Anieke Brombacher

Anieke Brombacher

Auto-generated profile, based on publicly available information

Anieke Brombacher

School of Ocean & Earth Science University of Southampton Southampton UK

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 July 2019 in Paleoceanography and Paleoclimatology
Verified
Journal Article
Open access
PDF file
AHAllison Y. Hsiang
Allison Y. Hsiang
ABAnieke Brombacher
Anieke Brombacher
MRMarina Costa Rillo
Marina Costa Rillo
MMMaryline J. Mleneck‐Vautravers
Maryline J. Mleneck‐Vautravers
SCStephen Conn
Stephen Conn
PHPincelli M. Hull
Pincelli M. Hull
Planktonic foraminiferal species identification is central to many paleoceanographic studies, from selecting species for geochemical research to elucidating the biotic dynamics of microfossil communities relevant to physical oceanographic processes and interconnected phenomena such as climate change. However, few resources exist to train students in the difficult task of discerning amongst closely related species, resulting in diverging taxonomic schools that differ in species concepts and boundaries. This problem is exacerbated by the limited number of taxonomic experts. Here we document our initial progress toward removing these confounding and/or rate‐limiting factors by generating the first extensive image library of modern planktonic foraminifera, providing digital taxonomic training tools and resources, and automating species‐level taxonomic identification of planktonic foraminifera via machine learning using convolution neural networks. Experts identified 34,640 images of modern (extant) planktonic foraminifera to the species level. These images are served as species exemplars through the online portal Endless Forams (endlessforams.org) and a taxonomic training portal hosted on the citizen science platform Zooniverse (zooniverse.org/projects/ahsiang/endless‐forams/). A supervised machine learning classifier was then trained with ~27,000 images of these identified planktonic foraminifera. The best‐performing model provided the correct species name for an image in the validation set 87.4% of the time and included the correct name in its top three guesses 97.7% of the time. Together, these resources provide a rigorous set of training tools in modern planktonic foraminiferal taxonomy and a means of rapidly generating assemblage data via machine learning in future studies for applications such as paleotemperature reconstruction.

1 September 2017 in The American Naturalist
Verified
Journal Article
Open access
ABAnieke Brombacher
Anieke Brombacher
PWPaul A. Wilson
Paul A. Wilson
IBIan Bailey
Ian Bailey
TEThomas H. G. Ezard
Thomas H. G. Ezard
The influence of within-species variation and covariation on evolutionary patterns is well established for generational and macroevolutionary processes, most prominently through genetic lines of least resistance. However, it is not known whether intraspecific phenotypic variation also directs microevolutionary trajectories into the long term when a species is subject to varying environmental conditions. Here we present a continuous, high-resolution bivariate record of size and shape changes among 12,633 individual planktonic foraminifera of a surviving and an extinct-going species over 500,000 years. Our study interval spans the late Pliocene to earliest Pleistocene intensification of northern hemisphere glaciation, an interval of profound climate upheaval that can be divided into three phases of increasing glacial intensity. Within each of these three Plio-Pleistocene climate phases, the within-population allometries predict evolutionary change from one time step to the next and that the within-p...

19 July 2017 in Biogeosciences
Verified
Journal Article
Open access
PDF file
LNLennart J. de Nooijer
Lennart J. de Nooijer
ABAnieke Brombacher
Anieke Brombacher
AMAntje Mewes
Antje Mewes
GLGerald Langer
Gerald Langer
Gernot NehrkeGernot Nehrke
Gernot Nehrke
GRGert-Jan Reichart
Gert-Jan Reichart
Barium (Ba) incorporated in the calcite of many foraminiferal species is proportional to the concentration of Ba in seawater. Since the open ocean concentration of Ba closely follows seawater alkalinity, foraminiferal Ba ∕ Ca can be used to reconstruct the latter. Alternatively, Ba ∕ Ca from foraminiferal shells can also be used to reconstruct salinity in coastal settings in which seawater Ba concentration corresponds to salinity as rivers contain much more Ba than seawater. Incorporation of a number of minor and trace elements is known to vary (greatly) between foraminiferal species, and application of element ∕ Ca ratios thus requires the use of species-specific calibrations. Here we show that calcite Ba ∕ Ca correlates positively and linearly with seawater Ba ∕ Ca in cultured specimens of two species of benthic foraminifera: Heterostegina depressa and Amphistegina lessonii. The slopes of the regression, however, vary two- to threefold between these two species (0.33 and 0.78, respectively). This difference in Ba partitioning resembles the difference in partitioning of other elements (Mg, Sr, B, Li and Na) in these foraminiferal taxa. A general trend across element partitioning for different species is described, which may help develop new applications of trace elements in foraminiferal calcite in reconstructing past seawater chemistry.

