Bias-corrected distribution surfaces
Point process models with sampling-effort covariates separate where species occur from where people look for them, and report prediction uncertainty by cell.
The Global Centre for Risk and Innovation (GCRI)
Biodiversity data are clustered, unevenly sampled and dependent from place to place. Spatial statistics accounts for that dependence, interpolates between sparse samples, detects hotspots and gives every map an uncertainty surface, so that gaps in sampling are not mistaken for gaps in nature.
GCRI · Established · service level R0
Spatial statistics is the set of methods that model how values vary and correlate across space. For biodiversity it corrects for clustered and uneven sampling, interpolates between sparse field measurements, detects hotspots of change and threat, and attaches an uncertainty surface so gaps in sampling are not read as gaps in nature.
The working screen behind this method: its structure, terms and states. Names are placeholders and values illustrative.
Spatial statistics and geostatistics analyse data that vary across space, accounting for spatial dependence. They estimate values at unsampled locations and test for spatial patterns. In biodiversity and nature, climate and hazards and oceans and coasts, spatial statistics produce continuous hazard and exposure surfaces with uncertainty. They reveal geographic clustering of risks and vulnerabilities across sectors. The canonical description is on the STEM Commons.
Point process models with sampling-effort covariates separate where species occur from where people look for them, and report prediction uncertainty by cell.
Local spatial autocorrelation statistics identify clusters of forest loss, species decline or overlapping threats, tested against randomised expectations.
Kriging and spatial regression estimate soil carbon, water quality or species richness between plots, with variance maps published beside the estimates.
Each term as this page uses it. Where a standard-setting body defines the term, the wording follows that body.
| Term | Definition |
|---|---|
| Sampling bias | Uneven survey effort, such as records clustered near roads, that distorts apparent species distributions. |
| Hotspot analysis | A statistical test for clusters of high or low values that are unlikely to arise by chance. |
| Uncertainty surface | A map showing how reliable an estimate is at each location. |
Mountain ranges, deserts, wetlands, glaciers and reefs, and how remote each division is from large cities, shown for the Mekong Basin as an example geography for this subject.
Data from the source register feeds the methods; calibration and an independent test gate the estimate and its limits; the decision stays with the competent authority.
Fig. 01Nodes carry their type, metrics and state; connectors show what feeds what; the gates are the validation steps; the timeline is one application. Design of the method's use, not a record of a run.
Datasets and records used by spatial statistics and geostatistics on this platform, with the role each plays and the label its values carry. Sources are listed in the source register.
| Data | Role | Label |
|---|---|---|
| Occurrence records with effort metadata | Bias correction | OBSERVED |
| Field plots and transects | Interpolation and model fitting | OBSERVED |
| Remote sensing covariates | Predictors for spatial models | OBSERVED |
| Administrative and ecosystem reporting units | Aggregation and reporting | OFFICIAL |
Predictions are tested using spatial cross-validation that respects dependence. Uncertainty maps are compared with independent observations.
| Check | How it is done |
|---|---|
| Spatial cross-validation | Test data are held out in spatial blocks so that dependence does not inflate skill |
| Residual autocorrelation | Model residuals are tested for remaining spatial structure |
| Scale sensitivity | Results are compared across grid sizes and zonings to expose the effects of aggregation |
Results depend on the scale and zoning of analysis. Sparse or clustered sampling limits prediction in unsampled areas.
Space and Earth Observation stewards spatial statistics and geostatistics for the Consortium and reviews how it is applied across platforms.
The current service level is R0: information and enquiries. An enquiry receives a reference and names the next step; applications, payments, compute allocations and registrations open only when their team, terms and review capacity exist.