Automated recognition by multiple convolutional neural networks of modern, fossil, intact and damaged pollen grains. (July 2020)

• Record Type: Journal Article
• Authors: Bourel, Benjamin; Marchant, Ross; de Garidel-Thoron, Thibault; Tetard, Martin; Barboni, Doris; Gally, Yves; Beaufort, Luc
• Is Part Of: Computers & geosciences. Volume 140(2020)
• Publication Date: 2020-07
• Subjects: Damaged pollen -- Fossil pollen -- Machine learning -- Image analysis -- Z-stacking -- Amaranthaceae; Environmental policy -- Periodicals; 550.5
• DOI: 10.1016/j.cageo.2020.104498
• Languages: English
• ISSNs: 0098-3004

Abstract

Abstract: Pollen grains are valuable paleoclimate and paleovegetation proxies which require extensive knowledge of morphotypes and long acquisition time under the microscope. The abundance of damaged, folded, and broken pollen grains in the fossil register and sometimes also in modern soil and sediment samples, has so far prevented automation of pollen identification. Recent improvements in machine learning, however, have allowed reconsidering this approach. Here we present an automated approach which is capable of assisting palynologists with poorly preserved pollen samples. Called multi-CNNs, this approach is based on multiple convolutional neural networks (CNNs) integrated in a decision tree system. To test it, we built a system designed for three botanical families very common in the modern and fossil pollen assemblages of Eastern Africa, namely Amaranthaceae, Poaceae, and Cyperaceae. Our system was tested on stacked optical images of 8 pollen types (6 Amaranthaceae, 1 Poaceae, 1 Cyperaceae) using a training dataset of 1102 intact pollen grains and three validation datasets of intact (276 grains), damaged (223 grains), and fossil pollen (97 grains). We show that our system successfully recognizes intact, damaged, and fossil pollen grains with very low misclassification rates of 0%, 2.8%, and 3.7%, respectively. The use of augmentation on stacked optical images during the training increases classification accuracy. Following a palynologist's approach, our system allows grains without obvious characters to be classified into a class of high taxonomic level or as indeterminable pollen. This is the first software able to process grains with a wide range of taphonomical stages, which makes it the first truly applicable to automated pollen identification of fossil material. Highlights: We developed an automated recognition software for pollen data acquisition. Our software uses multiple convolutional neural network with decision tree (multi-CNNs). Augmentation of stacked optical images increases classification accuracy. Our software successfully recognizes pollen at the genus or species rank. It achieves robust identification of intact, damaged, modern, and fossil pollen.