Question about Emerging hot Spot Analysis results

Question

Hi @LynneBuie @LaurenGriffin and folks from Esri Spatial Statistics Team,

I am using the Emerging hot Spot Analysis tool to analyze time-series of raster imagery data and have the following questions about the results from this tool:

1) There are several variables in the Emerging hot Spot Analysis result (Output Features) as shown in the screenshot below. However, neither the tool documentation nor online resources give specific explanations for them. I am particularly confused about the variable TREND_BIN (trend bin). Is it the same one as the EMERGING_{ANALYSIS_VARIABLE}_TREND_BIN variable or the {ANALYSIS_VARIABLE}_TREND_BIN variable that are added back to the Input Space Time Cube as described in this page: https://pro.arcgis.com/en/pro-app/latest/tool-reference/space-time-pattern-mining/emerginghotspots.htm?

I don’t fully understand what this variable EMERGING_{ANALYSIS_VARIABLE}_TREND_BIN measures. Based on the documentation, “The result category used to classify each location as having a statistically significant upward or downward trend for hot/cold spot z-scores.” Are the z-scores from the Getis-Ord Gi* statistic? For statistically significant positive Gi* statistic z-scores, the larger the z-score is, the more intense the clustering of high values (hot spot). For statistically significant negative z-scores, the smaller the z-score is, the more intense the clustering of low values (cold spot). So, what does the upward or downward trend for those z-scores imply? How does it help to understand the trends in spatial clustering in the data?

2) I would like to visualize the variable EMERGING_{ANALYSIS_VARIABLE}_HS_BIN, which is added back to the Input Space Time Cube. I tried to use Visualize Space time Cube in 2D, but none of the Display Theme offers displaying this variable. I also tired to use Add Multidimensional Layer to load the Space time cube and select this variable in the Select Variables table as described in this page (https://pro.arcgis.com/en/pro-app/2.6/help/data/imagery/working-with-a-multidimensional-raster-layer.htm) however, it didn’t allow me to apply the Unique Values Symbology to this variable.

Does anyone have any ideas or suggestions? Thank you very much!

Vanilla2020 · Answer

That is helpful. Thank you very much for your time and help!

LaurenGriffin · Answer

Hi again,

The EMERGING_{ANALYSIS_VARIABLE}_HS_BIN variable is one of 7 values for each bin in the Space Time Cube and can be visualized in 3D:

3: Statistically significant clustering of high/large values at the 0.01 level

2: Statistically significant clustering of high/large values at the 0.05 level

1: Statistically significant clustering of high/large values at the 0.10 level

0: no statistically significant clustering

-1: Statistically significant clustering of low/small values at the 0.10 level

-2: Statistically significant clustering of low/small values at the 0.05 level

-3: Statistically significant clustering of low/small values at the 0.01 level

That variable does not include the Mann-Kendal trend information. The 2D output layer from Emerging Hot Spot Analysis (EHSA) shows the patterns and encapsulates the hot spot and trend information.

To me, it is difficult to draw conclusions from 3D maps (unless your data set is very small). The 2D maps (like the default output from the EHSA tool) seem more useful, but it really very much depends on the questions you're hoping to answer with your analysis.

If you haven't seen it already, consider watching this video, (at about 5:41 I give some examples of interpreting the EHSA results). The entire learning path might be interesting to you, though (my colleague Kevin provides some great examples of Time Series Clustering and Forecasting).

Best wishes!

Lauren Griffin, Esri

Vanilla2020 · Answer

Thanks Lauren, I think now I understand how Gi* and Mann-Kendal together to classify each bin as one of the 17 categories. So if I want to create maps based on the emerging hotspot analysis results, which variables you would recommend being used? I feel that the most important one is the variable PATTERN which indicates the 17 categories. So for the variable EMERGING_{ANALYSIS_VARIABLE}_HS_BIN, what kind of inference I can make out of it? (since it just tells the up/down trend for the Gi* z scores but not directly about any intensifying or diminishing of hot/cold spots)

Thanks very much again!