by Saskia A. Otto

This site is all about data harvesting, analysis and communication to increase our understanding of marine system dynamics and improve marine conservation.

Marine Data Science (MDS)

Find out more about data science for marine data in section MDS

Courses and Tutorials

This website will provide access to different online courses and tutorials that all spin around programming, data harvesting, data analysis, marine ecology, and MDS in marine management (see Courses).

Data and databases

An overview of commonly used datasets and databases in marine sciences including their weblinks are provided in the Data section.

R, packages and other Software

The core programming environment in data science nowadays is R. A summary of useful packages tailored to address marine research questions is provided in the Software section together with a short overview of alternative programming languages.

Application in marine management

You will find application examples and tools on how MDS can be used in marine management in the different Blog entries.

Interested in Data Analysis with R?

Then try out this online course.


Blog topics

This website has just been created, so stay tuned for more posts on topics spinning around harvesting and visualization of marine data, spatio-temporal modelling, statistical and machine learning, tech-related information on communicating marine science, on programming, useful R packages and more.

Example code for an Integrated Trend Analysis (ITA)

By Saskia O. on November 3, 2019

I wrote the following R Code for an Integrated Trend Analysis (ITA) during my PhD thesis in 2010, when I attended for the first time the annual meeting of the ICES/HELCOM Working Group on Integrated Assessments of the Baltic Sea (WGIAB). The code helped running a cross-comparison of several Baltic Sea sub-systems (see the 2010 report1). Together with Rabea Diekmann we fine-tuned the code and published it along with a full description on ITA methods in a Book chapter2 in Climate Impacts on the Baltic Sea: From Science to Policy.

Continue reading

Comparison of change point detection methods

By Saskia on September 28, 2019

This post compares a few change point detection method available in R given different time series dynamics and research questions. Change points or breakpoints are abrupt variations in time series data and may represent transitions between different states. The detection of change points is useful in modelling and prediction of time series and is found in application areas such as medical condition monitoring, speech and image analysis or climate change detection.

Continue reading

Run Shiny Server on your own DigitalOcean droplet - Part 1

By Saskia on April 28, 2019

Do you also like shiny apps and would like to host more than 5 apps as currently permitted at Than the solution might be to run your own shiny server using any (virtual) server. In the following I will describe step-by-step how I set up my own Shiny as well as Rstudio Server using Digital Ocean. At the university I already use Rstudio Server extensively in my stats courses, which runs on a physical server at my research institute.

Continue reading

Run Shiny Server on your own DigitalOcean droplet - Part 2

By Saskia on April 28, 2019

This 2nd part will cover the installation of R, RStudio and the Shiny Server and is based on R’s Ubuntu packages for R tutorial, the DigitalOcean manual, RStudio’s RStudio Server and Shiny Server guides, and Dean Attali’s great blog post. Table of Contents - Part 2 Step 8: Some preparations Step 9: Install R and packages 9.1 R 9.2 R Packages Step 10: Install RStudio Server Step 11: Install and configure Shiny Server 11.

Continue reading