1 / 15

Accuracy Assessment

Accuracy Assessment. Validating a Land cover Map. AA_Vis_1. Students examine both the “true color” And “false-color Infrared” images provided by GLOBE. AA_Vis_2. Students construct a Land Cover Map keyed to the MUC System. AA_Vis_3. Students gather data From 90 x 90 m Qualitative Land

zurina
Download Presentation

Accuracy Assessment

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Accuracy Assessment Validating a Land cover Map AA_Vis_1

  2. Students examine both the “true color” And “false-color Infrared” images provided by GLOBE AA_Vis_2

  3. Students construct a Land Cover Map keyed to the MUC System AA_Vis_3

  4. Students gather data From 90 x 90 m Qualitative Land Cover Samples to “validate” their Map. AA_Vis_4

  5. Site 1 1222 Site 6 Site 2 1121 At each of these sites, The MUC value is determined, a GPS reading is taken, and photographs are taken. These are Validation Data. Site 3 92 1121 Site 4 Site 5 92 91 Site 7 Site 8 1222 1121 AA_Vis_5

  6. The Accuracy Assessment Data Work Sheet is filled out for all sites Warner’s Woods 1121 1222 X UPS Complex 92 92 √ State Park Area 1121 1121 √ Truck Terminal 92 92 √ Clark’s Loop 92 91 X Dale’s Grove 1121 1121 √ School Woodlot 1121 1222 X Town Grove 1121 1121 √ AA_Vis_6

  7. The Difference/Error Matrix is Constructed Validation Data (What we actually found) Map Data (What we expected to find) AA_Vis_7

  8. The Difference/Error Matrix is Constructed Validation Data (What we actually found) 1121 1222 92 91 Total 1121 Map Data (What we expected to find) 1222 92 91 Total AA_Vis_7

  9. Map and Validation Data Are Entered on the Matrix Validation Data (What we actually found) 1121 1222 92 91 Total | | | | | 1121 Map Data (What we expected to find) 1222 92 | | | 91 Total AA_Vis_8

  10. Totals Are Calculated for Rows and Columns Validation Data (What we actually found) 1121 1222 92 91 Total | | | 5 | | 1121 Map Data (What we expected to find) 1222 0 92 3 | | | 0 91 2 3 2 8 1 Total AA_Vis_9

  11. Overall Accuracy is Calculated Sum of Major Diagonal Tallies Overall Accuracy = -------------------------------------- x 100 Overall Accuracy = ----- x 100 = 63% Total Number of Samples 5 8 AA_Vis_10

  12. More Qualitative Sites are visited, and the Matrix is Developed for All Classes on the Map 1121 1222 92 91 93 94 63 71 72 52 821 823 Total 8 1121 3 11 2 5 1222 7 10 6 2 2 20 92 5 12 17 91 9 9 93 3 94 1 2 5 63 5 3 3 71 72 5 5 52 1 7 8 821 3 5 2 1 1 823 Total 12 8 17 18 9 4 5 3 5 9 3 1 94 AA_Vis_11

  13. Overall Accuracy is Calculated 70 Overall Accuracy = ----------- X 100 = 0.74 X 100 = 74% 94 AA_Vis_12

  14. REMOTELY SENSED FOREST VEGETATION MAPS:RASTER MAPS CREATED FROMLANDSAT TM IMAGERY July 1996 Landsat TM Image Pawtuckaway Study Area, NH, USA Forest Cover Type Map from Classification of July 1996 Landsat TM Image Pawtuckaway Study Area, NH, USA Legend Class Names White Pine White Pine-Hemlock Other Conifer Hemlock Oak Red Maple Mixed Forest Nonforest Beech Other Scale Kilometers AA_Vis_13

  15. ERROR MATRICES ANDESTIMATES OF ACCURACY AA_Vis_15

More Related