PROProduction

Detect spectral change between baseline and change-date multispectral bundles with profile-based sensitivity.

workflow pro

Workflow Narrative

Remote Sensing Change Detection

Problem It Solves

Where is meaningful vegetation change occurring, and which detections are reliable enough for reporting?

Who It Is For

Environmental monitoring analysts and EO operations teams.

Primary User

Environmental consultancies, forestry/conservation agencies, and compliance programs.

What It Does

Detects vegetation loss/gain between two dates using NDVI-style change logic.
Uses bundle-native multiband inputs with explicit red/NIR band indices.
Produces a signed change raster and a confidence raster for analyst triage.

How It Works

Computes NDVI-like indices per date from selected red and NIR bands.
Calculates signed per-pixel delta between change-date and baseline NDVI-like response.
Applies profile-dependent thresholds and local consistency checks to derive confidence.
Indicative formula: NDVI = (NIR - Red) / (NIR + Red), then change = NDVI_change - NDVI_baseline.

Why It Wins

Bundle-native inputs reduce parameter mismatch errors and make cross-date processing more reproducible.

Typical Buying Trigger

A client or regulator requires repeatable, confidence-scored vegetation change evidence for periodic reporting.

Typical Presets

aggressive: lower change threshold, more sensitive detection.
balanced: default tradeoff for general monitoring.
conservative: stricter thresholds, fewer false positives.

Inputs

Parameter	Optional	Description
baseline_bundle, baseline_red_band_index, baseline_nir_band_index	no	Baseline multispectral bundle and red/NIR band selectors used to compute baseline vegetation response.
change_bundle, change_red_band_index, change_nir_band_index	no	Change-date multispectral bundle and red/NIR band selectors used for signed change estimation.
optional intermediate_ndvi	yes	Intermediate-date NDVI raster used to strengthen temporal plausibility scoring.
profile: aggressive \| balanced \| conservative	yes	Processing profile controlling sensitivity, quality strictness, and runtime tradeoffs.
high_confidence_threshold	yes	Confidence threshold used for summary metrics (default `0.85`).

Outputs

Parameter	Type	Description
change_map	GeoTIFF	Primary change-intelligence raster showing direction and magnitude of detected change.
confidence	GeoTIFF	Confidence layer quantifying reliability of modeled outputs.
summary	JSON	Machine-readable summary report containing run metadata, QA diagnostics, and key metrics.
html_report	HTML	Human-readable customer-facing report generated from the summary contract for stakeholder review and QA traceability.

Python Example

import whitebox_workflows as wbw

wbe = wbw.WbEnvironment(include_pro=True, tier="pro")

change_map, confidence, summary = wbe.remote_sensing_change_detection(
    baseline_bundle="data/baseline_bundle.tif",
    baseline_red_band_index=0,
    baseline_nir_band_index=1,
    change_bundle="data/change_bundle.tif",
    change_red_band_index=0,
    change_nir_band_index=1,
    profile="balanced",
    output="output/rs_change",
)

print(change_map)
print(confidence)
print(summary)

License Notice

Use of this function requires a license for Whitebox Workflows Professional (WbW-Pro). Please visit www.whiteboxgeo.com to purchase a license.

Project Links

WbW Homepage User Manual Learn More