University of Cambridge > > AI4ER Seminar Series > CDT Team Challenge

CDT Team Challenge

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Tudor Suciu.

A Graph-Based Framework for Ecosystem Fragmentation in the Chernobyl Region

Biodiversity Team: Simon Mathis, Katherine Green, Herbie Bradley, Arduin Findeis, Yilin Li, Simon Thomas

Habitats are often fragmented by human development, and alongside the loss of overall habitat area, this fragmentation could have an effect on the biodiversity. The trial region we are using in this study is around Chernobyl, as we expect that reduced human impact resulting from the nuclear disaster may lead to a reduction in fragmentation over time. We are also able to compare trends inside and outside of the exclusion zone. The quantification of fragmentation is dependent on the resolution of the land data, the classification scheme, and the metric used. We intend to use a combination of Landsat data, with a classification model trained landcover data sets provided by ESA and the British Trust for Ornithology, and to trial new metrics calculated upon the resulting georeferenced graph. We will report on our progress so far as a team, and we look forward to answering your questions.

Assessing temporal change in exposure of informal settlements through repeat satellite observation

Natural Hazards Team: Ira Shokar, Joycelyn Longdon, Luke Cullen, Matt Allen, Natalie Yao, Seb Hickman

Exposure to natural hazards increases with building in hazardous areas. Particularly vulnerable to such hazards are informal settlements with unregulated construction standards, often located on disused land that may be too exposed for formal building. We are endeavouring to quantify exposure variation by combining a change detection model applied to repeat imagery from Sentinel-2, with a settlement classifier, to identify the appearance of exposed informal settlements. To quantify exposure we will use available socio-economic data, firstly to estimate human exposure, and secondly to estimate possible capital exposure should the exposed area be insured.

This talk is part of the AI4ER Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity