View this Newsletter in your web browser

Looking Back and Moving Forward:

IMBeR’s Presentation at the SCOR 2025 Annual Meeting

Read more

The 4th Mega-Delta Meeting: International Conference on Dialogue between Land and Sea was held in Shanghai on 20–21 October 2025, bringing together over 180 experts from 70 institutions across 31 countries and six continents. Focusing on the evolution and management of large river delta systems, the conference provided a global platform for interdisciplinary exchange and collaboration.

Read more

2025 Asia-Europe Large River Regional Dialogue was held on 21 October with the theme "Asia-Europe Large River Exchange and Cooperation." Global government officials, scholars and industry experts gathered to discuss transnational collaboration in multiple fields related to river basins and deltas.

Read more

From 22 to 24 October 2025, the international workshop “Assessment, Mitigation and Adaptation: Ocean - Climate Change Dialogue between China and Iran” was held in Shanghai and online. The outcomes of the workshop provided scientific foundations for the sustainable management of coastal zones in China and Iran, highlighting the crucial role of transnational and interdisciplinary collaboration in addressing global climate change.

Read more

This month’s selection highlights how artificial intelligence is reshaping marine and aquatic sciences—from microscopic plankton to vast coastal ecosystems. The featured studies demonstrate AI’s transformative role in automating species identification, enhancing ecosystem monitoring, and improving predictive modeling. Deep learning techniques are advancing plankton classification and ecological data analysis, while AI-driven remote sensing supports seagrass conservation and carbon cycle assessment. Machine learning models are uncovering key drivers of algal blooms and offering new tools for blue carbon monitoring in data-scarce polar regions. Together, these works illustrate how cutting-edge computational methods are accelerating discovery, improving accuracy, and fostering sustainable management of our ocean and freshwater environments.



If you have papers or reports you would like to share in future issues, please feel free to send the information to imber@ecnu.edu.cn.

Collaborative deep learning models to handle class imbalance

in FlowCam plankton imagery

Authors: T. Kerr, J. R. Clark, E. S. Fileman, C. E. Widdicombe, N. Pugeault

Publisher: IEEE

Using automated imaging technologies, it is now possible to generate previously unprecedented volumes of plankton image data which can be used to study the composition of plankton assemblages. However, the current need to manually classify individual images introduces a bottleneck into processing chains. Although Machine Learning techniques have been used to try and address this issue, past efforts have suffered from accuracy limitations, especially in minority classes. Here we use state-of-the-art methods in Deep Learning to investigate suitable architectures for training an automated plankton classification system which achieves high efficacy for both abundant and rare taxa. We collected live plankton from Station L4 in the Western English Channel and imaged 11,371 particles covering 104 taxonomic groups using the automated plankton imaging system FlowCam. The image set contained a severe class imbalance, with some taxa represented by > 600 images while other, rarer taxa were represented by just 14. We demonstrate that by allowing multiple Deep Learning models to collaborate in a single classification system, classification accuracy improves for minority classes when compared with the best individual model. The top collaborative model achieved a 6 % improvement in F1 accuracy over the best individual model, while overall accuracy improved by 3.2 %. This resulted in a 97.4 % overall accuracy score and a 96.2 % F1 macro score on a separate holdout test set containing 104 taxonomic groups. Based on a survey of similar studies in the literature, we believe collaborative deep learning models can significantly improve the accuracy of existing automated plankton classification systems.

Click to read the full paper

Figure 1. Schematic showing our processing pipeline for automatically classifying plankton in FlowCam image data. First, FlowCam images and accompanying numeric metadata are prepared for automatic classification. The data are then fed into a classification system consisting of one or more unique trained ConvNet models and a trained MLP model which work in collaboration to classify images.

AI-driven remote sensing enhances Mediterranean seagrass monitoring and conservation to combat climate change and anthropogenic impacts

Authors: M. Chowdhury, A. Martínez-Sansigre, M. Mole, E. Alonso-Peleato, N. Basos, J. M. Blanco, M. Ramirez-Nicolas, I. Caballero, I. de la Calle

