Deep learning model to detect solar panels from high resolution imagery. A brief summary of the item is not available. Add a brief summary about the item.
Deep learning package
from
Item created: May 28, 2021 Item updated: Dec 27, 2024 Number of downloads: 10,620
Description
Solar power is environment-friendly and is being promoted by government agencies and power distribution companies. Government agencies can use solar panel detection to offer incentives such as tax exemptions and credits to residents who have installed solar panels. Policymakers can use it to gauge adoption and frame schemes to spread awareness and promote solar power utilization in areas that lack its use. This information can also serve as an input to solar panel installation and utility companies and help redirect their marketing efforts.
Traditional ways of obtaining information on solar panel installation, such as surveys and on-site visits, are time-consuming and error-prone. Deep learning models are highly capable of learning complex semantics and can produce superior results. Use this deep learning model to automate the task of solar panel detection, reducing time and effort required significantly.
Using the model
Follow the guide to use the model. Before using this model, ensure that the supported deep learning libraries are installed. For more details, check Deep Learning Libraries Installer for ArcGIS.
Fine-tuning the model
This model can be fine-tuned using the Train Deep Learning Model tool. Follow the guide to fine-tune this model.
Input
High-resolution (5–15 cm) RGB imagery.
Output
Feature class containing detected solar panels.
Applicable geographies
The model is expected to work well in the United States.
Model architecture
The model uses the MaskRCNN model architecture implemented using ArcGIS API for Python.
Accuracy metrics
The model has an average precision score of 0.764.
Training data
This model has been trained on an Esri proprietary solar panel detection dataset.
Sample results
Here are a few results from the model.
An in-depth description of the item is not available.
Layers
Tools
Tables
Basemap
Project Contents:
Solution Contents
Contents
Layers
Screenshots
Terms of Use
No special restrictions or limitations on using the item's content have been provided.
Details
Dashboard views: Desktop
Source:
Creating data in:
Published as:
Other Views:
Dependent items in the recycle bin
Applicable: 2d
Size: 156.953 MB
ID: c2508d72f2614104bfcfd5ccf1429284
Image Count: 0
Image Properties
Layer Drawing
Using tiles from a cache
Dynamically from data
Share
Owner
Folder
Categories
This item has not been categorized.
Credits (Attribution)
No acknowledgements.Esri
Comments (11)
Will this consume credits to run?
Credits are consumed only when the model is run in ArcGIS Online or ArcGIS Enterprise.
This model does not work well with solar farms; would this be updated sometime to include solars farms.
At present, we have only these two pretrained models available for Solar Panels.
Tried the one mentioned below does not work well with high resolution imagery.
Hi, this model is trained to detect rooftop solar panels, we also have one more pretrained model - Solar Photovoltaic Park Classification - Global (https://www.arcgis.com/home/item.html?id=55600a3a452c4b208d3c54026c3f7cd1) which can be used for solar farms classification.
Hello there, I used this Deep Learning Package file to detect solar panels, but one particular quirk with this model is that it detects blue tarps, which are predominantly used in rural areas to cover wood, vehicles, and boats. My solar panel detection rate was 40-50% in a rural setting. The 90% or more confidence level is spot on and works pretty well. Also, I would leave out objects detected that are 4 square meters or less in area. I'm looking for ways to improve the accuracy and would volunteer to help in improving this model. Additionally, I'm looking to create a database of solar panels to be used in Deep Learning. Do DM me if interested. Thank you.
Hello, I receive a "bad zip file" error message when I try to load this DLPK as a pretrained model (in both ArcGIS Pro and Jupyter Notebook). The "Building Footprint Extraction - USA" DLPK does not produce this error message. Could you please test it on your end and upload a DLPK that works if necessary? Thank you.
@ptuteja_IVT thank you! It works for me.
@maja.kucharczyk_ucalgary Your issue is resolved. Thank you for using our models. Please let us know if you need any help!
To be more specific, I am trying to load this DLPK to perform further training, not inference.