Workflow Narrative

Time-Series Change Analysis

Problem It Solves

Where and when are structural shifts emerging in the time series, and how confident are those signals?

Who It Is For

Time-series monitoring teams and geospatial data science groups.

Primary User

Regional planning programs, policy/compliance analytics groups, and EO product teams.

What It Does

Performs multi-date trend and breakpoint analysis from temporal stacks.
Supports mode-dependent decomposition/segmentation behavior.
Emits confidence-scored temporal change surfaces.

How It Works

Traverses each pixel time series and estimates trend response over the observation window.
Uses algorithm_mode-specific breakpoint logic to detect structural shifts.
Converts fit strength, breakpoint support, and observation sufficiency into confidence output.
Indicative formula: confidence ~= f(|trend|, breakpoint_support, n_observations), bounded to [0, 1].

Why It Wins

Provides mode flexibility (fast/iterative/bfast) so users can balance throughput and analytical depth.

Typical Buying Trigger

A monitoring program moves from two-date snapshots to sustained time-series surveillance.

Typical Presets

fast: throughput-oriented screening.
iterative: stronger breakpoint refinement.
bfast: decomposition-oriented analysis.

Inputs

Parameter	Optional	Description
input_stack (required)	no	Primary temporal raster stack used for trend and breakpoint analysis.
optional qa_stack	yes	Optional temporal QA stack used to weight or suppress low-quality observations.
algorithm_mode and thresholding controls	no	Time-series change algorithm mode and threshold controls.

Outputs

Parameter	Type	Description
trend_change	GeoTIFF	Primary change-intelligence raster showing direction and magnitude of detected change.
breakpoint_count	GeoTIFF	Per-pixel count of detected temporal breakpoints.
breakpoint_date	GeoTIFF	Estimated timing raster for dominant detected breakpoint events.
change_confidence	GeoTIFF	Confidence surface for the time-series change detection result.
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")

result = wbe.time_series_change_intelligence(
    input_stack="data/time_stack.tif",
    qa_stack="data/time_stack_qa.tif",
    algorithm_mode="bfast",
    output_prefix="output/ts_change",
)

print(result)

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