[ml_ned] PhD candidate / Postdoc in Machine Learning for Ecology (1.0 FTE)

Tom Claassen tomc at cs.ru.nl
Mon Jul 10 14:16:10 CEST 2017


===========================================================
PhD candidate / Postdoc position in Machine Learning for Ecology (1.0 FTE, 4yrs./3yrs.)
Institution : Radboud University Nijmegen, Netherlands
Keywords : causal discovery, ecological modelling, machine learning, environmental change
Application deadline : 14 August 2017
Website : http://www.ru.nl/werken/details/details_vacature_0/?recid=598034
===========================================================
(apologies for crossposting)

Summary
The project aims to bridge the gap between state-of-the-art causal discovery and its application to observational ecological data, in order to help predict factors that drive biodiversity under environmental change. To that end, causal discovery algorithms will be developed that are capable of handling the spatiotemporal dependencies that are common in field monitoring data. After testing, the algorithms will be applied to reveal cause-effect relationships from various ecological monitoring datasets.
We are looking for talented, highly motivated PhD candidates and/or Postdocs: either students from the field of computer science/mathematics with an interest in real-world applications, or students from biology/environmental sciences with a strong background in modelling and/or statistical analysis.

Description
Predicting how species and ecosystems will respond to global environmental change is a central goal in ecology. As controlled experiments cannot fully address this goal, there is a clear need for innovative statistical and machine learning methods to analyse ecological field data. In this project you will be developing and testing novel machine learning algorithms that can be applied to reveal causal relationships from observational ecological data. Ecological monitoring data are typically characterised by multiple spatial and temporal dependencies. For example, due to auto-ecological processes such as reproduction and dispersal, species’ distribution patterns are often more clustered than would be expected based on abiotic gradients. A main challenge in this project will be to develop machine learning algorithms able to deal with such dependencies. After testing, you will apply the algorithms to large-scale ecological monitoring data in order to reveal causal relationships between species’ occurrence and underlying drivers. 

The project is a collaboration between the Data Science group of the Institute for Computing and Information Sciences and the Environmental Science group of the Institute for Water and Wetland Research (IWWR). You will be working in both groups, at the interface of ecology and machine learning.
The main focus of the Environmental Science group of the IWWR is on quantifying, understanding and predicting human impacts on the environment. To that end, we employ a variety of research methods, including process-based modelling, meta-analyses, field studies and lab work. In our research we cover multiple stressors, species and spatial scales, searching for overarching principles that can ultimately be applied to better underpin environmental management and biodiversity conservation. 
The Data Science group’s research concerns the design and understanding of (probabilistic) machine learning methods, with a keen eye on applications in other scientific domains as well as industry. The Data Science section is part of the vibrant and growing Institute for Computing and Information Sciences (iCIS). iCIS is consistently ranked as the top Computer Science department in the Netherlands (National Research Review of Computer Science 2002-2008 and 2009-2014).

What we expect from you:
You have an MSc degree in natural science, computer science, mathematics, or a related discipline. You are open-minded, with a strong interest in multidisciplinary research and a solid background mathematics, and you are highly motivated to perform scientific research. As you will be working in two different research groups, you need to be flexible, communicative and able to work in a multidisciplinary team.

For more information about this vacancy and details on how to apply, see the website or contact: 
* Prof. Mark Huijbregts, e-mail: m.huijbregts at science.ru.nl (IWWR)
* Prof. Tom Heskes, tel: +31 24 3652696, e-mail: t.heskes at science.ru.nl (iCIS)
* Dr. Tom Claasen, tel: +31 24 3652019, e-mail: tomc at cs.ru.nl (iCIS)


More information about the machine_learning_nederland mailing list