solar-mapper
Global PV Panel mapping with Sentinel-2 data
MIT License
Global Solar Panel Mapper
Description
This repo attempts to continue and extend this work on mapping global solar panel locations, with creating updated maps of their locations since the end of the data in that paper to now on a continuous basis. The Solar PV Inventory used Sentinel-2 data as well as high-resolution satellite imagery to detect solar plants and panels. To try to eliminate the need for expensive high resolution imagery, this project uses the WorldStrat model for super-resolution of Sentinel-2 imagery instead. This project would most likely run on Microsoft's Planetary Computer as it already has the Sentinel-2 data with the STAC spec to easily query and use the imagery.
Another paper on the subject, with an accompanying dataset is this one.
How to run
Install dependencies
# clone project
git clone https://github.com/YourGithubName/your-repo-name
cd your-repo-name
# [OPTIONAL] create conda environment
conda create -n myenv python=3.9
conda activate myenv
# install pytorch according to instructions
# https://pytorch.org/get-started/
# install requirements
pip install -r requirements.txt
Train model with default configuration
# train on CPU
python src/train.py trainer=cpu
# train on GPU
python src/train.py trainer=gpu
Train model with chosen experiment configuration from configs/experiment/
python src/train.py experiment=experiment_name.yaml
You can override any parameter from command line like this
python src/train.py trainer.max_epochs=20 datamodule.batch_size=64