Estimations of deforestation are crucial as increased levels of deforestation induce serious environmental problems. However, it is challenging to perform investigations over extensive areas, such as the Amazon rainforest, due to the vast size of the region and the difficulty of direct human access. Satellite imagery can be used as an effective solution to this problem; combining optical images with synthetic aperture radar (SAR) images enables deforestation monitoring over large areas irrespective of weather conditions. In this study, we propose a learning strategy for multi-modal deforestation estimations on this basis. Images from three different satellites, Sentinel-1, Sentinel-2, and Landsat 8, were utilized to this end. The proposed algorithm overcomes visibility limitations due to a long rainy season of the Amazon by creating a multi-modal dataset using supplementary SAR images, achieving high estimation accuracy. The dataset is composed of satellite data taken on a daily basis with relatively less monthly generated, ground truth masking data, which is called the many-to-one-mask condition. The Normalized Difference Vegetation Index and Normalized Difference Soil Index bands are selected to comprise the datasets. This yields better detection performance and a shorter training time than datasets consisting of RGB or all bands. Multiple deep neural networks are independently trained for each modality and an appropriate fusion method is developed to detect deforestation. The proposed method utilizes the distance similarity of the predicted deforestation rate to filter prediction results. The elements with high degrees of similarity are merged into the final result with average and denoising operations. The performances of five network variants of the U-Net family are compared, with Attention U-Net observed to exhibit the best prediction results. Finally, the proposed method is utilized to estimate the deforestation status of novel queries with high accuracy.

Coseismic surface ruptures are the ground truth of earthquake rupture along faults, and detailed mapping of earthquake surface ruptures provides an opportunity to understand the relationship between earthquakes and faults. One of the most effective tools for mapping earthquake surface ruptures is the use of remote sensing data such as high-resolution satellite imagery. This study proposes a crack detection model based on deep learning and analysis tools to extract the geometrical characteristics of surface rupture using high-resolution satellite imagery (Pléiades-1B) for an earthquake that occurred in the Bulnay region of Mongolia. By comparing the prediction result with a line map of the previous study [1], it was possible to confirm the reliability of the fault detection. The model achieved a rupture detection accuracy of approximately 90 % and extraction of characteristic features of crack error level of 5 % or less. To assess the broad applicability of the proposed model regardless of image size, we evaluated the model performance through quantitative and qualitative methods. The model accurately calculated essential characteristics such as the orientation and length of a diverse range of surface ruptures. These results confirm the general effectiveness of the proposed model in detecting and characterizing surface ruptures caused by earthquakes. The suggested model for automated target detection utilizing satellite imagery can serve as a fit-for-purpose solution for conducting field surveys and acquiring fundamental earthquake-related data. The proposed model can provide valuable insights into the aftermath of seismic events by identifying a range of surface ruptures and deformations induced by earthquakes.

SNUGLITE (Seoul National University Global navigation satellite system Laboratory satellITE) is a two-unit cube satellite (CubeSat) with dimensions 10 × 10 × 23 cm that requires an attitude system for missions and ground station telecommunication. A linear-quadratic-Gaussian-based optimal attitude system for the CubeSat platform has been developed using low-cost sensors, with the in-orbit verification of the attitude system being is one of main study objectives. Since launch, the SNUGLITE CubeSat has continuously broadcast in-orbit status information. In this study, a methodology for the analysis of in-orbit attitude estimation results using received data is presented, and this was achieved by comparing two sun-pointing vectors, i.e., the sun-pointing vector calculated using estimated attitude with the positions of the sun and the satellite and the reference vector generated by the power levels of the solar panels. Because the satellite position was required for the attitude analysis, the verification of the performance of the own-developed on-board Global Positioning System (GPS) receiver is also briefly described. Analyses indicate that the attitude estimation of the SNUGLITE CubeSat has achieved an in-orbit real-time pointing accuracy with a root mean square of 6.1°.

In recent years, research on increasing the spatial resolution and enhancing the quality of satellite images using the deep learning-based super-resolution (SR) method has been actively conducted. In a remote sensing field, conventional SR methods required high-quality satellite images as the ground truth. However, in most cases, high-quality satellite images are difficult to acquire because many image distortions occur owing to various imaging conditions. To address this problem, we propose an adaptive image quality modification method to improve SR image quality for the KOrea Multi-Purpose Satellite-3 (KOMPSAT-3). The KOMPSAT-3 is a high performance optical satellite, which provides 0.7-m ground sampling distance (GSD) panchromatic and 2.8-m GSD multi-spectral images for various applications. We proposed an SR method with a scale factor of 2 for the panchromatic and pan-sharpened images of KOMPSAT-3. The proposed SR method presents a degradation model that generates a low-quality image for training, and a method for improving the quality of the raw satellite image. The proposed degradation model for low-resolution input image generation is based on Gaussian noise and blur kernel. In addition, top-hat and bottom-hat transformation is applied to the original satellite image to generate an enhanced satellite image with improved edge sharpness or image clarity. Using this enhanced satellite image as the ground truth, an SR network is then trained. The performance of the proposed method was evaluated by comparing it with other SR methods in multiple ways, such as edge extraction, visual inspection, qualitative analysis, and the performance of object detection. Experimental results show that the proposed SR method achieves improved reconstruction results and perceptual quality compared to conventional SR methods.

Multitemporal synthetic aperture radar (SAR) images have been widely used for change detection and monitoring of the environment owing to their competency under all weather conditions. However, owing to speckle backgrounds and strong reflections, change detection in urban areas is challenging. In this study, to automatically extract changed objects, we developed a model that integrated change detection and object extraction in multiple Korean Multi-Purpose Satellite-5 (KOMPSAT-5) images. Initially, two arbitrary L1A-level SAR images were input into the proposed model, and after pre-processing, such as radio calibration and coordinate system processing, change detection was performed. Subsequently, the desired targets were automatically extracted from the change detection results. Finally, the model obtained images of the extraction targets and metadata, such as date and location. Noise was removed by applying scale-adaptive modification to the generated difference image during the change detection process, and the detection accuracy was improved by emphasizing the occurrence of the change. After polygonizing the pixel groups of the change detection map in the target extraction process, the morphology-based object filtering technique was applied to minimize the false detection rate. As a result of the proposed approach, the changed objects in the KOMPSAT-5 images were automatically extracted with 90% accuracy.

Deforestation in the Amazon rainforest is approaching historically worst levels, and accurate estimation of deforested areas is crucial to protect against further deforestation. In this letter, we propose a forest deforestation segmentation approach based on Mask2Former, which utilizes multisatellite information and an optimized backbone network. Particularly, we enable the determination of whether to use the corresponding optical imagery during the training phase based on the amount of cloud cover and applied a model to compensate for the resulting data sparsity. The model reflects deforestation occurrence information at specific points in time in the deforestation predictions at points in the same time series, thereby detecting deforestation with high accuracy while compensating for data shortages. In experiments, the proposed method achieved excellent performance, with a pixel accuracy of 91.1% and an F1 score of 88.8%. This method was validated by achieving the best segmentation performance for deforested areas in the official CVPR MultiEarth Workshop 2023 challenge.