Countrywide digital surface models and vegetation height models from historical aerial images

Abstract

Abstract. Historical aerial images, captured by film cameras in the previous century, are valuable resources for quantifying Earth's surface and landscape changes over time. In the post-war period, these images were often acquired to create topographic maps, resulting in the acquisition of large-scale aerial photographs with stereo coverage. Photogrammetric techniques applied to these stereo images enable the extraction of 3D information to reconstruct digital surface models (DSMs) and orthoimages. Here, we present a highly automated photogrammetric approach for generating countrywide DSMs of Switzerland, at a 1 m resolution, from approximately 32 000 scanned aerial stereo images acquired between 1979 and 2006, with known exterior and interior orientation. We derived four countrywide DSMs for the epochs 1979–1985, 1985–1991, 1991–1998, and 1998–2006. From the DSMs, we generated corresponding countrywide vegetation height models (VHMs). We assessed the quality of the historical DSMs at the country scale and within six representative study sites, evaluating the vertical accuracy and the completeness of image matching across different land cover types. Mean completeness ranged from 64 % for “glacial and perpetual snow” to 98 % for “sealed surfaces”, with a value of 93 % for the “closed forest” class. Across Switzerland, the median elevation accuracy of the historical DSMs compared with a reference digital terrain model (DTM) on sealed surface points ranged from 0.08 to 0.16 m, with a normalized median absolute deviation (NMAD) of around 0.8 m and a maximum root mean square error (RMSE) of 1.20 m. Similar accuracies are obtained when comparing historical DSMs with measured geodetic points. The VHMs generated in this study enabled the detection of major changes in forest areas due to windstorm damage, forest dynamics, and growth. This work demonstrates the feasibility of generating accurate, very-high-resolution DSM time series (spanning three decades) and VHMs from historical aerial images of the entire surface of Switzerland in a highly automated manner. The VHMs are already being used to estimate countrywide biomass changes. The countrywide DSMs and VHMs for the four epochs, along with auxiliary data, are available online at https://doi.org/10.16904/envidat.528 (Marty et al., 2024) and can be used to quantify long-term elevation changes and related processes across different surfaces.

Plant phenotyping relevance

歴史的航空画像から植生高モデルを生成する自動写真測量法を開発・精度評価し、森林の高さ変化という植物キャノピー形質を抽出しているため、測定法が中心的である。

Code and data availability

The paper's countrywide DSMs, VHMs, and auxiliary rasters (matching mask, vegetation mask, metadata shapefile) for four epochs are deposited publicly on EnviDat with an explicit DOI. These vegetation height models are the paper's plant/canopy phenotyping measurements. No author analysis code or trained models are named