Downscaling Landcover Data using Machine Learning (ML) Approach in Google Earth Engine

Показать описание

Take your geospatial analysis skills to the next level! This comprehensive tutorial shows you how to downscale land cover datasets to higher resolution using machine learning techniques in Google Earth Engine (GEE). Perfect for GIS enthusiasts, researchers, and remote sensing professionals!
Key Highlights of the Video:
1. Study Area Definition: Define the region of interest using WWF HydroSHEDS basin boundaries.
2. MODIS Land Cover Analysis: Explore and visualize MODIS land cover data (500m resolution).
3. Predictor Variables: Use Landsat 8, Sentinel-1 SAR, and urban area data for feature extraction.
4. Percentile Calculations: Summarize temporal variability with statistical percentiles for machine learning.
5. Stratified Sampling: Generate a robust training dataset from combined predictors.
6. Machine Learning Model: Train an SVM classifier for high-resolution (50m) land cover mapping.
7. Export Results: Export the high-resolution classified map for further analysis.
Why Watch This Tutorial?
• Learn how to integrate multi-source data (MODIS, Landsat, Sentinel) in GEE.
• Understand machine learning-based downscaling workflows for land cover mapping.
• Gain hands-on experience with stratified sampling and SVM classification in GEE.
-----------------------------------------------------------------
Useful link:
1. HydroSHEDS Basins Level 5:
2. MODIS Land Cover Type Yearly Global 500m:
3. USGS Landsat 8 Level 2:
4. Global built-up surface 1975-2030:
5. Sentinel-1 SAR:
-----------------------------------------------------------------
Who Is This For?
• GIS students & researchers
• Remote sensing enthusiasts
• Professionals working on land cover, climate studies, or urban planning
-----------------------------------------------------------------
💰🤝🏻Join Membership to get access to perks & Support us🤝🏻💰
-----------------------------------------------------------------
👩‍💻 Join the Terra Spatial Community:
Engage with fellow learners, share your experiences, and get support on our dedicated community forum.
🌐 Stay connected:
---------------------------------------------------------------
👍 **Don't forget to Like, Share, and Subscribe for more insightful tutorials! 🌐✨
#GoogleEarthEngine #LandCoverMapping #MachineLearning #GIS #RemoteSensing #Downscaling

Рекомендации по теме

Комментарии

Do you know difference between Index formula and regression formula for calculating pollution?

Ramilacookware

What is difference between 500 with 50?

Ramilacookware

Very interesting way to increase resolution of the image quality

FreeOnlineEducation-kgnx

Downscaling Landcover Data using Machine Learning (ML) Approach in Google Earth Engine

Downscaling Landcover Data using Machine Learning (ML) Approach in Google Earth Engine

Google Earth Engine Tutorial-59: GRACE Data Downscaling, using Machine Learning Techniques

DS340W Team4 Downscaling Climate Data w.Deep-Learning

🛑Land Use and Land Cover Classification with Change detection using Machine Learning in Earth Engine...

How to increase/decrease or Upscaling/downscaling or resample the satellite image

Supervised Classification with Sentinel 2 Satellite Images | Earth Engine | Machine Learning

Using EBK Regression Prediction to Downscale Climate Simulations

Initial Experiments with a Scalable Machine Learning Based Approach

Lesson 1: Climate scenarios and downscaling

Lesson 2: Understanding and operation of S8 Downscaler (S8DS)

Random and Systematic Sampling for Machine Learning with Earth Engine

Dynamical Downscaling - what is it good for? Presented by Professor Jason Evans.

ID 115 Using AI to downscale Ecosystem

Full Course - Supervised Classification & Land Cover Mapping with Earth Engine Python API & ...

Supervised classification in Google Earth Engine Land Use and Land Cover Classification Earth Engine

How Machine Learning Can Cut the Cost of Downscaling Evapotranspiration

Supervised Classification for Land Cover Mapping with Landsat 8 in Google Earth Engine

Can machine learning models trained using crowdsourced observations and high resolution land cover b

ENM2020 - W7T2 - Climate Data

Climate Data (Temperature, Precipitation, Humidity) from 1981-2022

Converting AOD to PM2.5: a Statistical Approach using Google Earth Engine || Particulate Matter 2.5

'Efficient Dynamical Downscaling of General Circulation Models Using Continuous ...' Ibrah...

Predicting LST with Population, Rain, and Elevation using Random Forest Regression in Earth Engine

240 Water Flow Prediction In Rivers Using In-situ And Satellite Data: The Experience Of Waterjade

'Efficient Dynamical Downscaling of General Circulation Models Using Continuous ...'　Ibrah...