On the Optimisation of Machine Learning Models for Predicting the Photosynthetically Available Radiation in the Water Column
DOI:
https://doi.org/10.26034/lu.akwi.2026.8843Keywords:
Machine Learning, Underwater Light Field, Photosynthetic Active Radiation, Freefall Profiler, KNIMEAbstract
Photosynthetically Available Radiation (PAR) is a crucial parameter in oceanography. This study explores the optimization of machine learning models to predict PAR in the water column using selected wavelengths of downwelling irradiance. By leveraging Genetic Algorithms (GA), optimal wavelength combinations were identified for two machine learning models: Linear Regression (LR) and Regression Trees (RT). The models were trained on data from the HE533 expedition and validated using datasets from multiple ship expeditions across different geolocations. Experimental results indicate that the LR model, with an optimal wavelength combination of Ed(469), Ed(501), and Ed(600), achieved the highest prediction accuracy (R² = 0.9992, MAE = 5.78). The RT model, using Ed(433), Ed(586), and Ed(687), performed slightly worse (R² = 0.9954, MAE = 16.37). While both models generalised well to unseen datasets, significant prediction errors were observed for small PAR values at lower water depths.
References
Berthold, M.R., Cebron, N., Dill, F., Gabriel, T.R., Kötter, T., Meinl, T., Ohl, P., Thiel, K., Wiswedel, B., 2009. KNIME - the Konstanz information miner: version 2.0 and beyond. SIGKDD Explor. Newsl. 11, 26–31. https://doi.org/10.1145/1656274.1656280
Bramer, M., 2020. Principles of Data Mining, Undergraduate Topics in Computer Science. Springer London, London. https://doi.org/10.1007/978-1-4471-7493-6
Breiman, L., Friedman, J., Olshen, R.A., Stone, C.J., 1984. Classification and Regression Trees. Routledge, New York. https://doi.org/10.1201/9781315139470
Dutkiewicz, S., Hickman, A.E., Jahn, O., Henson, S., Beaulieu, C., Monier, E., 2019. Ocean colour signature of climate change. Nat Commun 10, 578. https://doi.org/10.1038/s41467-019-08457-x
Field, C.B., Behrenfeld, M.J., Randerson, J.T., Falkowski, P., 1998. Primary Production of the Biosphere: Integrating Terrestrial and Oceanic Components. Science 281, 237–240. https://doi.org/10.1126/science.281.5374.237
Freedman, D.A., 2009. Statistical Models: Theory and Practice, 2nd ed. Cambridge University Press, Cambridge. https://doi.org/10.1017/CBO9780511815867
Friedman, J.H., 1991. Multivariate Adaptive Regression Splines. The Annals of Statistics 19, 1–67. https://doi.org/10.1214/aos/1176347963 Friedrichs, A., Schwalfenberg, K., Voß, D., Wollschläger, J., Zielinski, O., 2020. Hyperspectral underwater light field measured during the cruise MSM56 with RV MARIA S. MERIAN. https://doi.org/10.1594/PANGAEA.917534
Glibert, P.M., 2020. Harmful algae at the complex nexus of eutrophication and climate change. Harmful Algae, Climate change and harmful algal blooms 91, 101583. https://doi.org/10.1016/j.hal.2019.03.001
Holinde, L., Zielinski, O., 2016. Bio-optical characterization and light availability parameterization in Uummannaq Fjord and Vaigat–Disko Bay (West Greenland). Ocean Science 12, 117–128. https://doi.org/10.5194/os-12-117-2016
Holland, J., 1975. Adaptation in Natural and Artificial Systems.
Krause-Jensen, D., Duarte, C.M., 2016. Substantial role of macroalgae in marine carbon sequestration. Nature Geosci 9, 737–742. https://doi.org/10.1038/ngeo2790
Kumm, M.M., Nolle, L., Stahl, F., Jemai, A., Zielinski, O., 2022. On an Artificial Neural Network Approach for Predicting Photosynthetically Active Radiation in the Water Column, in: Bramer, M., Stahl, F. (Eds.), Artificial Intelligence XXXIX, Lecture Notes in Computer Science. Springer International Publishing, Cham, pp. 112–123. https://doi.org/10.1007/978-3-031-21441-7_8 Mascarenhas, V.J., Voß, D., Henkel, R., Wollschläger, J., Zielinski, O., 2020. Hyperspectral underwater light field measured during the cruise MSM65 with RV MARIA S. MERIAN. https://doi.org/10.1594/PANGAEA.917564
Pitarch, J., Leymarie, E., Vellucci, V., Massi, L., Claustre, H., Poteau, A., Antoine, D., Organelli, E., 2025. Accurate estimation of photosynthetic available radiation from multispectral downwelling irradiance profiles. Limnology & Ocean Methods lom3.10673. https://doi.org/10.1002/lom3.10673
Sloyan, B., Roughan, M., Hill, K., 2018. Global Ocean Observing System.
