Enhancement of Wave Radar Observation Data Quality at the Socheongcho Ocean Research Station

Min, Yongchim; Jeong, Jin-Yong; Min, In-Ki; Kim, Yong Sun; Shim, Jae-Seol; Do, Kideok

doi:10.2112/si85-115.1

Cited by 5 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…After a series of variation and approximation operations, the calculation method of the uncertainty of the observed data is shown in equation (9). It is mainly composed of the error term, the KL divergence term, and the log calculation term.…”

Section: E Principle Of the New Loss Functionmentioning

confidence: 99%

“…A supervised learning algorithm needs to learn complex relationships between large datasets, and then it can predict unknown data based on these weights and biases. is requires the accuracy, integrity, and uniformity of observational data [8,9]. If the accuracy of the observed data is relatively poor, it is easy to cause poor learning e ect and generalization ability.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of a New Loss Function-Based Support Vector Machine Algorithm in Quality Control of Measurement Observation Data

Tao

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The loss function of the traditional support vector machine (SVM) method consists of hinge function and regularization, which is difficult to achieve the quality control of observation data. It requires a new loss function to measure the quality of the observed data. At this stage, researchers will use data cleaning or data preprocessing to process observational data. The data preprocessing method will normalize the data features, which will make the data process the same interval and a distribution. However, this method is also difficult to guarantee the accuracy of the data. This study uses the SVM method to study the integrity, unity, and accuracy of the observation data. This study also proposes a new loss function, which can obtain the uncertainty distribution of the observed data. The loss function of traditional SVM methods is that the uncertainty distribution of the data cannot be obtained. The results show that the SVM algorithm with the new loss function has better accuracy in processing the observed data. For the maximum prediction error of the observed data, the error with the new loss function is only 2.58%, which is reduced by 0.21% compared to the SVM method with the old loss function. However, the prediction error of the SVM algorithm with the old loss function is 2.78%, and the SVM algorithm with the new loss function has obvious prediction accuracy.

show abstract

Section: E Principle Of the New Loss Functionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Application of a New Loss Function-Based Support Vector Machine Algorithm in Quality Control of Measurement Observation Data

Tao

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…It is essential to perform quality verification for scientific analysis because the MWR has low reliability at low-wind and calm-wave conditions. The MWR analysis software had been used by applying optimum filter configuration (Min et al 2018) to secure reliability of the observed wave data by comparing to wave observations from the Directional Waverider buoy, which has been widely used by commercial companies and local authorities for many years, thus being regarded as an industry standard (Uncles and Mitchell 2017). Range Finder is also being operated to observe ocean waves as an auxiliary instrument for measuring the sea surface height, and thus can also monitor sea level variations due to the surface waves, contributing to the quality assurance of ocean surface wave measurements.…”

Section: Oceanographic Observations and Applications For Process Studmentioning

confidence: 99%

Observations Utilizing Korea Ocean Research Stations and their Applications for Process Studies

Nam

Jeong

et al. 2019

Bulletin of the American Meteorological Society

Self Cite

View full text Add to dashboard Cite

The main purposes for establishing the Korea ocean research stations (KORS) are for advancing an overall understanding of atmospheric and oceanic phenomena in the Yellow and East China Seas; for providing core scientific data for the studies on global environmental change, typhoon dynamics, biogeochemical cycles, marine ecosystems and fisheries, atmospheric chemistry involving Asian dust and aerosols, air–sea interaction processes including sea fog, and regional oceanographic process studies; and for functioning as ground stations of ocean remote sensing. Here, ocean–atmosphere time series observations with data service and case studies of KORS applications that will facilitate collaboration among researchers in the international atmospheric and oceanographic communities are presented.

show abstract

“…There is a radar-type two-dimensional wave monitoring instrument (Miros Wave and Current Radar; SM-050 MKIII) on the northeast rim of the roof deck. This wave sensor looks down onto the sea surface at an angle of 10 • , generally identifying waves 100-m away from the station (Min et al, 2018). An electrical winch system on the intermediate deck operates four stainless steel cables, which allow instruments to be lowered into the water.…”

Section: The Socheongcho Ocean Research Station (S-ors) Its Facilitiementioning

confidence: 99%

A Yellow Sea Monitoring Platform and Its Scientific Applications

et al. 2019

Self Cite

View full text Add to dashboard Cite

The Yellow Sea is one of the most productive continental shelves in the world. This large marine ecosystem is experiencing an epochal change in water temperature, stratification, nutrients, and subsequently in ecological diversity. Research-oriented monitoring of these changes requires a sustainable, multidisciplinary approach. For this purpose, the Korea Institute of Ocean Science and Technology (KIOST) constructed the Socheongcho Ocean Research Station (S-ORS), a steel-framed tower-type platform, in the central Yellow Sea about 50 km off the western coast of the Korean Peninsula. This station is equipped with about forty sensors for interdisciplinary oceanographic observations. Since its construction in 2014, this station has continuously conducted scientific observations and provided qualified time series: physical oceanographic variables such as temperature, salinity, sea level pressure, wave, and current; biogeochemical variables such as chlorophyll-a, photosynthetically active radiation, and total suspended particles; atmospheric variables including air temperature, wind, greenhouse gasses, and air particles including black carbon. A prime advantage is that this platform has provided stable facilities including a wet lab where scientists can stay and experiment on in situ water samples. Several studies are in process to understand and characterize the evolution of environmental signals, including airsea interaction, marine ecosystems, wave detection, and total suspended particles in the central Yellow Sea. This paper provides an overview of the research facilities, maintenance, observations, scientific achievements, and next steps of the S-ORS with highlighting this station as an open lab for interdisciplinary collaboration on multiscale process studies.

show abstract

Enhancement of Wave Radar Observation Data Quality at the Socheongcho Ocean Research Station

Cited by 5 publications

References 0 publications

Application of a New Loss Function-Based Support Vector Machine Algorithm in Quality Control of Measurement Observation Data

Application of a New Loss Function-Based Support Vector Machine Algorithm in Quality Control of Measurement Observation Data

Observations Utilizing Korea Ocean Research Stations and their Applications for Process Studies

A Yellow Sea Monitoring Platform and Its Scientific Applications

Contact Info

Product

Resources

About