Estimate the building height at a 10-meter resolution based on Sentinel data

TL;DR

This study developed a high-resolution (10m) building height estimation method using Sentinel-1 and Sentinel-2 data, shape data, and advanced machine learning techniques, achieving accurate results with an R-squared of 0.78.

Contribution

It introduces a novel multi-source feature database and a stable feature selection process for high-resolution building height estimation using random forest models.

Findings

Achieved R-squared of 0.78 in building height prediction.

Demonstrated effective integration of SAR, optical, and shape data.

Compared ensemble methods, finding the best performance with the chosen approach.

Abstract

Building height is an important indicator for scientific research and practical application. However, building height products with a high spatial resolution (10m) are still very scarce. To meet the needs of high-resolution building height estimation models, this study established a set of spatial-spectral-temporal feature databases, combining SAR data provided by Sentinel-1, optical data provided by Sentinel-2, and shape data provided by building footprints. The statistical indicators on the time scale are extracted to form a rich database of 160 features. This study combined with permutation feature importance, Shapley Additive Explanations, and Random Forest variable importance, and the final stable features are obtained through an expert scoring system. This study took 12 large, medium, and small cities in the United States as the training data. It used moving windows to aggregate the pixels to solve the impact of SAR image displacement and building shadows. This study built a building height model based on a random forest model and compared three model ensemble methods of bagging, boosting, and stacking. To evaluate the accuracy of the prediction results, this study collected Lidar data in the test area, and the evaluation results showed that its R-Square reached 0.78, which can prove that the building height can be obtained effectively. The fast production of high-resolution building height data can support large-scale scientific research and application in many fields.