26 Aug 2022
26 Aug 2022
Status: this preprint is currently under review for the journal TC.

Detection of ice core particles via deep neural networks

Niccolo Maffezzoli1,2, Eliza Cook3, Willem G. M. van der Bilt4,5, Eivind Wilhelm Nagel Støren4, Daniela Festi6, Florian Muthreich5,7, Alistair W. R. Seddon5,7, François Burgay8, Giovanni Baccolo9,10, Amalie Regitze Faber Mygind11, Troels Petersen11, Andrea Spolaor2, Sebastiano Vascon1, Marcello Pelillo1, Patrizia Ferretti1, Rafael S. dos Reis1,2, Jefferson C. Simões12,13, Yuval Ronen4, Barbara Delmonte9, Marco Viccaro14, Jørgen Peder Steffensen3, Dorthe Dahl-Jensen3, Kerim Hestnes Nisancioglu4,5, and Carlo Barbante1,2 Niccolo Maffezzoli et al.
  • 1Ca’ Foscari University of Venice, Department of Environmental Sciences, Informatics and Statistics, Via Torino 155, 30172 Venice, Italy
  • 2Institute of Polar Sciences, ISP-CNR, Via Torino 155, 30172 Venice, Italy
  • 3Physics of Ice, Climate and Earth, Niels Bohr Institute, University of Copenhagen, 2200, Copenhagen, Denmark
  • 4Department of Earth Science, University of Bergen, Allégaten 41, 5020 Bergen, Norway
  • 5Bjerknes Centre for Climate Research, Jahnebakken 5, 5020 Bergen, Norway
  • 6Institute for Interdisciplinary Mountain Research, Austrian Academy of Sciences, Innrain 25, 6020 Innsbruck, Austria
  • 7Department of Biological Sciences, University of Bergen, Thormøhlensgate 53A, 5006 Bergen, Norway
  • 8Paul Scherrer Institut, Laboratory of Environmental Chemistry (LUC), Forschungsstrasse 111, 5232 Villigen PSI, Switzerland
  • 9Department of Environmental Sciences, University of Milano-Bicocca, P.zza della Scienza 1, 20126 Milan, Italy
  • 10Milano-Bicocca Section, Istituto Nazionale di Fisica Nucleare INFN, Milan, Italy
  • 11Niels Bohr Institute, University of Copenhagen, 2100, Copenhagen, Denmark
  • 12Centro Polar e Climático, Universidade Federal do Rio Grande do Sul, Porto Alegre, 91501-970, Brazil
  • 13Climate Change Institute, University of Maine, Orono, ME 04469, USA
  • 14Università degli Studi di Catania, Dipartimento di Scienze Biologiche, Geologiche e Ambientali, 95129 Catania, Italy

Abstract. Insoluble particles in ice cores record signatures of past climate parameters like vegetation, volcanic activity or aridity. Their analytical detection depends 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 7 commonly found classes: mineral dust, felsic and basaltic volcanic ash (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 potentials and 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 step. 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.

Niccolo Maffezzoli et al.

Status: open (until 22 Oct 2022)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Niccolo Maffezzoli et al.

Niccolo Maffezzoli et al.


Total article views: 289 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
193 91 5 289 15 3 3
  • HTML: 193
  • PDF: 91
  • XML: 5
  • Total: 289
  • Supplement: 15
  • BibTeX: 3
  • EndNote: 3
Views and downloads (calculated since 26 Aug 2022)
Cumulative views and downloads (calculated since 26 Aug 2022)

Viewed (geographical distribution)

Total article views: 283 (including HTML, PDF, and XML) Thereof 283 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 06 Oct 2022
Short summary
Multiple lines of research in ice core science are limited by manually intensive and time-consuming optical microscopy investigations for the detection of different types of insoluble particles, from pollen grains to volcanic shards. To help overcome these limitations and support researchers, we here present a novel methodology for the identification and autonomous classification of ice core insoluble particles based on flow image microscopy and neural networks.