species-distribution-modeling

Run end-to-end species distribution models with R and Python tools.

2|Updated Mar 2, 2026
One-click install
npx skills add https://github.com/baratadiego/ecological-agent-skills --skill species-distribution-modeling
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: species-distribution-modeling
Source: https://github.com/baratadiego/ecological-agent-skills/tree/main/skills/species-distribution-modeling
Command: npx skills add https://github.com/baratadiego/ecological-agent-skills --skill species-distribution-modeling

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires yaml, pandas, numpy, matplotlib, scikit-learn, elapid, joblib, and includes scripts (resource) components.

What problem does it solve?

The skill enables an AI agent to execute a full SDM/ENM workflow, from data preparation and predictor handling to model fitting, ensemble construction, projection, and interpretation, enabling reproducible, defensible habitat predictions.

Core Features & Use Cases

  • End-to-end SDM pipeline: occurrence cleaning, predictor selection, ensemble modeling (MaxEnt and alternative algorithms), projection under climate scenarios, and interpretation.
  • Reproducible workflows: structured steps, tuning, reporting, and traceable results suitable for ODMAP/ODMAP-style reporting.
  • Use Case: rapidly compare niche models across multiple species and generate policy-relevant maps and summaries for conservation planning.

Quick Start

Run a complete SDM for a target species using current predictors and project to future climates, then review the suitability maps and reports.

Frequently Asked Questions about species-distribution-modeling

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build an end-to-end species distribution modeling workflow with climate projections?

Yes, this species distribution modeling workflow supports model ensembles using MaxEnt and alternative algorithms, combining multiple model outputs to generate defensible habitat suitability maps.

Can I use MaxEnt and model ensembles for habitat suitability mapping across multiple species?

Yes, this species distribution modeling workflow supports model ensembles using MaxEnt and alternative algorithms, combining multiple model outputs to generate defensible habitat suitability maps for multiple species simultaneously.

Does this species distribution modeling pipeline support reproducible ODMAP-style reporting?

This species distribution modeling pipeline includes MESS and ExDet projection masking to identify extrapolation areas, ensuring climate-projected habitat suitability maps remain ecologically valid outside calibration environments.

Do I need Python and R tools like elapid and scikit-learn to run habitat suitability models?

You need Python tools like elapid, scikit-learn, pandas, and numpy to run these habitat suitability models, while the pipeline also integrates functionality comparable to R packages like biomod2 and ENMeval for algorithm tuning.

What is the best way to clean occurrence data and handle predictors for species distribution models?

The best way to clean occurrence data and handle predictors for species distribution models is using this integrated pipeline, which prepares data, tunes algorithms, and constructs ensembles before generating final projections.