Description

Citizen science is becoming mainstream. Every year more and more citizen science projects appear, and the citizen science community is getting organized in societies where know-how and ideas are openly shared. Citizen science is also known as crowdsourced science or volunteered monitoring because a crowd of volunteers actively contributes and drives the research.

Several studies have proven the value of crowdsourced or volunteered observations for scientific research. For instance, volunteers provide invaluable data to study vegetation seasonality (i.e. the timing of recurring biological events like leaf out, flowering or leaf fall). However, guiding the collection of volunteered observations will undoubtedly increase the quality and accelerate the production of scientifically valuable geo-information. Hence, this MSc topic will focus on reviewing approaches that could help to optimize data collection by volunteers. In particular, the student will investigate active learning approaches that could be used to mobilize volunteers so that they can deliver better data, which in turn can be used to create better phenological models. The Extended Spring-indices models and volunteered phenological observations of first leaf and first bloom across the USA could be used to define a case study for this MSc thesis.

Objectives and Methodology

To investigate the use of active learning methods to optimize volunteered data collection

Further reading

D. Tuia, M. Volpi, L. Copa, M. Kanevski, and J. Munoz-Mari, “A Survey of Active Learning Algorithms for Supervised Remote Sensing Image Classification,” IEEE J. Sel. Top. Signal Process., vol. 5, no. 3, pp. 606–617, 2011.