Geospatial mapping of distribution grid with machine learning and publicly-accessible multi-modal data
Abstract Detailed and location-aware distribution grid information is a prerequisite for various power system applications such as renewable energy integration, wildfire risk assessment, and infrastructure planning. However, a generalizable and scalable approach to obtain such information is still l...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-08-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-023-39647-3 |
| _version_ | 1797557868864471040 |
|---|---|
| author | Zhecheng Wang Arun Majumdar Ram Rajagopal |
| author_facet | Zhecheng Wang Arun Majumdar Ram Rajagopal |
| author_sort | Zhecheng Wang |
| collection | DOAJ |
| description | Abstract Detailed and location-aware distribution grid information is a prerequisite for various power system applications such as renewable energy integration, wildfire risk assessment, and infrastructure planning. However, a generalizable and scalable approach to obtain such information is still lacking. In this work, we develop a machine-learning-based framework to map both overhead and underground distribution grids using widely-available multi-modal data including street view images, road networks, and building maps. Benchmarked against the utility-owned distribution grid map in California, our framework achieves > 80% precision and recall on average in the geospatial mapping of grids. The framework developed with the California data can be transferred to Sub-Saharan Africa and maintain the same level of precision without fine-tuning, demonstrating its generalizability. Furthermore, our framework achieves a R2 of 0.63 in measuring the fraction of underground power lines at the aggregate level for estimating grid exposure to wildfires. We offer the framework as an open tool for mapping and analyzing distribution grids solely based on publicly-accessible data to support the construction and maintenance of reliable and clean energy systems around the world. |
| first_indexed | 2024-03-10T17:22:24Z |
| format | Article |
| id | doaj.art-5ca6def292754186a353c131a433def7 |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-03-10T17:22:24Z |
| publishDate | 2023-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-5ca6def292754186a353c131a433def72023-11-20T10:16:51ZengNature PortfolioNature Communications2041-17232023-08-0114111110.1038/s41467-023-39647-3Geospatial mapping of distribution grid with machine learning and publicly-accessible multi-modal dataZhecheng Wang0Arun Majumdar1Ram Rajagopal2Department of Civil & Environmental Engineering, Stanford UniversityDepartment of Mechanical Engineering, Stanford UniversityDepartment of Civil & Environmental Engineering, Stanford UniversityAbstract Detailed and location-aware distribution grid information is a prerequisite for various power system applications such as renewable energy integration, wildfire risk assessment, and infrastructure planning. However, a generalizable and scalable approach to obtain such information is still lacking. In this work, we develop a machine-learning-based framework to map both overhead and underground distribution grids using widely-available multi-modal data including street view images, road networks, and building maps. Benchmarked against the utility-owned distribution grid map in California, our framework achieves > 80% precision and recall on average in the geospatial mapping of grids. The framework developed with the California data can be transferred to Sub-Saharan Africa and maintain the same level of precision without fine-tuning, demonstrating its generalizability. Furthermore, our framework achieves a R2 of 0.63 in measuring the fraction of underground power lines at the aggregate level for estimating grid exposure to wildfires. We offer the framework as an open tool for mapping and analyzing distribution grids solely based on publicly-accessible data to support the construction and maintenance of reliable and clean energy systems around the world.https://doi.org/10.1038/s41467-023-39647-3 |
| spellingShingle | Zhecheng Wang Arun Majumdar Ram Rajagopal Geospatial mapping of distribution grid with machine learning and publicly-accessible multi-modal data Nature Communications |
| title | Geospatial mapping of distribution grid with machine learning and publicly-accessible multi-modal data |
| title_full | Geospatial mapping of distribution grid with machine learning and publicly-accessible multi-modal data |
| title_fullStr | Geospatial mapping of distribution grid with machine learning and publicly-accessible multi-modal data |
| title_full_unstemmed | Geospatial mapping of distribution grid with machine learning and publicly-accessible multi-modal data |
| title_short | Geospatial mapping of distribution grid with machine learning and publicly-accessible multi-modal data |
| title_sort | geospatial mapping of distribution grid with machine learning and publicly accessible multi modal data |
| url | https://doi.org/10.1038/s41467-023-39647-3 |
| work_keys_str_mv | AT zhechengwang geospatialmappingofdistributiongridwithmachinelearningandpubliclyaccessiblemultimodaldata AT arunmajumdar geospatialmappingofdistributiongridwithmachinelearningandpubliclyaccessiblemultimodaldata AT ramrajagopal geospatialmappingofdistributiongridwithmachinelearningandpubliclyaccessiblemultimodaldata |