Tentative schedule of our training is shown in the table below and is subject to change.
| Module | Topic | Goal |
|---|---|---|
| 1 | Introduction of Data Science | Basic concepts of data science |
| 2 | Basics of machine and deep learning | Main types of machine learning, and uncertainties in data and AI models |
| 3 | Basics of earth-atmosphere radiative energy balance | Introduction of radiative energy balance of the earth-atmosphere system, and its implications to the circulation system | 4 | Basics of radiative transfer simulation framework | Principles that control the transport of radiation in the Earth’s atmosphere | 5 | Remote sensing | Remote sensing theory in optical and infrared spectral ranges | 6 | Reproducible deep learning | Techniques for building fully reproducible machine learning workflows | 7 | Scalable deep learning | Scalable deep learning for large models and datasets | 8 | Leveraging national research CI for scalability & reproducibility | Able to access national research cyberinfrastructure | 9 | Physics-guided machine learning | Approaches for physics-guided machine learning | 10 | Project introduction and assignment | Project explanation from each team, including Q&A | 11-14 | Project progress report from each team and feedback from instructors | Report from each team including Q&A + rating | 15 | Final project presentation | Report, software, and final presentation from each team |