Sentinel-1A Images Research Articles

Lembang Fault Deformation Study Using Sentinel-1A Image with Ps-Insar Method

Badan Nasional Penanggulangan Bencana (BNPB) states that the earthquakes that have occurred in the territory of Indonesia during 2018 were 11,418. Nearly 95 percent of earthquakes occur in fault areas and plate boundaries. In West Java, especially in the Bandung area there is a fault structure called the Lembang Fault which is mostly occupied by community settlements. The Lembang Fault is an active fault, therefore it is necessary to conduct research related to monitoring the Lembang Fault for disaster mitigation purposes. One of parameter to determine the level of activity of a fault is deformation. The amount of deformation can be analyzed through the remote sensing methods, one of them is the Persistent Scatterer Interferometric Synthetic Aperture Radar (PS-InSAR) method. In this study the main data used is Sentinel-1A image data consist of eight scenes with acquisition time from January 2018 to March 2019. The results of the study concluded that the average deformation that occurred along the Lembang Fault was 2,485 mm with a graph that tends to rise. The area most affected by deformation is Cisarua Subdistrict with Line-of-Sight velocity of deformation of 28.4 - 48.9 mm / year. While the smallest deformation occurred in Lembang District with Line-of-Sight velocity of deformation of -2.3 - 19.2 mm / year.

A Persistent Scatterer Point Selection Method for Deformation Monitoring of Under-Construction Cross-Sea Bridges Using Statistical Theory and GMM-EM Algorithm

Using traditional algorithms to identify persistent scatterer (PS) points is challenging during bridge construction because of short-term changes at construction sites, such as earthworks, as well as the erection and dismantling of temporary structures. To address this issue, this study proposes a PS point selection method based on statistical theory and Gaussian Mixture Model-Expectation Maximization (GMM-EM) algorithm. This method adopts amplitude information as an incoherence evaluation indicator. Furthermore, the statistical median of the amplitude dispersion index and amplitude mean is screened twice to extract a set of candidate points, including PS points that exhibit stable backscattering over long durations. Temporal coherence is simultaneously used as the coherence evaluation indicator. Another candidate point set is obtained by extracting high-coherence PS points using the GMM-EM algorithm. These sets of candidate points are then combined to obtain a final PS points set. In the experiment, the deformation monitoring of the under-construction Shenzhen-Zhongshan Cross-Sea Bridge in China was selected as a case study, with 28 Sentinel-1A images used as the data source for PS selection and deformation information extraction. The results show that the proposed method enhanced the density and quality of PS points on the under-construction cross-sea bridge compared to existing PS selection methods, thus offering higher reliability. Deformation analysis further revealed fluctuating deformation trends at characteristic points of the Shenzhen-Zhongshan Cross-Sea Bridge, indicating the occurrence of elastic deformation during its construction.

Refined InSAR Mapping Based on Improved Tropospheric Delay Correction Method for Automatic Identification of Wide-Area Potential Landslides

Slow-moving landslides often occur in areas of high relief, which are significantly affected by tropospheric delay. In general, tropospheric delay correction methods in the synthetic-aperture radar interferometry (InSAR) field can be broadly divided into those based on external auxiliary information and those based on traditional empirical models. External auxiliary information is hindered by the low spatial–temporal resolution. Traditional empirical models can be adaptable for the spatial heterogeneity of tropospheric delay, but are limited by preset window sizes and models. In this regard, this paper proposes an improved tropospheric delay correction method based on the multivariable move-window variation model (MMVM) to adaptively determine the window size and the empirical model. Considering topography and surface deformation, the MMVM uses multivariate variogram models with iterative weight to determine the window size and model, and uses the Levenberg–Marquardt (LM) algorithm to enhance convergence speed and robustness. The high-precision surface deformation is then derived. Combined with hotspot analysis (HSA), wide-area potential landslides can be automatically identified. The reservoir area of the Baihetan hydropower station in the lower reaches of the Jinsha River was selected as the study area, using 118 Sentinel-1A images to compare with four methods in three aspects: corrected interferograms, derived deformation rate, and stability of time-series deformation. In terms of mean standard deviation, the MMVM achieved the lowest value for the unwrapped phase in the non-deformed areas, representing a reduction of 56.4% compared to the original value. Finally, 32 landslides were identified, 16 of which posed a threat to nearby villages. The experimental results demonstrate the superiority of the proposed method and provide support to disaster investigation departments.