Journal: Scientific Reports

Seagrasses are undergoing widespread loss due to anthropogenic pressure and climate change. Since 1960, the Mediterranean seascape lost 13–50% of the areal extent of its dominant and endemic seagrass-Posidonia oceanica, which regulates its ecosystem. Many conservation and restoration projects failed due to poor site selection and lack of long-term monitoring. Here, we present a fast and efficient operational approach based on a deep-learning artificial intelligence model using Sentinel-2 data to map the spatial extent of the meadows, enabling short and long-term monitoring, and identifying the impacts of natural and human-induced stressors and changes at different timescales. We apply ACOLITE atmospheric correction to the satellite data and use the output to train the model along with the ancillary data and therefore, map the extent of the meadows. We apply noise-removing filters to enhance the map quality. We obtain 74–92% of overall accuracy, 72–91% of user’s accuracy, and 81–92% of producer’s accuracy, where high accuracies are observed at 0–25 m depth. Our model is easily adaptable to other regions and can produce maps in in-situ data-scarce regions, providing a first-hand overview. Our approach can be a support to the Mediterranean Posidonia Network, which brings together different stakeholders such as authorities, scientists, international environmental organizations, professionals including yachting agents and marinas from the Mediterranean countries to protect all P. oceanica meadows in the Mediterranean Sea by 2030 and increase each country’s capability to protect these meadows by providing accurate and up-to-date maps to prevent its future degradation.

Click to read the full paper

Figure 2. Why conservation of P. oceanica is important?. Conceptual diagram depicting the ecosystem services of P. oceanica (outlined by blue lines) and the anthropogenic pressures on the meadows (outlined by red lines). The meadows are endemic and dominant seagrass species in the Mediterranean Sea that controls its coastal and aquatic ecosystem. They provide shelter as well as act as a nursery for thousands of marine animals and plants, several of which are endangered species such as sea turtles and dugongs. The plant itself oxygenates the water and stabilizes the sandy shores and sea beds. They provide food directly through grazing or indirectly through detritus cycle9. They create ecological corridors between different habitats and are also globally significant carbon sinks13. The meadows are threatened by different anthropogenic activities, i.e. coastal infrastructure development, water pollution, fishing, shipping and anchoring. Over the last 50 years, the Mediterranean basin lost 13–50% of the areal extent of this meadow4. The recent warming of the Mediterranean Sea exaggerates the situation even more, which calls for continuous monitoring of the meadows, identifying potential areas to mitigate the human impacts as well as selection of sites for conservation and restoration. Sketchup 2022 (https://www.sketchup.com/offline-download) and Photoshop 2023 (https://www.adobe.com/products/photoshop.html).

Deep-learning-powered data analysis in plankton ecology

Authors: H. Bachimanchi, M. I. M. Pinder, C. Robert, P. De Wit, J. Havenhand, A. Kinnby, D. Midtvedt, E. Selander, G. Volpe

Journal: Limnology and Oceanography Letters

The implementation of deep learning algorithms has brought new perspectives to plankton ecology. Emerging as an alternative approach to established methods, deep learning offers objective schemes to investigate plankton organisms in diverse environments. We provide an overview of deep-learning-based methods including detection and classification of phytoplankton and zooplankton images, foraging and swimming behavior analysis, and finally ecological modeling. Deep learning has the potential to speed up the analysis and reduce the human experimental bias, thus enabling data acquisition at relevant temporal and spatial scales with improved reproducibility. We also discuss shortcomings and show how deep learning architectures have evolved to mitigate imprecise readouts. Finally, we suggest opportunities where deep learning is particularly likely to catalyze plankton research. The examples are accompanied by detailed tutorials and code samples that allow readers to apply the methods described in this review to their own data.



Click to read the full paper

Figure 3. Workflow of a deep learning analysis applied to plankton studies. (a) Different kinds of sampling strategy for in situ and ex situ data. Plankton can be cultivated in the laboratory or collected from the field. Remote-sensing data can also be collected via drones and satellites. (b) Images and data are obtained using microscopic analyses or satellite imaging. (c) Data are processed using a deep learning network. (d) The output of a deep learning analysis can be used for a wide range of applications. Images credited to the authors.

Deep learning meets marine biology: Optimized fused features and

LIME-driven insights for automated plankton classification

Authors: M. Hassan, G. Salbitani, S. Carfagna, J. A. Khan

Journal: Computers in Biology and Medicine

Plankton are microorganisms that play an important role in marine food webs as primary producers in the trophic web. Traditional plankton identification methods using manual microscopy and sampling are time-consuming, labor-intensive, and prone to errors. Deep learning has improved the automation of plankton identification, but it remains challenging to achieve high accuracy and efficiency in computation with limited labeled data. In this paper, we proposed an improved plankton classification model that is more accurate and interpretable. We train two models, InceptionResNetV2 (transfer learning) and DeepPlanktonNet (from scratch), on the WHOI dataset. We utilize feature fusion to supplement feature representation, merging the outputs of both models. Feature selection is achieved through the Whale Optimization Algorithm (WOA), eliminating redundancy and making it more computationally efficient. Additionally, we also employ Local Interpretable Model-agnostic Explanations (LIME) to make the model more interpretable and gain insights into how the model makes decisions. Additionally, feature selection using WOA reduces feature space and has less inference and computational cost. Our method achieves a classification accuracy of 98.79 %, which is better than previous state-of-the-art methods. For robustness testing, we train nine machine learning classifiers on the optimized features. By significantly improving classification accuracy and speed, our method enables large-scale ecological surveys, water quality monitoring, and biodiversity studies. These advances allow researchers to and environmental scientists to automate plankton classification more reliably, supporting marine conservation and resource management.

