This workshop covers traditional and spatial Machine Learning tools currently in ArcGIS. These data-driven algorithms and techniques are used for prediction, classification, and clustering of data with applications in image classification, spatial pattern detection, multivariate prediction and more.
Data visualization techniques within ArcGIS can help you explore your data, interpret the results of analysis, and communicate findings. Using maps, charts and 3D scenes can help you compare categories and amounts, visualize distributions and frequency, explore relationships and correlations, and understand change over time or distance. | 2019 UC Slides
From simple methods for summarizing and describing spatial patterns to advanced machine learning clustering techniques, this workshop will introduce you to the power of spatial statistics and equip you with the knowledge necessary to get started exploring your data in new and useful ways. Concepts covered include describing the shape and spatial distribution of your data; comparing datasets in meaningful defensible ways; identifying spatial clusters; and mining for multivariate patterns. | 2019 UC Slides
Measuring and quantifying the patterns that we see is crucial for informed decision making. This workshop will explore the powerful spatial statistics techniques designed to quantify spatial and spatiotemporal patterns. Concepts covered include aggregating data spatially and temporally; identifying clusters and outliers in both space and in time; and best practices for interpreting and sharing your results. | Slides | 2019 UC Slides
Space and time are inseparable, and integrating the temporal aspect of your data into your spatial analysis leads to powerful discoveries. This workshop will build on the cluster analysis methods discussed in Spatial Data Mining I by presenting advanced techniques for analyzing your data in the context of both space and time. | Slides | 2019 UC Slides
This workshop covers techniques for modeling our spatial data to uncover relationships and predict spatial outcomes. Concepts covered include linear regression techniques (Ordinary Least Squares, and Geographically Weighted Regression) and explain different model types; and the new tool for detecting relationships between two variables, Local Bivariate Relationships.| 2019 UC Slides
Python and R provide a wide array of powerful modules that can expand the data science capabilities of ArcGIS. This session outlines integration techniques that allow you to call open source statistical packages to quantify patterns and relationships in your data.
This workshop will cover the basics of how the widely-used machine learning approach, random forest, can be used to solve complex spatial problems and make effective predictions. Learn how the Forest-based Classification and Regression tool brings together both vector and raster data in powerful ways and learn how to evaluate your model using a number of validation techniques and diagnostics. | 2019 UC Slides