MATH 223 Lecture Notes - Lecture 6: Static Variable, False Positive Rate, Sensitivity And Specificity

6 views5 pages
Meryem Atlagh
Lab 8 Section 1
8.1 Projecting a landscape change model
Q. Prediction image
Figure 1: The map above demonstrates a hard prediction of the 2000 land cover, which means that the
program decided which pixels will be transitioned to the land cover or stay as the original cover. In this
case Cusi Palm, water, and inundated savanna will remain identical to the model from 1994.
Q. The predicted amount of disturbance in 2000 showed that anthropogenic disturbance increased from
1986 to 1994 and to 2000 increased from 1986 hectares to 27799 hectares to 39565 hectares respectively.
However, comparing the predicted value of anthropogenic disturbance in 2000 to the actual value of the
anthropogenic disturbance which was equal to 69051, we can see that these values are very far from each
other. This shows that the model failed to accurately predict the anthropogenic disturbance of this land
cover since it really underestimated the value of disturbance. Visually comparing the predicted 2000 land
cover image to the actual land cover image shows more anthropogenic disturbance than the predicted
2000 land cove image.
Unlock document

This preview shows pages 1-2 of the document.
Unlock all 5 pages and 3 million more documents.

Already have an account? Log in
Q. Soft prediction model
Figure 2: The image above represents a soft prediction map for 2000 and it shows all the possible
transitions in this landcover.
8.2 Model performance
Q.
Unlock document

This preview shows pages 1-2 of the document.
Unlock all 5 pages and 3 million more documents.

Already have an account? Log in

Get OneClass Notes+

Unlimited access to class notes and textbook notes.

YearlyBest Value
75% OFF
$8 USD/m
Monthly
$30 USD/m
You will be charged $96 USD upfront and auto renewed at the end of each cycle. You may cancel anytime under Payment Settings. For more information, see our Terms and Privacy.
Payments are encrypted using 256-bit SSL. Powered by Stripe.