Given the large volume of remote sensing images collected daily, automatic object detection and segmentation have been a consistent need in Earth observation (EO). However, objects of interest vary in shape, size, appearance, and reflecting properties. This is not only reflected by the fact that these objects exhibit differences due to their geographical diversity but also by the fact that these objects appear differently in images collected from different sensors (optical and radar) and platforms (satellite, aerial, and unmanned aerial vehicles (UAV)). Although there exists a plethora of object detection methods in the area of remote sensing, given the very fast development of prevalent deep learning methods, there is still a lack of recent updates for object detection methods. In this paper, we aim to provide an update that informs researchers about the recent development of object detection methods and their close sibling in the deep learning era, instance segmentation. The integration of these methods will cover approaches to data at different scales and modalities, such as optical, synthetic aperture radar (SAR) images, and digital surface models (DSM). Specific emphasis will be placed on approaches addressing data and label limitations in this deep learning era. Further, we survey examples of remote sensing applications that benefited from automatic object detection and discuss future trends of the automatic object detection in EO.

Hyperspectral imaging is capable of capturing information beyond conventional RGB cameras; therefore, several applications of this have been found, such as material identification and spectral analysis. However, similar to many camera systems, most of the existing hyperspectral cameras are still passive imaging systems. Such systems require an external light source to illuminate the objects, to capture the spectral intensity. As a result, the collected images highly depend on the environment lighting and the imaging system cannot function in a dark or low-light environment. This work develops a prototype system for active hyperspectral imaging, which actively emits diverse single-wavelength light rays at a specific frequency when imaging. This concept has several advantages: first, using the controlled lighting, the magnitude of the individual bands is more standardized to extract reflectance information; second, the system is capable of focusing on the desired spectral range by adjusting the number and type of LEDs; third, an active system could be mechanically easier to manufacture, since it does not require complex band filters as used in passive systems. Three lab experiments show that such a design is feasible and could yield informative hyperspectral images in low light or dark environments: (1) spectral analysis: this system’s hyperspectral images improve food ripening and stone type discernibility over RGB images; (2) interpretability: this system’s hyperspectral images improve machine learning accuracy. Therefore, it can potentially benefit the academic and industry segments, such as geochemistry, earth science, subsurface energy, and mining.

Deriving LoD2 models from orthophoto and digital surface models (DSM) reconstructed from satellite images is a challenging task. Existing solutions are mostly system approaches that require complicated step-wise processes, including not only heuristic geometric operations, but also high-level steps such as machine learning-based semantic segmentation and building detection. Here in this paper, we describe an open-source tool, called SAT2LOD2, built based on a minorly modified version of our recently published work. SAT2LoD2 is a fully open-source and GUI (Graphics User Interface) based software, coded in Python, which takes an orthophoto and DSM as inputs, and outputs individual building models, and it can additionally take road network shapefiles, and customized classification maps to further improve the reconstruction results. We further improve the robustness of the method by 1) intergrading building segmentation based on HRNetV2 into our software; and 2) having implemented a decision strategy to identify complex buildings and directly generate mesh to avoid erroneous LoD2 reconstruction from a system point of view. The software can process a moderate level of data (around 5000*5000 size of orthophoto and DSM) using a PC with a graphics card supporting CUDA. Furthermore, the GUI is self-contained and stores the intermediate processing results facilitating researchers to learn the process easily and reuse intermediate files as needed. The updated codes and software are available under this GitHub page: https://github.com/GDAOSU/LOD2BuildingModel.

Intensifying fire regimes threaten forests globally ^1,2 , but the risk of persistent post-fire forest loss ^3,4 and its potential mitigation remains poorly quantified. We analyzed millions of wildfires worldwide from 2001 to 2024 and tracked recovery in satellite-observed forest structure and ecosystem function ^5,6 . Post-fire persistent forest loss, indicated by modeled non-recovery to pre-fire conditions over decadal timescales, affected 57.1% ± 1.4% (mean ± s.e.) of burned forest area globally since 2001, with hotspots in Pacific temperate and southern boreal forests. We then identified “crucial fires” as events exceeding a stringent modeled-risk probability threshold for persistent structural or functional non-recovery, with fire severity strongly predicting this loss. This severity dependence revealed a management pathway, as locations with prior low-severity fire experienced lower severity in subsequent wildfires ^7–9 and had lower modeled probability of becoming crucial. Under a model-based counterfactual scenario, applying the estimated severity attenuation was associated with a 7.6 ± 0.6% reduction; the top 1% of road-accessible areas accounted for 35% of this reduction. These results provide a global framework for identifying where wildfire threatens forest resistance and where targeted low-severity fire management like prescribed fire ^8,10 might be used to combat global forest loss.