Limitations in transferability of optical imaging and deep learning models for identifying freshwater benthic macroinvertebrates
Authors:
- Micah Nathaniel BowmanMBMicah Nathaniel Bowman
- Ryan A. McManamayRMRyan A. McManamay
- Teresa J. MathewsTMTeresa J. Mathews
- Natalie A. GriffithsNGNatalie A. Griffiths
- Molly E. LandonMLMolly E. Landon
Preprint
- 11 April 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Identifying benthic macroinvertebrates is a skill that requires time to master, resulting in fewer taxonomic experts and leading in part to the taxonomic impediment. The advancements of optical imaging and artificial intelligence (AI) technologies could prove useful in bridging this gap. Many researchers have turned to AI and machine learning (ML) techniques for identification of a wide range of living organisms, from algae to charismatic species, with great success. Recent work using ML or deep learning techniques, such as convolutional neural networks (CNNs) can achieve high accuracies in identifying various taxonomic groups of aquatic benthic macroinvertebrates. However, there are a few knowledge gaps in this application space. First, we questioned how image quality and quantity influence prediction accuracy. Second, we questioned how transferable are deep learning models across image domains, i.e. different courses of images? Here, we leveraged CNNs to accurately identify 23 families of the benthic macroinvertebrate orders Ephemeroptera, Plecoptera, and Trichoptera (EPT). Our CNN model achieved >99% accuracy on both EPT datasets with and without background. We found that minimal images are needed for accurate prediction when training and prediction occurs within the same image domain. However, we show that deep-learning CNN models for invertebrate taxonomic identification is only accurate when utilizing imagery collected within the same imaging domain as the model’s training imagery. We address the accessibility of these technologies in their current state and recommend future research be aimed at making these technologies more accessible to all researchers regardless of their taxonomic training.Keywords
This publication has 28 references indexed in Scilit:
- Optical imaging and machine learning to identify and enumerate early developmental stages of fish speciesEcological Informatics, 2026
- Effects of reservoir regulation on downstream benthic invertebrate drift in dammed rivers: A reviewEcological Indicators, 2025
- Impacts of droughts and heatwaves on river water quality worldwideJournal of Hydrology, 2023
- Impacts of wastewater treatment plants on benthic macroinvertebrate communities in summer and winterScience of The Total Environment, 2022
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based LocalizationInternational Journal of Computer Vision, 2019
- Effects of pollution on freshwater aquatic organismsWater Environment Research, 2019
- Benchmark database for fine-grained image classification of benthic macroinvertebratesImage and Vision Computing, 2018
- Macroinvertebrate short-term responses to flow variation and oxygen depletion: A mesocosm approachScience of The Total Environment, 2017
- Revisiting inland hypoxia: diverse exceedances of dissolved oxygen thresholds for freshwater aquatic lifeEnvironmental Science and Pollution Research, 2017
- Classification and retrieval on macroinvertebrate image databasesComputers in Biology and Medicine, 2011