In this tutorial, we will use the MODIS based V6 Terra Vegetation Indices 16-Day Global 250m product. This MODIS NDVI and EVI products are computed from atmospherically corrected bi-directional surface reflectances that have been masked for water, clouds, heavy aerosols, and cloud shadows. We will use this product to create NDVI based threshold classified thematic … CONTINUE READING
Category: Remote Sensing Page 1 of 2
Last week, I was doing some testing using the Python API interface for sentinel-1 toolbox with Snappy and the SNAP desktop to see the time taken by each of them. The workflow for processing the data is described here. The results were astonishing. Each and every steps were significantly slower, especially the co-registration process … CONTINUE READING
NASA’s Earth Observing System Data and Information System (EOSDIS) is the data distribution system facilitated with NASA’s Distributed Active Archive Centers (DAACs). Alaska Satellite Facility (ASF) is one of the DAAC providing various data sources to the public for free. We will use the ASF website (as of 28th October 2019) to download the 12.5 … CONTINUE READING
After the Geo for Good Summit 2019, all my focus has been geared toward integrating Machine Learning Models using Tensorflow with the Satellite data. One of the issues for exporting the training and testing data especially with a large number of features or huge areas for the neighborhood pixels if you are using the Fully … CONTINUE READING
Connected Pixel Count is one of the ways where the concept of the Minimum Mapping Unit (MMU) can be applied. Basically, the connected pixel count gives the image with every pixel containing the information on the number of the connected neighbors including the pixel in context. The neighbors can be 4- or 8-connected neighbors, and … CONTINUE READING
There are a couple of ways to calculate the area of the image in the Google Earth Engine. The full implementation of both method can be accessed using this link.
- Pixel Count Method
We can calculate the area of the image by counting the total number of unmasked pixels in that image. Then, multiply
With the recent release of TensorFlow 2.0, showcased at GEO for Good 2019, there is increased interest in employing an array of neural net approaches to solve various Remote Sensing research questions. A dedicated group from NASA SERVIR has spent the last 5 days exploring the Google Earth Engine, Google Colaboratory, and Google … CONTINUE READING
In this tutorial, we are going to perform the mosaicing of two adjacent Sentinel-1 scenes using Snappy, the Python interface for SNAP.
If you haven’t, follow along this tutorial to see how you can setup the development environment for SNAP in your machine. To overview, the basic steps that we cover in this tutorial are:… CONTINUE READING
This simple UI interface is built on the Google Earth Engine. It uses the primitives as percentage layers to assemble them to derive land cover maps. Here we are using the Random Forest algorithm to generate the land cover maps.
You can use the sliders to change the threshold input for the tree node structure … CONTINUE READING
The back-end on SNAP has been written in Java. But good news to Python enthusiast, they provide Python interface to Java API. It’s through their module called Snappy. In my previous tutorial, I showed you how you can install snappy in your machine and get geared up for the development work. And before we … CONTINUE READING
In this tutorial, we will learn how we can set up a development environment for Snappy. Snappy is the python interface for accessing the JAVA API of SNAP. SNAP can be used to process the Sentinel series of sensors. I prefer to have a separate environment for the Snappy so I can keep it clean … CONTINUE READING
In this tutorial, I will walk through some of the basic steps needed to process the Sentinel-1 SAR data using SNAP. For this tutorial, I am using SNAP version 7.0. You can check the version of the SNAP from Help -> About SNAP…
- If you do not have already, go ahead and download the SNAP