PhD student in Environmental Science, with a focus on machine learning

The Department of Environmental Science is one of the biggest departments at the Faculty of Science. The department consists of four units with more than 170 researchers, teachers, doctoral students and technical/administrative staff from over 30 countries. Research and teaching focuses on chemical contaminants, atmospheric science, biogeochemistry and (eco)toxicology. As an employee at the Department of Environmental Science you will be part of a dynamic environment with research in leading research areas and with a strong international profile. More information about us, please visit: the Department of Environmental Science.

Research in the Contaminant Chemistry Unit surrounds the occurrence of pollutants in the environment. Areas of particular focus include the discovery of new contaminants, understanding the physical, chemical, and biological pathways that contaminants follow, and the development of novel tools and techniques. We strive to synthesize our scientific understanding about the sources, transport, transformation, bioaccumulation, and pharmacokinetics of environmental contaminants into mathematical models that inspire new scientific hypotheses and support environmental decision-making.

Project description

Join our research group in a project at the intersection of environmental chemistry and data science. We seek a highly motivated PhD candidate to enhance the transparency of machine learning (ML) models designed to predict the biochemical activity of emerging organic pollutants such as per- and polyfluoroalkyl substances (PFAS), by applying explainable artificial intelligence (XAI) tools. This research will contribute to a deeper understanding of the mechanisms of chemical toxicity, a critical aspect of environmental risk assessment.

The ever-growing number of chemicals in the environment poses a significant challenge in assessing their potential health risks. To address this, techniques such as high-throughput screening (HTS) for bioactivity data generation and non-targeted screening (NTS) for environmental sample analysis have grown in popularity. While these methods generate large volumes of relevant data, the complexity of the datasets makes it challenging to derive meaningful insights. To overcome this, ML has emerged as a powerful tool to link these datasets and uncover hidden patterns, enabling the prediction of biochemical activity and the prioritization of harmful chemicals for further investigation.

However, despite their predictive power, advanced ML models are often referred to as “black boxes” due to the difficulty in explaining and interpreting their decision-making process and predictions, leading to skepticism about their reliability and hindering their practical use. In this project, we aim to overcome this limitation by utilizing XAI methods. Recent advances in post-hoc interpretability techniques have shown great potential for validating and debugging ML models, offering new insights into both the models' decisions and the underlying data.

This interdisciplinary project provides the opportunity to work in a collaborative and supportive environment. The candidate will receive personalized support to acquire the necessary skills in ML, cheminformatics, and environmental chemistry. If you are passionate about applying data science to environmental challenges and eager to contribute to a better understanding of how chemicals impact ecosystems and human health, we encourage you to apply!

Qualification requirements

In order to be admitted to postgraduate education, the applicant must have the general and specific entry requirements. The qualification requirements must be met by the deadline for applications.

You meet general entry requirements if you have completed a second-cycle degree, or completed courses equivalent to at least 240 higher education credits, of which 60 credits must be in the second cycle, or have otherwise acquired equivalent knowledge in Sweden or elsewhere.

Specific entry requirements  for doctoral studies in Environmental Science, is met if at least 45 of the credits at the second cycle is in one of the natural sciences (Biology, Chemistry, Earth Sciences, Physics, or Meteorology) including a 30 credits thesis project. The applicant should also have 30 credits in other natural science subjects different from the major. 

Selection

The selection among the eligible candidates will be based on their capacity to benefit from the training. The following criteria will be used to assess this capacity:

• documented knowledge in a relevant field of research
• capacity for analytical and creative thinking
• initiative
• independence
• ability to collaborate
• written and oral proficiency in English

Short-listed candidates will be required to demonstrate their problem-solving and programming skills through a small practical exercise.

Admission Regulations for Doctoral Studies at Stockholm University.

About the employment

We offer a fixed-term employment as a doctoral student according to Chapter 5 of the Higher Education Ordinance (1993:100). The period of employment may not be longer than what corresponds to full-time doctoral education for four years. As a doctoral student, you should primarily devote yourself to your own doctoral education, but the employment may include work with education, research and administration to a limited extent (maximum 20 %).

A new employment as a doctoral student is for a maximum of one year, the employment is then renewed for a maximum of two years at a time.

Stockholm University strives to be a workplace free from discrimination and with equal opportunities for all.

Contact

For more information, please contact Assistant Professor Ida Rahu, ida.rahu@aces.su.se.

Application

Apply for the PhD student position at Stockholm University's recruitment system. Attach a personal letter and CV as well as the attachments requested in the application form. It is the responsibility of the applicant to ensure that the application is complete in accordance with the instructions in the job advertisement, and that it is submitted before the deadline.

The instructions for applicants are available at: How to apply for a position.