Remote Sensing from satellite discovery to Machine Learning and GeoAI.
This guide describes iT Sensing as a product workspace: where data comes from, how imagery moves through processing, and how the 50+ Remote Sensing tools, RS Model Builder, GeoAI and Python Studio fit together. It intentionally focuses on product capability rather than developer interfaces.
Core product workflow
A practical path from Earth observation discovery to operational result.
Select the geographic area of interest.
Search Landsat, Sentinel or commercial categories.
Clip, stack, align, resample and derive inputs.
RS tools, ML, GeoAI, Builder or Python.
Publish reusable monitoring-ready outputs.
Satellite catalog knowledge
iT Sensing separates routine open-data discovery from variable-cost commercial imagery.
Landsat
Open multispectral archive suitable for long-term environmental and land monitoring.
Sentinel
Open optical and radar missions for regular Earth observation workflows.
Commercial catalog
Use premium imagery when a project requires commercial SAR, multispectral or hyperspectral data.
Satellite Finder & Data
Search, evaluate and acquire imagery before processing.
Raster Preprocessing
Prepare imagery for consistent analysis.
Spectral Indices
Generate common spectral indicators and custom formulas.
Texture & Spatial Features
Add neighborhood and texture information to models.
Classification
Create thematic raster products from training data or clustering.
Regression & Machine Learning
Predict continuous environmental and Earth observation variables.
GeoAI
Run model-driven geospatial intelligence workflows.
SAR & Change Workflows
Use radar information for complementary monitoring.
RS Model Builder
Design reusable visual Remote Sensing workflows.
Python Studio
Extend the toolbox with custom scientific processing.
Visualization & Interpretation
Inspect scientific rasters without changing source values.
Output & Monitoring
Turn analysis into reusable operational layers.