PAINT

Welcome to PAINT

This repository contains code associated with the PAINT database. The PAINT database makes operational data of concentrating solar power plants available in accordance with the FAIR data principles, i.e., making them findable, accessible, interoperable, and reusable. Currently, the data encompasses calibration images, deflectometry measurements, kinematic settings, and weather information of the concentrating solar power plant in Jülich, Germany, with the global power plant id (GPPD) WRI1030197. Metadata for all database entries follows the spatio-temporal asset catalog (STAC) standard.

🔥 To learn more, check out our publication in Nature Energy - https://doi.org/10.1038/s41560-026-02070-1 🔥

What can this repository do for you?

This repository contains two main types of code:

1. Preprocessing: This code was used to preprocess the data and extract all metadata into the STAC format. This preprocessing included moving and renaming files to be in the correct structure, converting coordinates to the WGS84 format, and generating all STAC files (items, collections, and catalogs). This code is found in the subpackage paint.preprocessing and executed in the scripts located in preprocessing-scripts. This code could be useful if you have similar data that you would also like to process and include in the PAINT database!
2. Data Access and Usage: This code enables data from the PAINT database to be easily accessed from a code-base and applied for a specific use case. Specifically, we provide a StacClient for browsing the STAC metadata files in the PAINT database and downloading specific files. Furthermore, we provide utilities to generate custom benchmarks for evaluating various calibration algorithms and also a torch.Dataset for efficiently loading and using calibration data. This code is found in the subpackage paint.data and examples of possible execution are found in the scripts folder.

In the following, we will highlight how to use the code in more detail!

Installation

We heavily recommend installing the PAINT package in a dedicated Python3.10+ virtual environment. You can install the latest stable version of PAINT directly from PyPI using:

  pip install paint-csp

Alternatively, You can install the latest developmental version of PAINT directly from the GitHub repository via:

pip install git+https://github.com/ARTIST-Association/PAINT

You can also install PAINT locally. To achieve this, there are two steps you need to follow:

1. Clone the PAINT repository:

   git clone https://github.com/ARTIST-Association/PAINT.git

2. Install the package from the main branch:
   • Install basic dependencies: pip install .
   • If you want to develop paint, install an editable version with developer dependencies: pip install -e ".[dev]"

Structure

The PAINT repository is structured as shown below:

.
├── html # Code for the paint-database.org website
├── markers # Saved markers for the WRI1030197 power plant in Jülich
├── paint # Python package/
│   ├── data
│   ├── preprocessing
│   └── util
├── plots # Scripts used to generate plots found in our paper
├── preprocessing-scripts # Scripts used for preprocessing and STAC generation
├── scripts # Scripts highlighting example usage of the data
├── test # Tests for the python package/
│   ├── data
│   ├── preprocessing
│   └── util
└── tutorials # Interactive notebooks showcasing how to get started with PAINT

Example usage:

In the scripts folder there are multiple scripts highlighting how PAINT can be used. Detailed descriptions of these scripts are available via our Documentation.

Furthermore, an interactive notebook is available in the tutorials folder - this is the perfect starting point to dive into PAINT!

How to cite

If you use the PAINT database in your research, please cite our paper:

Phipps, K., Kuhl, M., Weiel, M. et al. The PAINT database for operational concentrating solar power plant data following FAIR data principles. Nature Energy (2026). https://doi.org/10.1038/s41560-026-02070-1

BibTeX:

@article{Phipps2026PAINT,
  author  = {Phipps, Kaleb and Kuhl, Mathias and Weiel, Marie and Busch, Marlene and Lewen, Jan and Blumenr{\"o}hr, Nicolas and Maldonado Quinto, Daniel and Debus, Charlotte and G{\"o}hring, Felix and Kaufhold, Oliver and Streit, Achim and Pitz-Paal, Robert and G{\"o}tz, Markus and Pargmann, Max},
  title   = {The PAINT database for operational concentrating solar power plant data following FAIR data principles},
  journal = {Nature Energy},
  year    = {2026},
  doi     = {10.1038/s41560-026-02070-1},
  url     = {https://doi.org/10.1038/s41560-026-02070-1},
  issn    = {2058-7546}
}

How to contribute

Check out our contribution guidelines if you are interested in contributing to the PAINT project 🔥. Please also carefully check our code of conduct 💙.

Acknowledgments

This work is supported by the Helmholtz AI platform grant.

---