Our unique set of API-s allows streamlined data access for your own software, performing catalogue searches, image queries, pixel-by-pixel processing and area statistics with a few lines of code. Application Programming Interface (API) is an intermediary that allows applications to access the features or data of another application or system. Our API allows users to programmatically process satellite data and integrate it into their own applications, which can run directly on CREODIAS. Search the API documentation to get started. The Processing API is the most commonly used API in Sentinel Hub, as it provides images based on satellite data. Users can request raw satellite data, simple band combinations such as false colour composites, calculations of simple remote sensing indices like NDVI, or more advanced processing such as calculation of Leaf area index (LAI). For requesting large areas or longer time periods of data, we've developed a Batch Processing API, and for searching and viewing geospatial information of data collections or checking data availability, we provide a Catalog API. If you're interested in calculating statistical information from satellite imagery – including inside vector boundaries, use our Statistical API. You can use all the data collections already integrated in Sentinel Hub, bring in your own data, or even integrate commercial data of your choice. Learn more in our webinars on Process API Statistical API, Bring Your Own Data and Commercial Data in Sentinel Hub. New and in beta: the Batch Statistical API and the Asynchronous Process API, which acts as an intermediate tool between the Process API and the Batch Processing API.

By integrating Sentinel Hub APIs to processing pipelines, it is possible to build a full end-to-end agricultural monitoring system, ready for operational use at regional scale. Based on markers such as bare soil, mowing, homogeneity and crop group classification, a wide variety of scenarios can be validated. This allows creating a full monitoring solution for CAP subsidies running on CREODIAS 2.0.

Our custom script library leverages the power of evalscripts to provide a vast selection of algorithms for data analysis and visualisation compatible with many different satellite sensors. An evalscript (or "custom script") is a piece of JavaScript code which defines how the satellite data shall be processed by Sentinel Hub and what values the service shall return. It is a required part of any process, batch processing or OGC request.

Evalscripts can use any JavaScript function or language structures, along with certain utility functions we provide for your convenience. For running evalscripts we use the Chrome V8 JavaScript engine.

In the Evalscript V3 section you will find a technical documentation with detailed explanations of parameters and functions you can use in your evalscripts. Examples of various evalscripts together with their use and guidelines for writing new scripts can be found on our Custom Scripts Repository.

Sentinelhub-js is an open source Javascript/TypeScript library for seamless integration of Sentinel Hub and other similar EO web services in web or node.js applications — no need to construct queries using fetch, axios and similar anymore. The library is not limited just to the Sentinel Hub service either, it allows integration of any remote sensing service which supports standard OGC queries.

In other words, the goal of the library is to provide a simple, unified JavaScript interface to multiple Earth Observation (EO) services. All datasets are treated similarly in a sense that a set of common operations is provided for each of them, but user can still use dataset-specific functionality where available.

The full documentation is available on GitHub

The sentinelhub Python package is a Python wrapper that allows users to run requests for most of the Sentinel Hub API-s within their Python workflows, besides offering numerous utility functions (eg. Transfer statistics output to dataframe, request monitoring managers):requests to download and process satellite images within your Python scripts. It supports Sentinel-2 L1C and L2A, Sentinel-1, Landsat 8, MODIS and DEM data collections. The available codebase includes support for OGC web services requests, pixel-level processing with spectral indices, zonal statistics, support for multi-temporal requests, different coordinate systems and data format conversion.

The full documentation is available on GitHub

EO-learn is an open-source Python library that acts as a bridge between Earth Observation and the Python ecosystem for data science and machine learning. The main purpose of this package is to automatically extract complex patterns in spatio-temporal data. This collection of open-source Python packages has been developed to seamlessly access and process spatio-temporal image sequences acquired by any satellite fleet in a timely and automatic manner. EO-Learn allows prototyping of complex EO workflows in an easy, fast and accessible way, to make entry to the field of remote sensing for non-experts easier and bringing the state-of-the-art tools for computer vision, machine learning, and deep learning existing in the Python ecosystem to the fingertips of remote sensing experts. EO-learn is easy to use, its design is modular and encourages collaboration.

Read about the philosophy and technical background of EO-Learn in more detail in this blog post, watch this webinar or go straight to the full documentation