Machine learning to identify environmental drivers of phytoplankton blooms in the Southern Baltic Sea
Abstract Phytoplankton blooms exhibit varying patterns in timing and number of peaks within ecosystems. These differences in blooming patterns are partly explained by phytoplankton:nutrient interactions and external factors such as temperature, salinity and light availability. Understanding these in...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-85605-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585797157519360 |
|---|---|
| author | Maximilian Berthold Pascal Nieters Rahel Vortmeyer-Kley |
| author_facet | Maximilian Berthold Pascal Nieters Rahel Vortmeyer-Kley |
| author_sort | Maximilian Berthold |
| collection | DOAJ |
| description | Abstract Phytoplankton blooms exhibit varying patterns in timing and number of peaks within ecosystems. These differences in blooming patterns are partly explained by phytoplankton:nutrient interactions and external factors such as temperature, salinity and light availability. Understanding these interactions and drivers is essential for effective bloom management and modelling as driving factors potentially differ or are shared across ecosystems on regional scales. Here, we used a 22-year data set (19 years training and 3 years validation data) containing chlorophyll, nutrients (dissolved and total), and external drivers (temperature, salinity, light) of the southern Baltic Sea coast, a European brackish shelf sea, which constituted six different phytoplankton blooming patterns. We employed generalized additive mixed models to characterize similar blooming patterns and trained an artificial neural network within the Universal Differential Equation framework to learn a differential equation representation of these pattern. Applying Sparse Identification of Nonlinear Dynamics uncovered algebraic relationships in phytoplankton:nutrient:external driver interactions. Nutrients availability was driving factor for blooms in enclosed coastal waters; nutrients and temperature in more open regions. We found evidence of hydrodynamical export of phytoplankton, natural mortality or external grazing not explicitly measured in the data. This data-driven workflow allows new insight into driver-differences in region specific blooming dynamics. |
| format | Article |
| id | doaj-art-b24ca8ee29f4410d8c22f281eb8d707f |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-b24ca8ee29f4410d8c22f281eb8d707f2025-01-26T12:32:13ZengNature PortfolioScientific Reports2045-23222025-01-0115111610.1038/s41598-025-85605-yMachine learning to identify environmental drivers of phytoplankton blooms in the Southern Baltic SeaMaximilian Berthold0Pascal Nieters1Rahel Vortmeyer-Kley2Department of Biology, Faculty of Science, Mount Allison UniversityInstitute of Cognitive Science, Osnabrück UniversityInstitute for Chemistry and Biology of the Marine Environment, Carl von Ossietzky University OldenburgAbstract Phytoplankton blooms exhibit varying patterns in timing and number of peaks within ecosystems. These differences in blooming patterns are partly explained by phytoplankton:nutrient interactions and external factors such as temperature, salinity and light availability. Understanding these interactions and drivers is essential for effective bloom management and modelling as driving factors potentially differ or are shared across ecosystems on regional scales. Here, we used a 22-year data set (19 years training and 3 years validation data) containing chlorophyll, nutrients (dissolved and total), and external drivers (temperature, salinity, light) of the southern Baltic Sea coast, a European brackish shelf sea, which constituted six different phytoplankton blooming patterns. We employed generalized additive mixed models to characterize similar blooming patterns and trained an artificial neural network within the Universal Differential Equation framework to learn a differential equation representation of these pattern. Applying Sparse Identification of Nonlinear Dynamics uncovered algebraic relationships in phytoplankton:nutrient:external driver interactions. Nutrients availability was driving factor for blooms in enclosed coastal waters; nutrients and temperature in more open regions. We found evidence of hydrodynamical export of phytoplankton, natural mortality or external grazing not explicitly measured in the data. This data-driven workflow allows new insight into driver-differences in region specific blooming dynamics.https://doi.org/10.1038/s41598-025-85605-yScientific machine learningSparse identification of nonlinear dynamicsGeneral additive mixed modelBaltic SeaPhytoplankton blooms |
| spellingShingle | Maximilian Berthold Pascal Nieters Rahel Vortmeyer-Kley Machine learning to identify environmental drivers of phytoplankton blooms in the Southern Baltic Sea Scientific Reports Scientific machine learning Sparse identification of nonlinear dynamics General additive mixed model Baltic Sea Phytoplankton blooms |
| title | Machine learning to identify environmental drivers of phytoplankton blooms in the Southern Baltic Sea |
| title_full | Machine learning to identify environmental drivers of phytoplankton blooms in the Southern Baltic Sea |
| title_fullStr | Machine learning to identify environmental drivers of phytoplankton blooms in the Southern Baltic Sea |
| title_full_unstemmed | Machine learning to identify environmental drivers of phytoplankton blooms in the Southern Baltic Sea |
| title_short | Machine learning to identify environmental drivers of phytoplankton blooms in the Southern Baltic Sea |
| title_sort | machine learning to identify environmental drivers of phytoplankton blooms in the southern baltic sea |
| topic | Scientific machine learning Sparse identification of nonlinear dynamics General additive mixed model Baltic Sea Phytoplankton blooms |
| url | https://doi.org/10.1038/s41598-025-85605-y |
| work_keys_str_mv | AT maximilianberthold machinelearningtoidentifyenvironmentaldriversofphytoplanktonbloomsinthesouthernbalticsea AT pascalnieters machinelearningtoidentifyenvironmentaldriversofphytoplanktonbloomsinthesouthernbalticsea AT rahelvortmeyerkley machinelearningtoidentifyenvironmentaldriversofphytoplanktonbloomsinthesouthernbalticsea |