Rapid technological advances in airborne hyperspectral and lidar systems paved the way for using machine learning algorithms to map urban environments. Both hyperspectral and lidar systems can discriminate among many significant urban structures and materials properties, which are not recognizable by applying conventional RGB cameras. In most recent years, the fusion of hyperspectral and lidar sensors has overcome challenges related to the limits of active and passive remote sensing systems, providing promising results in urban land cover classification. This paper presents principles and key features for airborne hyperspectral imaging, lidar, and the fusion of those, as well as applications of these for urban land cover classification. In addition, machine learning and deep learning classification algorithms suitable for classifying individual urban classes such as buildings, vegetation, and roads have been reviewed, focusing on extracted features critical for classification of urban surfaces, transferability, dimensionality, and computational expense.

Technological innovations and advanced multidisciplinary research increase the demand for multisensor data fusion in Earth observations. Such fusion has great potential, especially in the remote sensing field. One sensor is often insufficient in analyzing urban environments to obtain comprehensive results. Inspired by the capabilities of hyperspectral and Light Detection and Ranging (LiDAR) data in multisensor data fusion at the feature level, we present a novel approach to the multitemporal analysis of urban land cover in a case study in Høvik, Norway. Our generic workflow is based on bitemporal datasets; however, it is designed to include datasets from other years. Our framework extracts representative endmembers in an unsupervised way, retrieves abundance maps fed into segmentation algorithms, and detects the main urban land cover classes by implementing 2D ResU-Net for segmentation without parameter regularizations and with effective optimization. Such segmentation optimization is based on updating initial features and providing them for a second iteration of segmentation. We compared segmentation optimization models with and without data augmentation, achieving up to 11% better accuracy after segmentation optimization. In addition, a stable spectral library is automatically generated for each land cover class, allowing local database extension. The main product of the multitemporal analysis is a map update, effectively detecting detailed changes in land cover classes.

The integration of imaging spectroscopy and aeromagnetics provides a cost-effective and promising way to extend the initial analysis of a mineral deposit. While imaging spectroscopy retrieves surface spectral information, magnetic responses are used to determine magnetization at both shallower and greater depths using 2D and 3D modeling. Integration of imaging spectroscopy and magnetics improves upon knowledge concerning lithology with magnetic properties, enhances understanding of the geological origin of magnetic anomalies, and is a promising approach for analyzing a prospective area for minerals having a high iron-bearing content. To combine iron diagnostic information from airborne hyperspectral and magnetic data, we (a) used an iron absorption feature ratio to model pseudo-magnetic responses and compare them with the measured magnetic data and (b) estimated the apparent susceptibility along the surface by some equivalent source modeling, and compared them with iron ratios along the surface. For this analysis, a Modified Iron Feature Depth index was developed and compared to the surface geochemistry of the rock samples in order to validate the spectral information of iron. The comparison revealed a linear increase in iron absorption feature depths with iron content. The analysis was performed by empirically modeling the statistical relationship between the diagnostic absorption features of hyperspectral (HS) image spectra of selected rock samples and their corresponding geochemistry. Our results clearly show a link between the spectral absorption features and the magnetic response from iron-bearing ultra/-mafic rocks. The iron absorption feature ratio of Fe³⁺/Fe²⁺ integrated with aeromagnetic data (residual magnetic anomaly) allowed us to distinguish main rock types based on physical properties. This separation matches the lithology of the Niaqornarssuit complex, our study area in West Greenland.

Multisensor data fusion has become a hot topic in the remote sensing research community. This is thanks to significant technological advances and the ability to extract information that would have been challenging with a single sensor. However, sensory enhancement requires advanced analysis that enables deep learning. A framework is designed to effectively fuse hyperspectral and lidar data for semantic segmentation in the urban environment. Our work proposes a method of reducing dimensions by exploring the most representative features from hyperspectral and lidar data and using them for supervised semantic segmentation. In addition, we chose to compare segmentation models based on 2D and 3D convolutional operations with two different model architectures, such as U-Net and ResU-Net. All algorithms have been tested with three loss functions: standard Categorical Cross-Entropy, Focal Loss and a combination of Focal Loss and Jaccard Distance—Focal–Jaccard Loss. Experimental results demonstrated that the 3D segmentation of U-Net and ResU-Net with Focal and Focal–Jaccard Loss functions had significantly improved performance compared to the standard Categorical Cross-Entropy models. The results show a high accuracy score and reflect reality by preserving the complex geometry of the objects.