How theeliad/geospatial-watches-and-warnings-app works
This is a Streamlit coastal flood-risk application. Users select a NOAA station, load historical water levels, train a station-specific LSTM, then request a live forecast combining the model’s next-hour estimate with NWS precipitation and station flood thresholds. The graph separates station discovery, historical-data handling, model training, and forecast/risk evaluation. Source excerpts show the central calls and storage behavior; the README documents the three-step workflow. Some UI and integration details are described in the README but are not fully visible in the sampled source.
Main entry points: main.py Streamlit Workflow · predictor.py Live Predictor · data_loader.py Historical Loader · model_trainer.py LSTM Trainer
Components 14
Station Discovery
- Streamlit Workflow
main.py - Station Metadata
stations_df_func.py - Station Registry CSV
all_noaa_coops_stations_with_states.csv
Historical Data
- Historical Loader
data_loader.py - NOAA Water Fetcher
data_fetcher.py - Historical CSV Cache
Model Training
- LSTM Trainer
model_trainer.py - Model and Scaler Files
Forecast and Risk
- Live Predictor
predictor.py - Flood Thresholds and Classification
data_fetcher.py - Precipitation Forecast
nws_fetcher.py
Other components
- User
- NOAA CO-OPS API
- National Weather Service API
Connections 16
- User → Streamlit Workflow: selects and requests
README.md - Streamlit Workflow → Station Metadata: loads stations
main.py - Station Metadata → Station Registry CSV: reads
stations_df_func.py - Streamlit Workflow → Historical Loader: loads history
README.md - Historical Loader → NOAA Water Fetcher: requests water levels
data_loader.py - NOAA Water Fetcher → NOAA CO-OPS API: fetches observations
data_fetcher.py - Historical Loader → Historical CSV Cache: writes history
data_loader.py - Streamlit Workflow → LSTM Trainer: starts training
README.md - LSTM Trainer → Historical CSV Cache: reads training data
model_trainer.py - LSTM Trainer → Model and Scaler Files: saves model and scaler
model_trainer.py - Streamlit Workflow → Live Predictor: requests forecast
main.py - Live Predictor → Historical Loader: loads recent cache
predictor.py - Live Predictor → Model and Scaler Files: loads model and scaler
predictor.py - Live Predictor → Precipitation Forecast: fetches precipitation
predictor.py - Precipitation Forecast → National Weather Service API: requests forecast data
nws_fetcher.py - Live Predictor → Flood Thresholds and Classification: classifies predicted level
predictor.py