GRASS GIS is a general purpose Free and Open Source geographic information system (GIS) that offers raster, 3D raster and vector data processing support. GRASS GIS has also incorporated a powerful support for time series, the so called TGRASS. Through this, it became the first open source temporal GIS with comprehensive spatio-temporal analysis, processing and visualization capabilities. The temporal functionality makes it easy to manage, analyse and visualize climatic data, vegetation index time series, harvest data or land use changes over time. Raster, vector and 3D raster time series are handled through a special data type called space time data sets (STDS) which are used as input in TGRASS modules. TGRASS incredibly simplifies the processing and analysis of large time series of hundreds of thousands of maps. For example, users can aggregate a daily time series into a monthly time series in just a single line; they can retrieve the date per year in which a certain value is reached; select maps from a time series in time periods in which a different time series reaches a certain value; perform different temporal as well as spatial operations among time series, and so much more.

In this 4-hours hands-on workshop we will present and exemplify the use of a subset of the more than 45 temporal modules in combination with other GRASS GIS modules and Add-ons in a workflow starting from the download of remote sensing data to the creation of a simple model and visualization of results. We will first learn how go to create STDS and assign time stamps to maps. In addition, we will learn different methods to gap-fill incomplete data, temporal algebra operations, temporal aggregation, queries and retrieval of basic and zonal statistics for time series. All along the session, we'll see different visualization options available in GRASS GIS. Moreover, we will show how this workflow might be included in python scripts and executed from outside GRASS GIS.

GRASS GIS exists for more than 30 years and provides a very large and diverse set of state-of-the-art tools for the analysis of spatial data. Less known by many, remote sensing tools have been part of it almost from the beginning. GRASS GIS provides a series of imagery analysis tools for pre-processing (radiometric correction, cloud detection, pansharpening, etc), creating derived indices (vegetation indices, texture analysis, principal components, fourier transform, etc), classifying (management of training zones, different classifiers, validation tools), and producing other derived products such as evapotranspiration and energy balance models. Next to these tools for satellite images, other tools exist for the handling of aerial photography for creation of orthophotos, and for the import and analysis of Lidar data.

In addition to these tools, efforts have gone into integrating current state-of-the-art methods such as object-based image analysis (OBIA) and machine learning. A complete toolchain exists to segment images using different algorithms, to create superpixels, to collect statistics characterizing the resulting objects, and to apply machine learning algorithms for classification. New modules also include unsupervised segmentation parameter optimization and active learning. Options for pixel-based classification have also been enlarged to a host of machine learning algorithms.

In this 4-hours hands-on workshop, users will learn how to use the entire OBIA toolchain in order to create a classification of a very-high resolution image. We will go through all the steps from segmentation all the way to classification. All the steps will be run via the GRASS GIS GUI, but we will also demonstrate how these tools can be used in an automated fashion through scripts.