Login for PhD students/staff at UCPH      Login for others
Data Science in Chemistry
Provider: Faculty of Science

Activity no.: 5782-21-10-31 
Enrollment deadline: 30/07/2021
PlaceHCØ
Universitetsparken 5, 2100 København Ø
Date and time30.08.2021, at: 08:00 - 03.09.2021, at: 16:00
Regular seats60
ECTS credits3.00
Contact personHanne Eglund    E-mail address: hannee@chem.ku.dk
Written languageEnglish
Teaching languageEnglish
Exam formActive participation during the campus course
Exam detailsExam form and criteria for assessment Pass/fail. Must attend 80% of the lectures and exercises and make a presentation during the course.
Grading scalePassed / Not passed
Course workload
Course workload categoryHours
Lectures15.00
Theory exercises15.00
Exam0.00
Preparation50.00
Sum80.00
Content
In recent years, data science has increasingly become a part of modern chemistry with the introduction of advanced statistical methods and machine learning as part of the chemist’s toolbox of analysis techniques. While this has long been true in what is traditionally known as chemometrics, it is also expanding across chemistry more generally. In this course we provide an overview of the range of methods and their application across chemistry. The course is designed to supplement the specialist machine learning and advanced statistics courses offered at other departments with a focus on the challenges in using data science to deliver physical/chemical insight, considerations when publishing in chemical journals and how this training can be used in the data science job market in Denmark.

Scientific content
Supervised and unsupervised methods including traditional as well as newer statistical methods. We will cover exploratory analysis and visualization (PCA, t-SNE, clustering) as well as linear and nonlinear regression such as neural networks. Methods for transforming data and feature selection. Concepts related to critical application of methods including: overfitting, bias, building trust in models and prediction and in explanation. Application of these techniques in materials structure analysis and single-molecule spectroscopy.

Exam form and criteria for assessment
Pass/fail. Must attend 80% of the lectures and exercises and make a presentation during the course.

Learning outcome
Knowledge of:
Machine learning and advanced statistical techniques relevant for chemistry
Issues and considerations in the choice of method for different chemical problems
The current state of the field in the application of data science in chemistry as highlighted in recent publications
The ongoing research activities relating data science to chemical problems in a range of research groups at UCPH and abroad.
Considerations related to publishing data science work in traditional chemistry journals.
The progression from a data science related PhD in Chemistry to a data science job in industry in Denmark.

Skills:
The student will be able to:
Identify a range of machine learning and advanced statistical methods as applied to chemistry problems.
Read and critically evaluated published work in chemistry journals related to data science.
Present high-level scientific content to a broad audience.

Competence:
The student will be able to critically discuss different machine learning and advanced statistics methods and issues related to their application in chemistry.

Teaching and learning methods
Lectures (hybrid – available in-person and on zoom), student presentations of published papers and ongoing research projects, and independent preparation.

Search
Click the search button to search Courses.


Course calendar
See which courses you can attend and when
JanFebMarApr
MayJunJulAug
SepOctNovDec



Publication of new courses
All planned PhD courses at the PhD School are visible in the course catalogue. Courses are published regularly.