Lab 4: Ground Truthing and Accuracy Assessment

Ground Truthing and Accuracy Assessment

This week I conducted a ground truthing and accuracy assessment of land use/land cover map I produced last week in lab 3. I created a point feature class to capture 30 samples in a stratified random pattern. Then I verified the accuracy of the assigned land use/land classification at each point using Google Street View. Those points that were accurate are marked with a green dot, and those points that were not accurate are marked with a red dot. The overall accuracy was calculated by dividing the total number of correct samples by the total number of samples.

Lab 3: Land Use/Land Cover Classification Mapping

Land Use/Land Cover Classification

This is a land use/land cover classification map classified to level 2 of 4 of the USGS Standard Land Use/Land Cover Classification System. This map was created by systematically digitizing all areas of an aerial photograph according its land cover and land use. The only resource for the classification was the photograph itself.

Project 1: Analyze Week

OLS Results

This is a screen shot of the Ordinary Least Squares (OLS) results window after performing what Esri calls "The Six Checks". The checks are necessary to determine which explanatory/independent variables are unneeded in the model.

Standard Residuals Results

This map shows the standard residuals results of a regression model used to predict meth lab locations in  West Virginia. The model predicted fewer meth labs in areas where the standard deviation is less than -0.5 than actually are there. In areas where the standard deviation is greater than 0.5, the model predicted there would be more.  

Visual Interpretation

Identifying Tone and Texture

This map was created to show the differences between tone and texture in aerial photography. Tone ranges from Very Light to Very Dark while Texture ranges from Very Fine to Very Coarse.

Identifying Features

This map was created as an example of how features can be identified based on four different visual attributes; Shape & Size, Shadows, Pattern and Association.

Project 1: Prepare Week

Basemap of Study Area

This week I prepared to study whether or not socio-economic factors can be used to determine the most likely locations of future methamphetamine labs. This is a basemap of the study area around Charleston, WV where I will be conducting my analysis.