremely low and high RHns conditions (i.e., <30% or >70%, respectively) were augmented by applying an oversampling method to avoid biased training. The machine learning models based on random forest (RF) and XGBoost were trained and validated using 94 in situ observation sites from meteorological administrations of both countries from 2012 to 2017. The results showed that XGBoost produced slightly better performance than RF, and the spatially continuous RHns model combined based on XGBoost yielded the coefficient of determination of 0.72 and a root-mean-square error of 10.61%. Spatiotemporal patterns of the estimated RHns agreed with in situ observations, reflecting the effect of topography on RHns. We expect that the proposed RHns model could be used in various environmental studies that require RHns under all sky conditions as input data
Estimation of Sea Surface Salinity Around the Korean Peninsula Using Machine Learning
No full textSalinity is one of the most important indicators of ocean circulation and affects the marine environment. Sea Surface Salinity (SSS) is highly related to various ocean-atmosphere phenomena and thus, the monitoring of SSS is crucial to investigate regional/global ocean environment and climate change. Field surveys, which are often used for SSS observation, are time-consuming and expensive, and do not cover vast areas with spatial continuity. On the other hand, satellite data (e.g., passive microwave) or numerical models can be used to quantify SSS with spatially continuous coverage. However, they have a relatively coarse resolution and often high regional uncertainty. In particular, existing satellite and model-derived SSS around the Korean Peninsula focusing on coastal areas has spatiotemporally varied uncertainty, which requires more regional SSS estimation models. The purpose of this study is to estimate SSS around the Korean Peninsula with higher resolution than existing satellite-derived SSS products using multi-sensor data fusion based on machine learning approaches such as random forest and neural network. In this study, Geostationary Ocean Color Imager (GOCI) and passive microwave satellites and Hybrid Coordinate Ocean Model (HYCOM) reanalysis data were used as main input data in this study. GOCI is the world first geostationary ocean color observation sensor, and it collects 8 images hourly per day at 500 m resolution. The reflectance data and basic products of GOCI with 500m resolution were used to improve the spatial resolution of SSS especially focusing on coastal regions. The results showed that SSS estimated using the proposed approach yielded a higher accuracy than the existing SSS data. This advanced model is expected to more accurately monitor SSS around the Korean peninsula
Detection of melt ponds on sea ice in the Chukchi Sea in summer season using TerraSAR-X dual-polarization data
No full text?????? ??????????????? ??????????????? ????????? ???????????? ?????? ?????? ??????
No full textOcean salinity affects ocean circulation on a global scale and low salinity water around coastal areas often has an impact on aquaculture and fisheries. Microwave satellite sensors (e.g., Soil Moisture Active Passive [SMAP]) have provided sea surface salinity (SSS) based on the dielectric characteristics of water associated with SSS and sea surface temperature (SST). In this study, a Light Gradient Boosting Machine (LGBM)-based model for generating high resolution SSS from Geostationary Ocean Color Imager (GOCI) data was proposed, having machine learning-based improved SMAP SSS by Jang et al. (2022) as reference data (SMAP SSS (Jang)). Three schemes with different input variables were tested, and scheme 3 with all variables including Multi-scale Ultra-high Resolution SST yielded the best performance (coefficient of determination = 0.60, root mean square error = 0.91 psu). The proposed LGBM-based GOCI SSS had a similar spatiotemporal pattern with SMAP SSS (Jang), with much higher spatial resolution even in coastal areas, where SMAP SSS (Jang) was not available. In addition, when tested for the great flood occurred in Southern China in August 2020, GOCI SSS well simulated the spatial and temporal change of Changjiang Diluted Water. This research provided a potential that optical satellite data can be used to generate high resolution SSS associated with the improved microwave-based SSS especially in coastal areas
Improving Short-Term Prediction of Ocean Fog Using Numerical Weather Forecasts and Geostationary Satellite-Derived Ocean Fog Data Based on AutoML
No full textOcean fog, a meteorological phenomenon characterized by reduced visibility due to tiny water droplets or ice particles, poses significant safety risks for maritime activities and coastal regions. Accurate prediction of ocean fog is crucial but challenging due to its complex formation mechanisms and variability. This study proposes an advanced ocean fog prediction model for the Yellow Sea region, leveraging satellite-based detection and high-performance data-driven methods. We used Himawari-8 satellite data to obtain a lot of spatiotemporal ocean fog references and employed AutoML to integrate numerical weather prediction (NWP) outputs and sea surface temperature (SST)-related variables. The model demonstrated superior performance compared to traditional NWP-based methods, achieving high performance in both quantitative—probability of detection of 81.6%, false alarm ratio of 24.4%, f1 score of 75%, and proportion correct of 79.8%—and qualitative evaluations for 1 to 6 h lead times. Key contributing variables included relative humidity, accumulated shortwave radiation, and atmospheric pressure, indicating the importance of integrating diverse data sources. The study emphasizes the potential of using satellite-derived data to improve ocean fog prediction, while also addressing the challenges of overfitting and the need for more comprehensive reference data
Icing detection from geostationary satellite data over Korea and Japan using machine learning approaches
No full textDevelopment of Red Tide Detection Algorithm using GOCI Image based on Random Forest
No full textThe socio-economic damages on the fishery and aquacultural industries caused by the red tide have been increased in Korea. The remote sensing techniques using the ocean color (OC) satellite imagery has been developed in order to observe the red tide. However, the Korean red tide information system (RTIS) is still relying on ship surveillance. It has limitations to cover the whole coastal area as well as take lots of cost and time. This study developed the random forest (RF) based red tide detection model using the Geostationary Ocean Color Imager (GOCI) satellite imagery which has a higher spatio-temporal resolution (i.e., 500 x 500m, hourly). The spectral characteristics, quantitative and qualitative analysis, and spatio-temporal analysis of red tides in the South Sea of Korea during July ??? August 2018 were examined. The RF model showed promising detection accuracy (R2 = 0.701) than the other three algorithms at high concentrations (over 1,000 cells/mL) quantitatively as well as qualitatively. (i.e., modified red tide index (MRI, R2 = 0.192), red-to-blue ratio (RBR, R2 = 0.683), and spectral shape (SS, R2 = 0.531)). The detection model can provide an accurate red tide alert map in near-realtime as well as contribute to reducing socio-economic damages from the red tides in Korea
Ocean Fog Detection using Himawari-8 data over the Yellow sea with Machine Learning Approaches
No full textOcean fog (OF) is a phenomenon in which the visibility distance is less than 1km over the ocean due to the droplets. OF has a role not only as a moisture source, for the plants when it enters the land, also as an obstacle to maritime traffic. Many harbors set up fog detectors on the land to monitor OF occurrence near their port, but it covers a limited area. Recently, satellite remote sensing which covers wider area was usually applied on this criterion, but it is hard to identify the OF condition because of the complexity of generation condition and optical-thermal properties. Thus, in this study, machine learning approaches (e.g., random forest, support vector machine, logistic regression) were used to observe OF occurrence. As spatial coverage, temporal coverage is also important for maritime traffic, so the geostationary satellite (i.e., Himawari-8) data were used. The study area is the Yellow sea, which is suffering from OFs frequently. The Cloud-Aerosol Lidar with Orthogonal Polarization data were used to get OF location as follows Wu et. al. (2015). For the temporal seamless monitoring, infrared channels 0of Himawari-8 were used as the input images. From the input images, not only thermal feature such as mean, maximum and minimum, but also spatio-temporal feature such as roughness of buffer area, temporal anomaly. Additional post processing was applied to check the reliability of each OF pixels
