Advanced Remote Sensing Analysis in QGIS & Open Cloud Tools

Learn image differencing as a simple change-detection method and apply cloud-based spectral indices like NDVI and NBR to detect vegetation changes and burnt areas across two time steps.

Explore spectral indices from satellite data to estimate land surface properties using red and near infrared bands, including the normalized difference vegetation index and simple ratio from Landsat.

Explore visual change detection with the EO browser, using Sentinel-2 images to compare July 2020 and July 2018, identify qualitative changes, and examine spectral indices and color composites.

Compute the ndvi from landsat bands in qgis using the raster calculator, or use the semi automatic classification plugin, based on near infrared and red bands.

Compute ndvi from landsat bands in qgis to monitor vegetation cover and forest change over time, then classify results into water, bare soil, and vegetation classes.

Compute ndvi differences between 1985 Landsat 5 and 2013 Landsat 8 in QGIS by using band 5 minus band 4, reclassify changes, and generate a vegetation-change map.

Assess burn severity with the normalized burn ratio, comparing pre- and post-fire imagery; interpret delta NBR values with seasonal variation and USGS guidelines for rehabilitation planning.

Compute the normalized burn ratio index (nbr) from Sentinel-2 using infrared (band 8a) and shortwave infrared (band 12) with the semi-automatic classification plugin to map wildfire impact and burn severity.

Perform post-classification change detection in qgis using two land cover maps from different times to create a change map and quantify area change.

Install and access the Trends Earth plugin in QGIS 10.3, then navigate the raster menu for post-classification change detection tools and consult the online or offline user guides.

Explore post-classification change detection in QGIS using the trend earth plugin, raster calculator, and semi-automatic classification plugin, with 2010–2015 land cover maps for Rwanda.

Investigate time series analysis of satellite remote sensing data to study land surface change, vegetation dynamics, and phenology with vegetation indices like ndvi, across decades and sensor systems.

Extract and interpret time series data for individual pixels using normalized vegetation indices via the Appears surface from NASA. Subset, sample, visualize, and summarize 20-year 16-day data across global locations.

Log in to appears, set date range from 2020 to year-end, add data for selected points, and submit the request to generate twenty years of time series from vegetation indices.

Learn time series analysis in QGIS using the Trend Earth plugin to compute NDVI trends with linear regression and select data resolutions for vegetation productivity.

Time series analysis of 250-meter MODIS imagery in QGIS to monitor drought using ndvi anomalies, comparing July 2015 with July 2001–2010 and scaling data with a 0.001 factor.

Apply cropping and clip by extent in QGIS to isolate land areas for drought monitoring using MODIS time series, saving temporal layers for 2001–2010 and 2015.

In QGIS, compute the average MODIS image from 2001–2010, subtract it from the July 2015 image to form a normal drought anomaly, with blue/green positives and red negatives.

Advance your skills in remote sensing, data science, and machine learning through the Udemy instructor page and the Jio World YouTube channel.