# CENG 463 Project Fall 2022
Climate change has become a serious threat to humanity. Global land cover maps serve as an important means to tackle this problem. ESA has produced Global Land Cover Map from Sentinel-2 data. 
We will generate land cover maps for unseen data by using a limited number of training samples. Gibraltar is selected as a study area as there is a wide variety of land cover types. 
## Data:
![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F2285546%2F61185976705294ac2f34dd74ddde425d%2FTrainingData.jpg?generation=1670604296605320&alt=media)

Data Link: https://drive.google.com/drive/folders/1diOV3oaKTsXul3SB8YSWpEQ8AvtZO-Uk?usp=sharing 
Test Data will be provided later. 
Data is UInt16, Class labels are Uint8. 
Training data: S2A_MSIL1C_20220516_TrainingData.tif 
Training labels: S2A_MSIL1C_20220516_Train_GT.tif 

## Class List: 
 ![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F2285546%2F01ce381c9ec97efd5bf5e6e2a2a4671e%2FCodes.png?generation=1670604363281149&alt=media)

Reference: https://esa-worldcover.s3.eu-central-1.amazonaws.com/v200/2021/docs/WorldCover_PUM_V2.0.pdf 
Note that some of the classes may not be present in the data set. You may ignore classes that are not present in both datasets. 
## Methods:
You are limited to methods that are covered in the course however you may perform feature engineering such as selecting bands or taking ratios of bands. Methods such as neural networks or deep learning should not be used. 
## Software: 
You may only use SKLearn, OpenCV, GDAL (Data Read), Numpy, and Matplotlib (Those used in your lab sessions.)
## Deadline: 
The week after the end of the final exams. 
## Report: 
You should prepare a report which includes your implementation details, and a link to your GitHub repo which includes codes. In addition, you may prepare a report in IEEE Paper format such as RAST2023 conference. 
Your report should include details about your project such as the number of training samples, how you selected a method, and how it performs with the provided data. You should search literature briefly from Google Scholar (spend the 1st week’s effort).
Presentation & Competition: 
There will be project presentations by project teams. There will be a competition based on your classification score, report, and presentation. 
## Teams: 
You can team up to 2 students.