Analysis Of Land Subsidance Rates In DKI JAKARTA In 2018, 2020 And 2022 With The DINSAR Method

Abstract DKI Jakarta, the capital city of Indonesia, as the center of growth and development has a high population. The high population has an impact on land use change in an effort to fulfill housing which directly impacts the increase in building density or Normalized Diffrence Built-up Index (NDBI). The purpose of this research is to analyze the rate of land subsidence in DKI Jakarta and analyze the effect of building density on land subsidence. The impact of high growth rates creates the potential for natural and anthropogenic disasters. This research uses the Differential Inferometry Synthetic Aperarure Radar (DinSAR) method, in observing land subsidence with accuracy reaching cm units. The data used in this research is Sentinel 1A image with observation time in 2018, 2020, and 2023. The results showed that land subsidence in DKI Jakarta was dominated in the North Jakarta area, the highest land subsidence value reached -26.08 cm/year. The fastest land subsidence occurs in densely populated areas prone to flooding. The correlation results show that there is no relationship between the high level of building density and land subsidence.

Computer model for detecting tsunami wave hazard on built-up land using machine learning and sentinel 2A satellite imagery

<p>The aim of this research is to compile a tsunami wave hazard scale based on built-up land density extracted and classified by machine learning from Sentinel 2A satellite and digital elevation model (DEM) imageries. This research was carried out in 5 stages, namely: (i) pre-processing of Sentinel 2A and DEM images, (ii) Classification of VI data using the machine learning algorithms, (iii) Spatial prediction using the ordinary kriging method, (iv) Field testing using the confusion matrix method, (v) Preparation of decision matrix for tsunami wave hazard. The results of the study show that the most accurate classification algorithm for classifying built-up indices data is the k-nearest neighbor (k-NN) algorithm. The results of the statistical accuracy test show that the most accurate is normalized difference built-up index (NDBI) with a mean of square error (MSE) value of 0.073 and a mean of absolute error (MAE) of 0.003. DEM analysis shows that the research area is at an altitude of 0–15 meters above sea level so it is in the high vulnerability to medium vulnerability category. Field testing showed user accuracy of 91.11%, manufacturer accuracy of 92.16%, and overall average accuracy of 91%.</p>

Triggering of Land Subsidence in and Surrounding the Hangjiahu Plain Based on Interferometric Synthetic Aperture Radar Monitoring

In the early stages, uncontrolled groundwater extraction led to the Hangjiahu (HJH) Plain becoming one of the areas with the most severe land subsidence in China. Since the beginning of this century, comprehensive measures have been taken to control the continuous aggravation of large land subsidence patterns in some areas; however, urban land subsidence issues, influenced by various factors, still persist and exhibit complex geographical distribution characteristics. In this study, we utilized Sentinel-1A images and the SBAS-InSAR technique to capture surface deformation over the HJH Plain in Zhejiang from 16 March 2017 to 20 January 2023. Through a comparative analysis with geological conditions, changes in surface mass loading, rainfall and groundwater, and land use types, we discussed the contributions of natural and anthropogenic factors to land subsidence. Augmented with optical remote sensing images and field investigations, we conducted a correlation analysis of the land subsidence status. The preliminary findings suggest that changes in surface mass loading and short-term heavy rainfall under extreme weather conditions can lead to periodic land subsidence changes in the region. Additionally, extensive infrastructure construction triggered by urbanization has resulted in significant and sustained land subsidence deformation. The research findings play an important guiding role in formulating scientifically effective strategies for land subsidence prevention and control, as well as urban planning and construction.

