[general]
name=QMaxent
qgisMinimumVersion=3.44
qgisMaximumVersion=3.99
description=Maxent species distribution modeling (SDM) in QGIS via the elapid Python library — full workflow from data preparation through post-prediction survey planning.
version=0.1.2
author=Byeong-Hyeok Yu
email=bhyu@knps.or.kr
about=QMaxent runs the full Maxent SDM workflow inside QGIS, integrating
    the elapid Python library so the user never has to leave the GIS.

    Modeling:
    - Auto / Manual feature types (LQPHT) with the maxnet auto-rule
    - Categorical variable support via one-hot encoding
    - Optional distance-weight bias correction (Phillips 2009)

    Data preparation:
    - Check + Harmonize raster workflow (CRS, extent, resolution)
    - One-click example datasets — Bradypus and Ariolimax

    Evaluation:
    - Cross-validation: Geographic K-Fold (default), Random K-Fold,
      Checkerboard, Buffered LOO
    - Jackknife variable importance averaged across CV folds
      (train + held-out test AUCs)
    - ROC and per-variable response curves

    Projection:
    - Cloglog / logistic / raw output transforms
    - Auto-styled habitat-suitability layer added to the project
    - Save / load (.pkl) with guided variable-mapping dialog

    Priority Sites for Survey:
    - Discovery mode: random or top-N sampling within a high-suitability
      band (auto-set to raster max × 0.9), with spacing constraints
      relative to existing presences and between candidate sites
    - Validation mode: stratified sampling across four suitability
      quartiles (Rhoden et al. 2017), with MTP / T10 / MaxSSS / Custom
      threshold methods defining the lower bound
    - OpenStreetMap Nominatim reverse geocoding (no API key)

    Results export:
    - Multi-sheet styled XLSX (Times New Roman, academic-paper
      Supplementary Table convention) covering experimental setup,
      variable inventory, cross-validation, jackknife importance,
      and Priority Sites thresholds — ready to paste into a
      manuscript supplement.

    Bilingual UI (English / Korean). Dependencies install into a
    per-plugin virtual environment that does not affect QGIS.
tracker=https://github.com/osgeokr/qmaxent/issues
repository=https://github.com/osgeokr/qmaxent
tags=species distribution model,maxent,sdm,ecology,biogeography,habitat suitability,spatial cross-validation,jackknife,priority sites,conservation,raster,vector,korean
homepage=https://osgeokr.github.io/qmaxent/
category=Analysis
icon=icons/icon.png
experimental=False
deprecated=False
hasProcessingProvider=False
changelog=0.1.2 - Projection: training-unseen categorical codes are now auto-masked to NoData rather than blocking the run; the user is still notified of which codes were masked. Categorical preflight now reads at full raster resolution so rare codes are no longer missed by downsampling. Categorical-mask notice and continuous-extrapolation warning are now combined into a single preflight dialog. Training log: removed the warning glyph from the jackknife dummy-