Detection of ice core particles via deep neural networks
Insoluble particles in ice cores record signatures of past climate parameters like vegetation dynamics, volcanic activity, and aridity. For some of them, the analytical detection relies on intensive bench microscopy investigation and requires dedicated sample preparation steps. Both are laborious, r...
Published in: | The Cryosphere |
---|---|
Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://curis.ku.dk/portal/da/publications/detection-of-ice-core-particles-via-deep-neural-networks(444e8406-6daf-4cce-92c6-1f563d745974).html https://doi.org/10.5194/tc-17-539-2023 https://curis.ku.dk/ws/files/337796558/tc_17_539_2023.pdf |
id |
ftcopenhagenunip:oai:pure.atira.dk:publications/444e8406-6daf-4cce-92c6-1f563d745974 |
---|---|
record_format |
openpolar |
spelling |
ftcopenhagenunip:oai:pure.atira.dk:publications/444e8406-6daf-4cce-92c6-1f563d745974 2024-06-09T07:40:41+00:00 Detection of ice core particles via deep neural networks Maffezzoli, Niccolo Cook, Eliza van der Bilt, Willem G. M. Storen, Eivind N. Festi, Daniela Muthreich, Florian Seddon, Alistair W. R. Burgay, Francois Baccolo, Giovanni Mygind, Amalie R. F. Petersen, Troels Spolaor, Andrea Vascon, Sebastiano Pelillo, Marcello Ferretti, Patrizia dos Reis, Rafael S. Simoes, Jefferson C. Ronen, Yuval Delmonte, Barbara Viccaro, Marco Steffensen, Jorgen Peder Dahl-Jensen, Dorthe Nisancioglu, Kerim H. Barbante, Carlo 2023-02-07 application/pdf https://curis.ku.dk/portal/da/publications/detection-of-ice-core-particles-via-deep-neural-networks(444e8406-6daf-4cce-92c6-1f563d745974).html https://doi.org/10.5194/tc-17-539-2023 https://curis.ku.dk/ws/files/337796558/tc_17_539_2023.pdf eng eng info:eu-repo/semantics/openAccess Maffezzoli , N , Cook , E , van der Bilt , W G M , Storen , E N , Festi , D , Muthreich , F , Seddon , A W R , Burgay , F , Baccolo , G , Mygind , A R F , Petersen , T , Spolaor , A , Vascon , S , Pelillo , M , Ferretti , P , dos Reis , R S , Simoes , J C , Ronen , Y , Delmonte , B , Viccaro , M , Steffensen , J P , Dahl-Jensen , D , Nisancioglu , K H & Barbante , C 2023 , ' Detection of ice core particles via deep neural networks ' , Cryosphere , vol. 17 , no. 2 , pp. 539-565 . https://doi.org/10.5194/tc-17-539-2023 MINERAL DUST DOME GREENLAND FLOWCAM GLACIER SIZE VARIABILITY ANTARCTICA MARKER RECORD article 2023 ftcopenhagenunip https://doi.org/10.5194/tc-17-539-2023 2024-05-16T11:29:28Z Insoluble particles in ice cores record signatures of past climate parameters like vegetation dynamics, volcanic activity, and aridity. For some of them, the analytical detection relies on intensive bench microscopy investigation and requires dedicated sample preparation steps. Both are laborious, require in-depth knowledge, and often restrict sampling strategies. To help overcome these limitations, we present a framework based on flow imaging microscopy coupled to a deep neural network for autonomous image classification of ice core particles. We train the network to classify seven commonly found classes, namely mineral dust, felsic and mafic (basaltic) volcanic ash grains (tephra), three species of pollen (Corylus avellana, Quercus robur, Quercus suber), and contamination particles that may be introduced onto the ice core surface during core handling operations. The trained network achieves 96.8 % classification accuracy at test time. We present the system's potential and its limitations with respect to the detection of mineral dust, pollen grains, and tephra shards, using both controlled materials and real ice core samples. The methodology requires little sample material, is non-destructive, fully reproducible, and does not require any sample preparation procedures. The presented framework can bolster research in the field by cutting down processing time, supporting human-operated microscopy, and further unlocking the paleoclimate potential of ice core records by providing the opportunity to identify an array of ice core particles. Suggestions for an improved system to be deployed within a continuous flow analysis workflow are also presented. Article in Journal/Newspaper Antarc* Antarctica glacier Greenland ice core University of Copenhagen: Research Greenland The Cryosphere 17 2 539 565 |
institution |
Open Polar |
collection |
University of Copenhagen: Research |
op_collection_id |
ftcopenhagenunip |
language |
English |
topic |
MINERAL DUST DOME GREENLAND FLOWCAM GLACIER SIZE VARIABILITY ANTARCTICA MARKER RECORD |
spellingShingle |
