Photovoltaic (PV) energy generation plays a crucial role in the energy transition. Small-scale, rooftop PV installations are deployed at an unprecedented pace, and their safe integration into the grid requires up-to-date, high-quality information. Overhead imagery is increasingly being used to improve the knowledge of rooftop PV installations with machine learning models capable of automatically mapping these installations. However, these models cannot be reliably transferred from one region or imagery source to another without incurring a decrease in accuracy. To address this issue, known as distribution shift, and foster the development of PV array mapping pipelines, we propose a dataset containing aerial images, segmentation masks, and installation metadata (i.e., technical characteristics). We provide installation metadata for more than 28000 installations. We supply ground truth segmentation masks for 13000 installations, including 7000 with annotations for two different image providers. Finally, we provide installation metadata that matches the annotation for more than 8000 installations. Dataset applications include end-to-end PV registry construction, robust PV installations mapping, and analysis of crowdsourced datasets.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9884299 | PMC |
| http://dx.doi.org/10.1038/s41597-023-01951-4 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A graph neural architecture search approach for identifying bots in social media.
Front Artif Intell
December 2024
Decision Support Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece.
Social media platforms, including X, Facebook, and Instagram, host millions of daily users, giving rise to bots automated programs disseminating misinformation and ideologies with tangible real-world consequences. While bot detection in platform X has been the area of many deep learning models with adequate results, most approaches neglect the graph structure of social media relationships and often rely on hand-engineered architectures. Our work introduces the implementation of a Neural Architecture Search (NAS) technique, namely Deep and Flexible Graph Neural Architecture Search (DFG-NAS), tailored to Relational Graph Convolutional Neural Networks (RGCNs) in the task of bot detection in platform X.
View Article and Find Full Text PDFPod5Viewer: a GUI for inspecting raw nanopore sequencing data.
Bioinformatics
November 2024
Institute of Pharmaceutical and Biomedical Sciences, Johannes Gutenberg-University Mainz, Mainz, 55128, Germany.
Motivation: Oxford Nanopore Technologies recently adopted the POD5 file format for storing raw nanopore sequencing data. The information stored in these files provides detailed insights into the sequencing features and enhances the understanding of raw nanopore data. However, the process of visualizing the data can be cumbersome, especially for users without programming skills.
View Article and Find Full Text PDF3-axis computer numerical control machine positioning error dataset for thermal error compensation.
Data Brief
December 2024
University Center of Mauá Institute of Technology, Praça Mauá 1, São Caetano do Sul, São Paulo 09580-900, Brazil.
This article reports on a comprehensive dataset detailing positioning errors in a 3-axis milling center machine (MCM) with computer numerical control (CNC) specifically curated for thermal error compensation. The data, which includes separate datasets for the X, Y, and Z axes, was collected through systematic measurements using an interferometric laser (IL) system under monitored thermal conditions. Each axis's acquisition was recorded with a resolution to capture dynamic variations influenced by thermal fluctuations.
View Article and Find Full Text PDFExisting evidence on the effects of photovoltaic panels on biodiversity: a systematic map with critical appraisal of study validity.
Environ Evid
November 2023
PatriNat (OFB (Office Français de la Biodiversité) - MNHN (Muséum National d'Histoire Naturelle)), 75005, Paris, France.
Background: To phase out fossil fuels and reach a carbon-neutral future, solar energy and notably photovoltaic (PV) installations are being rapidly scaled up. Unlike other types of renewable energies such as wind and hydroelectricity, evidence on the effects of PV installations on biodiversity has been building up only fairly recently and suggests that they may directly impact ecosystems and species through, for instance, habitat change and loss, mortality, behaviour alteration or population displacements. Hence, we conducted a systematic map of existing evidence aiming at answering the following question: what evidence exists regarding the effects of PV installations on wild terrestrial and semi-aquatic species?
Methods: We searched for relevant citations on four online publication databases, on Google Scholar, on four specialised websites and through a call for grey literature.
Evidence on the ecological and physical effects of built structures in shallow, tropical coral reefs: a systematic map.
Environ Evid
May 2024
National Centers for Coastal Ocean Science, National Ocean Service, National Oceanic and Atmospheric Administration, 101 Pivers Island Road, Beaufort, NC, 28516, USA.
Article Synopsis
- Shallow tropical coral reefs are under threat from climate change, coastal development, pollution, and physical disturbances, prompting efforts to restore these ecosystems using built structures.
- Restoration practitioners are increasingly employing various types of built structures, including artificial and natural interventions, but there is a lack of synthesized evidence on their effectiveness in enhancing coral growth and survival.
- To address this knowledge gap, a systematic review was conducted to map global evidence on the performance of these built structures in shallow tropical coral ecosystems across contexts like restoration and coastal protection.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!