Search

The risk and damage of wildfires have been increasing due to various reasons including climate change, and the Republic of Korea is no exception to this situation. Burned area mapping is crucial not only to prevent further damage but also to manage burned areas. Burned area mapping using satellite data, however, has been limited by the spatial and temporal resolution of satellite data and classification accuracy. This article presents a new burned area mapping method, by which damaged areas can be mapped using semantic segmentation. For this research, PlanetScope imagery that has high-resolution images with very short revisit time was used, and the proposed method is based on U-Net which requires a unitemporal PlanetScope image. The network was trained using 17 satellite images for 12 forest fires and corresponding label images that were obtained semiautomatically by setting threshold values. Band combination tests were conducted to produce an optimal burned area mapping model. The results demonstrated that the optimal and most stable band combination is red, green, blue, and near infrared of PlanetScope. To improve classification accuracy, Normalized Difference Vegetation Index, dissimilarity extracted from Gray-Level Co-Occurrence Matrix, and Land Cover Maps were used as additional datasets. In addition, topographic normalization was conducted to improve model performance and classification accuracy by reducing shadow effects. The F1 scores and overall accuracies of the final image segmentation models are ranged from 0.883 to 0.939, and from 0.990 to 0.997, respectively. These results highlight the potential of detecting burned areas using the deep learning based approach.

Abstract Sea surface temperature (SST) is crucial for understanding the physical characteristics and ecosystems of coastal seas. SST varies near the tidal flat, where exposure and flood recur according to the tidal cycle. However, the variability of SST near the tidal flat is poorly understood owing to difficulties in making in-situ observations. The high resolution of Landsat 8 enabled us to determine the variability of SST near the macro tidal flat. The spatial distribution of the SST extracted from Landsat 8 changed drastically. The seasonal SST range was higher near the tidal flat than in the open sea. The maximum seasonal range of coastal SST exceeded 23 °C, whereas the range in the open ocean was approximately 18 °C. The minimum and maximum horizontal SST gradients near the tidal flat were approximately − 0.76 °C/10 km in December and 1.31 °C/10 km in June, respectively. The heating of sea water by tidal flats in spring and summer, and cooling in the fall and winter might result in a large horizontal SST gradient. The estimated heat flux from the tidal flat to the seawater based on the SST distribution shows seasonal change ranging from − 4.85 to 6.72 W/m2.

Enhancement of vessel detection performance in synthetic aperture radar (SAR) images generated academic advancements related to amelioration of the algorithmic accuracy and training data procurement. For practical implementation of vessel detection algorithm to maritime surveillance, however, presentation of authentic position of vessels was essential. Accordingly, this article aimed to propose an algorithm, which demonstrated realistic and azimuth shift-corrected position of vessel, especially out of conventional vessel monitoring apparatus: automated identification system (AIS) and vessel-pass (VPASS) information. Two different analyses regarding the vessel detection output utilization were, therefore, presented. Primary analysis demonstrated a vessel identification algorithm, comparing the vessel detection output with elaborately preprocessed AIS and VPASS information, which indicated the discrete position and velocity of vessel. The other presented a position restoration algorithm via i) velocity estimator complementing the conventional fractional Fourier transform velocity estimation analysis, while investigating the effect of range acceleration in deriving the azimuth velocity and ii) measuring the vessel orientation angle from Radon transform. Both algorithms were implemented to the vessel detection output in Cosmo-SkyMed SAR images, depicting an enhanced accuracy compared to the conventional algorithm both in velocity estimation and azimuth shift estimation; velocity offset reduced from 1.64 m/s to 1.29 m/s and average azimuth shift offset reduced from 70.75 m to 62.39 m. The presented algorithms would be decisive in terms of practicality if robustly attached to convolutional neural network-based vessel detection algorithms demonstrating ideal detection performances.

