Spatial analysis allows you to solve complex location-oriented problems, explore and understand your data from a geographic perspective, determine relationships, detect and quantify patterns, assess trends, and make predictions and decisions. Spatial analysis goes beyond mapping and allows you to study the characteristics of places and the relationships among them. Spatial analysis lends new perspectives to your decision-making.
Using spatial analysis, you can combine information from many sources and derive new information by applying a set of spatial operators. This collection of spatial analysis tools allows you to answer complex spatial questions. Statistical analysis can determine whether the patterns that you see are significant. You can analyze various layers to calculate the suitability of a place for a particular activity and, using image analysis, you can detect change over time. These tools allow you to address important questions and decisions that are beyond the scope of simple visual analysis.
You can use the analysis and geoprocessing capabilities in ArcGIS Pro to answer many spatial questions and perform spatial analysis. Spatial analysis in ArcGIS Pro is extended from 2D to 3D and through time.
A typical spatial analysis workflow involves the following:
- Frame the question you want to answer
- Find and prepare the data using data engineering to make it ready for analysis
- Explore the data on a map and with charts to better understand it
- Perform the spatial analysis, using the right tool or set of tools to answer the question
- You may want to make the analysis easy to repeat or automate using modeling and scripting
- Share your results to communicate findings or allow others to repeat the process
Using data engineering, you can explore, visualize, clean, and prepare your data. The data engineering process is a common first step for many spatial analysis and mapping workflows. The Data Engineering view and ribbon can help you better understand your data and prepare it for GIS workflows.
Visualization with charts
Visualizing data using charts can uncover data patterns, trends, relationships, and structures that may otherwise be difficult to see as raw numbers in a table. Interpret the results of your analysis and communicate the findings with charts.
Using spatial analysis capabilities in ArcGIS Pro, you can perform the following types of operations on geographic data:
- Extract and overlay data.
- Add and calculate attribute fields.
- Summarize and aggregate data.
- Calculate statistics.
- Model relationships and discover patterns.
ArcGIS Pro includes the following analysis extensions to help you answer specialized spatial questions:
- 3D Analyst—Analyze and create 3D GIS data and perform 3D surface operations using rasters, TINs, terrains, and LAS datasets (lidar).
- Business Analyst—Analyze market trends, including customer and competitor analysis, site evaluation, and territory planning.
- Geostatistical Analyst—Analyze and predict the values associated with spatial or spatiotemporal phenomena.
- Image Analyst—Interpret and exploit imagery, perform feature extraction and measurement, and perform classification and object detection using machine learning.
- Network Analyst—Measure distances and travel times along a network to find a route between multiple locations, create drive-time buffers or service areas, and find the best locations for facilities to serve a set of locations.
- Spatial Analyst—Perform interpolation, overlay, distance measurement, density, hydrology modeling, site suitability, and math and statistics on cell-based raster data.
Machine learning and artificial intelligence
Machine learning refers to a set of data-driven algorithms and techniques that automate the prediction, classification, and clustering of data. Deep learning is an important subset of machine learning techniques that uses artificial neural networks to learn from data. Machine learning and deep learning can play a critical role in spatial problem solving in a wide range of application areas, from image classification to spatial pattern detection to multivariate prediction.
In addition to traditional machine learning techniques, ArcGIS Pro has a subset of machine learning techniques that are inherently spatial. These spatial methods that incorporate some notion of geography directly into their computation can lead to deeper understanding. The spatial component often takes the form of some measure of shape, density, contiguity, spatial distribution, or proximity. Both traditional and inherently spatial machine learning can play an important role in solving spatial problems, and ArcGIS Pro supports their use in a number of ways.
Machine learning can be computationally intensive and often involves large and complex data. Advancements in data storage and both parallel and distributed computing make solving problems at the intersection of machine learning and GIS increasingly possible.
The following capabilities and tools leverage machine learning and deep learning:
- The Spatial Statistics toolbox's Mapping Clusters toolset and Modeling Spatial Relationships toolset
- The Space Time Pattern Mining toolbox's Time Series Forecasting toolset
- Feature, tabular, and text analysis tools in the GeoAI toolbox
- The Image Analyst toolbox's Multidimensional Analysis toolset and Deep Learning toolset
- The 3D Analyst toolbox's Point Cloud toolset
- Interactive deep learning-based object detection tool
Big data analytics
ArcGIS Pro has tools to transform massive spatial data into manageable information. Using parallel processing on a single machine or distributed processing using multi-node servers you can analyze and gain insights from large volumes of data that were previously too big or complex.
You can use the following capabilities and toolboxes to analyze your big data:
- The GeoAnalytics Desktop toolbox provides a parallel processing framework for analysis on a desktop machine using Apache Spark. Through aggregation, regression, detection, and clustering you can visualize, understand, and interact with your feature and tabular big data. These tools work with big datasets and allow you to gain insight into your data through patterns, trends, and anomalies.
Tools in the Intelligence toolbox's Movement Analysis toolset also utilize Spark.
- The GeoAnalytics Server toolbox provide the same capabilities as the GeoAnalytics Desktop toolbox but scale to analyze even larger datasets using ArcGIS GeoAnalytics Server to distribute the analysis between multiple server nodes.
- The Raster Analysis toolbox contains a set of tools and raster functions for performing raster analysis on imagery layers and other services in your portal. By distributing the processing between multiple server nodes, you can process large datasets in less time than processing using your desktop machine. Raster Analysis tools are powered by ArcGIS Image Server.
- You can perform visual analytics and data exploration of big data in a cloud data warehouse or other enterprise source using charts.
- Dynamically bin your big data and display on a map to aggregate and summarize the data on the fly without running pre-processing steps.
Modeling and scripting
Save time on repetitive tasks, minimize errors, and iterate on your analysis efficiently by creating models or scripts. Then turn your model or script into a custom tool. Use Python to script your workflows or build models of your workflow using ModelBuilder.
You can also add third-party libraries using the Package Manager to extend ArcGIS Pro.
Sharing and collaboration
You can share the analysis methodology as well as the data you have analyzed in ArcGIS Pro with your colleagues, organization, or community as geoprocessing packages or web tools. With these shared analysis tools, anyone can use your expertise in spatial analysis while performing the analysis themselves.