Seminar: “Ocean exploration with machine learning: An Antidote to Chaos?“
The coming Friday 2nd August Maike Sonnewald from MIT will give a talk titled “Ocean exploration with machine learning: An Antidote to Chaos?“ at 10h in the seminar room 4020 (west wing)
Abstract: Machine learning has the potential to revolutionize oceanography, if applied with care. Three case studies highlight the potential for greatly accelerating the efficiency of ocean exploration using supervised (neural networks) and unsupervised (clustering) machine learning. Firstly, two decades of data from the realistic ECCO state estimate 3D physical fields are used to objectively determine global physical regimes using k-means clustering. The identified regions corresponds closely to those predicted by canonical theory from physical oceanography and the method can be scaled to analyze vast amounts of data from e.g. the Climate Model Intercomparison Project. Secondly, the highdimentional dataset from the biogoechemical DARWIN model reveals the existence of ecological niches using t-SNE and DBSCAN clustering. Constraining ocean biomes, niches and larger regions can be examined to understand how sensitive they are to climate forcing which is crucial to protecting our ocean food chain. Lastly, a multilayer perceptron (MLP) is trained to predict which global physical regime is present on the basis of local sea surface height. Using the results from the k-means clustering as labels, we achieve a recognition rate of >80%, with good performance across the physical regions. These case studies demonstrate that algorithms can be developed to explore the ocean that have vast potential for understanding complex problems.
This year the Bjerknes Centre is arranging several debates and panel discussions. Among them, a debate between the Norwegian and Danish climate ministries on wind energy policies and economics. Beforehand, we're sailing down with the sailing vessel Statsraad Lehmkuhl, having workshops on the future of climate change with the participants.Les mer
Sea surface temperature variability and predictability based on prescribed wind-stress simulations
Name of speaker: Annika Reintges. Affiliation: GEOMAR Helmholtz Centre for Ocean Research. Click on the link to find abstract for the seminar. Note that this seminar will take place at the Nansen Centre.Les mer
Seminar: Tropical Atlantic Variability: A Personal View
Name of speaker: Ingo Richter, affiliation: JAMSTEC, Japan. Please find more information via link.Les mer
A Python-based implementation of low-dimensional energy balance models (EBMs) with application example: Late Holocene climate response to various forcings
Name of speaker: Benjamin Schmiedel. Affiliation: University of Heidelberg. Click the link for more information about the seminar.
A hands-on mini-workshop will be arranged the following day after the seminar with Benjamin Schmiedel (Tuesday 20th13:00-15:00 G-lab GFI), offering the opportunity to learn how to work with the EBM package and run these EBMs in different configurations on workstations or laptop. No registration, drop-in.Les mer
Hands- on mini-workshop: Learn how to work with the EBM package
A hands-on mini-workshop will be arranged the following day after the seminar with Benjamin Schmiedel (Tuesday 20th13:30-15:00 G-lab GFI), offering the opportunity to learn how to work with the EBM package and run these EBMs in different configurations on workstations or laptop. No registration, drop-in. Find more information via link.Les mer
Seminar: Atmospheric origins of variability in the South Atlantic meridional overturning circulation
Name of speaker: Timothy Smith. Affiliation: The University of Texas at Austin. Please find abstract via link.Les mer