Git Product home page Git Product logo

yosemitetalusproj's Introduction

Motivation

Methods

How to use the machine learning model

Step 1: Download data

Get the DEM, Satellite, Slope, and Aspect data for the region you want to use the model on (Data should be at least 10m). I recommend using https://apps.nationalmap.gov/downloader/

Step 2: Open Google Earth Engine Code

Open the following link in a new tab for the code to generate the files that will be used for the ML model. https://code.earthengine.google.com/db48d72a0f230c4ccc0a536f3addeac3?noload=true

What you should see: image

IMPORTANT INFO: If you use the USGS link to download the data, the DEM data will be 10m, which is perfect. However, the satellite data will be 1m, which may make the file size too big for Google Earth Engine to import it. In that case, you may need to import the satellite data as separate GeoTiff files so that Google Earth Engine can handle the import. This won't be a problem, however, as there are instructions in the code as to how to deal with mutiple satellite files.

Step 3: Run Code

Click the "Run" button near the top of the code tab

Step 4: Create folder to store files

Go to Google Drive and create a folder to store your data in

What you should see:

image

Step 5: Download DEM file from GEE

Once the code has finished running, go to the Tasks tab on the right-hand side of the screen and click the "RUN" button for the DEM task. Once the button is clicked, a prompt will pop up, asking you to enter some information. In the CRS section, enter EPSG:4326. Near the bottom, enter the Google Drive folder this data should be exported to as well as the file name. Then, click "RUN" and the process should begin.

What you should see: image

Step 6: Download all files from GEE

Repeat Step 5 for the remaining tasks.

Step 7: Create Chunks, Output, and MegaNumpy folders

Go to Google Drive and create 3 empty folders

Folder 1:

image

Folder 2:

image

Folder 3:

image

Step 8: Create subfolders in Chunks folder

Go inside of the "Chunks" Folder and create four more empty folders, one for each input type(DEM, Satellite, Slope, Aspect)

What you should see:

image

Step 9: Download model

Check this GitHub project and find the "model.h5" file. Download that file, and save it to Google Drive.

Step 10: Open Colab

Check this GitHub project and find the "FinalTalus.ipynb" file. Then, open it in Google Colab using the button.

Example 1:

image

Example 2: image

Step 11: Give Colab access to Google Drive

Run the first cell (The one to import data stored in Google Drive). Do this by clicking on the cell, and then clicking on the small play button that appears on the left of the cell. Then, follow the instructions.

What you should see:

image

Step 12: Run all code in Colab

Go through the entire file and look for the green comments. Most are instructions that will help you set up the Colab correctly. Follow all of those instructions, and then begin running each cell in order.

IMPORTANT INFO: Most of the directions are regarding finding a path to a certain Google Drive file or folder. In order to find that path, click on the files tab to the left and choose the correct drop down options to get to your folder/file. Then, click on the three dots next to the file/folder name and click "Copy path". This will copy the path name to your clipboard, so you can just paste it where required.

Example:

image

Finished!

You should now have a file that displays the areas where a talus is expected to be in the output folder you previously made. Check the image that is displayed to make sure the data seems accurate. It is a jpg, though, so unfortunately, there won't be any geographical data stored.

yosemitetalusproj's People

Contributors

sriramrajagopal42 avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.