Landscape soils and surface environments - Week 3 Workshop 2a
2026-03-04
Recap from previous sessions:
Today’s question: WHAT do we DO with the data?
Two fundamental goals:
Tip
Choice depends on research, ecological, or management question…and data availability!
When the objective is to compare, assess differences, estimate totals.
Methods used:
Classical statistics
Example 1: How much C stock do forest hold compared to woodlands?
Doesn’t tell you WHERE C is high/low.
Example 2: Estimate total aboveground biomass in catchment
Doesn’t tell you WHERE biomass is high/low.
When the objective is to quantify spatial variability, predict values at unsampled locations, or create maps.
E.g. How does soil pH vary across the SCP? Where are the acidic soils?
Methods: Spatial modelling
Geostatistics (e.g. kriging):
Uses spatial autocorrelation
Digital or Predictive Mapping:
Uses environmental relationships
Data needed:
Method:
Note
Uses a semivariogram (model of spatial variation), and gives estimates of uncertainty.
“Everything is related…but near things are more related than distant things.”
W. Tobler (1970)
Why?
Dissimilarity increases with distance ➡️ spatial dependence (autocorrelation)
We can use spatial relationships to predict!
Tells you how much a measured quantity changes as you move farther away:
Note
A semivariogram measures how spatial similarity decreases with distance.
A semivariogram shows how the variance of a mesured quantity changes with distance.
To calculate it, we:
Group pairs by separation distance (lag)
Compare all pairs of sample points
Calculate variance between each pair
Average variance for each lag distance to get semivariance
\[ \hat{\gamma}(h) = \frac{1}{2N(h)} \sum_{i=1}^{N(h)} \big[ Z(x_i) - Z(x_i + h) \big]^2 \]
where \(\hat{\gamma}(h)\) is the semivariance at lag distance \(h\), \(Z(x_i)\) and \(Z(x_i + h)\) are values at locations separated by \(h\), and \(N(h)\) is the number of such pairs.
You are not expected to memorise this formula, but to understand it conceptually
Important
Shows how pairs at distance \(h\) differ: small values → similar, large values → different.
Note
The semivariogram model (dash line) provides the parameters for kriging
We fit a variogram model through the points.
Spherical: rises then clearly flattens at the sill
Exponential: rises then gradually reaches the sill
Gaussian: very smooth near the origin.
Different shapes describe different spatial continuity.
Note
Choice of model depends on the shape of the data and the underlying spatial processes.
Note
Nugget depicts data quality. Large nugget → need better sampling or measurement.
Note
Sill shows property variation across the landscape. At sill spatial autocorrelation ends
Important
Sample at appropriate distance (range) to capture variation
Depending on the shape of the semivariogram, different models can be fitted (Exponential, Gaussian, linear, etc.).
Here is an example of the fitting process for spherical model:
Kriging is a spatial interpolation method — it makes a map from point samples. It:
Predicts values at unsampled locations as a weighted average of nearby samples
Uses the variogram to decide the weights: closer samples get more weight, farther samples get less weight, and the weights also depend on the nugget, sill, range
Tells you how confident the prediction is at every location (kriging variance)
Derive and fit semivariogram to quantify spatial variability and autocorrelation structure
For each prediction location:
Objective: Learn about semivariograms and kriging.
Link to activity Or copy and paste this URL into your browser:
https://ravr19.github.io/lsse_teaching/kriging_app.html
Follow instructions in the app to:
1. Use the app to simulate spatial data, fit variogram models, and see how they affect kriging predictions.
2. Changing one setting at a time to see its impact on the variogram and the kriging prediction and variance.
3. Answer questions to test your understanding.
1. Two approaches for different questions:
2. Tobler’s Law: Near things are more related → spatial autocorrelation
3. Semivariogram parameters:
4. Kriging uses the semivariogram to map point data with uncertainty
5. Grid spacing ≤ half the range to capture spatial structure