The classification and quantification of ice-rafted debris(IRD)in marine sediments are key to reconstructing glacial-interglacial dynamics and sediment provenance.However,traditional IRD analysis,based on manual grain...The classification and quantification of ice-rafted debris(IRD)in marine sediments are key to reconstructing glacial-interglacial dynamics and sediment provenance.However,traditional IRD analysis,based on manual grain identification under binocular microscopes,is time-consuming and dependent on expertise,which acted as a barrier to entry for IRD research.Here,we present a deep learning-based framework for the automated detection and lithological classification of IRD from high-resolution microscopic images with grains from natural Arctic sediments.Using the YOLOv11 algorithm,we designed a two-stage model:an instance segmentation model(Model 1)that detects individual IRD from multi-grain images,and a classification model(Model 2)that categorizes each grain into one of four lithological types(i.e.,quartz,detrital carbonate,clastic,and crystalline).The dataset comprises 110 images containing 9642 grains from the Chukchi Sea sediment core ARA14C-ST12.Model 1 achieved the detection performance with precision=0.95,recall=0.97,mAP50=0.98,mAP50-95=0.85,and F1 score=0.96,demonstrating high model performance to detect the complex morphology of grain.The evaluation metric of Model 2,used to identify lithological classes,showed average Top-1 accuracy of 0.87 and 0.75 on the validation and test sets,respectively.The classification model showed reliable recognition for quartz and detrital carbonate,with moderate confusion between clastic and crystalline grains.These results demonstrate that the proposed YOLOv11-based approach enables rapid,reproducible,and objective lithological classification of IRD grains,providing an efficient alternative to conventional manual counting.展开更多
Understanding the sediment record during the Little Ice Age(LIA)can help elucidate natural sea ice fluctuation and carbon cycle variability.This study analyzed the grain size composition(including ice-rafted debris),t...Understanding the sediment record during the Little Ice Age(LIA)can help elucidate natural sea ice fluctuation and carbon cycle variability.This study analyzed the grain size composition(including ice-rafted debris),total organic carbon(TOC),total nitrogen(TN)content,and stable isotopic composition(δ13C andδ15N)of the sediment record(approximately 490 a)of core ARC7-R11 in the northern part of the Chukchi Shelf.The sediment grains comprise mostly(>90%)silt and clay components.The grain size composition suggests generally low-energy hydrodynamic conditions across the region,yet reveals a trend of enhancement in hydrodynamics from the bottom to top layers of the sediment core,particularly after the 1940s.It also shows occurrences of seasonal sea ice and retreat of the perennial sea ice margin during warmer periods of the LIA and the post-LIA period.The organic matter content is high throughout the core,with heavierδ13C values and moderate TOC/TN ratios indicating primarily marine origin;the terrestrial input is<37.5%according to the endmember model.The variation trend of marine-derived organic carbon(OC)content is similar to that of summer temperature anomalies;while variation trend of terrestrially derived OC shows significant correlation with that of the number of ice-free days in the southern shelf region,except for the period from approximately 1700s to the 1870s.During the LIA,the TOC content fluctuated and decreased,and the relative contribution of terrestrial OC was higher than during the modern warm period.The amount of OC buried in the sediment has increased with climate warming,especially after the 1940s,reflecting the enhanced ability of sediment to sequester carbon during warmer periods.展开更多
Quantitative analytic results of the biogenic components in Core B2-9 fromthe northern Bering Sea slope indicate that the coarse fraction and opal content, serving as proxiesof surface productivity, have increased ste...Quantitative analytic results of the biogenic components in Core B2-9 fromthe northern Bering Sea slope indicate that the coarse fraction and opal content, serving as proxiesof surface productivity, have increased stepwise since the marine isotope stageCMISJS.S, reflectingperiodic enhancement in surface productivity.The surface productivity attained its highest levelduring the Holocene, followed by MIS 3.2 to 2 and then MIS 5.3 to 3.3 with a lowest level. Hightotal organic carbon(TOC) contents, together with high C/N ratios, which stand mostly between 7 and20, show that the TOC was deposited from mixing sources. Therefore,one has to be cautious to use TOCas a proxy of surface productivity.The high TOC and C/N ratio during MIS 5.1, 3.3 to 3.2 and theHolocene reflect that the terrigenous organic matter input increased during interglacialperiods.Increases in the fine- and silt-grained terrigenous components from MIS 5.3 to the middleHolocene imply that with the cooling climate, sea ice on the Bering Sea slope extended continuously.Ice-rafted and charcoal detritus increased during glacial, interstadial and the last deglaciationperiods and decreased during interglacial periods, suggesting that sea ice on the slope increasedand melted, respectively, during glacial and interglacial periods. The extension of sea ice duringglacial periods.which was linked with the climate over the North American Continent, responded toglobal climate change during late Quaternary glacial and interglacial cycles.展开更多
Results of grain size analysis and rock magnetic measurements of core NP95-1 from Prydz Bay, Antarctica revealed two series of ice-rafted detritus layers, which correspond to cold climatic events, Younger Dryas and He...Results of grain size analysis and rock magnetic measurements of core NP95-1 from Prydz Bay, Antarctica revealed two series of ice-rafted detritus layers, which correspond to cold climatic events, Younger Dryas and Heinrich event 1, occurring at about 11.7-10.3 and 14.3-13.6 kaB.P. respectively. Studies also show that the sequence of paleoclimatic changes in Antarctica can be correlated with that in other parts of the world, and that the millennial climate of the earth could change synchronously and globally. In addition, magnetic fabric analysis also shows a close relationship between paleoclimatic change and ocean circulation re-assemblage.展开更多
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Ministry of Education(RS-2023-00301974)the Ministry of Science and ICT of Korea(RS-2024-00453681 and RS-2025-02293161)supported by the Korea Polar Research Institute(KIMST Grant,20210632)funded by the Ministry of Ocean and Fisheries,South Korea.
