DEDNet: Offshore Eddy Detection and Location with HF Radar by Deep Learning

Liu, Fangyuan; Zhou, Hao; Wen, Biyang

doi:10.3390/s21010126

Cited by 16 publications

(8 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Streamline dihitung pada sekeliling pusat eddy dengan menggunakan medan arus geostropik yang didapatkan dari SLA; 3. Streamline tertutup dipilih dengan mencari streamline yang memiliki nilai WA absolut lebih atau sama dengan 2𝜋 (Liu et al, 2020); 4. Pusat eddy diidentifikasi dengan menentukan titik potensial yang dikelilingi oleh streamline tertutup; 5.…”

Section: Deteksi Eddy Dengan Winding Angleunclassified

Ketidakseragaman Sebaran Spasial Variabilitas Musiman Eddy di Perairan Barat Laut Indonesia

Kartadikaria,

Napitupulu,

Rangga

et al. 2024

J. Kel. Trop.

View full text Add to dashboard Cite

Sea level anomaly (SLA) data spanning from 1993 – 2022 were used to analyze the characteristic of eddy current in Northwest Indonesian. An improved winding angle method was used and was able to detect 1663 anticyclonic eddies (AEs) and 1748 cyclonic eddies (CEs). The average eddy lifespan is approximately four weeks. The eddy in the West Indonesian Ocean has a radius ranging from 40 – 100 km and a high number of mesoscale eddy (radius more than 100 km) detected in the northern area of West Indonesian Ocean (4° N - 10° N). The eddy kinetic energy (EKE) increased proportionally with their radius, whereas the eddy vorticity decreased proportionally with their increasing radius. The seasonal cycles of eddy circulation in the west Indonesian Ocean were differ for both AEs and CEs, where AEs were dominated during east monsoon season (JJA) and CEs came with longer periods from November to March, yet for both AEs and CEs they have similar radius per month. During weak periods of both eddies, their meridional distributions differ; CEs tend to be formed in relatively lower latitude, while AEs were concentrated in relatively higher latitude. Data anomali permukaan laut/sea level anomaly (SLA) dalam kurun waktu 1993 – 2022 digunakan untuk mempelajari karakteristik sirkulasi arus eddy di perairan barat laut Indonesia. Metode Winding Angles yang telah dimodifikasi mampu mendeteksi 1663 anticyclonic eddies (AE) dan 1748 cyclonic eddies (CE). Rata-rata umur eddy yang terdeteksi adalah sekitar empat minggu. Mayoritas sirkulasi arus eddy memiliki radius 40 – 100 km dan eddy dengan radius berskala meso (lebih dari 100 km) banyak terkonsentrasi di bagian utara (4° N - 10° N) perairan barat laut Indonesia. Nilai energi kinetik eddy (EKE) bertambah sebanding dengan pertambahan radius, sedangkan nilai vortisitas berbanding terbalik dengan radius. Sirkulasi arus eddy di perairan barat laut Indonesia pada musim timur (JJA) didominasi oleh AE , sedangkan CE mendominasi di musim barat (DJF) dengan periode yang lebih panjang dari November hingga Maret, namun dengan rata-rata radius yang sama setiap bulannya. Pada saat periode di mana kejadian eddy minimum, ditemukan perbedaan letak distribusi meridional eddy bervortisitas tinggi yang menunjukkan CE lebih didukung pembentukannya pada lintang yang lebih rendah daripada AE.

show abstract

Section: Deteksi Eddy Dengan Winding Angleunclassified

Ketidakseragaman Sebaran Spasial Variabilitas Musiman Eddy di Perairan Barat Laut Indonesia

Kartadikaria,

Napitupulu,

Rangga

et al. 2024

J. Kel. Trop.

View full text Add to dashboard Cite

show abstract

“…Conventional ocean current measuring instruments, such as current recorders and acoustic doppler current profilers (ADCP), measure data at single points. High-frequency radars (HFR) can be developed as an alternative for measuring surface currents at higher temporal and spatial resolutions; HFR is now widely applied [4][5][6]. HFR can provide highly resolved temporal (tens of minutes) and spatial data vital to understanding marine mechanisms over relatively large domains [7].…”