MINERAL DUST DOME GREENLAND FLOWCAM GLACIER SIZE VARIABILITY ANTARCTICA MARKER RECORD Maffezzoli, Niccolo Cook, Eliza van der Bilt, Willem G. M. Storen, Eivind N. Festi, Daniela Muthreich, Florian Seddon, Alistair W. R. Burgay, Francois Baccolo, Giovanni Mygind, Amalie R. F. Petersen, Troels Spolaor, Andrea Vascon, Sebastiano Pelillo, Marcello Ferretti, Patrizia dos Reis, Rafael S. Simoes, Jefferson C. Ronen, Yuval Delmonte, Barbara Viccaro, Marco Steffensen, Jorgen Peder Dahl-Jensen, Dorthe Nisancioglu, Kerim H. Barbante, Carlo Detection of ice core particles via deep neural networks |
topic_facet |
MINERAL DUST DOME GREENLAND FLOWCAM GLACIER SIZE VARIABILITY ANTARCTICA MARKER RECORD |
description |
Insoluble particles in ice cores record signatures of past climate parameters like vegetation dynamics, volcanic activity, and aridity. For some of them, the analytical detection relies on intensive bench microscopy investigation and requires dedicated sample preparation steps. Both are laborious, require in-depth knowledge, and often restrict sampling strategies. To help overcome these limitations, we present a framework based on flow imaging microscopy coupled to a deep neural network for autonomous image classification of ice core particles. We train the network to classify seven commonly found classes, namely mineral dust, felsic and mafic (basaltic) volcanic ash grains (tephra), three species of pollen (Corylus avellana, Quercus robur, Quercus suber), and contamination particles that may be introduced onto the ice core surface during core handling operations. The trained network achieves 96.8 % classification accuracy at test time. We present the system's potential and its limitations with respect to the detection of mineral dust, pollen grains, and tephra shards, using both controlled materials and real ice core samples. The methodology requires little sample material, is non-destructive, fully reproducible, and does not require any sample preparation procedures. The presented framework can bolster research in the field by cutting down processing time, supporting human-operated microscopy, and further unlocking the paleoclimate potential of ice core records by providing the opportunity to identify an array of ice core particles. Suggestions for an improved system to be deployed within a continuous flow analysis workflow are also presented. |
format |
Article in Journal/Newspaper |
author |
Maffezzoli, Niccolo Cook, Eliza van der Bilt, Willem G. M. Storen, Eivind N. Festi, Daniela Muthreich, Florian Seddon, Alistair W. R. Burgay, Francois Baccolo, Giovanni Mygind, Amalie R. F. Petersen, Troels Spolaor, Andrea Vascon, Sebastiano Pelillo, Marcello Ferretti, Patrizia dos Reis, Rafael S. Simoes, Jefferson C. Ronen, Yuval Delmonte, Barbara Viccaro, Marco Steffensen, Jorgen Peder Dahl-Jensen, Dorthe Nisancioglu, Kerim H. Barbante, Carlo |
author_facet |
Maffezzoli, Niccolo Cook, Eliza van der Bilt, Willem G. M. Storen, Eivind N. Festi, Daniela Muthreich, Florian Seddon, Alistair W. R. Burgay, Francois Baccolo, Giovanni Mygind, Amalie R. F. Petersen, Troels Spolaor, Andrea Vascon, Sebastiano Pelillo, Marcello Ferretti, Patrizia dos Reis, Rafael S. Simoes, Jefferson C. Ronen, Yuval Delmonte, Barbara Viccaro, Marco Steffensen, Jorgen Peder Dahl-Jensen, Dorthe Nisancioglu, Kerim H. Barbante, Carlo |
author_sort |
Maffezzoli, Niccolo |
title |
Detection of ice core particles via deep neural networks |
title_short |
Detection of ice core particles via deep neural networks |
title_full |
Detection of ice core particles via deep neural networks |
title_fullStr |
Detection of ice core particles via deep neural networks |
title_full_unstemmed |
Detection of ice core particles via deep neural networks |
title_sort |
detection of ice core particles via deep neural networks |
publishDate |
2023 |
url |
https://curis.ku.dk/portal/da/publications/detection-of-ice-core-particles-via-deep-neural-networks(444e8406-6daf-4cce-92c6-1f563d745974).html https://doi.org/10.5194/tc-17-539-2023 https://curis.ku.dk/ws/files/337796558/tc_17_539_2023.pdf |
geographic |
Greenland |
geographic_facet |
Greenland |
genre |
Antarc* Antarctica glacier Greenland ice core |
genre_facet |
Antarc* Antarctica glacier Greenland ice core |
op_source |
Maffezzoli , N , Cook , E , van der Bilt , W G M , Storen , E N , Festi , D , Muthreich , F , Seddon , A W R , Burgay , F , Baccolo , G , Mygind , A R F , Petersen , T , Spolaor , A , Vascon , S , Pelillo , M , Ferretti , P , dos Reis , R S , Simoes , J C , Ronen , Y , Delmonte , B , Viccaro , M , Steffensen , J P , Dahl-Jensen , D , Nisancioglu , K H & Barbante , C 2023 , ' Detection of ice core particles via deep neural networks ' , Cryosphere , vol. 17 , no. 2 , pp. 539-565 . https://doi.org/10.5194/tc-17-539-2023 |
op_rights |
info:eu-repo/semantics/openAccess |
op_doi |
https://doi.org/10.5194/tc-17-539-2023 |
container_title |
The Cryosphere |
container_volume |
17 |
container_issue |
2 |
container_start_page |
539 |
op_container_end_page |
565 |
_version_ |
1801369087787401216 |