Click to read the full paper

Figure 6. Proposed methodology for plankton's classification using hybrid and LIME explainability model.

Artificial intelligence in aquatic biology:

Identifying and conserving aquatic species

Authors: H. Yang, Q. Feng, L. Zouyi, X. Du, J. Xu, W. Xu, Z. Liu, Z. Wu, Y. Zhang

Journal: Water & Ecology

Artificial intelligence (AI) plays a transformative role in the identification and conservation of aquatic species. By synthesizing recent advancements, this paper highlights the effectiveness of machine learning algorithms in processing complex datasets from various sensing technologies. AI-driven models, such as convolutional neural networks and recurrent neural networks, have demonstrated higher accuracy and scalability in species identification, habitat monitoring, and threat detection compared to conventional ecological approaches. The review addresses challenges such as data variability, the requirement for large training datasets, and ethical considerations. Emphasizing interdisciplinary collaboration, the establishment of standardized protocols, and the development of open-access data repositories, the paper underscores AI’s essential role in enhancing the understanding of aquatic ecosystems and improving conservation strategies. The integration of AI with established ecological practices presents substantial opportunities for sustainable management and biodiversity preservation in marine and freshwater environments. Future directions for AI in aquatic conservation are also discussed, emphasizing the necessity of continuous innovation and cross-disciplinary collaboration.

Click to read the full paper

Figure 7. Graphic abstract.

Mapping the global coastal ocean with AI: Artificial neural networks can help better constrain the global carbon cycle in shallow seas

Authors: A. Roobaert

Journal: Science

Climate change is one of the major challenges of the 21st century. To mitigate its effects, we need to drastically reduce emissions of carbon dioxide (CO₂), the main anthropogenic greenhouse gas, the concentration of which has been rising severely in the atmosphere since the beginning of the industrial revolution as a result of human activities (1). The ocean plays a key role in mitigating climate change by absorbing ~25% of human-made CO₂ emissions (1). However, the role of coastal seas in the ocean’s ability to act as an inhibitor for atmospheric CO₂ accumulation and buffer against climate change, as well as the response of the coastal ocean to anthropogenic pressures, remains subject to considerable uncertainties. By using the most cutting-edge method based on artificial intelligence (AI), my research (2, 3) has contributed to improving our understanding of the interactions between the sea surface and the atmosphere of CO₂ for coastal seas worldwide.

Click to read the full paper

Figure 8. Adapted from Alizée Roobaert by A. Fisher (Science); AI icon by Panom Kimsue.

Identifying key taxa for algal blooms in a large aquatic ecosystem

through machine learning

Authors: X. Liu, Y. Deng, S. Chen, J. Wang, Y. Zhang, M. Li, W. Zhong, L. Zhang, X. Zhang

Journal: Environmental Science & Technology

Identifying key species responsible for excessive growth of algae communities, as reflected by the floating algae index (FAI), is crucial for developing targeted management strategies to control algal blooms (ABs). However, current approaches for algal biomonitoring in large aquatic ecosystems are limited by either low taxonomic resolution or insufficient spatial coverage. To address these limitations, this study developed a supervised machine learning (ML) approach that integrates environmental DNA metabarcoding, remote sensing, and water quality parameters to identify the key algal bloom species and map their spatial distribution. Results demonstrated that the gradient boosting tree model achieved high predictive accuracy, with a mean MAPE of 11.20% across different algal taxa. Using this model, the spatial distribution maps were generated for 34 algal taxa. Prediction accuracy was further validated by comparing model outputs with morphological survey data, revealing a significant positive correlation (Spearman’s correlation coefficient 0.366–0.709, p < 0.05) for 75% of the species. By integrating spatial mapping of algal distributions and FAI with principal component regression, the contributions of various algae taxa to the overall community structure were quantified across different regions. Nostocales and Stephanodiscales were identified as the key taxa driving FAI variations throughout Poyang Lake, with the toxic alga Nostocales exerting a greater influence in the northern region compared to other species. This study presents a novel framework for large-scale species-level simulation of algal dynamics, representing a significant advance toward more precise and comprehensive monitoring and management of algal blooms.



Click to read the full paper

Figure 9. Graphic abstract.

