Grounded icebergs around Antarctica: a high-resolution dataset derived from deep learning and Sentinel-1 synthetic aperture radar

{"Abstract.":[0],"Icebergs":[1],"frequently":[2],"run":[3],"aground":[4],"on":[5,7,95,179,214,272],"shoals":[6],"the":[8,150,159,180,196,215,247,262,282,318,326],"continental":[9,217,274],"shelf":[10],"around":[11,204],"Antarctica.":[12,205],"Once":[13],"rendered":[14],"immobile,":[15],"they":[16],"can":[17],"anchor":[18],"landfast":[19],"sea":[20,121],"ice":[21,122,163,184,230,287,368],"(fast":[22],"ice)":[23],"and":[24,67,69,120,147,170,228,276,291,310,373],"their":[25,51],"supply":[26],"of":[27,58,63,77,161,201,208,238,261,278,286,307,317,325,331,347],"limiting":[28],"trace":[29],"nutrients":[30],"contribute":[31,344],"to":[32,124,155,191,194],"driving":[33],"coastal":[34,138],"marine":[35,48],"productivity.":[36],"They":[37],"are":[38,241,269,311],"also":[39],"associated":[40],"with":[41,44,108,321],"seabed":[42],"scouring,":[43],"implications":[45],"for":[46,258,365],"benthic":[47,375],"ecosystems.":[49],"Despite":[50],"importance,":[52],"there":[53],"is":[54,385],"currently":[55],"a":[56,71,103,109,141,304,356,362],"lack":[57],"accurate,":[59],"continent-wide":[60,199],"automated":[61,89],"mapping":[62,374],"grounded":[64,78,90,168,202,226,266,301,333,350,378],"iceberg":[65,91,153,267,294,379],"distribution":[66],"size":[68,154],"as":[70,243],"consequence,":[72],"no":[73],"large-scale,":[74],"complete":[75],"map":[76],"icebergs":[79,203,211,251,302,340],"exists.":[80],"To":[81],"address":[82],"these":[83,221,239,300],"gaps,":[84],"this":[85,348],"study":[86],"implements":[87],"an":[88],"detection":[92,142],"framework":[93],"based":[94],"Sentinel-1":[96],"Synthetic":[97],"Aperture":[98],"Radar":[99],"(SAR)":[100],"imagery,":[101],"integrating":[102],"proposed":[104],"ResUNet":[105],"deep-learning":[106],"network":[107],"multi-temporal":[110],"identification":[111],"algorithm,":[112],"incorporating":[113],"strict":[114],"physical":[115],"constraints":[116],"derived":[117],"from":[118,136],"bathymetry":[119],"concentration":[123],"mitigate":[125],"environmental":[126],"false":[127],"positives.":[128],"The":[129,377],"method":[130],"demonstrates":[131],"strong":[132],"robustness":[133],"against":[134],"interference":[135],"complex":[137,290],"conditions,":[139],"achieving":[140],"F1":[143],"score":[144],"exceeding":[145],"0.91":[146],"successfully":[148],"reducing":[149],"minimum":[151],"detectable":[152],"0.016":[156],"km².":[157],"Since":[158],"presence":[160],"fast":[162,175,183,229,367],"makes":[164],"distinction":[165],"between":[166],"\\"truly":[167],"icebergs\\"":[169,227],"\\"those":[171],"held":[172],"motionless":[173],"by":[174],"ice\\",":[176],"we":[177],"capitalise":[178],"unprecedented":[181],"low":[182],"extent":[185],"in":[186],"early":[187,192],"2025":[188],"(late":[189],"February":[190],"April)":[193],"construct":[195],"first":[197],"high-resolution,":[198],"dataset":[200,297,380],"A":[206],"total":[207,349],"38,905":[209],"stationary":[210,222],"were":[212],"identified":[213,242],"Antarctic":[216,319],"shelf.":[218],"We":[219],"partition":[220],"targets":[223,240],"into":[224],"\\"high-confidence":[225],"entrapped":[231],"candidates.":[232],"Analysis":[233],"shows":[234],"that":[235,299],"70.5":[236],"%":[237,260,316,324,330,346],"high-confidence":[244],"grounded.":[245],"Across":[246],"entire":[248],"dataset,":[249],"tiny":[250,339],"(<":[252,341],"1":[253,342],"km²)":[254,343],"dominate":[255],"numerically,":[256],"accounting":[257],"92.2":[259],"total.":[263],"These":[264,352],"high-density":[265],"clusters":[268,354],"primarily":[270],"concentrated":[271],"shallow":[273],"shelves":[275],"west":[277],"(i.e.,":[279],"downstream":[280],"of)":[281],"actively":[283],"disintegrating":[284],"fronts":[285],"shelves,":[288],"forming":[289],"discontinuous":[292],"\\"grounded":[293],"chains\\".":[295],"Our":[296],"reveals":[298],"cover":[303],"combined":[305],"area":[306],"13,719":[308],"km²":[309],"widely":[312],"distributed":[313],"along":[314],"56.7":[315],"coastline,":[320],"just":[322],"14.2":[323],"coastline":[327],"containing":[328],"80":[329],"all":[332],"icebergs.":[334],"Crucially,":[335],"while":[336],"typically":[337],"overlooked,":[338],"52.6":[345],"area.":[351],"dense":[353],"imply":[355],"potential":[357],"\\"picket":[358],"fence":[359],"effect\\",":[360],"providing":[361],"quantitative":[363],"baseline":[364],"modelling":[366],"stability,":[369],"assessing":[370],"nutrient":[371],"fluxes,":[372],"habitats.":[376],"(Jiao":[381],"et":[382],"al.,":[383],"2026)":[384],"available":[386],"at":[387],"https://doi.org/10.25959/54sx-pt47.":[388]}