1 May 2017 in Marine Micropaleontology
Verified
Journal Article
Open access
ABAnieke Brombacher
Anieke Brombacher
PWPaul A. Wilson
Paul A. Wilson
TEThomas H.G. Ezard
Thomas H.G. Ezard

19 June 2024 in Royal Society Open Science
Verified
Journal Article
Open access
JMJames M. Mulqueeney
James M. Mulqueeney
ASAlex Searle-Barnes
Alex Searle-Barnes
ABAnieke Brombacher
Anieke Brombacher
MSMarisa Sweeney
Marisa Sweeney
AGAnjali Goswami
Anjali Goswami
TEThomas H. G. Ezard
Thomas H. G. Ezard
Deep learning has emerged as a robust tool for automating feature extraction from three-dimensional images, offering an efficient alternative to labour-intensive and potentially biased manual image segmentation methods. However, there has been limited exploration into the optimal training set sizes, including assessing whether artficial expansion by data augmentation can achieve consistent results in less time and how consistent these benefits are across different types of traits. In this study, we manually segmented 50 planktonic foraminifera specimens from the genus Menardella to determine the minimum number of training images required to produce accurate volumetric and shape data from internal and external structures. The results reveal unsurprisingly that deep learning models improve with a larger number of training images with eight specimens being required to achieve 95% accuracy. Furthermore, data augmentation can enhance network accuracy by up to 8.0%. Notably, predicting both volumetric and shape measurements for the internal structure poses a greater challenge compared with the external structure, owing to low contrast differences between different materials and increased geometric complexity. These results provide novel insight into optimal training set sizes for precise image segmentation of diverse traits and highlight the potential of data augmentation for enhancing multivariate feature extraction from three-dimensional images.

2 July 2018 in Journal of Foraminiferal Research
Verified
Journal Article
Closed access
ABAnieke Brombacher
Anieke Brombacher
LELeanne E. Elder
Leanne E. Elder
PHPincelli M. Hull
Pincelli M. Hull
PWPaul A. Wilson
Paul A. Wilson
TEThomas H. G. Ezard
Thomas H. G. Ezard
Body size is one of the most commonly measured traits in ecology and evolution because it covaries with environmental (e.g., temperature, latitude, degree of population isolation) and life-history (e.g., metabolic rate, generation time) traits. However, the driving mechanisms of body size variation in the distant geological past are poorly known and complicated by partial specimen recovery, limited population-level sampling, and the use of linear measurements as proxies for three-dimensional volumetric-size data. How much information are we missing by using approximate metrics of body size? Here we examine this question in an evolving lineage of planktonic foraminifera. We measure test diameter and surface area of over 500 individuals of the species Globoconella puncticulata using two-dimensional images. These results are compared with measurements of test volume of the same individuals as measured by a recently developed high-throughput method for analysing three-dimensional morphometrics as well as high-resolution three-dimensional computed tomography scanning. Our results show that even in a lineage showing substantial morphological change, a cross-sectional test area can provide a consistent proxy for body volume. Approximating body volume with one-dimensional (linear) size measurements is more problematic as it systematically over- and underestimates the smallest and largest tests, respectively. In our study, shape (here measured as shell-aspect ratio) only explained marginally more variation when included in the regressions. The use of 3D light microscopy introduces a small degree of scatter in the data, but the number of individuals necessary to detect trends in body size with sufficient statistical power is comparable to the sample size required for other traits. These results imply that even in an evolving lineage undergoing substantial morphological change, cross-sectional area can provide a consistent proxy for body size.