-
1. Introduction to Vegetation Inventory, Assessment, and Monitoring
The purpose of this section is to explore steps in designing and conducting vegetation monitoring projects. Specific concepts and tools will complete the story in subsequent sections of this course.
-
2. Sampling Principles
This unit focuses on the principles of sampling: why we sample, the relationship between population parameters and sample statistics, accuracy and precision, types of error and their causes, and using confidence intervals to make inferences about populations. Very simply, we sample so that we can gather accurate and precise information about populations, and to make inferences about populations with confidence.
-
3. Sampling Design
This module focuses on the elements of sampling design. Sampling design encompasses all of the practical components of a sampling endeavor: where to sample, what to sample, and how to sample!
-
4. Monitoring Implementation, Data Quality, and Best Practices
Data management is fundamental to any type of data gathering activity. It is a process that includes many steps, each of which provide opportunities to introduce non-sampling errors related to human error. This module focuses on the best management practices that can be used to reduce or eliminate potential errors associated with data management.
-
5. Indicators, Methods, Descriptors, and Covariates
This section explores the distinctions between indicators and methods, introduces the concepts of site descriptors and covariates that are used to help classify and interpret monitoring data.
-
6. Density
This module focuses on plant density: what it is, how it is measured, and how density data are used by land managers to inform resource management decisions. Very simply, density is defined as the number of individuals per unit area, and reflects the closeness of individuals.
-
7. Frequency
This module focuses on plant frequency: what it is, how it is measured, and how frequency data are used by land managers to inform resource management decisions. Very simply, frequency measurements record the presence of species in quadrats or plots placed repeatedly across a stand of vegetation. Frequency reflects the probability of finding a species at any location in the vegetated area.
-
8. Cover
This module focuses on cover: what it is, how it is measured, and how cover data are used by land managers to inform resource management decisions.
-
9. Vegetation Height and Structure
This module focuses on vegetation structure: what structure represents, how it is measured, and how information about vegetation structure is used to inform resource management decisions. Very simply, vegetation structure refers to the three-dimensional arrangement of plants and plant materials on a site or across a landscape. Vegetation structure is primarily influenced by plant cover on horizontal and vertical planes.
-
10. Biomass and Production
This module focuses on plant biomass: what it is, how it is measured, and how biomass data are used by land managers to inform resource management decisions.
-
11. Utilization
This module focuses on plant utilization: what it is, how it is measured, and how utilization data are used by land managers to inform resource management decisions.
-
12. Composition, Diversity, Similarity
This module focuses on plant community diversity: how it is described, how it is measured, and how diversity is interpreted by land managers to inform management decisions.
-
13. Remote Sensing for Vegetation Monitoring and Assessment
Remote sensing techniques offer many opportunities to inform, supplement, and sometimes replace traditional field-based aproaches to vegetation assessment and monitoring. This module explores ways in which remote sensing can be used in monitoring and provides example applications.
-
14. Assessment and Monitoring Programs
This module explores some established rangeland assessment and monitoring programs, describes their protocols, and discusses how the collected data are used in management decision making.
13.3 Image Classification
Learning Guide
Image classification assigns pixels or groups of pixels in a remote-sensing image to one of a set of classes based on spectral (i.e., color), texture, or context information in the image. There are two types of classes:
- Information classes are the categories that have meaning relative to the intended application of the classification, or meaning to the end user. Examples of information classes are: rock, water, sagebrush steppe, grassland. These are the categories that we wish to identify and map from the image.
- Spectral classes are groups of pixels that have similar image values. The feature space plot below illustrates the relationship between spectral classes and information classes.
The goal of image classification is to relate the information classes (i.e., what you really want to map) to distinct spectral classes (i.e., what you can reliably discriminate in the image).

Types of Image Classification
There are many different techniques for classifying images, but they basically fall into one of two categories:
Unsupervised Classification
In unsupervised classification, an image processing program or algorithm first classifies the image into a number of spectral classes, and then meaning or interpretation is applied to those classes (i.e., the spectral classes are assigned information class names). For unsupervised classification, you must tell the classification algorithm how many classes you want and it creates that number of classes in a way that maximizes the difference between the spectral classes.

Unsupervised classification is appealing because it is a simple approach that does not require a lot of training data or assumptions. It will produce a map with the desired number of classes where each pixel is assigned to a class. However, these classes may or may not correspond well to your desired information classes. Unsupervised classification often results in too many classes, and classes need to be combined to create a meaningful map. In other cases, the classification may result in spectral classes that contain multiple information classes, necessitating further splitting of the unsupervised classes. For this reason, unsupervised classifications are generally used only for data exploration or as a preliminary step for more sophisticated classifications.
Supervised Classification
Supervised classification starts with verified locations of the information classes and the classification uses that information as “training data” to describe the spectral “signature” for each information class. The algorithm then assigns each pixel in the image to the class it most likely belongs to (i.e., the class that it most closely resembles digitally). In supervised classification, the training areas must be homogeneous, representative samples of the information classes, and selection of appropriate training areas is critical. Many of the new machine learning or artificial intelligence (AI) techniques being used in remote sensing are instances of supervised classification.

Supervised classifications can be very effective and accurate in classifying satellite images and can be applied at the individual pixel level or to groupings of adjacent pixels (i.e., image objects). However, for the process to work effectively, the person supervising the classification must have good knowledge (field data, aerial imagery, first-hand experience) of where and what the information classes are and be able to identify them in the imagery.