Events, Webinars and Conferences

Information shared by our contacts:

• International Conference on Marine Fisheries and Blue Innovations: Safeguarding Ocean Harmony, 1-4 December 2025, University of Chittagong, Bangladesh. Submit abstract by 5 November 2025.

• ECSA 61 - Bridging the gap between science and policy in estuarine and coastal marine biodiversity: the way forward, 24-27 August 2026, Square, Brussels, Belgium.
• Propose a special session by 24 November 2025.

• Southern Ocean Bio-optics Workshop, 10-14 November 2025, Hobart, Australia. Mark your calendars.

• PICES-2025: Innovative Approaches and Applications to Foster Resilience in North Pacific Ecosystems. 8–14 November 2025. Yokohama, Japan.

• CONVERGE CDR Forum: Marine Carbon Dioxide Removal in Canada, 2-3 December 2025, Halifax, Canada. Registration by 21 November 2025.

• American Geophysical Union (AGU) 25 Annual Meeting, 15-19 December 2025, New Orleans, USA. The early bird registration deadline is 6 November 2025.

• Ocean Science Meeting, 22 - 27 February 2026, Glasgow, Scotland. Early-bird registration by 14 Jan 2026.

• ASLO-SIL 2026 Joint Meeting: Aquatic Confluence – Science, People, Knowledge. 12–16 May 2026. Montreal, Quebec, Canada. The abstract submission deadline is 19 November.

• 7th World Conference on Marine Biodiversity, 17 - 20 November 2026, Bruges, Belgium. Submit abstract by 17 March 2026.

Jobs and Opportunities

Information shared by our contacts:

• Funding Opportunity: Hifadhi Blu Call for Motivation Letters
• Submit concise motivation letters by 29 November 2025.
• Open to organizations managing Marine Conservation Areas in the Western Indian Ocean region. Read more

• Postdoctoral Researcher in Microbial Oceanography and Multi-Omics Bioinformatics
• 2-year position to study marine microbial communities using multi-omic approaches; strong bioinformatics and programming (Python, R) skills required. Read more

• Anthropocene Coasts Recruiting Position: Associate Editors
• Applications will continue until the position is filled.
• Anthropocene Coasts is a Golden Open Access journal hosted by East China Normal University, and published by Springer. The journal publishes multidisciplinary research addressing the interaction of human activities with our estuaries and coasts. To help build on the success of Anthropocene Coasts and to expand the opportunities for international collaboration and contributions to the work of the journal, the journal is seeking more international Associate Editors. Read more

• Assistant Professor – Physical Oceanography
• Department of Marine, Earth, and Atmospheric Sciences at North Carolina State University
• Review begins November 15.

• Coastal Resilience Program Manager & Coastal Resilience Extension Specialist
• S.C. Sea Grant Consortium, Charleston, South Carolina
• Open until filled.

• Tenure-Track Faculty: Aquatic Ecotoxicology
• Division of Coastal Sciences (COA), School of Ocean Science and Engineering (SOSE), The University of Southern Mississippi
• Open until filled.

• Assistant Teaching Professor – Coastal & Marine Sciences
• Batten School of Coastal & Marine Sciences & VIMS, William & Mary
• Apply by 1 December 2025.

• Research Technician – Ocean Acidification Program
• Mote Marine Laboratory, Sarasota, Florida
• Open until filled.

• Funding Opportunity: ITOPF R&D Award 2026
• 1 September 2025 - 1 December 2025
• Open to researchers in the field of marine pollution response. Read more

• Funding Opportunity: U.S. National Science Foundation
• Collaborations in Artificial Intelligence and Geosciences (CAIG)
• February 4 2026 - Deadline date. Read more
• Biological Oceanography (BioOce)
• February 17 2026 - Target date. Read more
• Chemical Oceanography
• February 17 2026 - Target date. Read more

Turn Your Innovation into Global Impact

Capturing IMBeR: Share Your Photos and Memories

We invite all IMBeR participants - past and present - to contribute photos that capture the spirit of IMBeR’s activities over the years. Whether from fieldwork, meetings, workshops, summer schools, or community engagement events, your photos will help illustrate IMBeR’s impact and legacy.

Please send high-resolution images, along with a brief description and credit information, to imber@ecnu.edu.cn.

More jobs and opportunities for ECRs, please sign up for IMECaN newsletter

If you would like to put some recruitment information in the IMBeR monthly newsletter, please contact us through imber@ecnu.edu.cn.

IMBeR monthly newsletter archive - Find more

Chief Editor: Suhui QIAN

Editors: GiHoon HONG, Fang ZUO, Kai QIN

Contact us

IMBeR International Project Office

State Key Laboratory of Estuarine and Coastal Research, East China Normal University

500 Dongchuan Rd., Shanghai 200241, China