To support capacity enhancement activities in the network SANBI-GBIF aims to:

1. Build capacity towards ensuring that relevant, high quality biodiversity information is available and used by scientists, managers and decision makers,
2. Grow a coordinated network of partners with the commitment and capacity to digitise, share and use biodiversity information.

SANBI-GBIF supports the community through physical training events and an online eLearning Platform, as a repository of re-usable training materials for various scientific areas including: data management (data cleaning, formatting and publishing), geo-referencing, data mobilisation, data use and its applications.

SANBI wishes to acknowledge GBIF-Spain, as the host of the eLearning Technology Platform.

Training Courses and Available Content and Curricula

Analytical Techniques in Biodiversity Big Data Using GBIF: Making an Impact

The vast quantities of biodiversity data put together in a uniform, FAIR way, and now available, in part led by GBIF, is recognized as an enabler of high-impact innovative science, and a key to respond to the current societal challenges. However, the exploitation of this resource is often hindered by limited capacity.

This course has been designed as a Partnership initiative between SANBI-GBIF and GBIF Spain, which aims to exploring ways of using big data analytics to enable the mining of the data, and the identification of some key tools, techniques and approaches that can be used to ask some pertinent research questions related to time, space and taxonomy.

The contents of the course includes aspects such as the GBIF API, the use of Jupyter notebooks, using big data analytic techniques to manage aspects of data quality like time, space and taxonomy, data visualisation, conservation planning and species distribution modelling using deep learning approaches.

This course will includes trainers from GBIF South Africa and GBIF Spain including key experts from the Spanish National Research Council, with expertise in Data Science and Big Data Analytics. The South African team includes the National Biodiversity Assessment Team from SANBI, and collaborators involved in the mission to establish a Centre for Biodiversity Informatics, including Sol Plaatje University, University of Free State and the University of Cape Town.

New users of the eLearning Platform can view details of the course, and access the platform by signing up with the following link:

View the Course and Sign-Up

Registered users can log in to the eLearning Platform and subscribe to the Analytical Techniques in Biodiversity Big Data Using GBIF: Making an Impact course by clicking the link below:

Access the eLearning Platform

Data Management and Cleaning supporting Science, Policy and Sustainable Development

This course aims to focus on the management and cleaning of primary biodiversity data, to ensure that data and the information derived from this is relevant, and can ultimately be used for improved decision making. Through this course, participants will learn more about the SANBI-GBIF Node and the GBIF Platform. Participants will also be introduced to key software packages to manage, clean and visualize data such as the R package and QGIS. Participants will also learn about R basics, issues with biodiversity data and the need for data cleaning, getting a standardized taxonomy, resolving coordinate issues and biodiversity geo referencing.

This course was first developed as a training workshop conducted by SANBI-GBIF and was facilitated by Vernon Visser and Fatima Parker-Allie.

New users of the eLearning Platform can view details of the course, and access the platform by signing up with the following link:

View the Course and Sign-Up

Registered users can log in to the eLearning Platform and subscribe to the Data Management and Cleaning supporting Science, Policy and Sustainable Development course by clicking the link below:

Access the eLearning Platform

Fitness for Use of Biological Data

This course aims to expose participants to the key areas of data management and quality control, which are relevant to the production of data that is “fit-for-use”. This enhanced data is then relevant for use in biodiversity research and assessments that can ultimately inform policy development and environmental decision-making. Relevant topics include:

• Online data cleaning tools
• Geo-referencing best practice
• New and developing methodologies

This course was first developed as a training workshop held by SANBI-GBIF in 2018 and was facilitated by Arthur Chapman.

New users can access the course by signing up with the following link:

View the Course

Registered users can log in to the eLearning Platform and subscribe to the Fitness for Use of Biological Data course by clicking the link below:

Access the eLearning Platform

Species Distribution Modelling

This course is intended to focus on the use and application of data, with species distribution modelling being the key focus area of this short course. Species distribution modelling, or niche modelling as it is commonly referred to, is a data analysis technique using primary biodiversity data, together with environmental data to predict spatial patterns of environmental suitability for species. This technique has received considerable attention in the last decade and is a growing area of research in ecology, conservation and invasion biology. This course has focused on the use of R for species distribution modelling and is relevant for both terrestrial and marine stakeholder communities.

This course was first developed as a training workshop held by SANBI-GBIF in 2015 and was facilitated by Dr. Vernon Visser and Ms. Fatima Parker-Allie.

New users of the eLearning Platform can view details of the course, and access the platform by signing up with the following link:

View the Course and Sign-Up

Registered users can log in to the eLearning Platform and subscribe to the SANBI-GBIF course in using R for Species Distribution Modelling by clicking the link below:

Access the eLearning Platform

SANBI-GBIF Hosted Training Events taking place in 2024