How ezrah442/climate-feedback-prediction works
This repository is a climate-science machine-learning workflow for estimating radiative responses from atmospheric inputs and evaluating the resulting models. The main path is configuration and climate-data preparation, preprocessing and dataset assembly, model training, then inference and scientific analysis of predictions, kernels, and closure residuals. Separate evaluation scripts cover ensembles, autoencoders, clouds, legacy models, and comparison tables. The README is empty; relationships below rely on the supplied source excerpts and SOURCE INDEX, so unsampled connections are omitted or marked unverified.
Main entry points: config_utils.py Configuration · preprocessing.py Preprocessing · eval.py Model evaluation · dataloader.py Climate dataset
Components 23
Data preparation
- Data requests
data_requests.py - Preprocessing
preprocessing.py - ECOD calculation
ecod_calculation.py - Preprocess runner
preprocess.py - Climate dataset
dataloader.py
Model learning
- Neural model
model.py - Training runner
train.py
Scientific evaluation
- Model evaluation
eval.py - Ensemble evaluation
eval_ensemble.py - Closure analysis
eval_closure.py - Ensemble closure
eval_closure_ensemble.py - Model comparisons
make_comparison_tables.py
Specialized analyses
- Autoencoder evaluation
eval_autoencoder.py - Interactive autoencoder
eval_autoencoder_interactive.py - Cloud evaluation
eval_cloud.py - Legacy model evaluation
eval_old_model.py - Legacy closure
eval_closure_old_model.py - Shakirova analysis
eval_shakirova.py
Shared runtime
- Configuration
config_utils.py - Climate utilities
utils.py - Map utilities
utils_cartopy.py
Other components
- Researcher
- Climate data
Connections 38
- Researcher → Preprocess runner: runs preparation
- Researcher → Training runner: trains model
- Researcher → Model evaluation: runs evaluation
- Climate data → Climate dataset: loads climate inputs
- Preprocess runner → Preprocessing: uses preprocessing
preprocess.py - Preprocess runner → Configuration: loads settings
preprocess.py - Preprocessing → Configuration: builds from settings
preprocessing.py - Preprocessing → ECOD calculation: calculates ECOD
preprocessing.py - Climate dataset → Configuration: loads settings
dataloader.py - Climate dataset → Preprocessing: transforms inputs
dataloader.py - Climate dataset → Climate utilities: uses data helpers
dataloader.py - Training runner → Configuration: loads settings
train.py - Training runner → Climate dataset: loads batches
train.py - Training runner → Neural model: trains model
train.py - Climate utilities → Configuration: uses variable config
utils.py - Climate utilities → Preprocessing: uses transforms
utils.py - Climate utilities → Neural model: loads model
utils.py - Model evaluation → Configuration: loads settings
eval.py - Model evaluation → Preprocessing: transforms inputs
eval.py - Model evaluation → Neural model: runs predictions
eval.py - Model evaluation → Map utilities: plots maps
eval.py - Ensemble evaluation → Configuration: loads settings
eval_ensemble.py - Ensemble evaluation → Preprocessing: transforms inputs
eval_ensemble.py - Ensemble evaluation → Neural model: runs ensemble
eval_ensemble.py - Closure analysis → Configuration: loads settings
eval_closure.py - Closure analysis → Map utilities: plots maps
eval_closure.py - Ensemble closure → Configuration: loads settings
eval_closure_ensemble.py - Model comparisons → Configuration: reads settings
make_comparison_tables.py - Model comparisons → Model evaluation: uses evaluation results
make_comparison_tables.py - Model comparisons → Preprocess runner: uses preprocessing results
make_comparison_tables.py - Autoencoder evaluation → Configuration: loads settings
eval_autoencoder.py - Interactive autoencoder → Autoencoder evaluation: uses evaluation
eval_autoencoder_interactive.py - Cloud evaluation → Configuration: loads settings
eval_cloud.py - Legacy closure → Legacy model evaluation: uses legacy evaluation
eval_closure_old_model.py - Legacy closure → Closure analysis: uses closure analysis
eval_closure_old_model.py - Legacy model evaluation → Climate utilities: uses climate helpers
eval_old_model.py - Shakirova analysis → Configuration: loads settings
eval_shakirova.py - Shakirova analysis → Map utilities: plots maps
eval_shakirova.py