Authors

Institutions

Publication Details

Journal
Earth system science data
Published
2026-08-25
DOI
https://doi.org/10.5194/essd-18-6017-2026
Citations
1
Primary Topic
Cryospheric studies and observations
Type
article
Field-Weighted Citation Impact
4.60

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
article

Grounded icebergs around Antarctica: a high-resolution dataset derived from deep learning and Sentinel-1 synthetic aperture radar

Johannes Lohse, Alexander T. Bradley, Pat Wongpan, Caitlin Adams et al.
1 citations
Earth system science data
Cryospheric studies and observations
4.60
article

Grounded icebergs around Antarctica: a high-resolution dataset derived from deep learning and Sentinel-1 synthetic aperture radar

Johannes Lohse, Alexander T. Bradley, Pat Wongpan, Caitlin Adams, Kaihong Jiao, Alexander D. Fraser
article en
1 citations

Abstract

Abstract. Icebergs frequently run aground on shoals on the continental shelf around Antarctica. Once rendered immobile, they can anchor landfast sea ice (fast ice) and their supply of limiting trace nutrients contribute to driving coastal marine productivity. They are also associated with seabed scouring, with implications for benthic marine ecosystems. Despite their importance, there is currently a lack of accurate, continent-wide automated mapping of grounded iceberg distribution and size and as a consequence, no large-scale, complete map of grounded icebergs exists. To address these gaps, this study implements an automated grounded iceberg detection framework based on Sentinel-1 Synthetic Aperture Radar (SAR) imagery, integrating a proposed ResUNet deep-learning network with a multi-temporal identification algorithm, incorporating strict physical constraints derived from bathymetry and sea ice concentration to mitigate environmental false positives. The method demonstrates strong robustness against interference from complex coastal conditions, achieving a detection F1 score exceeding 0.91 and successfully reducing the minimum detectable iceberg size to 0.016 km². Since the presence of fast ice makes distinction between "truly grounded icebergs" and "those held motionless by fast ice", we capitalise on the unprecedented low fast ice extent in early 2025 (late February to early April) to construct the first high-resolution, continent-wide dataset of grounded icebergs around Antarctica. A total of 38,905 stationary icebergs were identified on the Antarctic continental shelf. We partition these stationary targets into "high-confidence grounded icebergs" and fast ice entrapped candidates. Analysis shows that 70.5 % of these targets are identified as high-confidence grounded. Across the entire dataset, tiny icebergs (< 1 km²) dominate numerically, accounting for 92.2 % of the total. These high-density grounded iceberg clusters are primarily concentrated on shallow continental shelves and west of (i.e., downstream of) the actively disintegrating fronts of ice shelves, forming complex and discontinuous "grounded iceberg chains". Our dataset reveals that these grounded icebergs cover a combined area of 13,719 km² and are widely distributed along 56.7 % of the Antarctic coastline, with just 14.2 % of the coastline containing 80 % of all grounded icebergs. Crucially, while typically overlooked, tiny icebergs (< 1 km²) contribute 52.6 % of this total grounded area. These dense clusters imply a potential "picket fence effect", providing a quantitative baseline for modelling fast ice stability, assessing nutrient fluxes, and mapping benthic habitats. The grounded iceberg dataset (Jiao et al., 2026) is available at https://doi.org/10.25959/54sx-pt47.

Earth system science dataVol. 18(8)
University of Tasmania (AU), Australian Antarctic Division (AU), Geoscience Australia (AU), Department of Climate Change, Energy, the Environment and Water (AU), UiT The Arctic University of Norway (NO)
Department of Climate Change, Energy, the Environment and Water, Australian Research Council
Life below water
Openalex Percentile: Top 7%
Cryospheric studies and observations
4.60
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.