remote-sensing-analysis

Detect deforestation using satellite imagery by applying machine learning classification and temporal analysis to a time series of optical or SAR data. This Skill processes the imagery to identify changes in forest cover and generate environmental monitoring insights.

Yes, this Skill supports SAR data processing for change detection and object detection in satellite imagery. It handles radar data alongside optical multispectral and panchromatic data to extract valuable information for environmental monitoring.

Remote sensing analysis and ML classification require rasterio, numpy, scipy, sklearn, geopandas, xarray, opencv-python, and torch. These dependencies process geospatial raster data and power the machine learning models for classification and time series analysis.

Preprocess multispectral satellite images for radiometric and atmospheric corrections using the optical image processing capabilities of this Skill. It handles hyperspectral and panchromatic data, preparing the imagery for accurate machine learning classification and temporal analysis.

Yes, monitoring crop health with a time series of satellite images is a supported use case. The Skill applies machine learning classification and temporal analysis to the satellite imagery to detect changes and generate agricultural insights.

The best way to classify land cover using hyperspectral satellite data is to apply machine learning models through this remote sensing analysis pipeline. It preprocesses the imagery and uses sklearn and torch models to extract valuable classification information.