Target group
Interested users in research and industryYour requirements
Basic GIS knowledge is advantageous for successful application.Our offer
We offer a holistic solution covering consultancy, training, and implementation of this segmentation approach. The method is seamlessly integrated into QGIS via the user-friendly Deepness plugin and can be intuitively applied to geographic base maps worldwide. After segmentation, capacity factors can be used to calculate the performance of each identified PV system. Due to its global applicability, this solution is easily transferable to different geographical contexts and is accessible to users without programming knowledge.By integrating the method into QGIS, users can effortlessly identify solar photovoltaic systems and calculate their capacity based on a capacity factor.Requirements
No in-depth programming skills are required. Thanks to its user-friendly integration in QGIS, the application is also suitable for those new to renewable energy analysis.Success stories
Read and test the models online:
Approach for training: Kleebauer, M., Marz, C., Reudenbach, C., & Braun, M. (2023). Multi-Resolution Segmentation of Solar Photovoltaic Systems Using Deep Learning. Remote Sensing, 15(24), 5687.
Code for training on GitHub: multi-resolution-pv-system-segmentation
Google Colab application to try it yourself (requires a Colab account!)
Software to run the application: Aszkowski, P., Ptak, B., Kraft, M., Pieczyński, D., & Drapikowski, P. (2023). Deepness: Deep neural remote sensing plugin for QGIS. SoftwareX, 23, 101495.
An overview of the model zoo for application: QGIS: Deepness: Deep neural remote sensing.
