Have you ever wondered how scientists map things like soil quality, air pollution, or even the spread of disease? These maps often rely on data collected at specific locations, but what about the areas in between? This is where geostatistics comes in.

Geostatistics is a branch of statistics that specifically deals with spatial data, meaning data that has a location associated with it. Unlike traditional statistics, which focus on analyzing data without considering its spatial context, geostatistics takes into account the fact that things closer together are often more similar than things farther apart. This principle, known as Tobler’s First Law of Geography, forms the foundation of geostatistical analysis.

Breaking down Geostatistics: Applications, Techniques, and Benefits

Geostatistics is a continually growing field and has evolved dramatically over time. Here are some key things to know about geostatistics:


Geostatistics was originally developed for the mining industry to predict ore grades. However, it’s now used in a wide range of fields, including environmental science, hydrology, meteorology, agriculture, and even epidemiology.


Geostatisticians use various techniques and tools to analyze and model spatial data. These techniques include:

  • Semivariograms: These graphs depict the spatial dependence of data points, helping to identify patterns and trends.
  • Kriging: This is a method for interpolating values at unsampled locations, taking into account the spatial autocorrelation of the data.
  • Geostatistical simulations: These simulations allow scientists to create realistic scenarios of how spatial phenomena might evolve over time or space.


Geostatistics provides several benefits over traditional statistical methods when dealing with spatial data. It allows for:

  • More accurate predictions and maps
  • Improved understanding of spatial patterns and relationships
  • Quantification of uncertainty associated with predictions

Contrasting Spatial Autocorrelation Analysis and Geostatistics

While both spatial autocorrelation analysis and geostatistics deal with spatial data, they have some key distinctions. Let’s delve into the differences within focus, techniques, and applications:


  1. Spatial autocorrelation analysis: Primarily focuses on identifying and quantifying the presence of spatial autocorrelation in data, which refers to the tendency of similar values to cluster together in space.  It is the foundation of inferential spatial statistics.
  2. Geostatistics: Takes spatial autocorrelation a step further by utilizing it to model and predict the values of unsampled locations, ultimately aiming to create informative maps and understand spatial processes.


  1. Spatial autocorrelation analysis: Employs a range of statistical tests, such as Moran’s I and Geary’s C, to assess the level of spatial clustering or dispersion in data.
  2. Geostatistics: Builds upon spatial autocorrelation analysis by incorporating techniques like semivariograms and kriging. These techniques not only identify the presence of spatial autocorrelation but also quantify its strength and range, allowing for more sophisticated predictions and simulations.

Users will also have to consider the similarity of Theoretical Basis. Mathematically, one can go back and forth from the semi-variogram to the correlogram. They are simply different ways of looking at self-similarity, measured either by variance or correlation, as a function of spatial lag.


  1. Spatial autocorrelation analysis: Often used as a preliminary step in spatial data analysis to explore the underlying spatial structure of the data before further investigation.
  2. Geostatistics: Offers a wider range of applications, including creating accurate spatial predictions, understanding the spatial dynamics of phenomena, and quantifying uncertainty associated with spatial predictions.

In essence, spatial autocorrelation analysis lays the foundation by identifying the presence and strength of spatial patterns, while geostatistics builds upon this foundation by utilizing these patterns to create informative maps, predictions, and simulations.

A Historical Look at Geostatistics

The field of geostatistics boasts a fascinating history, evolving from a specific need in one industry to a widely used tool across various disciplines. Here’s a glimpse into its past:

  • Early Beginnings (1950s): The roots of geostatistics can be traced back to the 1950s in the mining industry. D.G. Krige, a South African mining engineer, and H.S. Sichel, a statistician, developed a new method called kriging to estimate ore reserves more accurately. This method took into account the spatial distribution of the ore, which was a significant improvement upon traditional methods that ignored spatial patterns.
  • Formalization and Expansion (1960s-1970s): French engineer Georges Matheron is considered the father of geostatistics. He further developed and formalized Krige’s concept of kriging, coining the term itself and establishing a theoretical framework for geostatistics. During this time, geostatistics began to see applications beyond mining, venturing into fields like forestry and meteorology.
  • Rise of Computing and Wider Adoption (1980s-present): The advent of high-speed computers in the 1970s significantly accelerated the adoption of geostatistics. Complex calculations required for geostatistical modeling became feasible, leading to its wider use in various scientific disciplines. The oil and gas industry adopted geostatistics in the late 1980s, further solidifying its place as a valuable tool for understanding and managing natural resources.
  • Application in Medical Geography and Environmental Health (2000s-present):  As recognition of links between human health and environment burgeoned, geostatistics has emerged as a foundational technique in medical geography.  Here, geostatistics is used to estimate underlying disease risk, detect areas with significantly higher risk, and analyze relationships with putative risk factors.

Geostatistics Versus Geospatial Analysis

Geostatistics and geospatial analysis are often used interchangeably, and while they are related concepts, they refer to different facets of spatial data analysis.

As you’ve already learned, geostatistics is a branch of statistics that specifically deals with spatial data. It focuses on analyzing and interpreting data related to spatial features and uses intricate mathematical models and techniques to understand patterns in data.

Geospatial analysis, on the other hand, is the process of analyzing geographic information to retrieve insights, patterns, and trends. It’s a much broader field than geostatistics and can be used to address a variety of challenges in environmental science, urban planning, and public health. So while geostatistics and geospatial analysis are related concepts, they are very different in execution.

The Role of Geostatistics Today

Today, geostatistics continues to evolve with advancements in computational power and the development of new techniques. It plays a crucial role in various scientific endeavors, helping us to better understand and manage our complex world.  Some of the most advanced and state-of-the-art geostatistical techniques can be found in SpaceStat and Vesta.