I am an oceanographer based in Zürich, Switzerland. My work combines the exciting field of machine learning with earth system science, particularly the marine carbonate system. In the past, my work has ranged from the measurement of CO2 at sea and the processing of these samples in the laboratory, data management and quality control. Now, I work on machine learning products that estimate the amount of CO2 that the ocean is taking up from satellites. In my work at ETH, I am using these CO2 estimates to look at the changes in the ocean's acidity (pH) and where and when this coincides with extreme warming events. On the side, I dabble in Python and have created tools that are designed to streamline the processing of raw scientific data to being publication-ready. I am currently working on a tool for scientists to explore and process profiling glider data.
My work aims to use satellites to assess the impact of pH and temperature extremes in the global surface oceans. Machine learning estimates of CO2 are used to calculate pH from satellites. Watch this space!
I focussed on developing a global surface CO2 product through various machine learning methods. I was also involved in optimising sampling strategies for CO2 for the Southern Ocean. I also dipped my toes in the pool of data management for the SOCCO group's Wave Gliders, Seagliders and Slocum gliders. I started the development of the GliderTools package while at the CSIR.
I have developed tools in Python to process ocean data from raw format to a publishable stage. These tools are developed in Python using a suite of packages:
Pandas, xarray, netCDF4, flask to mention a few – these can be seen in my GitHub and GitLab profiles. I have done short term contract back-end dev work for Prosento (www.prosento.com) including front-end work in
I have done several guest lectures and workshops at the University of Cape Town. In workshops, students are taught to work with different ocean data sources and how to compare and plot these data. These lectures can be found on my GitHub profile. My other lectures have been on the marine carbonate system.
I have also partaken in several research cruises in the Southern Ocean. On these cruises, I ran the VINDTA 3C by (Marianda) and underway pCO2 system (by General Oceananics). I have extensive knowledge of troubleshooting these instruments.
Department of Oceanography
Awarded the Joseph Arenow award for the best Ph.D. in the Faculty of Science in 2017.
Supervisors: Pedro Monteiro, Schalk Kok, Marcello Vichi
Title: Improved estimates and understanding of interannual trends of CO2 fluxes in the Southern Ocean
Department of Oceanography
By dissertation and passed with distinction
Supervisors: Pedro Monteiro, Howard Waldron
Title: Seasonality of the marine carbonate system in the Southern Benguela: nutrient stoichiometry, alkalinity production, and CO2 flux.
Majoring in Ocean & Atmospheric Science, and Environmental & Geographical Science.
Was on the Dean's Merit list for 2006, 2007 and 2008.
Passed Honours in 2009 with distinction.
Passed with A-aggregate and was awarded the Values Award for reflecting the schools mission on a sustained basis.
I grew up speaking English to my father, Dutch to my mother (kitchen dutch), and Afrikaans at school. I am thus proficient in English and Afrikaans writing.
I have experience in running and troubleshooting the VINDTA 3C instrument (measures Total Alkalinity and Dissolved Inorganinc Carbon) and the General Oceanics underway system (measures pCO2).
My technical skills have been honed through more than six years of data wrangling and analysis during my MSc and PhD. During my MSc I chose to switch from MATLAB to Python as a free and community supported programming language.
An interactive Python (ideally Jupyter) toolkit for processing Seaglider basestation NetCDF files: despiking, smoothing, outlier detection, backscatter, fluorescence quenching, gridding and interpolating.
Plotting functions are also included.
Process raw output from the CSIR/STS CO2 instrument into a readable table format. There are interactive plotting features for data exploration. This package is built using
Flask, but is still in development and may be unstable.
A python package that allows for the recalculation of VINDTA data. This requires the .dbs file + .dat files for all the alkalinity recalculations. The package writes the output to an Excel file to make filling in nutrient data easier.
Gregor, L. , Lebehot, A. D., Kok, S., Monteiro, P.M.S. (2019). A comparative assessment of the uncertainties of global surface-ocean CO2 estimates using a machine learning ensemble (CSIR-ML6 version 2019a) – have we hit the wall? Geosci. Model Dev. Discuss., in review. https://doi.org/10.5194/gmd-2019-46
Gregor, L. , Kok, S., Monteiro, P.M.S. (2018). Interannual drivers of the seasonal cycle of CO2 in the Southern Ocean. Biogeosciences, 15(8), 2361-2378. https://doi.org/10.5194/bg-15-2361-2018
Thomalla, S. J., Moutier, W., Ryan-Keogh, T. J., Gregor, L., & Schütt, J. (2018). An optimized method for correcting fluorescence quenching using optical backscattering on autonomous platforms. Limnology and Oceanography: Methods, 16(2), 132–144. https://doi.org/10.1002/lom3.10234
Gregor, L., Kok, S., & Monteiro, P. M. S. (2017). Empirical methods for the estimation of Southern Ocean CO2: support vector and random forest regression. Biogeosciences, 14(23), 5551–5569. https://doi.org/10.5194/bg-14-5551-2017
Bakker, D. C. E., Pfeil, B., Landa, C. S., Metzl, N., O’Brien, K. M., Olsen, A., …, Gregor, L. … Xu, S. (2016). A multi-decade record of high-quality fCO2 data in version 3 of the Surface Ocean CO2 Atlas (SOCAT). Earth System Science Data, 8(2), 383–413. https://doi.org/10.5194/essd-8-383-2016
Monteiro, P. M. S., Gregor, L., Lévy, M., Maenner, S., Sabine, C. L., & Swart, S. (2015). Intraseasonal variability linked to sampling alias in air-sea CO2 fluxes in the Southern Ocean. Geophysical Research Letters, 42(20), 8507–8514. https://doi.org/10.1002/2015GL066009
Gregor, L., & Monteiro, P. M. S. (2013). Seasonal cycle of N:P:TA stoichiometry as a modulator of CO2 buffering in eastern boundary upwelling systems. Geophysical Research Letters, 40(20), 5429–5434. https://doi.org/10.1002/2013GL058036
Gregor, L., & Monteiro, P. M. S. (2013). Is the southern benguela a significant regional sink of CO2? South African Journal of Science, 109(5), 1–5. https://doi.org/10.1590/sajs.2013/20120094