# eco4cast/forecast_submissions architecture

> Architecture diagram of the GitHub repository eco4cast/forecast_submissions, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-07). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/eco4cast/forecast_submissions
- Repository: https://github.com/eco4cast/forecast_submissions

## Overview

EFI Theory is a collection of ecological forecasting models for multiple NEON data streams in the EFI forecast challenge. Its documented operational workflow is that forecast models run daily; the README also describes a separate train-then-forecast approach for computationally intensive machine-learning models. The tree shows many model-family directories and a submissions-analysis area, but no source excerpts were provided, so internal calls, data transfers, and submission handoffs cannot be verified. Model groups below represent the repository’s documented capabilities and directory structure, not a confirmed execution pipeline.

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_timeseries["Time-series models"]
  node_arima["ARIMA"]
  node_ets["ETS"]
  node_tbats["TBATS"]
  node_nnetar["NNETAR"]
  node_linear["Temperature linear models"]
  node_linearall["All-site linear models"]
end

subgraph group_theory["Theory-group models"]
  node_tgmodels["Theory-group forecasts"]
end

subgraph group_ml["Machine-learning models"]
  node_svm["SVM"]
  node_xgboost["XGBoost"]
  node_lasso["Lasso"]
  node_forest["Random forest"]
  node_bagmlp["Bagged MLP"]
  node_bagtree["Bagged trees"]
end

subgraph group_analysis["Forecast analysis"]
  node_analysisfiles["Submission analysis"]
end

node_challenge(("EFI forecast challenge"))
node_streams[("NEON data streams")]
node_daily["Daily forecast models"]

node_daily -->|"run forecasts"| node_challenge
node_streams -.->|"forecast across"| node_daily

click node_arima "https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/ARIMA"
click node_ets "https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/ETS"
click node_tbats "https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/TBATS"
click node_nnetar "https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/NNETAR"
click node_linear "https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/temp_lm"
click node_linearall "https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/temp_lm_all_sites"
click node_tgmodels "https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts"
click node_svm "https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/tg_SVM"
click node_xgboost "https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/tg_XGBoost"
click node_lasso "https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/tg_lasso"
click node_forest "https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/tg_randfor"
click node_bagmlp "https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/tg_bag_mlp"
click node_bagtree "https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/tg_bag_tree_all_sites"
click node_analysisfiles "https://github.com/eco4cast/forecast_submissions/tree/main/Analyze_submissions"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_arima,node_ets,node_tbats,node_nnetar,node_linear,node_linearall toneBlue
class node_tgmodels,node_streams toneAmber
class node_svm,node_xgboost,node_lasso,node_forest,node_bagmlp,node_bagtree toneMint
class node_analysisfiles toneRose
class node_challenge,node_daily toneIndigo
```

## Components

### Time-series models

- [ARIMA](https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/ARIMA): `Generate_forecasts/ARIMA`
- [ETS](https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/ETS): `Generate_forecasts/ETS`
- [TBATS](https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/TBATS): `Generate_forecasts/TBATS`
- [NNETAR](https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/NNETAR): `Generate_forecasts/NNETAR`
- [Temperature linear models](https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/temp_lm): `Generate_forecasts/temp_lm`
- [All-site linear models](https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/temp_lm_all_sites): `Generate_forecasts/temp_lm_all_sites`

### Theory-group models

- [Theory-group forecasts](https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts): `Generate_forecasts`

### Machine-learning models

- [SVM](https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/tg_SVM): `Generate_forecasts/tg_SVM`
- [XGBoost](https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/tg_XGBoost): `Generate_forecasts/tg_XGBoost`
- [Lasso](https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/tg_lasso): `Generate_forecasts/tg_lasso`
- [Random forest](https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/tg_randfor): `Generate_forecasts/tg_randfor`
- [Bagged MLP](https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/tg_bag_mlp): `Generate_forecasts/tg_bag_mlp`
- [Bagged trees](https://github.com/eco4cast/forecast_submissions/tree/main/Generate_forecasts/tg_bag_tree_all_sites): `Generate_forecasts/tg_bag_tree_all_sites`

### Forecast analysis

- [Submission analysis](https://github.com/eco4cast/forecast_submissions/tree/main/Analyze_submissions): `Analyze_submissions`

### Other components

- **EFI forecast challenge**
- **NEON data streams**
- **Daily forecast models**

## Connections

- Daily forecast models → EFI forecast challenge: run forecasts (evidence: `README.md`)
- NEON data streams → Daily forecast models: forecast across
