1. Lecture Materials (Slides + Notes)

• Conceptual modules on data architectures, distributed computing, and ML integration
• Case studies in smart water management, industrial process control, and environmental monitoring

2. Hands-On Labs and Notebooks

• Jupyter/Colab notebooks for each week (Python-based)
• Scenarios including ingestion pipelines, feature engineering, model building, and deployment

3. Tools & Platforms

• Programming: Python (Pandas, Dask, Scikit-learn, TensorFlow, Streamlit, MLflow)
• Data: SQL, Parquet, Delta Lake, Kafka
• Deployment: Docker, FastAPI, Colab, GitHub, AWS/GCP
• Visualization: Plotly, GeoPandas, QGIS
• Deployment: FastAPI, Docker, Streamlit
• Data Sources: EPA, USGS, Copernicus, OpenStreetMap, Kaggle datasets
• Cloud: Google Colab, AWS S3/EC2 (intro), GitHub Actions

4. Resources

• Project charter and design templates
• GitHub project starter kit
• Peer-review and self-assessment rubrics

Week	Focus Area	Example Datasets	Tools / Libraries
1	Systems Thinking	– Conceptual	Miro, Lucidchart, Draw.io
1	Data Engineering	– OpenAQ Sensor Data – EPA Real-Time Sensors	Apache Kafka, MQTT, Pandas
1	Large Data Wrangling	– USGS Water Quality  – EPA ECHO Dataset	Dask, PySpark, Pandas, Jupyter
2	Spatiotemporal Analytics	– SCADA Logs (simulated) – UCI Air Quality Dataset	Matplotlib, Seaborn, SciPy
2	MLOps & Lifecycle	– Any time-series set	MLflow, Weights & Biases, GitHub
3	Real-Time Inference	– Simulated prediction model	FastAPI, Streamlit, Docker
3	Forecasting at Scale	– NYC Water Consumption  – Electricity Load (UCI)	Prophet, LSTM (TensorFlow/PyTorch), Dask
3	Remote Sensing / GIS	– Copernicus Sentinel Data  – Landsat Imagery  – Global Surface Water	GeoPandas, Rasterio, QGIS
4	Cloud Architectures	– Any prior datasets in cloud storage	Google Colab, AWS S3/EC2, GitHub Actions
4	Capstone	– Student-selected or recombined from above	All tools above, including Git/GitHub, MLOps stack, notebooks, Docker