Title
Using AI to dampen the unpredictability brought by climate change
Abstract
Climate change is by WHO considered the single biggest threat to human health, not just because it increases prevalence of several disease, but also because changing climate increase the unpredictability of health impacts. Early warning systems based on time series forecasting has been proposed as a cost-effective solution to improve climate resilience of the health system. I will present how we approach this problem as part of a recently started 8-year Wellcome funded projected at the HISP centre at UiO where we work in close collaboration with data scientists and governments in ten countries in Africa and South East Asia.
At the core, we are developing statistical and machine learning-based spatiotemporal multivariate time series models. As our aim is to make the methodology available across multiple country and disease contexts, we are developing a software platform that will strengthen reuse and longevity. To ensure relevance and uptake, we work as part of a broad interdisciplinary team that also study the sociotechnical aspects of decision support needs and organisational uptake.
Bio
Professor Geir Kjetil Ferkingstad Sandve, University of Oslo, Department of Informatics
Practical
The speaker is presenting in person at the Blindern campus, Niels Henrik Abels building, 8th floor.
The Tuesdays seminars series are devoted to various topics relevant for the Integreat´s research focus. Presenters from the Integreat community and beyond have 40 minutes to present, followed by a group discussion.
Seminars are open for attendance for everybody.
For those unable to attend in person: https://uio.zoom.us/j/62535744013
Point of contacts:
- Organiser and moderator: Professor Lilja Øvrelid, University of Oslo
- Integreat Administrative Leader Maria Dikova, University of Oslo