Plankton Detection with Adversarial Learning and a Densely Connected Deep Learning Model for Class Imbalanced Distribution

Abstract

Detecting and classifying the plankton in situ to analyze the population diversity and abundance is fundamental for the understanding of marine planktonic ecosystem. However, the features of plankton are subtle, and the distribution of different plankton taxa is extremely imbalanced in the real marine environment, both of which limit the detection and classification performance of them while implementing the advanced recognition models, especially for the rare taxa. In this paper, a novel plankton detection strategy is proposed combining with a cycle-consistent adversarial network and a densely connected YOLOV3 model, which not only solves the class imbalanced distribution problem of plankton by augmenting data volume for the rare taxa but also reduces the loss of the features in the plankton detection neural network. The mAP of the proposed plankton detection strategy achieved 97.21% and 97.14%, respectively, under two experimental datasets with a difference in the number of rare taxa, which demonstrated the superior performance of plankton detection comparing with other state-of-the-art models. Especially for the rare taxa, the detection accuracy for each rare taxa is improved by about 4.02% on average under the two experimental datasets. Furthermore, the proposed strategy may have the potential to be deployed into an autonomous underwater vehicle for mobile plankton ecosystem observation.

Applications of Machine Learning in Chemical and Biological Oceanography

“…The model also improved the accuracy of detecting rare taxa by an average of 4.02% and has the potential to be included in autonomous underwater vehicles for real-time identification and plankton ecosystem observation. 119 The model proposed by Gorsky et al 104 ZooScan with ZooProcess was successfully implemented in the identification and estimation of ZP abundance in the bay of Villefranche-sur-Mer, France. 120 This shows that ML algorithms are a potential tool not only for the identification of ZP but also used to solving ecological problems.…”

“…The data generated by CycleGAN was successfully classified by a densely connected YOLO V3, which outperformed previous state-of-the-art models with mean Average Precision (mAP) of 97.21% and 97.14% (two experimental data sets with varied numbers of rare taxa). The model also improved the accuracy of detecting rare taxa by an average of 4.02% and has the potential to be included in autonomous underwater vehicles for real-time identification and plankton ecosystem observation . The model proposed by Gorsky et al ZooScan with ZooProcess was successfully implemented in the identification and estimation of ZP abundance in the bay of Villefranche-sur-Mer, France .…”

Usefulness of synthetic datasets for diatom automatic detection using a deep-learning approach

“…For automatic bounding box detection, Convolutional Neural Networks (CNNs) can improve performance in terms of reliability and robustness (Girshick, 2015;Redmon et al, 2016). This has been demonstrated in microscopy image detection, mainly for planktonic organisms (Shi et al, 2019;Li et al, 2021), and also specifically for benthic diatoms (Salido et al, 2020). However, the approaches still suffer from overlapping bounding boxes when diatoms are close to each other.…”

“…In addition to being a time-consuming and laborious process, human intervention is also a source of error and bias (Sager et al, 2021). Thus, when available labelled data are limited, one can use synthetic datasets for pre-training the network before fine-tuning it with a real dataset (Li et al, 2021). Depending on the method adopted, images generated could be fully or partially synthetic.…”

A Novel Algorithm for the Retrieval of Chlorophyll a in Marine Environments Using Deep Learning

“…In contrast, remote sensing technology offers significant advantages over traditional methods, including high spatiotemporal resolution, low cost, and high efficiency. It can effectively overcome these limitations [7][8][9][10]. Currently, commonly used satellite sensors [11] include the Sea-viewing Wide Field-of-view Sensor (SeaWiFS), launched by NASA in 1997, the Moderate Resolution Imaging Spectroradiometer (MODIS), jointly launched by NASA and the US Geological Survey (USGS) in 1999, the Medium Resolution Imaging Spectrometer (MERIS), launched by the European Space Agency (ESA) in 2002, and the Ocean and Land Colour Instrument (OLCI), launched by ESA in 2016 [12].…”