Who are you, and what is the name of your institute?
My name is Anders Torstensson, a marine biologist specializing in phytoplankton, employed at the Swedish Meteorological and Hydrological Institute (SMHI) in Gothenburg.
What type of data does your institute produce, how is it produced, and in which regions do you operate?
We are committed to a diverse range of activities crucial for supporting sustainable development and decision-making in Sweden. Across the Baltic Sea, Kattegat, and Skagerrak regions, we conduct monitoring assessments spanning physicochemical and biological measurements. Aboard the research vessel Svea, we conduct regular monitoring cruises to gather vital data for the Swedish National Monitoring Program, analysing parameters such as oxygen concentration, salinity, and nutrient levels, along with detailed assessments of zoo- and phytoplankton communities.
Recently, we have incorporated state-of-the-art technology into our systems, deploying an Imaging FlowCytobot (IFCB) within the FerryBox system onboard RV Svea since 2021. This innovation revolutionizes our sampling and image analysis capabilities for microzoo- and phytoplankton. Leveraging machine learning techniques, we quantify, measure, and classify plankton taxa or groups, augmenting traditional microscopy-based analyses. These advancements provide spatially high-resolution measurements, enhancing our understanding of marine ecosystems and contributing to broader scientific knowledge.
The IFCB automates phytoplankton sampling and analysis by capturing thousands of images triggered by plankton fluorescence or scattering as the sample flows through a specialized chamber. Machine learning methods trained on annotated images by phytoplankton specialists enable accurate classification and quantification of phytoplankton taxa, offering valuable insights into marine ecosystem dynamics and supporting ecosystem management and conservation decisions.
How will your project add value to existing data flows?
Our project will substantially enhance existing data flows by augmenting the frequency and spatial resolution of phytoplankton data delivered to EMODnet Biology. Currently, SMHI provides data from Swedish monitoring programs, including results from microscopic phytoplankton analysis. However, our integration of an IFCB onto the research vessel Svea is revolutionizing data collection. The IFCB operates autonomously, sampling every thirty minutes, even in the absence of SMHI staff onboard. This continuous sampling will vastly increase the number of occurrences captured and significantly enhance spatial resolution.
Furthermore, our project aims to streamline data sharing across Europe by developing a standardized data format for IFCB data and a public data pipeline. By facilitating other IFCB users in Europe to submit their data to EMODnet Biology, we hope to centralize phytoplankton data from multiple automated instruments. This centralized repository will offer researchers and policymakers a comprehensive and easily accessible dataset for studying phytoplankton dynamics and their impact on marine ecosystems. Ultimately, our project will enrich scientific understanding and support evidence-based decision-making regarding marine environmental management and conservation efforts.
What is the expected impact of your proposed project?
By integrating IFCB data into existing data flows, we anticipate several key outcomes. Firstly, the inclusion of IFCB data will substantially enhance the richness and depth of phytoplankton datasets. Unlike traditional microscopy, which provides snapshots of phytoplankton communities at discrete time points, the IFCB operates autonomously, offering continuous sampling at high frequencies. This continuous stream of data will capture temporal variability in phytoplankton abundance and diversity with unprecedented detail, including the detection of algal blooms that may otherwise go unnoticed.
Secondly, our project will contribute to a more holistic understanding of marine ecosystems in European waters. By combining data from both traditional microscopy and cutting-edge IFCB technology, researchers will gain insights into phytoplankton dynamics that were previously unattainable. This perspective will shed light on the complex interactions between phytoplankton communities and their environment, informing ecosystem management and conservation strategies.
Finally, the availability of enhanced phytoplankton datasets will benefit a wide range of stakeholders, including researchers, policymakers, and resource managers. These stakeholders will have access to more accurate and timely information for decision-making, leading to more effective measures for protecting marine biodiversity and ecosystem health. Overall, the expected impact of our proposed project extends beyond scientific research to encompass broader societal and environmental benefits.
How will this involvement or opportunity enhance your institute's capacity?
This involvement presents an opportunity for our institute to enhance its capacity in several key areas. Machine learning algorithms enables us to efficiently process large volumes of complex data, extracting valuable insights and identifying patterns that may have previously gone unnoticed. The publication of these types of data will significantly enhance our institute's ability to generate actionable information not only for marine ecological research but also for public awareness and education initiatives.
Additionally, the establishment of a standardized data format and public data pipeline for IFCB data from SMHI will expand our institute's access to valuable data, including datasets used for training an image classifier. Currently, SMHI's IFCB data is not publicly available, limiting opportunities for collaboration and knowledge sharing. By fostering standardization and promoting data sharing, our institute will not only provide, but also gain access to a wealth of previously inaccessible information from other users, enriching our research capabilities and facilitating interdisciplinary collaboration.
Moreover, this involvement presents an opportunity for our institute to strengthen its collaborative networks and engage with experts in the field of marine ecology. By sharing expertise, code, and best practices with other institutions involved in similar initiatives, we will foster a culture of collaboration and innovation within the marine research community. This collaborative approach will not only enhance our institute's capacity to leverage IFCB data but also contribute to the advancement of marine ecological research on a broader scale.
In conclusion, this involvement presents a unique opportunity for our institute to enhance its capacity in data sharing, expand access to valuable datasets, and foster collaboration within the marine research community. By leveraging machine learning techniques, promoting data sharing, and engaging in collaborative partnerships, we will establish a robust framework for advancing marine ecological research and management.