Students should refer to Canvas for the most up-to-date information on assignment deadlines.
Reading response deadlines and discussion questions will be posted on Canvas. Typically reading responses will be submitted as posts on Ed Discussion and are due 2 days before the class session.
Carey et al. (2020). Ten Simple Rules for Reading a Scientific Paper, PLoS Computational Biology.
Keshav (2007). How to read a paper [pdf], ACM SIGCOMM Computer Communication Review.
Rasp (2021). “If you have a hammer…”: Five questions to ask before starting a machine learning project, Blog post.
[optional] Pain (2016). How to (seriously) read a scientific paper, Science Careers.
[optional] Introduction to Machine Learning Problem Framing. Google Developers Course.
Reading response deadlines and discussion questions will be posted on Canvas. Typically reading responses will be submitted as posts on Ed Discussion and are due 2 days before the class session.
Kashinath et al. (2021). Physics-informed machine learning: Case studies for weather and climate modeling [Review paper]. Philosophical Transactions of the Royal Society A. [Reading Assignment: Sections 1 & 2 , parts of Section 3 - see Canvas, and Section 4].
Yuval, O'Gorman and Hill (2021). Use of Neural Networks for Stable, Accurate and Physically Consistent Parameterization of Subgrid Atmospheric Processes with Good Performance at Reduced Precision. Geophysical Research Letters.
Code available on GitHub.
Pathak et al. (2022). FourCastNet: A Global Data-Driven High-Resolution Weather Model using Adaptive Fourier Neural Operators. arXiv:2202.11214.
Code available on GitHub.
Blanchard et al. (2022). A Multi-Scale Deep Learning Framework for Projecting Weather Extremes. NeurIPS Workshop on Tackling Climate Change with Machine Learning.
Reading response deadlines and discussion questions will be posted on Canvas. Typically reading responses will be submitted as posts on Ed Discussion and are due 2 days before the class session.
Kuglitsch et al. (2022). AI for Disaster Risk Reduction: Opportunities, challenges and prospects. World Meteorological Organization (WMO) Bulletin.
McGovern et al. (2019). Making the Black Box More Transparent: Understanding the Physical Implications of Machine Learning. Bulletin of the American Meteorological Society.
Hilburn et al. (2021). Development and Interpretation of a Neural-Network-Based Synthetic Radar Reflectivity Estimator Using GOES-R Satellite Observations. Journal of Applied Meteorology and Climatology.
Kong et al. (2016). MyShake: A Smartphone Seismic Network for Earthquake Early Warning and Beyond. Science Advances.
Kong et al. (2019). Machine Learning Aspects of the MyShake Global Smartphone Seismic Network. Seismological Research Letters.
Nevo (2019). An Inside Look at Flood Forecasting. Google Research blog.
Nevo (2020a). The Technology Behind our Recent Improvements in Flood Forecasting. Google Research blog.
Nevo et al. (2020b). ML-based Flood Forecasting: Advances in Scale, Accuracy and Reach. AI for HADR Workshop, NeurIPS.
Moshe et al. (2020). HydroNets: Leveraging River Structure for Hydrological Modeling. AI for Physical Sciences Workshop, ICLR.
Reading response deadlines and discussion questions will be posted on Canvas. Typically reading responses will be submitted as posts on Ed Discussion and are due 2 days before the class session. A copy of all assigned papers are available on the course Google Drive [login required].
Rolnick et al. (2022). Tackling Climate Change with ML - Section 6: Farms & Forests. ACM Computing Surveys.
Finer et al. (2018). Combating deforestation: From satellite to intervention. Science.
Xie et al. (2015). Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping. AAAI.
Düben et al. (2021). Machine Learning at ECMWF: A roadmap for the next 10 years. ECMWF Technical Memoranda.
Wang et al. (2022). Unlocking Large-Scale Crop Field Delineation in Smallholder Farming Systems with Transfer Learning and Weak Supervision. Remote Sensing.
[optional - see Canvas for instructions] Wang et al. (2020). Weakly Supervised Deep Learning for Segmentation of Remote Sensing Imagery. Remote Sensing.
Code for Wang et al. (2020) available on GitHub.
Rußwurm et al. (2020). Meta-learning for few-shot land cover classification. CVPRW.
Tseng et al. (2021). Learning to predict crop type from heterogeneous sparse labels using meta-learning. CVPRW.
Norouzzadeh et al. (2020). A deep active learning system for species identification and counting in camera trap images. Methods in Ecology and Evolution.
Kellenberger et al. (2018). Detecting mammals in UAV images: Best practices to address a substantially imbalanced dataset with deep learning. Remote Sensing of the Environment.
McGovern et al. (2022). Why we need to focus on developing ethical, responsible, and trustworthy AI approached for environmental science. Environmental Data Science.
[optional] Coeckelbergh (2020). AI for climate: freedom, justice, and other ethical and political challenges. AI Ethics.
Readings to be completed by all students:
Overview of Case Study A: CUREE: Curious Robot for Ecosystem Exploration. Project website.
Overview of Case Study B: Acoustic Detection of Humpback Whales Using a Convolutional Neural Network. Google Research Blog.
Overview of Case Study C: Coral Reef Video Game Will Help Create Global Database. Eos.
Each student should complete additional reading for their assign case study (see Canvas)
Case Study A: Autonomous Underwater Vehicles for Ecosystem Exploration
Cai et al. (2023). Semi-Supervised Visual Tracking of Marine Animals using Autonomous Underwater Vehicles. International Journal of Computer Vision.
[optional] Katija et al. (2022). FathomNet: A global image database for enabling AI in the ocean. Scientific Reports.
[optional] Katija et al. (2021). Visual tracking of deepwater animals using ML-controlled robotic underwater vehicles. WACV.
Supporting materials:
Case Study B: Bioacoustics for Ecosystem Monitoring
Allen et al. (2021). A CNN for Automated Detection of Humpback Whale Song in a Diverse, Long-Term Passive Acoustic Dataset. Frontiers in Marine Science.
Denton & Wisdom (2022). Separating Birdsong in the Wild for Classification. Google Research Blog.
[optional] Zhong et al. (2021). Detecting, classifying and counting blue whale calls with Siamese neural networks. Journal of the Acoustical Society of America.
Case Study C: Crowdsourced Coral Reef Mapping
Van Den Bergh et al. (2021). NeMO-Net: Gamifying 3D Labeling of Multi-modal Reference Datasets to Support Automated Marine Habitat Mapping. Frontiers in Marine Science. (Note: you can skip the “3D Painting Background” section)
Chirayath & Li (2019). Next-Generation Optical Sensing Technologies for Exploring Ocean Worlds. Frontiers in Marine Science. (Note: focus on the "NeMO-Net" Section, you can skip the “Fluid Lensing & FluidCam” and “MiDAR” sections under “Emerging NASA Technologies and Methods”).
Supporting materials:
NASA NeMO-Net project website
Videos: Trailer + NeMO-Net Welcome + NASA ESTO FluidCam + Comprehensive Guide
Presentation Schedule & Tasks (Google sheet)
moved to Project Page