Proximal sensing for scalable mapping of shallow coastal habitats

Daniel Schürholz is currently based at the Max-Planck-Institute for Marine Microbiology in Bremen, Germany. He finished his Bachelor in Computer Science at the Catholic University San Pablo in Arequipa, Peru, his home country. He received his Master in Computer Science as part of the EU joint masters program Pervasive Computing and COMunications for sustainable development (PERCCOM) in France, Finland, Sweden and Australia.

His current project will look into creating fine-scaled benthic habitat maps using underwater proximal sensing, comprised by hyperspectral imaging, 3D modeling, and extended multi-sensor data. He will apply deep learning and computer vision algorithms to generate classified habitat maps in a scalable way, describing underwater scenes. His research will focus on using these maps to tackle descriptive ecological questions about coral reefs, for example the composition of patch communities, and functional questions, such as the role of turf algae on reef productivity.

Publications

• Schürholz D, Chennu, A. (2022) Digitizing the coral reef: Machine learning of underwater spectral images enables dense taxonomic mapping of benthic habitats.  Methods in ecology and evolution, 00, 1-18.  https://doi.org/10.1111/2041-210X.14029
• Schürholz D, et al. (2022) Artificial Intelligence-enabled context-aware air quality prediction for Smart Cities. Elsevier Journal of Cleaner Production, 271. https://doi.org/10.1016/j.jclepro.2020.121941
• Schürholz D, Zaslavsky A, Kubler S (2019) Context-and situation prediction for the MyAQI urban air quality monitoring system. In Galinina O, Andreev S, Balandin S, Koucheryavy Y (eds) Internet of Things, Smart Spaces, and Next Generation Networks and Systems, pp. 77-90. Springer, Cham. doi: 10.1007/978-3-030-30859-9_7
• Schürholz D, Nurgazy M, Zaslavsky A, Jayaraman PP, Kubler S, Mitra K, Saguna S (2019) MyAQI: context-aware outdoor air pollution monitoring system. Proceedings of the 9th International Conference on the Internet of Things: 1-8. doi: 10.1145/3365871.3365884