home / skills / benchflow-ai / skillsbench / meteorology-driver-classification

meteorology-driver-classification skill

/tasks/lake-warming-attribution/environment/skills/meteorology-driver-classification

This skill classifies environmental variables into driver categories for attribution analysis to simplify impact assessment.

npx playbooks add skill benchflow-ai/skillsbench --skill meteorology-driver-classification

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

1.9 KB

---
name: meteorology-driver-classification
description: Classify environmental and meteorological variables into driver categories for attribution analysis. Use when you need to group multiple variables into meaningful factor categories.
license: MIT
---

# Driver Classification Guide

## Overview

When analyzing what drives changes in an environmental system, it is useful to group individual variables into broader categories based on their physical meaning.

## Common Driver Categories

### Heat
Variables related to thermal energy and radiation:
- Air temperature
- Shortwave radiation
- Longwave radiation
- Net radiation (shortwave + longwave)
- Surface temperature
- Humidity
- Cloud cover

### Flow
Variables related to water movement:
- Precipitation
- Inflow
- Outflow
- Streamflow
- Evaporation
- Runoff
- Groundwater flux

### Wind
Variables related to atmospheric circulation:
- Wind speed
- Wind direction
- Gust speed
- Atmospheric pressure

### Human
Variables related to anthropogenic activities:
- Developed area
- Agriculture area
- Impervious surface
- Population density
- Industrial output
- Land use change rate

## Derived Variables

Sometimes raw variables need to be combined before analysis:
```python
# Combine radiation components into net radiation
df['NetRadiation'] = df['Longwave'] + df['Shortwave']
```

## Grouping Strategy

1. Identify all available variables in your dataset
2. Assign each variable to a category based on physical meaning
3. Create derived variables if needed
4. Variables in the same category should be correlated

## Validation

After statistical grouping, verify that:
- Variables load on expected components
- Groupings make physical sense
- Categories are mutually exclusive

## Best Practices

- Use domain knowledge to define categories
- Combine related sub-variables before analysis
- Keep number of categories manageable (3-5 typically)
- Document your classification decisions

Overview

This skill classifies environmental and meteorological variables into coherent driver categories to support attribution and factor analysis. It helps you translate raw observations into meaningful groups like Heat, Flow, Wind, and Human so analyses reflect physical processes. Use it to standardize inputs before statistical grouping or multivariate modeling.

How this skill works

The skill inspects your dataset, maps each variable to a driver category based on physical meaning, and suggests derived variables when components should be combined (for example, net radiation = shortwave + longwave). It flags variables that do not fit expected categories and encourages validation steps such as checking component loadings or correlation structure. The output is a categorized variable list ready for downstream attribution analysis.

When to use it

Preparing inputs for attribution or multivariate decomposition
Grouping many raw sensor or model variables into interpretable factors
Creating derived variables that aggregate related components (e.g., net radiation)
Validating that statistical groupings align with physical expectations
Standardizing datasets from different sources for comparative analysis

Best practices

Start with domain knowledge to assign categories before automatic grouping
Combine sub-components into physically meaningful derived variables first
Keep the number of categories manageable (typically 3–5) for clarity
Ensure categories are mutually exclusive and document any judgment calls
After statistical grouping, verify variables load on expected components

Example use cases

Converting meteorological station outputs into Heat, Flow, Wind drivers for trend attribution
Merging radiation channels into a single net radiation variable for energy balance studies
Grouping hydrological observations (precipitation, runoff, groundwater flux) for watershed analysis
Separating anthropogenic metrics (land use, population density) from natural drivers in impact studies
Preparing a consistent driver matrix for causal modeling or machine learning feature sets

FAQ

How do I handle variables that seem to belong to more than one category?

Prefer physical meaning and primary mechanism; if truly mixed, create a derived or hybrid variable and document the rationale.

What if statistical grouping disagrees with my initial classification?

Revisit variable definitions and derived combinations, check for measurement issues, and prefer physically interpretable groupings even if statistical loadings require adjustment.