Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Satellite Sunroof: High-res Digital Surface Models and Roof Segmentation for Global Solar Mapping

Vishal Batchu, Alex Wilson, Betty Peng, Carl Elkin, Umangi Jain, Christopher Van Arsdale, Ross Goroshin, Varun Gulshan

TL;DR

This paper tackles challenges involved in building a Digital Surface Model (DSM) and roof instance segmentation from lower resolution and single oblique views using deep learning models, and significantly enhances the Solar API's potential to promote solar adoption.

Abstract

The transition to renewable energy, particularly solar, is key to mitigating climate change. Google's Solar API aids this transition by estimating solar potential from aerial imagery, but its impact is constrained by geographical coverage. This paper proposes expanding the API's reach using satellite imagery, enabling global solar potential assessment. We tackle challenges involved in building a Digital Surface Model (DSM) and roof instance segmentation from lower resolution and single oblique views using deep learning models. Our models, trained on aligned satellite and aerial datasets, produce 25cm DSMs and roof segments. With ~1m DSM MAE on buildings, ~5deg roof pitch error and ~56% IOU on roof segmentation, they significantly enhance the Solar API's potential to promote solar adoption.

Satellite Sunroof: High-res Digital Surface Models and Roof Segmentation for Global Solar Mapping

TL;DR

This paper tackles challenges involved in building a Digital Surface Model (DSM) and roof instance segmentation from lower resolution and single oblique views using deep learning models, and significantly enhances the Solar API's potential to promote solar adoption.

Abstract

The transition to renewable energy, particularly solar, is key to mitigating climate change. Google's Solar API aids this transition by estimating solar potential from aerial imagery, but its impact is constrained by geographical coverage. This paper proposes expanding the API's reach using satellite imagery, enabling global solar potential assessment. We tackle challenges involved in building a Digital Surface Model (DSM) and roof instance segmentation from lower resolution and single oblique views using deep learning models. Our models, trained on aligned satellite and aerial datasets, produce 25cm DSMs and roof segments. With ~1m DSM MAE on buildings, ~5deg roof pitch error and ~56% IOU on roof segmentation, they significantly enhance the Solar API's potential to promote solar adoption.
Paper Structure (22 sections, 4 equations, 9 figures, 4 tables)

This paper contains 22 sections, 4 equations, 9 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Data
  3. Inputs, labels and pre-processing
  4. Dataset
  5. Methods
  6. Base model
  7. Refinement model
  8. Satellite Solar API pipeline
  9. Results and future work
  10. Data
  11. Human labeled roof segments
  12. Geometry based reprojection
  13. Distribution of train/val/test dataset splits
  14. Modeling
  15. Masking techniques for loss/metrics
  16. ...and 7 more sections

Figures (9)

  • Figure 1: Overview of inputs and outputs from our ML models. Both DSMs are visualized with a hillshade visualizer. A few sides of buildings are highlighted in the off-nadir satellite RGB with red ovals to emphasize the off-nadir nature of the image. Location: Ankara, Turkey.
  • Figure 2: Sample inputs and outputs from the Satellite Solar API pipeline. All outputs are nadir. Location: Brasilia, Brazil.
  • Figure 3: Human labeled roof segments visualization.
  • Figure 4: Geometry-based reprojection.
  • Figure 5: Geographical distribution of train, validation and test splits (in order). Red represents RGB+DSM data and blue represents RGB only data.
  • ...and 4 more figures