mcp · Global

Wildlife-Movement-Analysis-CLI

Config-driven CLI pipeline for GPS telemetry movement analysis. Computes home ranges (MCP, KDE), adaptive spatial clustering (DBSCAN/HDBSCAN), behavioural states (GMM), seasonal dynamics, and environmental interactions. Outputs publication-ready figures, tables, and GIS layers.

Visit source ↗GitHub repository ↗

Claim this listing

Represent Wildlife-Movement-Analysis-CLI? Send a claim for review so we can discuss listing updates. Claims do not automatically grant ownership or verification.

Explore paid sponsorship →

What's in it

Data offered docs-verified: home range: 100% MCP and 95% trimmed MCP per individual and per season · home range: fixed-bandwidth KDE utilisation distribution · spatial clusters: DBSCAN (knn eps) or HDBSCAN · behavioural states: GMM on log-speed and turning angle (transit, rest, tortuous) · seasonal wet/dry home range comparison with Wilcoxon test · distance to water by behavioural state and season (requires water_path) · per-individual metric summary table and population figures
Coverage llm-inferred: Global (location-agnostic; depends on the user's GPS input and chosen metric CRS)
Resolution docs-verified: Temporal: set by resample_interval_minutes (e.g. 60; 0 disables). Distances computed in a user-chosen metric_crs (e.g. EPSG:32734).
Formats docs-verified: CSV (input fixes, output tables) · YAML (config) · GeoJSON (cluster layers; optional water input) · PNG (figures) · JSON (run_metadata.json)
Access llm-inferred: Free, open source under MIT licence; runs locally (Python 3.10+, pip install -r requirements.txt); no authentication described

Useful for

Use cases llm-inferred: EIA/planning ecological baseline: seasonal home range (MCP/KDE) and range contraction for a species affected by a scheme · Water-proximity assessment: distance to water by behavioural state (fig7) to inform mitigation near abstractions or drainage features · GIS hotspot layers: clusters.geojson for habitat mapping in QGIS or ArcGIS
Audience llm-inferred: ecologists · environmental consultants · GIS analysts · planners

Limitations

Constraints llm-inferred: Docs describe a command-line pipeline (python run.py config.yaml); no MCP server interface, transport or callable tool names are documented · The ENTRY tools list contains output filenames, not callable MCP tools · Tested only on African lions, mountain caribou and African elephants · Requires Python 3.10+ and a local install; HDBSCAN is an optional extra · KDE can be slow on large datasets; reduce kde_max_pts or kde_grid_size · Water-based outputs (fig7, fig10) require a water_path input · Input columns must match config mappings exactly (case-sensitive) · Degenerate clustering (all noise, single cluster, >85% noise) needs config tuning

Licence: MIT
Authentication: Unknown — review source docs
GitHub stars: 4
Last commit: 12/04/2026
Last successful page check: 14/10/2026
Page health: healthy
Package: Not recorded
Verification: Not independently verified

Auto-extracted, unverified fields: tools, install, auth. Check upstream documentation.

Provenance & evidence

Tools/install/auth auto-extracted from README; quality score heuristic (stars, recency, tool count, licence).

Metadata observed 15/10/2026 · research sweep: github-search