{"name": "QMaxent", "package_name": "qmaxent", "description": "Maxent species distribution modeling (SDM) in QGIS via the elapid Python library \u2014 full workflow from data preparation through post-prediction survey planning.", "about": "QMaxent runs the full Maxent SDM workflow inside QGIS, integrating\nthe elapid Python library so the user never has to leave the GIS.\nThe Main Analysis Dock guides the user through five sequential tabs:\n\n\u2460 Data:\n- Presence layer + environmental raster selection\n- Check Raster Consistency + Harmonize to Folder workflow\n(CRS, extent, resolution alignment)\n- One-click example datasets (Bradypus, Ariolimax) with\nPre-harmonized and Mismatch demo variants\n- Export for external Maxent: Samples + Raster (samples CSV\n+ .asc layers, single-command maxent.jar fit with projection\nraster) OR SWD (CSV pair, extracted values), each with a\ngeneric maxent.jar command-line README\n\n\u2461 Parameters:\n- Feature types (LQPHT) \u2014 Auto (Phillips et al. 2017 sample-size\nrule) or Manual\n- Beta multiplier\n- Categorical variable support via one-hot encoding\n- Optional distance-weight bias correction (Phillips 2009)\n- Cross-validation: Geographic K-Fold (default), Random K-Fold,\nCheckerboard, Buffered LOO, or None (training AUC only)\n- Jackknife variable importance\n- Permutation importance (sklearn permutation_importance,\nconfigurable repeats; normalized as % of total to match\nmaxent.jar's convention)\n- Fixed random seed (default 42) for reproducibility\n\n\u2462 Training:\n- Live training log with deterministic progress bar\n- Clear log / Copy log / Save log as\u2026 buttons for manual export\n- training_log.txt auto-saved next to model.pkl at the end of\nRun Maxent\n\n\u2463 Results \u2014 four sub-tabs:\n- Response Curves: per-variable marginal-effect plots\n- Jackknife Importance: per-variable train + held-out test AUC\nbars\n- Permutation Importance: AUC-drop bars (% of total), with\nSave PNG / Save CSV buttons for individual export\n- Spatial Projection: cloglog / logistic / raw output transforms;\nauto-styled habitat-suitability layer; save / load (.pkl) with\nguided variable-mapping dialog; optional auto-save of all four\nanalysis charts (response curves, ROC, jackknife, permutation)\nas PNG alongside the prediction raster\n\n\u2464 Priority Sites for Survey:\n- Discovery mode: random or top-N sampling within a high-\nsuitability band (auto-set to raster max \u00d7 0.9), with spacing\nconstraints relative to existing presences and between\ncandidate sites\n- Validation mode: stratified sampling across four suitability\nquartiles (Rhoden et al. 2017), with MTP / T10 / MaxSSS /\nCustom threshold methods defining the lower bound\n- OpenStreetMap Nominatim reverse geocoding (no API key)\n\nAuxiliary dialogs (outside the main flow):\n- Dependency Installer \u2014 first-run isolated-venv setup\n- Example Dataset Downloader \u2014 one-click example datasets\n\nResults export: multi-sheet styled XLSX (Times New Roman,\nacademic-paper Supplementary Table convention) covering\nexperimental setup, variable inventory, cross-validation,\njackknife importance, permutation importance, and Priority Sites\nthresholds \u2014 ready to paste into a manuscript supplement.\n\nBilingual UI (English / Korean). Dependencies install into a\nplugin-private virtual environment that does not affect QGIS\n(~590 MB on disk).", "homepage": "https://osgeokr.github.io/qmaxent/", "repository": "https://github.com/osgeokr/qmaxent", "tracker": "https://github.com/osgeokr/qmaxent/issues", "author": "Byeong-Hyeok Yu", "tags": ["vector", "ecology", "raster", "sdm", "species distribution model", "maxent", "conservation", "jackknife", "spatial cross-validation", "korean", "habitat suitability", "priority sites", "biogeography"], "downloads": 241, "latest_version": "0.1.7", "versions": [{"version": "0.1.7", "experimental": false, "qgis_min": "3.44.0", "qgis_max": "3.99.0", "downloads": 186, "uploaded_by": "bhyu", "upload_datetime": "2026-05-16T21:27:56.602747"}, {"version": "0.1.2", "experimental": false, "qgis_min": "3.44.0", "qgis_max": "3.99.0", "downloads": 55, "uploaded_by": "bhyu", "upload_datetime": "2026-05-11T22:47:46.652512"}]}