Missouri Botanical Garden Open Conference Systems, TDWG 2016 ANNUAL CONFERENCE

Font Size: 
Towards Recommending Visualization for Biodiversity Data
Pawandeep Kaur

Building: CTEC
Room: Auditorium
Date: 2016-12-08 12:00 PM – 12:15 PM
Last modified: 2016-11-17


To address the critical challenges of biodiversity conservation and study its impact on the ecosystem, scientists have been producing a large amount of highly heterogeneous and distributed data. Managing, processing, and visualizing this data, requires informatics skills. While many biologists lack these skills, informaticians are limited in their understanding of biological domain requirements and the context of the data. Studies have shown that the potential of visualization has not been fully utilized in scientific journals, due to inappropriate visualization selection with respect to the nature of data and message to convey. Inappropriate visualization selection does not only impede analysis but also results in misleading conclusions. To aid scientists in exploring and understanding their data and to provide a solution for this problem, we propose a semi‐automated context‐aware visualization recommendation model.  To be useful, such suggestions need to be based on the visualization knowledge of domain experts. To gather such knowledge and to understand the requirements of biodiversity scientist we have designed the survey available at:


Acquired information and knowledge will be used in the development of a visualization recommendation framework serving the biodiversity research community. In the recommendation model, information will be extracted from data and metadata and annotated with suitable ecological operations (analytical tasks like spatial distribution, relative species abundance). This information will be mapped to the visualization semantics, i.e., each extracted operation in which variables are involved and how they are visually represented. This helps in deriving the relevant visualizations for that data.