Model Generalisation for Predicting the Amount of Photosynthetically Available Radiation in the Water Column from Freefall Profiler Observations

Authors

  • Christoph Tholen German Research Center for Artificial Intelligence
  • Lars Nolle German Research Center for Artificial Intelligence, Jade University of Applied Sciences
  • Jochen Wollschläger Carl von Ossietzky Universität Oldenburg School of Mathematics and Science Institute for Chemistry and Biology of the Marine Environment (ICBM)
  • Frederic Stahl German Research Center for Artificial Intelligence

DOI:

https://doi.org/10.26034/lu.akwi.2024.6224

Keywords:

Machine Learning, Underwater Light Field, Photosynthetic Active Radiation, Freefall Profiler, KNIME

Abstract

In modern oceanography Photosynthetically Available Radiation (PAR) is used for modelling vegetation growth as it is a requirement for the process of photosynthesis. PAR as integrated value of the light spectrum between 400-700 nm can be measured directly using respective sensor systems. However, PAR can also be determined indirectly using measurements from only a small number of discrete wavelengths. In this paper, such a modelling approach is presented for predicting PAR in the water column. The approach uses spectral information within the water column and from above the sea surface. Three different modelling approaches based on artificial intelligence (AI) were used. It was shown that the artificial neural network (ANN) approach outperformed the regression tree (RT) and the linear regression (LR) approaches. It was also shown that the models generalise well, with an accuracy loss of 10 % based on the median, on data recorded in other geolocations without additional modification or re-training.

References

Alfred-Wegener-Institut Helmholtz-Zentrum für Polar- und Meeresforschung, 2017. Research Vessel HEINCKE Operated by the Alfred-Wegener-Institute. Journal of large-scale research facilities JLSRF 3, A120–A120. https://doi.org/10.17815/jlsrf-3-164

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

Breiman, L., Friedman, J., Olshen, R.A., Stone, C.J., 1984. Classification and Regression Trees. Routledge, New York. https://doi.org/10.1201/9781315139470

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

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

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

Mascarenhas, V.J., Voß, D., Wollschläger, J., Zielinksi, O., 2017. Fjord light regime: Bio-optical variability, absorption budget, and hyperspectral light availability in Sognefjord and Trondheimsfjord, Norway. Journal of Geophysical Research: Oceans 122, 3828–3847. https://doi.org/10.1002/2016JC012610

Riedmiller, M., Braun, H., 1993. A direct adaptive method for faster backpropagation learning: the RPROP algorithm, in: IEEE International Conference on Neural Networks. Presented at the IEEE International Conference on Neural Networks, pp. 586–591 vol.1. https://doi.org/10.1109/ICNN.1993.298623

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

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

2025-01-09

Issue

Section

Fundamentals