Post related to Tag:
GOOGLE EARTH ENGINE (GEE)
Minimum, Mean and Maximum NDVI values for Polygon samples on Google Earth Engine (Python API)
Every time I saw the curve as shown above in research papers and blogs, I wondered how it was prepared and what it meant. I used to think the sample curve like this was prepared based upon the point feature. I never thought this could be made based on the polygon samples. Normalized Difference Vegetation Index (NDVI): The Normalized Difference Vegetation Index (NDVI) measures the difference between near-infrared (which vegetation strongly reflects) and red light (which vegetation absorbs) to quantify vegetation. NDVI always ranges from -1 to +1. I am now interested to analyze the time series NDVI statistics (Min, Mean & Max) with polygon samples. NDVI statistics(Min, Max & Mean): Let's take the case; We have multiple crop samples …
Read More →
Histogram from the Image on Google Earth Engine (GEE) with python API
Let’s dive in with the basic concept first. I would like to go with an introduction and use case. Introduction: When presenting and summarizing discrete or continuous data, histogram is the chart you are looking for. By displaying the amount of data points that fall inside a given range of values (referred to as "bins or interval" or "buckets"), it essentially provides a visual interpretation of numerical data. It resembles a horizontal bar graph. A histogram, in contrast to a vertical bar graph, does not display any gaps between the bars. Components of a Histogram: The title: The title describes the information included in the histogram. X-axis: The intervals on the X-axis display the range of values that the measurements …
Read More →
Time series EVI data with Savitzky-Golay filter in Google Earth Engine (GEE) with python API
Let's begin with time series data and its analysis: Time series Analysis: A particular method of examining data points gathered over time is called a "time series analysis." Instead of just capturing the data points intermittently or arbitrarily, time series analyzers record the data points at regular intervals over a predetermined length of time. But this kind of study involves more than just gathering data over time. The data analysis can show how variables change over time. Consider a case of predicting weather changes is time series analysis, which aids meteorologists in projecting everything from tomorrow's weather report to upcoming years of climate change. Likewise, we can take the following examples for time series analysis. Weather data Rainfall measurements Temperature …
Read More →
Accessing the Planet's imagery (NICFI's) for analysis from Google Earth Engine (GEE)
Users can now access Planet's high-resolution, analysis-ready mosaics of the world's tropics through Norway's International Climate & Forests Initiative (NICFI) with an objective to help reduce and reverse the loss of tropical forests, combat climate change, conserve biodiversity, and facilitate sustainable development for non-commercial purposes. This program is launched in partnership with Norway's International Climate and Forest Initiative (NICFI), Kongsberg Satellite Services (KSAT), and Planet. Please, go to this link: https://www.planet.com/nicfi/#sign-up for signing up. You have to fillup the form, and it will guide you on how to proceed with accessing data. For details and accessing the data, please do visit: https://www.planet.com/nicfi/ Planet Developer's note on NICFI Before we move on, we need details of resolution and band information of the planet image. Here's the …
Read More →
Extraction of raster values from point samples on Google Earth Engine (GEE)
Background: In this tutorial, We plan to extract the raster cell values from the set of point features nd records the values in the attribute table as an output. on Google Earth Engine (GEE) with python API. Before we dive into the working steps, I will explain the general idea of how this concept can be implemented. The process of raster value extraction can be implemented in two ways, Directly extracting the raster values by overlaying raster with point data. Raster value which perfectly overlays with the point is taken. Buffer (circle, square) around the point is created, and raster statistics (mean) are obtained. This mean is taken as the raster value for points. Refer this: Scenario, where you are going …
Read More →
Downloading images from Google Earth Engine to local drive ( A case study for Timesat image Preparation for Planting Date)
Satellite image processing might be very painful, depending upon the volume of data. I don't like to be suggesting the data download and do image analysis on your local device. But there might be a time when we can't follow this suggestion. I passed through a similar situation for analyzing MODIS EVI datasets to determine the planting date for Rice. I was advised to use Timesat (Welcome to the TIMESAT pages! (lu.se)) for this task. Instead, I had no options to download MODIS EVI data (250 m resolution, 8 Day temporal resolution-terra and Aqua sensors combined). I used Google Earth Engine (GEE) to download the data into my local device and prepare the dataset in the desired format for Timesat …
Read More →
Retrieving Leaf Area Index (LAI) on Sentinel 2 image with Google Earth Engine (GEE)
What is Leaf area index (LAI)? The leaf area index (LAI), equal to half of the total green leaf area per unit of the horizontal ground surface, is a crucial structural feature of vegetation. Canopy interception, evapotranspiration, and gross photosynthesis are directly related to LAI since leaf surfaces constitute the primary frontier of energy and mass exchange. I have explained this on my previous post, but I thought it needs to be covered in sperate post along with step by step guide for computation of LAI. I have uploaded the notebook for it's implementation at the end of this article. Leaf Area Index (LAI) Formula: This index is used to forecast crop growth and yield and estimate foliage cover. ENVI calculates …
Read More →
Calculating different Vegetation Indices in Google Earth Engine (Sentinel -2 images)
In previous post, I have published the article for EVI and NDVI calculation from sentinel 2 image on Google earth engine (GEE) platform. In this article, I will be showing how various vegetation indices can be computed on GEE platforms and can be added to image collection. So, let's dive into various vegatation indices directly. Greenness (Green Leaf Index) The Green Leaf Index, also known as the Greenness Index, shows how the reflectance in the green channel compares to the other two visible wavelengths (red and blue). The formula for calculation of GLI is: GLI = (2*GRN-RED-BLU)/(RED+GRN+BLU) GRN pixel values from the GREEN band RED pixel values from the RED band BLU pixel values from the BLUE band The lower the greenness index, the higher …
Read More →
Calculating NDVI from Sentinel-2 Images
Let's start with the introduction: What is NDVI (Normalized Difference Vegetation Index)? The Normalized Difference Vegetation Index (NDVI) measures the difference between near-infrared (which vegetation strongly reflects) and red light (which vegetation absorbs) to quantify vegetation. NDVI always ranges from -1 to +1. If there are no green leaves, the value is zero. A zero denotes no vegetation, whereas a value close to +1 (0.8-0.9) suggests the highest density of green leaves conceivable. However, the land cover type does not have its specific limit of NDVI values. Normalized Difference Vegetation Index (NDVI) Formula: The formula for calculating NDVI is as follows: NDVI = (NIR — RED)/(NIR + RED) NIR – reflection in the near-infrared spectrum RED – reflection in the …
Read More →
Enhanced Vegetation Index (EVI) from Sentinel-2 image on Google Earth Engine
What is Enhanced Vegetation Index (EVI)? The enhanced vegetation index (EVI) is an 'optimal' vegetation index that decouples the canopy background signal and reduces atmospheric impacts to improve the vegetation signal with greater sensitivity in high biomass regions and improved vegetation monitoring. The Enhanced Vegetation Index (EVI) from Landsat, Sentinel-2 image is comparable to the Normalized Difference Vegetation Index (NDVI), and it quantifies the vegetation greenness. While the EVI is calculated in the same way as the NDVI, it accounts for some distortion in reflected light caused by airborne particles and the ground cover beneath the vegetation. When examining rainforests and other areas of the Earth with high levels of chlorophyll, the EVI data product does not get saturated as …
Read More →
