Registration for this program is now closed.

Please see other training programs offered by MIDAS under the “Training” tab above, and all of our events under the “Events” tab.

This program helps participants develop data science skills that can be applied to environmental science research, broadly defined as encompassing environmental, climate, earth sciences and ecology. It also helps participants develop strategies for integrating data science into their grant applications, work effectively with data scientists, and build new collaborations.

Topics

  • Review of math foundation and introduction to High-Performance Computing.
  • Basics of Machine Learning (ML).
  • Generalized Linear Model and regression.
  • Bayesian models; spatial statistics; time series analysis.
  • Examples of environmental science research projects with data science methods; Developing research ideas and selecting appropriate data and analytical methods.

Academy Details

Outcomes:

  • Certification of completion
  • Ability to work on a breadth of data science topics with data science experts as collaborators
  • Skills to abstractly consider data science solutions and apply them to environmental problems

Tuition cost:
We sent payment instructions along with acceptance decisions.

  • $3,000 for external participants (30% discount for U-M Alums)
  • Thanks to support from the University, we are able to offer a reduced price of $100 for U-M personnel and students

Cancellation Policy:
>14 days before the first day: full refund minus $50 processing fee
Cancellation between 7 and 14 days of the first day: 50% refund
Less than 7 days: no refund

Who should attend:
This academy workshop is open to all U-M and external environmental scientists, but the content is geared towards junior faculty members and those from the public and private sector who are interested in learning about incorporating data science into their research.

Prerequisites:
College-level math or statistics. No previous coding experience is required.
Students are expected to bring a laptop for programming components of the workshop.

Location:
Weiser Hall 10th floor – 500 Church St. Ann Arbor, MI 48109

Instructors

Yang Chen
Assistant Professor of Statistics

Paramveer Dhillon

Paramveer Dhillon 
Assistant Professor, School of Information

Xun Huan

Xun Huan
Assistant Professor, Mechanical Engineering

Ken Reid

Ken Reid
Data Scientist, MIDAS
Coordinator

Stilian Stoev
Professor, Department of Statistics

Guest Speakers

Arun Agrawal

Arun Agrawal
Professor,
School for Environment and Sustainability

Runzi Wang

Runzi Wang 
Assistant Professor,
School for Environment and Sustainability

Kai Zhu
Associate Professor,
School for Environment and Sustainability

Topics

  • Review of linear algebra and probability; Introduction to estimation and inference; Basic regression analysis; Considerations for experimental design; Functional data analysis; Introduction to High-Performance Computing.
  • Basics of Machine Learning (ML); Supervised ML methods; Unsupervised ML methods; Causal inference.
  • Generalized Linear Model; Generalized Estimating Equations; Multilevel regression; Nonparametric regression; Factor analysis; Dimension reduction regression.
  • Bayesian models; Computational algorithms; Spatial statistics; Time series analysis.
  • (with guest speakers) Examples of environmental science research projects with data science methods; Developing research ideas and selecting appropriate data and analytical methods (all participants are welcome to present their research ideas and receive coaching from the instructors).

Curriculum

Monday, July 31

8:30am – 9:00am

Session 1: Breakfast, Introduction

9:00am – 10:30am

Session 2: Intro, Linear Algebra and Probability Review (Xun Huan)

10:30am – 10:45am

Break

10:45am – 12:00pm

Session 3: Over of Estimation and Inference, Sampling (Xun Huan)

12:00pm – 1:00pm

Lunch Break

1:00pm – 2:30pm

Session 4: Introduction to Machine Learning: Basics (Paramveer Dhillon)

2:30pm – 2:45pm

Break

2:45pm – 4:30pm

Session 5: Introduction to Machine Learning: Supervised Machine Learning (Paramveer Dhillon)

Tuesday, Aug. 1

8:30am – 9:00am

Session 1: Breakfast, Introduction

9:00am – 10:30am

Session 2: Design of Experiments 1 (Xun Huan)

10:30am – 10:45am

Break

10:45am – 12:00pm

Session 3: Design of Experiments 2 (Xun Huan)

12:00pm – 1:00pm

Lunch Break

1:00pm – 2:30pm

Session 4: Introduction to Machine Learning: Unsupervised Machine Learning (Paramveer Dhillon)

2:30pm – 2:45pm

Break

2:45pm – 4:30pm

Session 5: Introduction to Machine Learning: Deep Learning (Paramveer Dhillon)

Wednesday, Aug. 2

8:30am – 9:00am

Session 1: Breakfast, Introduction

9:00am – 10:30am

Session 2: Bayesian toolkits for practitioners (Yang Chen)

10:30am – 10:45am

Break

10:45am – 12:00pm

Session 3: Networking Group Session – Talk about your research

12:00pm – 1:00pm

Lunch Break

1:00pm – 2:30pm

Session 4: Time series analysis – ABCs (Yang Chen)

2:30pm – 2:45pm

Break

2:45pm – 4:30pm

Session 5: Ethical AI for Environmental Scientists (Ken Reid)

Thursday, Aug. 3

8:30am – 9:00am

Session 1: Breakfast, Introduction

9:00am – 10:30am

Session 2: Geospatial Data Analysis (Stilian Stoev)

10:30am – 10:45am

Break

10:45am – 12:00pm

Session 3: Geospatial Data Analysis (Stilian Stoev)

12:00pm – 1:00pm

Lunch Break

1:00pm – 2:30pm

Session 4: Handling missing data: Do’s and Don’ts (Yang Chen)

2:30pm – 2:45pm

Break

2:45pm – 4:30pm

Session 5: Geospatial Data Analysis (Stilian Stoev)

Friday, Aug. 4

8:30am – 9:00am

Session 1: Breakfast, Introduction

9:00am – 10:30am

Session 2: Introduction and overview of Generative AIs (Ken Reid)

10:30am – 10:45am

Break

10:45am – 12:00pm

Session 3: Guest Speaker (Arun Agrawal)

12:00pm – 1:00pm

Lunch Break

1:00pm – 2:30pm

Session 4 : Region-wide Grassland community shifts driven by Climate Change (Kai Zhu)

2:30pm – 2:45pm

Break

2:45pm – 4:30pm

Session 5 : Data Science Approach Towards the Investigation of Stream Water Quality in the Socio-Environmental System (Runzi Wang)

Follow-up Sessions

Follow-up sessions were offered to help attendees develop the data science components of their grant proposals and connect with collaborators.

Contact

For questions, please contact MIDAS Data Scientist and session coordinator Ken Reid (kenreid@umich.edu).