Below is a non-exhaustive list of resources to help environmental scientists get started with machine learning; consider reaching out by email if you think a resource is missing or outdated.
Tutorials with Code
Machine Learning Courses
- Coursera Machine Learning: Beginner courses in machine learning
- fast.ai: Online deep learning course
- DeepLearning.AI: Online deep learning course
- Stanford CS20: Tensorflow/Keras course
- Stanford CS231n: Popular course in deep learning for computer vision
- paperswithcode.com: Trending machine learning articles with code
Machine Learning for Environmental Science Courses
- Machine Learning for Climate and Energy: Beginner course designed for environmental science students
- Machine Learning for Weather and Climate: Short course designed by CIRA for atmospheric science researchers
- Explainable Artificial Intelligence for Environmental Science: Short course designed for AI2ES/CIRA researchers
- Artificial Intelligence for Earth Monitoring: Hands-on course from the Copernicus Programme for students
- (To get started before machine learning) An Introduction to Earth and Environmental Data Science: Basics of research computing in Earth science for students
- (To get started before machine learning) Pythia Foundations: A community learning resource for Python-based computing in the geosciences
Useful Libraries for Machine Learning
- Scikit-learn Tutorial: Python library for scientific machine learning
- Tensorflow Tutorial: Python library for deep learning
- PyTorch Tutorial: Python library for deep learning
- MLib Tutorial: Spark library for machine learning
Literature Reviews on Machine Learning for Environmental Science
- Beucler et al. (2021): Machine Learning for Clouds and Climate
- Reichstein et al. (2019): Deep Learning and Process Understanding for Data-Driven Earth System Science
- Bergen et al. (2019): Machine Learning for Data-Driven Discovery in Solid Earth Geoscience
- Rolnick et al. (2019): Tackling Climate Change with Machine Learning
- Willard et al. (2020): Integrating Physics-Based Modeling with Machine Learning: A Survey
- Chantry et al. (2021): Machine Learning for Weather and Climate Modelling
- Raghu and Schmidt (2020): A Survey of Deep Learning for Scientific Discovery
Textbooks and Pedagogical Articles
- Géron (2019): Hands-on Machine Learning with Scikit-Learn, Keras & Tensorflow [code1/code2/code/pdf]
- Chollet (2017): Deep Learning with Python [code/pdf]
- Molnar (2021): Interpretable Machine Learning [website]
- Goodfellow et al. (2016): Deep Learning [website]
- Foster (2019): Generative Deep Learning [website/code]
- Nielsen (2019): Neural Networks and Deep Learning [website/code]
- Parr and Howard (2018): The Matrix Calculus you Need for Deep Learning [pdf]
- James et al. (2013): An Introduction to Statistical Learning [website/pdf/code]
- Hastie et al. (2017): The Elements of Statistical Learning [website/pdf]
- Bishop (2006): Pattern Recognition and Machine Learning [pdf/code/Matlab]
Environmental Datasets for Machine Learning Research
- List of benchmark datasets (maintained by Pangeo)
- Open datasets for machine learning (maintained by Kaggle)