ISHANGO-ai/Remote-Sensing-Of-Tobacco-Fields-in-Malawi-and-Mozambique

Use remote sensing monitoring and public available datasets satellite image to classify land cover , crop identification, area of crop field. using computer vision skills, image classification,image detection or deep learning # Satellite imagery analysis for land cover classification ## 1.Introduction By using remote monitoring and leveraging publicly available datasets, we want to differentiate and if possible classify different types of land surfaces in order to help identify areas that are more likely to include tobacco fields. ## 2.Access satelitte imagery (sentine2A, landsat) The instruction about how you can access and download the data from satellite, read on data.txt. 1.Search and Download Sentinel 2A imagery using Sentinelsat API Run python sentineldownload_data.py 2.Search and download landsat image using landsatxplore API Run python landsat_download.py ## 3.Data visualization the 4 bands(blue,green,red,NIR) ouf 12 and RGB true color image Run python visualize.py Run python RGB.py ## 4. Analysis of sentinel2A, Indices to make Vegetation Analysis Complete The use of remote sensing indices in order to obtain information for vegetation distributions, heath and patterns is a popular practice with applicability at different scales of detail. NDVI(Normalized Difference Vegetation Index) that are widely used to analyze vegetation but is sensitive to the effects of soil and atmosphere, that’s why it’s recommended to apply additional indexes for more accurate analysis of vegetation. ### 1. NDVI(Normalized Difference Vegetation Index) It describes the difference between visible and near-infrared reflectance of vegetation cover and can be used to estimate the density of green on an area of land and it varies from -1 to 1 Run python NDVI.py ### 2.NDWI(Normalized Difference Water Index) Normalized Difference Water Index (NDWI) may refer to one of at least two remote sensing-derived indexes related to liquid water: One is used to monitor changes in water content of leaves, using near-infrared (NIR) and short-wave infrared (SWIR) wavelengths Another is used to monitor changes related to water content in water bodies, using green and NIR wavelengths Have a look on NDWI us …