- Author: Priyanka Vyas
At a time when GeoAI, machine learning, and big data analytics remain the most popular topics in data science, ESRI maintains its commitment towards classical statistics and spatial statistics. While these sessions did not draw few hundred people as some of the sessions related to deep learning and GeoAI had, it certainly lured niche audiences working in the realm of data analysis. Day 4 of the ESRI User Conference had several sessions focused on novel approaches and tools to perform spatial and temporal analysis.
Neighborhood Explorer:
If you have done hot spot analysis in ArcGIS Pro, you may have manually hovered over a cluster and explored values at that location and at its neighboring locations. Or you may have used Select by Attribute tool to explore values at all locations within a neighborhood. Gone are the days when you must do such tasks manually. ESRI has introduced Neighborhood Explorer tool that will spit out an attribute table when you select a polygon in the cluster. Let's say you select a census tract in one of the hot spot analysis clusters. The software will show the attribute values that just includes all the features in the neighborhood of the selected census tract.
Spatial Weights with Network Data:
Traditionally, creating spatial weights had been limited to contiguity, adjacency, or distance-based methods. Now, users can include a barrier layer such as a freeway or street data. The weights matrix file that is created will account for whether these features are divided by a freeway or not. Since the type of neighborhood that is one side of the freeway can be different from the opposite side of the freeway, ESRI has created tools that can account for real world conditions.
Hot Spot Comparison:
How many times did you run hot spot analysis on one variable and were tempted to run on another variable and compare the patterns in hot spots between the two variables? ESRI has heard its user requests and developed a new tool called Hot Spot Comparison tool that allows a user to compare hot spots in two layers.
- Do hot spots of asthma overlap with hot spots of wildfire?
- Are hot spots of rent in 2020 in Los Angeles the same as hot spots of rent in 2024?
These are some of the questions that the tool allows you to answer by creating a standardized approach to compare hot spots between two different variables or between different time points of the same variable.
Time Series Forecasting:
Outside of space-time cubes which were introduced a few years ago to examine spatial and temporal data, ESRI now offers new tools from classical time series models. The cross-correlation function that is used to compare two time series and examine whether one variable leads the other or lags the other can be assessed in ArcGIS Pro.
- How does energy consumption increase as temperature increases?
- What is the relation between covid-19 reported cases and deaths?
These are some of the questions that can be answered using the time series analysis tools to understand the lag between one variable and the other.
Compare Geostatistical Layer:
This tool allows users to compare the results based on output of different kriging methods. Let's say a user ran the tool with simple kriging and then re-ran the tool with ordinary kriging then this tool provides various parameters that would allow users to identify the best method.
3D Interpolation & Nearest Neighbor 3D:
While tools for performing Inverse Distance Weighting, Kriging, and Empirical Bayesian Kriging have been existing since quite a long time, ESRI has expanded some of these tools to include 3D models. This includes Empirical Bayesian Kriging with 3D and Nearest Neighbor 3D.
Causal Inference:
While this was the last session towards the end of the conference, right before the party at Balboa Park, it still did not deter the audience from staying for the entire duration of the session. The session did an excellent job in explaining to the audience the principles of randomized control trials and causal inference, the tools in ArcGIS, and how to assess uncertainty in the model.
- Does social capital increase life expectancy after controlling for confounding variables?
- Does living in close proximity to a toxic release facility increase respiratory-illness related hospital visits after controlling for median household income?
- How does changing the amount of fertilizer increase crop yield after controlling for soil type?
These are some of the questions that researchers can now explore and visualize the results spatially.