文摘The classification and quantification of ice-rafted debris(IRD)in marine sediments are key to reconstructing glacial-interglacial dynamics and sediment provenance.However,traditional IRD analysis,based on manual grain identification under binocular microscopes,is time-consuming and dependent on expertise,which acted as a barrier to entry for IRD research.Here,we present a deep learning-based framework for the automated detection and lithological classification of IRD from high-resolution microscopic images with grains from natural Arctic sediments.Using the YOLOv11 algorithm,we designed a two-stage model:an instance segmentation model(Model 1)that detects individual IRD from multi-grain images,and a classification model(Model 2)that categorizes each grain into one of four lithological types(i.e.,quartz,detrital carbonate,clastic,and crystalline).The dataset comprises 110 images containing 9642 grains from the Chukchi Sea sediment core ARA14C-ST12.Model 1 achieved the detection performance with precision=0.95,recall=0.97,mAP50=0.98,mAP50-95=0.85,and F1 score=0.96,demonstrating high model performance to detect the complex morphology of grain.The evaluation metric of Model 2,used to identify lithological classes,showed average Top-1 accuracy of 0.87 and 0.75 on the validation and test sets,respectively.The classification model showed reliable recognition for quartz and detrital carbonate,with moderate confusion between clastic and crystalline grains.These results demonstrate that the proposed YOLOv11-based approach enables rapid,reproducible,and objective lithological classification of IRD grains,providing an efficient alternative to conventional manual counting.
基金supported by the National Science Foundation of China(Grant no.42376064)the Chinese Polar Environment Comprehensive Investigation&Assessment Programs(Grant no.CHINARE 2016-03-02).
文摘Understanding the sediment record during the Little Ice Age(LIA)can help elucidate natural sea ice fluctuation and carbon cycle variability.This study analyzed the grain size composition(including ice-rafted debris),total organic carbon(TOC),total nitrogen(TN)content,and stable isotopic composition(δ13C andδ15N)of the sediment record(approximately 490 a)of core ARC7-R11 in the northern part of the Chukchi Shelf.The sediment grains comprise mostly(>90%)silt and clay components.The grain size composition suggests generally low-energy hydrodynamic conditions across the region,yet reveals a trend of enhancement in hydrodynamics from the bottom to top layers of the sediment core,particularly after the 1940s.It also shows occurrences of seasonal sea ice and retreat of the perennial sea ice margin during warmer periods of the LIA and the post-LIA period.The organic matter content is high throughout the core,with heavierδ13C values and moderate TOC/TN ratios indicating primarily marine origin;the terrestrial input is<37.5%according to the endmember model.The variation trend of marine-derived organic carbon(OC)content is similar to that of summer temperature anomalies;while variation trend of terrestrially derived OC shows significant correlation with that of the number of ice-free days in the southern shelf region,except for the period from approximately 1700s to the 1870s.During the LIA,the TOC content fluctuated and decreased,and the relative contribution of terrestrial OC was higher than during the modern warm period.The amount of OC buried in the sediment has increased with climate warming,especially after the 1940s,reflecting the enhanced ability of sediment to sequester carbon during warmer periods.
基金supported by the National Key Basic Research Special Foundation Pro-gram of China under contract No.G2000078500the National Natural Science Foundation of China under contract Nos 40321603,40276020 and 40176015the Foundation for the Author of National Excellent Doctoral Dissertation of China under contract No.200126.
文摘Quantitative analytic results of the biogenic components in Core B2-9 fromthe northern Bering Sea slope indicate that the coarse fraction and opal content, serving as proxiesof surface productivity, have increased stepwise since the marine isotope stageCMISJS.S, reflectingperiodic enhancement in surface productivity.The surface productivity attained its highest levelduring the Holocene, followed by MIS 3.2 to 2 and then MIS 5.3 to 3.3 with a lowest level. Hightotal organic carbon(TOC) contents, together with high C/N ratios, which stand mostly between 7 and20, show that the TOC was deposited from mixing sources. Therefore,one has to be cautious to use TOCas a proxy of surface productivity.The high TOC and C/N ratio during MIS 5.1, 3.3 to 3.2 and theHolocene reflect that the terrigenous organic matter input increased during interglacialperiods.Increases in the fine- and silt-grained terrigenous components from MIS 5.3 to the middleHolocene imply that with the cooling climate, sea ice on the Bering Sea slope extended continuously.Ice-rafted and charcoal detritus increased during glacial, interstadial and the last deglaciationperiods and decreased during interglacial periods, suggesting that sea ice on the slope increasedand melted, respectively, during glacial and interglacial periods. The extension of sea ice duringglacial periods.which was linked with the climate over the North American Continent, responded toglobal climate change during late Quaternary glacial and interglacial cycles.
文摘Results of grain size analysis and rock magnetic measurements of core NP95-1 from Prydz Bay, Antarctica revealed two series of ice-rafted detritus layers, which correspond to cold climatic events, Younger Dryas and Heinrich event 1, occurring at about 11.7-10.3 and 14.3-13.6 kaB.P. respectively. Studies also show that the sequence of paleoclimatic changes in Antarctica can be correlated with that in other parts of the world, and that the millennial climate of the earth could change synchronously and globally. In addition, magnetic fabric analysis also shows a close relationship between paleoclimatic change and ocean circulation re-assemblage.
