Emulating Marine Ecosystem Dynamics: A Machine Learning Approach For Biomass Prediction And Forecasting
Dr. Gokhan Kul, Computer & Information Science/Data Science
Committee Members:
Dr. Gavin Fay, SMAST Fisheries & Oceanography
Dr. Firas Khatib, Computer & Information Science/Data Science
Dr. Ashokkumar Patel, Computer & Information Science/Data Science
Abstract: Marine ecosystem models such as Atlantis valuable insight into multispecies interactions , spatial dynamics and fisheries management, but their high computational cost limits rapid scenario analysis and real-time decision making. This study presented a data-driven ecosystem emulator for the Northeast U.S. Atlantis model using automated machine learning approaches. A large -scale dataset (~3.4 million records) spanning 1964-2020 was constructed , integrating bio ass of species functional groups , spatial polygons , temporal indices and environments variables such as temperature and salinity. The emulator framework employed automated machine learning techniques, including Random Forest and Extra tress regression, with model selection and hyperparameter optimization performance using AutoML strategies. In addition, AutoKeras was utilized to explore neural network architectures in an automated manner, enabling data-driven model allocation, lagged variables to capture ecological inertia and time-aware transformations. Model performance was evaluated using out-of-sample temporal validation, recursive back testing, and ecological plausibility assessments. Result demonstrated string predictive performance, with species -level R2 values frequently exceeding 0.90 and overall model accuracy approaching 94%. The emulator achieved high computational efficiency, with end-to-end prediction completed in under few seconds, substantiality reducing runtime compared to traditional Atlantis simulations. This work established a scalable and efficient AutoML-driven alternative to process-based ecosystem model, enabling rapid biomass estimation and supporting data-driven fisheries management and ecosystem analysis.
For further information please contact Dr. Gokhan Kul at gkul@umassd.edu
Online/Teams (https://teams.microsoft.com/meet/210134622120814?p=HF1gXRarGipViGBpda)
Dr. Gokhan Kul
gkul@umassd.edu
https://teams.microsoft.com/meet/210134622120814?p=HF1gXRarGipViGBpda