CDT Team Challenge
- đ¤ Speaker: AI4ER CDT 2020 cohort
- đ Date & Time: Tuesday 16 February 2021, 11:00 - 12:30
- đ Venue: https://zoom.us/j/6708259482?pwd=Qk03U3hxZWNJZUZpT2pVZnFtU2RRUT09
Abstract
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.
Series This talk is part of the AI4ER Seminar Series series.
Included in Lists
- AI4ER Seminar Series
- bld31
- Cambridge Centre for Data-Driven Discovery (C2D3)
- Cambridge talks
- Chris Davis' list
- https://zoom.us/j/6708259482?pwd=Qk03U3hxZWNJZUZpT2pVZnFtU2RRUT09
- Interested Talks
- ndk22's list
- ob366-ai4er
- rp587
- Trust & Technology Initiative - interesting events
- yk449
Note: Ex-directory lists are not shown.
![[Talks.cam]](/static/images/talkslogosmall.gif)

AI4ER CDT 2020 cohort
Tuesday 16 February 2021, 11:00-12:30