ArcGIS Pro contains many tools and raster functions that work with imagery and raster data. Regardless of whether your pixel-based data is an image from a satellite, an aerial sensor, a raster dataset, or a DEM, there are many ways that you can work with this data when performing analysis.
If the data you are displaying is satellite imagery, it's likely supported as a raster product within ArcGIS. Raster products have a few different templates with various band operation already performed on the fly as you roam or zoom into the image.
Using raster functions is an efficient way to process and analyze your rasters in ArcGIS. Raster functions are operations that apply processing directly to the pixels of imagery and raster datasets in the map display, as opposed to geoprocessing tools, which write a new raster output to disk. Calculations are applied to the pixels of the original data as the image is displayed, so only pixels that are visible on your screen are processed. You can apply raster function to all types of images and rasters, and the output will be a function raster layer visible in the map display and listed in the Contents pane. After achieving your desired results, you can save the layer to disk.
The Imagery tab provides access to functions that you can use to perform analysis and process your data. The Process gallery contains some commonly used functions. It is a subset of the entire suite of raster functions; these process functions are set up for quick access and analysis and allow you to recognize the difference between two selected raster layers or to mosaic multiple rasters into one. The Indices gallery contains multiple indices that you can use to analyze multiband data, such as performing a Normalized Differential Vegetation Index (NDVI) or a Normalized Burn Ratio (NBR). The Imagery tab also provides access to the Raster Functions pane, which contains hundreds of raster functions to process and analyze your imagery and raster data. You can modify these functions to control how they process your raster data.
Combine raster functions into function chains, which you can save as raster function templates using the Function Editor. Raster function templates perform multiple raster function operations on layers, mosaic datasets, and image services. You can save the results at any point in the processing chain.
Save raster function templates, share them with other users, and import them in several places across the ArcGIS platform.
Geoprocessing is the traditional way to process raster and image data where the output from the tool is saved as a file on disk. The raster-related geoprocessing tools are dispersed in various toolsets in the geoprocessing toolboxes. The majority of the raster data management tools are located in the Raster toolset in the Data Management toolbox, and in the Multidimension toolbox. The analytical tools are located in various toolboxes—Image Analyst toolbox, Raster toolset in the 3D Analyst toolbox, Geostatistical Analyst toolbox, Raster Analytics toolbox, and Spatial Analyst toolbox.
Similar to raster functions, you can combine multiple geoprocessing tools into a processing chain using ModelBuilder. Your geoprocessing model can be saved, edited, and shared.
To learn more about geoprocessing, see What is geoprocessing?
There are many ways to use raster data in analysis operations. When performing these operations, your main concern will be how the data is represented by the values of the pixels; therefore, you will be performing operations that manipulate these values. There are many tools that allow you to work with raster data for data management, conversion, transformation, and analysis. If you require additional tools to perform more specific analysis, you can use one of the following extensions:
- ArcGIS Image Analyst extension—Provides the capability for image interpretation and exploitation and allows you to do advanced raster and image analysis workflows using machine learning and feature extraction tools, functions, and capabilities.
- ArcGIS Spatial Analyst extension—Provides a comprehensive set of advanced spatial modeling and analysis tools that allow you to perform integrated raster and vector analysis.
- ArcGIS Geostatistical Analyst extension—Provides the capability for surface modeling using deterministic and geostatistical methods.
- ArcGIS 3D Analyst extension—Allows you to effectively visualize, analyze, and generate surface data and provides the tools for 3D modeling and analysis.
If you are signed in to an ArcGIS Enterprise portal that has an ArcGIS Image Server configured for Raster Analysis , you can process large raster datasets at full resolution and full extent and perform distributed raster analysis. When a tool or raster function is invoked, ArcGIS Pro serves as a client and the processing occurs on the servers federated with ArcGIS Enterprise. The portal tools are available in the Raster Analytics toolbox and the raster functions are available in the Raster Functions pane. It accepts local files and portal items from your portal as input and creates output in your portal.
If you are interested in land use or land coverage, ArcGIS Pro has many tools that classify imagery. You can choose to classify image pixels or segmented objects using parametric or machine learning classifiers. The Image Classification Wizard guides you through the steps to classify your imagery. To learn more about image classification, see Overview of image classification.
The tools and capabilities provided in the ortho mapping suite of capabilities perform photogrammetric processing of aerial, satellite, and drone imagery. These tools and capabilities allow users to produce a variety of products, such as seamless orthoimage mosaics, to support map generation and revision, change detection, and other feature extraction applications.
Multidimensional analysis tools and capabilities allow you to perform and visualize complex analysis on multidimensional raster data to explore scientific trends and anomalies. Multidimensional data represents geospatial data captured at multiple times and multiple depths or heights. These data types are commonly used in atmospheric, oceanographic, and earth sciences. You can capture multidimensional raster data by satellite observations where data is collected at certain time intervals or generated from numerical models where data is aggregated, interpolated, or simulated from other data sources.
For more information about multidimensional data, see An overview of multidimensional raster data.
Deep learning tools detect features in imagery using multiple layers in neural networks where each layer is capable of extracting one or more unique features in the image. These tools take advantage of GPU processing to perform the analysis in a timely manner.
For more information about deep learning using imagery and raster data, see Deep learning in Raster Analysis.