Stahl, F., Nolle, L., Zielinski, O., Jemai, A., 2022. A Model for Predicting the Amount of Photosynthetically Available Radiation from BGC-ARGO Float Observations in the Water Column, in: ECMS 2022 Proceedings Edited by Ibrahim A. Hameed, Agus Hasan, Saleh Abdel-Afou Alaliyat. Presented at the 36th ECMS International Conference on Modelling and Simulation, ECMS, pp. 174–180. https://doi.org/10.7148/2022-0174
Tholen, C., Nolle, L., Wollschlaeger, J., Stahl, F., 2024. Model generalisation for predicting the amount of photosynthetically available radiation in the water column from freefall profiler observations, in: ECMS 2024 Proceedings Edited by Daniel Grzonka, Natalia Rylko, Grazyna Suchacka, Vladimir Mityushev. Presented at the 38th ECMS International Conference on Modelling and Simulation, ECMS, pp. 381–386. https://doi.org/10.7148/2024-0381
Voß, D., Henkel, R., Wollschläger, J., Zielinski, O., 2020a. Hyperspectral underwater light field measured during the cruise SO248 with RV SONNE. https://doi.org/10.1594/PANGAEA.911988
Voß, D., Henkel, R., Wollschläger, J., Zielinski, O., 2020b. Hyperspectral underwater light field measured during the cruise SO267/2 with RV
SONNE. https://doi.org/10.1594/PANGAEA.912028
Voß, D., Henkel, R., Wollschläger, J., Zielinski, O., 2020c. Hyperspectral underwater light field measured during the cruise SO245 with RV SONNE. https://doi.org/10.1594/PANGAEA.911558
Voß, D., Henkel, R., Wollschläger, J., Zielinski, O., 2020d. Hyperspectral underwater light field measured during the cruise SO254 with RV SONNE. https://doi.org/10.1594/PANGAEA.912001
Voß, D., Wollschläger, J., Henkel, R., Zielinski, O., 2020e. Hyperspectral underwater light field measured during the cruise HE533 with RV HEINCKE. https://doi.org/10.1594/PANGAEA.918041
Voß, D., Wollschläger, J., Henkel, R., Zielinski, O., 2020f. Hyperspectral underwater light field measured during the cruise HE492 with RV HEINCKE. https://doi.org/10.1594/PANGAEA.918047
Wang, L., Gong, W., Li, C., Lin, A., Hu, B., Ma, Y., 2013. Measurement and estimation of photosynthetically active radiation from 1961 to 2011 in Central China. Applied Energy 111, 1010–1017. https://doi.org/10.1016/j.apenergy.2013.07.001
Wollschläger, J., Henkel, R., Voß, D., Zielinski, O., 2020a. Hyperspectral underwater light field measured during the cruise HE503 with RV HEINCKE. https://doi.org/10.1594/PANGAEA.912073
Wollschläger, J., Henkel, R., Voß, D., Zielinski, O., 2020b. Hyperspectral underwater light field measured during the cruise HE516 with RV HEINCKE. https://doi.org/10.1594/PANGAEA.912033
Wollschläger, J., Henkel, R., Voß, D., Zielinski, O., 2020c. Hyperspectral underwater light field measured during the cruise HE527 with RV
HEINCKE. https://doi.org/10.1594/PANGAEA.912054
Wollschläger, J., Tietjen, B., Voß, D., Zielinski, O., 2020d. An Empirically Derived Trimodal Parameterization of Underwater Light in Complex Coastal Waters – A Case Study in the North Sea. Frontiers in Marine Science 7.
Wood, S.N., Goude, Y., Shaw, S., 2015. Generalized Additive Models for Large Data Sets. Journal of the Royal Statistical Society Series C: Applied Statistics 64, 139–155. https://doi.org/10.1111/rssc.12068
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Frederic Stahl, Lars Nolle, Martin Kumm, Christoph Tholen
This work is licensed under a Creative Commons Attribution 4.0 International License.