Tidal flats are internationally protected areas because of their environmental, geological, and economic value. Nevertheless, these are areas where casualties are common among visitors. To ensure the safety of visitors, efforts must be made to understand the geomorphologic characteristics of tidal flats. It is necessary to use three-dimensional (3-D) topographic data to clearly determine when an exposed tidal flat rapidly disappears as a result of periodic tidal fluctuations. Digital elevation models (DEMs) created using unmanned aerial vehicle (UAV) imaging and commercial photogrammetric software to measure tidal flats are produced using ground control points (GCPs). It is difficult to conduct field surveys and readings of image coordinates that correspond to these because tidal flat areas are difficult to access. The distribution of GCPs affects the accuracy of a DEM because the entire test region cannot be covered during a survey. Without GCPs, the DEM generated with the UAV images and photogrammetric software using the structure from the motion technique probably has nonlinear distortion such as a bowl shape. This article proposes a practical method of least-squares 3-D surface matching with a polynomial model (LS3D-PM) to correct a distorted DEM. For this LS3D-PM matching, a global TanDEM-X DEM was used instead of a field survey to collect the GCPs in a tidal flat. Practical testing was conducted using the proposed method. The root-mean-square error with respect to the height decreased from approximately 1.0 to 0.1 m, and the bowl-effect error was eliminated. With the DEM corrected using the proposed method and the classified orthoimages, the exposed tidal flat changes due to seawater invasion were estimated at different times during flood tide. This method has nontrivial technical values for quick and relatively precise DEM generations at a low cost compared to that of other techniques, particularly in emergency situations such as tsunamis, landslides, and earthquakes.

This manuscript presents a self-interferometric phase analysis technique for sea surface observation using a single scatterometer system. The self-interferometric phase is proposed to complement the imprecise analysis results due to the very meager signal strength measured at a high incident angle of more than 30°, which is a vulnerability of the existing analysis method using the Doppler frequency based on the backscattered signal strength. Moreover, compared to conventional interferometry, it is characterized by the phase-based analysis using consecutive signals from a single scatterometer system without any auxiliary system or channel. To apply the interferometric signal process on the moving sea surface observation, it is necessary to secure a reference target; however, this is hard to solve in practice. Hence, we adopted the back-projection algorithm to project the radar signals onto a fixed reference position above the sea surface, where the theoretical model for extracting the self-interferometric phase was derived from the radar-received signal model applying the back-projection algorithm. The observation performance of the proposed method was verified using the raw data collected at the Ieodo Ocean Research Station in Republic of Korea. In the observation result for wind velocity at the high incident angles of 40° and 50°, the self-interferometric phase analysis technique shows a better performance of a correlation coefficient of more than about 0.779 and an RMSE (root-mean-square error) of about 1.69 m/s compared to the existing method of a correlation coefficient of less than 0.62 and RMSE of more than 2.46 m/s.

Human civilization is rapidly developing thanks to the spread of geospatial technology and artificial intelligence [...]

Satellite-based flood monitoring for providing visual information on the targeted areas is crucial in responding to and recovering from river floods. However, such monitoring for practical purposes has been constrained mainly by obtaining and analyzing satellite data, and linking and optimizing the required processes. For these purposes, we present a deep learning-based flood area extraction model for a fully automated flood monitoring system, which is designed to continuously operate on a cloud-based computing platform for regularly extracting flooded area from Sentinel-1 data, and providing visual information on flood situations with better image segmentation accuracy. To develop the new flood area extraction model using deep learning, initial model tests were performed more than 500 times to determine optimal hyperparameters, water ratio, and best band combination. The results of this research showed that at ‘waterbody ratio 30%’, which yielded higher segmentation accuracies and lower loss, precision, overall accuracy, IOU, recall, and F1 score of ‘VV, aspect, topographic wetness index, and buffer input bands’ were 0.976, 0.956, 0.894, 0.964, and 0.970, respectively, and averaged inference time was 744.3941 s, which demonstrate improved image segmentation accuracy and reduced processing time. The operation and robustness of the fully automated flood monitoring system were demonstrated by automatically segmenting 12 Sentinel-1 images for the two major flood events in Republic of Korea during 2020 and 2022 in accordance with the hyperparameters, waterbody ratio, and band combinations determined through the intensive tests. Visual inspection of the outputs showed that misclassification of constructed facilities and mountain shadows were extremely reduced. It is anticipated that the fully automated flood monitoring system and the deep leaning-based waterbody extraction model presented in this research could be a valuable reference and benchmark for other countries trying to build a cloud-based flood monitoring system for rapid flood monitoring using deep learning.

