UNIVERSITY OF HELSINKI

Postdoc­toral Re­searcher in Stat­ist­ics and Ma­chine Learn­ing

7 days left

Location
Helsinki, Finland
Posted
Jul 01, 2020
End of advertisement period
Aug 16, 2020
Contract Type
Fixed Term
Hours
Full Time

The University of Helsinki, founded in 1640, is one of the world’s leading universities for multidisciplinary research. The university has an international academic community of 40,000 students and staff members. The University of Helsinki offers comprehensive services to its employees, including occupational health care and health insurance, sports facilities, and opportunities for professional development. The International Staff Services office assists employees from abroad with their transition to work and life in Finland.

The Organismal and Evolutionary Biology Research Programme (OEB) of the Faculty of Biological and Environmental Sciences comprises roughly 40 research groups which employ 40 principal investigators and 120 researchers. The research programme is situated in the Viikki science park.

The Organismal and Evolutionary Research Programme invites applications for a

POSTDOCTORAL RESEARCHER

in statistics and machine learning for a fixed term of two years. There will be a trial period of four months in the beginning. The post doc position is part of the Research Centre for Ecological Change (REC) and are funded by the Jane and Aatos Erkko Foundation for 1.1.2021-31.12.2022. PIs of the Centre are prof. Anna-Liisa Laine, prof. Otso Ovaskainen, prof. Tomas Roslin, assist. prof. Jarno Vanhatalo and assoc. prof. Marjo Saastamoinen. The starting date is 1.1.2021.

The overreaching aim of the Centre is to generate a coordinated analysis of long-term ecological data to understand impacts of global change. To unravel how populations and interactions between species in nature are responding to ongoing environmental change, the project takes advantage of the unique long-term datasets collected in Finland. The centre also develops state-of-the-art methodology for analysing long-term spatially structured data sets within a joint species distribution modelling framework. For more information on the Centre, please visit https://www.helsinki.fi/en/researchgroups/research-centre-for-ecological....

This statistics and machine learning position is aimed at developing statistical and computational methods for analyzing large and heterogeneous ecological data. The methodological work focuses specifically on development of Bayesian hierarchical multivariate spatio-temporal models and predictive model comparison methods within so called joint species distribution modeling (JSDM) framework. JSDMs are multivariate models that can be applied to hierarchical, spatial and temporal study designs, and many kinds of response data. The JSDMs used in this project are built around novel latent factor and Gaussian process models. For our recent methodological publications, see the reference list at the end.

The successful applicant should have doctoral degree in statistics, machine learning, applied mathematics or other relevant field, and have experience in the development and application of Bayesian methods for computationally challenging problems. Prior experience in ecology is not necessary, but considered an advantage. The exact direction of the work can be agreed upon based on the experience and interests of the candidate.

For more information, contact prof. Otso Ovaskainen and/or assist. prof. Jarno Vanhatalo: otso.ovaskainen@helsinki.fi, jarno.vanhatalo@helsinki.fi.

The salary will be based on level 5 of the demands level chart for teaching and research personnel in the salary system of Finnish universities. In addition, the appointee will be paid a salary component based on personal performance. The starting salary will be ca. 3300-3800 euros/month, depending on the appointee’s qualifications and experience.

Applications should include the following documents as a single pdf file: motivational letter (max 1 page), CV (max 2 pages), and publication list. Please also include contact information of two persons willing to provide a reference letter by separate request.

Please submit your application using the University of Helsinki Recruitment System via the Apply for the position link. Applicants who are employees of the University of Helsinki are requested to leave their applications via the SAP HR portal. The deadline for submitting the application is 16 August 2020.

References

Hartmann, M., Hosack, G. R., Hillary, R. M. and Vanhatalo, J. (2017). Gaussian processs framework for temporal dependence and discrepancy functions in Ricker-type population growth models. Annals of Applied Statistics, 11(3):1375-1402.

Itter, I., Vanhatalo, J. and Finley, J. (2019). EcoMem: An R package for quantifying ecological memory. Environmental Modelling & Software, 119: 305-308.

Liu, J. and Vanhatalo, J. (2020). Bayesian model based spatio-temporal sampling designs and partially observed log Gaussian Cox process. Spatial Statistics, 35:100392.

Ovaskainen, O., Tikhonov, G., Norberg, A., Blanchet, F. G., Duan, L., Dunson, D., Roslin, T. and Abrego, N. (2017a). How to make more out of community data? A conceptual framework and its implementation as models and software. Ecology Letters 20, 561-576

Ovaskainen, O., Tikhonov, G., Dunson, D., Grøtan, V., Engen, S., Sæther, B.-E. and Abrego, N. (2017b). How are species interactions structured in species rich communities? A new method for analysing time-series data. Proceedings of the Royal Society B: Biological Sciences 284, 20170768.

Tikhonov, G., Duan, L., Abrego, N., Newell, G., White, M., Dunson, D., and Ovaskainen, O. 2019. Computationally efficient joint species distribution modeling of big spatial data. Ecology 00 (00):e02929.

Vanhatalo, J., Hartmann, M and Veneranta, L (2019). Additive multivariate Gaussian processes for joint species distribution modeling with heterogeneous data. Bayesian Analysis, doi:10.1214/19-BA1158

Vanhatalo, J., Li, Z. and Sillanpää, M. (2019). A Gaussian process model and Bayesian variable selection for mapping function-valued quantitative traits with incomplete phenotype data. Bioinformatics, 35(19):3684-3692.

Vanhatalo, J., Hosack, G. R. and Sweatman, H. (2017). Spatio-temporal modelling of crown-of-thorns starfish outbreaks on the Great Barrier Reef to inform control strategies. Journal of Applied Ecology, 54:188-197.

Due date

16.08.2020 23:59 EEST

Similar jobs

Similar jobs