Towards a standardized framework for AI-assisted, image-based monitoring of nocturnal insects

TY - JOUR

T1 - Towards a standardized framework for AI-assisted, image-based monitoring of nocturnal insects

AU - Roy, D. B.

AU - Alison, J.

AU - August, T. A.

AU - Bélisle, M.

AU - Bjerge, K.

AU - Bowden, J. J.

AU - Bunsen, M. J.

AU - Cunha, F.

AU - Geissmann, Q.

AU - Goldmann, K.

AU - Gomez-Segura, A.

AU - Jain, A.

AU - Huijbers, C.

AU - Larrivée, M.

AU - Lawson, J. L.

AU - Mann, H. M.

AU - Mazerolle, M. J.

AU - McFarland, K. P.

AU - Pasi, L.

AU - Peters, S.

AU - Pinoy, N.

AU - Rolnick, D.

AU - Skinner, G. L.

AU - Strickson, O. T.

AU - Svenning, A.

AU - Teagle, S.

AU - Høye, T. T.

N1 - Publisher Copyright: © 2024 The Authors.

PY - 2024/6/24

Y1 - 2024/6/24

N2 - Automated sensors have potential to standardize and expand the monitoring of insects across the globe. As one of the most scalable and fastest developing sensor technologies, we describe a framework for automated, image-based monitoring of nocturnal insects - from sensor development and field deployment to workflows for data processing and publishing. Sensors comprise a light to attract insects, a camera for collecting images and a computer for scheduling, data storage and processing. Metadata is important to describe sampling schedules that balance the capture of relevant ecological information against power and data storage limitations. Large data volumes of images from automated systems necessitate scalable and effective data processing. We describe computer vision approaches for the detection, tracking and classification of insects, including models built from existing aggregations of labelled insect images. Data from automated camera systems necessitate approaches that account for inherent biases. We advocate models that explicitly correct for bias in species occurrence or abundance estimates resulting from the imperfect detection of species or individuals present during sampling occasions. We propose ten priorities towards a step-change in automated monitoring of nocturnal insects, a vital task in the face of rapid biodiversity loss from global threats. This article is part of the theme issue 'Towards a toolkit for global insect biodiversity monitoring'.

AB - Automated sensors have potential to standardize and expand the monitoring of insects across the globe. As one of the most scalable and fastest developing sensor technologies, we describe a framework for automated, image-based monitoring of nocturnal insects - from sensor development and field deployment to workflows for data processing and publishing. Sensors comprise a light to attract insects, a camera for collecting images and a computer for scheduling, data storage and processing. Metadata is important to describe sampling schedules that balance the capture of relevant ecological information against power and data storage limitations. Large data volumes of images from automated systems necessitate scalable and effective data processing. We describe computer vision approaches for the detection, tracking and classification of insects, including models built from existing aggregations of labelled insect images. Data from automated camera systems necessitate approaches that account for inherent biases. We advocate models that explicitly correct for bias in species occurrence or abundance estimates resulting from the imperfect detection of species or individuals present during sampling occasions. We propose ten priorities towards a step-change in automated monitoring of nocturnal insects, a vital task in the face of rapid biodiversity loss from global threats. This article is part of the theme issue 'Towards a toolkit for global insect biodiversity monitoring'.

KW - biodiversity monitoring

KW - camera trap

KW - machine learning

KW - moths

UR - http://www.scopus.com/inward/record.url?scp=85192313534&partnerID=8YFLogxK

U2 - 10.1098/rstb.2023.0108

DO - 10.1098/rstb.2023.0108

M3 - Journal article

C2 - 38705190

AN - SCOPUS:85192313534

SN - 0962-8436

VL - 379

JO - Philosophical Transactions of the Royal Society B: Biological Sciences

JF - Philosophical Transactions of the Royal Society B: Biological Sciences

IS - 1904

M1 - 20230108

ER -