A multifunctional scatterometer system and optimized radar signal processing for simultaneous observation of various physical oceanographic parameters are described in this paper. Existing observation methods with microwave remote sensing techniques generally use several separate systems such as scatterometer, altimeter, and Doppler radar for sea surface monitoring, which are inefficient in system operation and cross-analysis of each observation data. To improve this point, we integrated separate measurement functions into a single observation system by adding a measurement function of Doppler frequency to the existing system. So it enables to simultaneously measure the range and polarimetric responses of backscattering as well as movements of the sea surface. Here, the simultaneous measurement function of Doppler frequency was implemented by sampling an FMCW (frequency modulated continuous wave) radar signal as 2D raw data consisting of fast- and slow-time samples, i.e., the range and backscattering of radar target signals are analyzed from the fast-time samples while the Doppler frequency by the radar target’s movement extracts from the slow-time samples. Through the Fourier transformed-based range-Doppler signal process, distance (R), backscattering (σ°), and Doppler frequency (fD) are sequentially extracted from the 2D raw data, and a correlation to the physical oceanographic parameters is analyzed. Operability of the proposed system was examed through total 3 times of field campaigns from June 2017 to August 2020 and the observation data retrieved by the radar measurement data (R, σ°, fD) was also cross-analyzed with in-situ data: e.g., tide, significant wave height, and wind speed and direction. Differences in the comparative results as an observational accuracy are as follows. Tidal level (Root Mean Square Error 0.169 m (R)), significant wave height (RMSE 0.127 m (R), 0.362 m (σ°)), wind speed (RMSE 1.880 m/s (fD), 2.094 m/s (σ°)) and direction (18.84° (fD)).

Deep learning is a promising method for image classification, including satellite images acquired by various sensors. However, the synergistic use of geospatial data for water body extraction from Sentinel-1 data using deep learning and the applicability of existing deep learning models have not been thoroughly tested for operational flood monitoring. Here, we present a novel water body extraction model based on a deep neural network that exploits Sentinel-1 data and flood-related geospatial datasets. For the model, the U-Net was customised and optimised to utilise Sentinel-1 data and other flood-related geospatial data, including digital elevation model (DEM), Slope, Aspect, Profile Curvature (PC), Topographic Wetness Index (TWI), Terrain Ruggedness Index (TRI), and Buffer for the Southeast Asia region. Testing and validation of the water body extraction model was applied to three Sentinel-1 images for Vietnam, Myanmar, and Bangladesh. By segmenting 384 Sentinel-1 images, model performance and segmentation accuracy for all of the 128 cases that the combination of stacked layers had determined were evaluated following the types of combined input layers. Of the 128 cases, 31 cases showed improvement in Overall Accuracy (OA), and 19 cases showed improvement in both averaged intersection over union (IOU) and F1 score for the three Sentinel-1 images segmented for water body extraction. The averaged OA, IOU, and F1 scores of the ‘Sentinel-1 VV’ band are 95.77, 80.35, and 88.85, respectively, whereas those of ‘band combination VV, Slope, PC, and TRI’ are 96.73, 85.42, and 92.08, showing improvement by exploiting geospatial data. Such improvement was further verified with water body extraction results for the Chindwin river basin, and quantitative analysis of ‘band combination VV, Slope, PC, and TRI’ showed an improvement of the F1 score by 7.68 percent compared to the segmentation output of the ‘Sentinel-1 VV’ band. Through this research, it was demonstrated that the accuracy of deep learning-based water body extraction from Sentinel-1 images can be improved up to 7.68 percent by employing geospatial data. To the best of our knowledge, this is the first work of research that demonstrates the synergistic use of geospatial data in deep learning-based water body extraction over wide areas. It is anticipated that the results of this research could be a valuable reference when deep neural networks are applied for satellite image segmentation for operational flood monitoring and when geospatial layers are employed to improve the accuracy of deep learning-based image segmentation.