Loosdorf-MSL dataset: multispectral LiDAR data for LULC classification, supporting current and prospective European NMCAs' schemes

Dataset Characteristics The Loosdorf-MSL dataset was acquired in October 2023 using a commercial MS airborne LiDAR system, RIEGL VQ-1560i-DW, operating at green (532 nm) and NIR (1064 nm) wavelengths over the village of Loosdorf and the city of Melk in Lower Austria. The Loosdorf-MSL dataset covers 1.7 km 2 of suburban and forested landscapes and comprises 103,238,318 manually labeled points categorized into eight and 20 classes, which are used for training and evaluating DL models.

Table 1 reports the specifications of the Loosdorf-MSL dataset. Photogrammetric point clouds and orthophotos (at 20 cm resolution) are generated by dense image matching using SURE nFrames and are provided in the Loosdorf-MSL dataset as auxiliary data to support future multimodal data integration studies. It is worth noting that the photogrammetric data do not cover the val4 plot.

For further information on Loosdorf-MSL data, please refer to our paper mentioned in Section 5. To check the LAZ files, LiDAR processing software like CloudCompare and OPALS can be used. We recommend QGIS software for checking orthophotos.

Table 1. Specifications of the Loosdorf-MSL dataset. MS LiDAR system Wavelength Point density (point/m2) Pulse repetition rate (kHz) Laser beam divergence (mrad) Flight altitude (m) VQ-1560i-DW 532 nm 9.1 1000 2.2 700 m 1064 nm 14.7 1000 0.3 2.1 LiDAR Data Attributes In addition to the spatial coordinates, the LiDAR point cloud includes eight attributes, summarized in Table 2, of which three are spectral.

Table 2. LiDAR point cloud attributes. Attribute Description Green Green reflectance normalized between 0 and 1 NIR NIR reflectance normalized between 0 and 1 VI Vegetation index, pseudo normalized difference vegetation index (pNDVI) NormalizedZ Normalized height Return_Number Return number Number_Of_Returns Number of returns GT_L1 Ground truth at L1 (current needs of NMCAs), classes 0-7 GT_L2 Ground truth at L2 (NMCAs’ prospective requirements), classes 0–19 3.

Annotation Procedure and Labels Definition Point clouds are manually annotated using CloudCompare software by three annotators. To ensure the accuracy of the annotated point clouds, the annotations are verified using auxiliary photogrammetric point clouds and field survey data. In addition, the annotation quality is further ensured through multiple rounds of independent visual inspection by the authors of the correlated paper to verify label consistency and minimize potential misannotations.

In the Loosdorf-MSL dataset, LULC classes are defined based on the current (GT_L1) and prospective (GT_L2) ALS-based LULC classification schemes of NMCAs. Table 3 provides descriptions of the semantic categories included in the Loosdorf-MSL dataset at both levels. The Loosdorf-MSL dataset is divided into training, testing, and validation plots using a 71:17:12 ratio.

This division maintains geographical independence among the training, validation, and testing sets as much as possible while ensuring that all classes at both levels of detail are represented in each subset whenever feasible. The dataset includes a total of 15 plots, of which six are used for training, four are used for testing, and the remaining plots are used for validation. Table 3.

Description of the semantic labels available in the Loosdorf-MSL dataset. Label ID GT_L1 GT_L2 0 Ground Asphalt 1 Water Soil 2 Low vegetation Road 3 Medium vegetation Water 4 High vegetation Low vegetation 5 Building Medium vegetation 6 Bridge High vegetation 7 Other Roof 8 NA Façade 9 NA Chimney/roof objects 10 NA Solar panel 11 NA Vehicle 12 NA Electric tower 13 NA Cable 14 NA Pole 15 NA Bridge 16 NA Fence/wall 17 NA Sport area 18 NA Road marking 19 NA Other 4.

What makes the Loosdorf-MSL dataset unique? The following characteristics make Loosdorf-MSL a unique dataset: Multimodal data integration: Combines multispectral LiDAR data with multispectral aerial imagery. Hierarchical annotations: Provides ground-truth annotations at two levels of detail.

Operationally relevant LULC classification: Annotations follow the NMCA's current (L1) and prospective (L2, fine-grained) LULC classification schemes. High geometric accuracy: LiDAR and photogrammetric data are precisely georeferenced and co-registered through a hybrid adjustment procedure, ensuring spatial consistency between the two data sources. Large spatial coverage: Covers approximately 1.7 km² , enabling the development and evaluation of data-intensive deep learning methods.

A summary comparing the Loosdorf-MSL with other relevant benchmark datasets for LULC classification is presented in the Table 4. Table 4. Comparison of the Loosdorf-MSL benchmark dataset with other suburban/urban MS LiDAR benchmark datasets.

MS LiDAR datasets are marked with *. Benchmark dataset Sensors Number of classes Spatial size (km 2 ) Point density (points/m 2 ) Labeled points (millions) Channels LULC scheme Auxiliary data *DFC2018 Optech Titan, ALS 20 5 15 NA 1550 nm, 1064 nm, and 532 nm ✕ RGB and hyperspectral orthophotos DublinCity ALS 13 2 250-348 260 1064 nm ✕ NA Hessigheim ULS 11 0.08 800 125 1064 nm ✕ Photogrammetric point clouds (RGB) WHU3D ALS + MLS 37 0.0065 35 393 1064 nm ✕ NA TerLiDAR ALS 11 51.4 8-16 692 1064 nm ✕ Photogrammetric point clouds (RGBI) *FGI-EMIT HeliALS- TW, ALS 5 0.04 1660 60 1550 nm, 905 nm, and 532 nm ✕ NA *Loosdorf- MSL (ours) VQ-1560i- DW, ALS 8/20 1.7 47.1 103 1064 nm and 532 nm NMCAs Hybrid adjusted photogrammetric point clouds and RGB orthophotos 5.

Citation

Any work using the data should cite the following paper: Takhtkeshha, N., Rizaldy, A., Hollaus, M., Hyyppä, J., Remondino, F., Mandlburger, G., 2026. Loosdorf-MSL: Benchmarking deep learning models for European NMCAs’ LULC schemes with multispectral LiDAR. ISPRS Open Journal of Photogrammetry and Remote Sensing , 100154. doi.org/10.1016/j.ophoto.2026.100154 .