• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.33 no.6
• /
• pp.265-274
• /
• 2021

Outlier detection research in ocean data has traditionally been performed using statistical and distance-based machine learning algorithms. Recently, AI-based methods have received a lot of attention and so-called supervised learning methods that require classification information for data are mainly used. This supervised learning method requires a lot of time and costs because classification information (label) must be manually designated for all data required for learning. In this study, an autoencoder based on unsupervised learning was applied as an outlier detection to overcome this problem. For the experiment, two experiments were designed: one is univariate learning, in which only SST data was used among the observation data of Deokjeok Island and the other is multivariate learning, in which SST, air temperature, wind direction, wind speed, air pressure, and humidity were used. Period of data is 25 years from 1996 to 2020, and a pre-processing considering the characteristics of ocean data was applied to the data. An outlier detection of actual SST data was tried with a learned univariate and multivariate autoencoder. We tried to detect outliers in real SST data using trained univariate and multivariate autoencoders. To compare model performance, various outlier detection methods were applied to synthetic data with artificially inserted errors. As a result of quantitatively evaluating the performance of these methods, the multivariate/univariate accuracy was about 96%/91%, respectively, indicating that the multivariate autoencoder had better outlier detection performance. Outlier detection using an unsupervised learning-based autoencoder is expected to be used in various ways in that it can reduce subjective classification errors and cost and time required for data labeling.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.6B
• /
• pp.531-539
• /
• 2011

It has been widely acknowledged that climate system associated with extreme rainfall events was difficult to understand and extreme rainfall simulation in climate model was more difficult. This study developed a new model for extracting rainfall filed associated with extreme events as a way to characterize large scale climate system. Main interests are to derive location, size and direction of the rainfall field and this study developed an algorithm to extract the above characteristics from global climate data set. This study mainly utilized specific humidity and wind vectors driven by NCEP reanalysis data to define the rainfall field. Geometric first and second moments have been extensively employed in defining the rainfall field in selected zone, and an ellipsoid based model were finally introduced. The proposed geometric moments based ellipsoid model works equally well with regularly and irregularly distributed synthetic grid data. Finally, the proposed model was applied to space-time real rainfall filed. It was found that location, size and direction of the rainfall field was successfully extracted.

• Proceedings of KOSOMES biannual meeting
• /
• 2004.11a
• /
• pp.43-47
• /
• 2004

Two different sensors (here, KOMPSAT and RADARSAT) are considered for ship detection, and are used to delineate the detection performance for their data The experiments are set for coastal regions of Mokpo Port and Ulsan Port and field experiments on board pilot boat are conducted to collect in situ ship validation information such as ship type and length This paper introduce mainly the experiment result of ship detection by both RADARSAT SAR imagery and land-based RADAR data, operated by the local Authority of South Korean, so called vessel traffic system (VTS) radar. Fine imagery of Ulsan Port was acquired on June 19, 2004 and in-situ data such as wind speed and direction, taking pictures of ships and natural features were obtained aboard a pilot ship. North winds, with a maximum speed of 3.1 m/s were recorded Ship's position, size and shape and natural features of breakwaters, oil pipeline and alongside ship were compared using SAR and VTS. It is shown that KOMPSAT/EOC has a good performance in the detection of a moving ship at a speed of kts or more an hour that ship and its wake can be imaged. The detection capability of RADARSAT doesn't matter how fast ship is running and depends on a ship itself, e.g. its material, length and type. Our results indicate that SAR can be applicable to automated ship detection for a VTS and SAR combination service.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2004.06a
• /
• pp.3-17
• /
• 2004

Space-borne Earth observation technique is one of the most cost effective and rapidly advancing Earth science research tools today and the potential field and micro-wave radar applications have been leading the discipline. The traditional optical imaging systems including the well known Landsat, NOAA - AVHRR, SPOT, and IKONOS have steadily improved spatial imaging resolution but increasing cloud covers have the major deterrent. The new Earth observation satellites ENVISAT (launched on March 1 2002, specifically for Earth environment observation), ALOS (planned for launching in 2004 - 2005 period and ALOS stands for Advanced Land Observation Satellite), and RADARSAT-II (planned for launching in 2005) all have synthetic aperture radar (SAR) onboard, which all have partial or fully polarimetric imaging capabilities. These new types of polarimetric imaging radars with repeat orbit interferometric capabilities are opening up completely new possibilities in Earth system science research, in addition to the radar altimeter and scatterometer. The main advantage of a SAR system is the all weather imaging capability without Sun light and the newly developed interferometric capabilities, utilizing the phase information in SAR data further extends the observation capabilities of directional surface covers and neotectonic surface displacements. In addition, if one can utilize the newly available multiple frequency polarimetric information, the new generation of space-borne SAR systems is the future research tool for Earth observation and global environmental change monitoring. The potential field strength decreases as a function of the inverse square of the distance between the source and the observation point and geophysicists have traditionally been reluctant to make the potential field observation from any space-borne platforms. However, there have recently been a number of potential field missions such as ASTRID-2, Orsted, CHAMP, GRACE, GOCE. Of course these satellite sensors are most effective for low spatial resolution applications. For similar objects, AMPERE and NPOESS are being planned by the United States and France. The Earth science disciplines which utilize space-borne platforms most are the astronomy and atmospheric science. However in this talk we will focus our discussion on the solid Earth and physical oceanographic applications. The geodynamic applications actively being investigated from various space-borne platforms geological mapping, earthquake and volcano .elated tectonic deformation, generation of p.ecise digital elevation model (DEM), development of multi-temporal differential cross-track SAR interferometry, sea surface wind measurement, tidal flat geomorphology, sea surface wave dynamics, internal waves and high latitude cryogenics including sea ice problems.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.3 no.3
• /
• pp.135-142
• /
• 2001

This study attempts to categorizes the factors of forest fire occurrences based on regional meteorologic data and general forest no characteristics of 18 cities and guns in Kangwon province. lo accomplish this goal, some statistical analyses such as analysis of variance, correspondence analysis and multidimensional scaling were adopted. To reveal the forest fires pattern of study region, a categorization process was conducted by employing the quantification approach which modified and quantified the metric-data of fire occurrence dates. Also, The fire occurrence similarity was compared by using multidimensional scaling for each study region. The major results are summarized as follows: It was found that the meteorological factors emerged as different to each region are average and maximum temperature, minimum dew point temperature and average and maximum wind speed. In the result of correspondence analysis representing relationships between fire causes and study regions, Kangrung is caused by arsonist, Chulwon, Hwachen and Yanggu caused by military factor, Sokcho and Chunchen caused by the debris burning, and Samchuk caused by general man-caused fires, respectively. Finally, the forest fire occurrence pattern of this study regions were divided into five areas such as, group I including Samchuk, Kangryung, Chunchen, Wonju, Hongchen and Hhoingsung, group II including Donghae, Taebaek, Yangyang and Pyongchang, group III including Jungsun, Chulwon and Whachen, group Ⅵ including Gosung, Injae and Yanggu, and group V including Shokcho and Youngwol.