Section: Introductionmentioning

confidence: 99%

Assessment of Ocean Circulation Characteristics off the West Coast of Ireland Using HF Radar

Ren,

Pan,

Yang

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Research on coastal ocean circulation patterns over long time periods is significant for various marine endeavors: environmental protection, coastal engineering construction, and marine renewable energy extraction. Based on sea surface current data remotely observed using a shore-based high frequency radar (HFR) system for one year (2016), spatiotemporal characteristics of surface flow fields of sea surface flow fields along the west coast of Ireland are studied using harmonic analysis, rotary spectral analysis and representative flow fields over different seasons and the whole year. Coastal surface currents in the study area are strongly affected by tidal dynamics of the M2 constituent, showing significant characteristics of regular semidiurnal tide, such as M2 and S2. The energy spectrum distribution indicates that the tidal constituents M2 and S2 are the dominant periodic energy constituents in a counterclockwise spectrum, which mainly presents rotating flow; the representative diurnal tidal constituents is the constituent K1, and its energy spectrum distribution is mainly clockwise. A comparison between probable maximum current velocity (PMCV) and measured maximum current velocity (MMCV) is presented. It shows that although tidal current characteristics in the study area are significant, the main driving force of the currents at the time of the maximum currents is wind energy. These results provide new insights into a region of huge societal potential at early stages of sustainable economic exploitation where few data currently exist.

show abstract

“…This is the most commonly used method because it directly generates the desired output without extra steps. Studies related to its use include [431][432][433][434][435]. Lguensat et al [432] adopted U-Net [100] to classify each pixel into non-eddy, anticyclonic-eddy, or cycloniceddy from SSH maps.…”

mentioning

confidence: 99%

“…Lguensat et al [432] adopted U-Net [100] to classify each pixel into non-eddy, anticyclonic-eddy, or cycloniceddy from SSH maps. Both Xu et al [434] and Liu et al [433] leveraged PSPNet [283] to identify eddies from satellite-derived data. Although these studies adopt various networks, most of them fuse multi-scale features from the input, e.g., spatial pyramid operation [436] in PSPNet and FPN [58] in RetinaNet.…”

mentioning

confidence: 99%

GeoAI for Large-Scale Image Analysis and Machine Vision: Recent Progress of Artificial Intelligence in Geography

Hsu

2022

IJGI

View full text Add to dashboard Cite

GeoAI, or geospatial artificial intelligence, has become a trending topic and the frontier for spatial analytics in Geography. Although much progress has been made in exploring the integration of AI and Geography, there is yet no clear definition of GeoAI, its scope of research, or a broad discussion of how it enables new ways of problem solving across social and environmental sciences. This paper provides a comprehensive overview of GeoAI research used in large-scale image analysis, and its methodological foundation, most recent progress in geospatial applications, and comparative advantages over traditional methods. We organize this review of GeoAI research according to different kinds of image or structured data, including satellite and drone images, street views, and geo-scientific data, as well as their applications in a variety of image analysis and machine vision tasks. While different applications tend to use diverse types of data and models, we summarized six major strengths of GeoAI research, including (1) enablement of large-scale analytics; (2) automation; (3) high accuracy; (4) sensitivity in detecting subtle changes; (5) tolerance of noise in data; and (6) rapid technological advancement. As GeoAI remains a rapidly evolving field, we also describe current knowledge gaps and discuss future research directions.

show abstract

DEDNet: Offshore Eddy Detection and Location with HF Radar by Deep Learning

Cited by 16 publications

References 33 publications

Ketidakseragaman Sebaran Spasial Variabilitas Musiman Eddy di Perairan Barat Laut Indonesia

Ketidakseragaman Sebaran Spasial Variabilitas Musiman Eddy di Perairan Barat Laut Indonesia

Assessment of Ocean Circulation Characteristics off the West Coast of Ireland Using HF Radar

GeoAI for Large-Scale Image Analysis and Machine Vision: Recent Progress of Artificial Intelligence in Geography

Contact Info

Product

Resources

About