Fall 2023 Lab Lecture -
Spring 2023 Lab Lecture -
Dr. Sounny and Matthew discussed the process of adding new predictor bands to their data set, including the creation of a new band from analytics and the use of Landsat image as a variable. They encountered technical issues related to passing strings and band names in their system and worked on adding a new band to their image and changing prediction bands from Landsat 1 to Landsat 2. They also discussed the process of adding new dots, the impact of increasing the number of samples extracted from the composite and unsupervised sampling on the results, and the potential frustration with coding in Earth Engine.
Lab 13 - Improving your Classifications
In this lab, you will improve the code you created in Lab 11 - Supervised Classification and Lab 12 - Unsupervised Classification. You'll see if you can improve the classifications by completing the following assignments. You can use your code from Lab 12 or use the following code: https://code.earthengine.google.com/82c02e163ca780304a5536c29c6c4461
Assignment 1. For the supervised classification, try collecting more points for each class. The more points you have, the more spectrally represented the classes are. It is good practice to collect points across the entire composite and not just focus on one location. Also, look for pixels of the same class that show variability. For example, for the water class, collect pixels in parts of rivers that vary in color. For the developed class, collect pixels from different rooftops.
Assignment 2. Add more predictors. Usually, the more spectral information you feed the classifier, the easier it is to separate classes. Try calculating and incorporating a band of NDVI or the Normalized Difference Water Index as a predictor band. Do you think this helps the classification? Could you check for developed areas classified as herbaceous or vice versa?
Assignment 3. Use more trees in the Random Forest classifier. Do you see any improvements compared to 50 trees? Note that the more trees you have, the longer it will take to compute the results and that more trees might not always mean better results.
Assignment 4. Increase the number of samples extracted from the composite in the unsupervised classification. Does that improve the result?
Assignment 5. Increase the number of k of clusters for the k-means algorithm. What would happen if you tried 10 classes? Does the classified map result in meaningful classes?
Assignment 6. Test other clustering algorithms. We only used k-means; try other options under the ee.Clusterer object.
Complete the Assignments above and add comments showing where they are clearly, and comment on any codes. Submit a URL to your final work product.
Lab Submission
Submit lab via email.
Subject: Lab 13 - Improving your Classifications - [Your Name]