Multi-Resolution Segmentation of Solar Photovoltaic Systems Using Deep Learning - DeepLabV3 ResNet101 Model

The models weights shared here corresponds to the research detailed in the article Kleebauer, M.; Marz, C.; Reudenbach, C.; Braun, M. Multi-Resolution Segmentation of Solar Photovoltaic Systems Using Deep Learning. Remote Sens. 2023, 15, 5687. The following abstract briefly describes the article: 

In the realm of solar photovoltaic system image segmentation, existing deep learning networks focus almost exclusively on single image sources both in terms of sensors used and image resolution. This often prevents the wide deployment of such networks. Our research introduces a novel approach to train a network on a diverse range of image data, spanning UAV, aerial, and satellite imagery at both native and aggregated resolutions of 0.1 m, 0.2 m, 0.3 m, 0.8 m, 1.6 m, and 3.2 m. Using extensive hyperparameter tuning, we first determined the best possible parameter combinations for the network based on the DeepLabV3 ResNet101 architecture. We then trained a model using the wide range of different image sources. The final network offers several advantages. It outperforms networks trained with single image sources in multiple test applications as measured by the F1-Score (95.27%) and IoU (91.04%). The network is also able to work with a variety of target imagery due to the fact that a diverse range of image data was used to train it. The model is made freely available for further applications. 

The model is a DeepLabV3 ResNet101 model with approx. 61 million model parameters and 258.7 GFLOPS. Trained with Python 3.10, Torch 1.14.0, and Torchvision 0.15.0, the configurations of the final model are summarized below. BCE loss was used as the loss function, Adam as the optimizer, 0.0001 as the learning rate, a batch size of 8, 100 epochs, and a stride of 2. The ASSP segmentation head was set to 2048 input channels and 12, 24, and 36 dilation rates. 

A test application can be found on Google Colab. Further details on the model, training and validation can be found in the Article and on Github.