Sentinel 1a-2a Incorporating an Object-Based Image Analysis Method for Flood Mapping and Extent Assessment

Abstract. This study presents flood extent extraction and mapping from Sentinel images. Here we suggest an algorithm for extracting flooded areas from object-based image analysis (OBIA) using Sentinel-1A and Sentinel-2A images to map and assess the flood extent from the beginning to one week after the event. This study used multi-scale parameters in OBIA for image segmentation. First, we identified the flooded regions by applying our proposed algorithm on the Sentinel-1A. Then, to evaluate the effects of the flood on each land-use/land cover (LULC) class, Sentinel-2A images is classified using the OBIA after the event. Besides, we also used the threshold method to compare the proposed algorithm applying OBIA to determine the efficiency in computing parameters for change detection and flood extent mapping. The findings revealed the best performance for the segmentation process with an Object Fitness Index (OFI) is 0.92 when the scale parameter of 60 is applied. The results also show that 2099.4 km2 of the study area is flooded at the beginning of the flood. Furthermore, we found that the most flooded LULC classes are agricultural land and orchards with 695.28km2 (32.4%) and 708.63 km2 (33.7%), respectively. In comparison, about 33.9% of the remaining flooded area has occurred in other classes (i.e., fish farm, built-up, bare land and water bodies). The resulting object of each scale parameter was evaluated by Object Pureness Index (OPI), Object Matching Index (OMI), and OFI. Finally, our Overall Accuracy (OA) method incorporated field data using the Global Positioning System (GPS) shows 93%, 90%, and 89% for LULC, flood map (i.e., using our proposed algorithm), and threshold method, respectively.

Surface Deformation Monitoring and Subsidence Mechanism Analysis in Beijing based on Time-series InSAR

Abstract. This article uses 43 Sentinel-1A image datasets covering Beijing to obtain time series surface deformation information in the study area from January 2022 to October 2023. It analyzes the causes of land subsidence by integrating precipitation and urban construction. The main research results are as follows: (1) Three distinct subsidence areas are identified in the eastern part of Chaoyang District in Beijing (Subsidence Area A), the northwestern part of Tongzhou District in Beijing (Subsidence Area B), and Yanjiao Town in Hebei Province (Subsidence Area B), which is adjacent to Beijing. Subsidence Areas A and B exhibit a dispersed pattern, with maximum land subsidence rates exceeding −30 mm/year. In contrast, Subsidence Areas C displays a funnel-shaped subsidence, where the majority of areas experience land subsidence rates exceeding −25 mm/year, with a maximum rate reaching −45 mm/year. (2) Precipitation has a significant impact on surface deformation in the study area, and there is a strong correlation between precipitation and land subsidence, with correlation values of 0.77, 0.77, and 0.74, respectively. (3) Urban construction has a certain impact on land subsidence, but the degree of impact varies in different regions.

Spatio-temporal evolution of land subsidence and susceptibility zonation of associated ground fissures in the urban area of loess plateau: a case in Xianyang city, China

For over 50 years, the Xianyang city on the Chinese loess plateau, has been deeply affected by land subsidence and its associated ground fissures. In this study, 67 Sentinel-1A images from 2015 to 2022 were analysed to obtain the spatio-temporal evolution of land subsidence. Subsidence centers identified in Yunyang town and Luqiao town exhibit annual subsidence rates of −31 mm/a and −26.7 mm/a, respectively, culminating in total subsidence of −258 mm in Yunyang town and −139 mm in Luqiao town. Moreover, time series analysis revealed that both towns exhibit pronounced seasonal subsidence patterns. It is believed that human cultivation and groundwater overuse, combined with the effects of active faults, have led to uneven land subsidence. Then, the gradient of land subsidence and its potential relation to ground fissure hazards were evaluated. The results highlight a strong spatial correlation between high subsidence gradient areas and dense ground fissure distribution. Therefore, we proposed for the first time to introduce the land subsidence gradient factors for the susceptibility mapping of ground fissures using the artificial neural network algorithm. The susceptibility zonation results show that integrating the gradient factor can improve the rationality of the susceptibility evaluation. The above understanding provides valuable support for disaster prevention and mitigation in urban areas affected by land subsidence and ground fissures in loess regions.

Performance test of clean-coastal-water composite sentinel 2A image for shallow water bathymetry mapping

The “clean-coastal-water time-series composite” image preprocessing algorithm is one of the alternatives for obtaining minimal atmospheric disturbance satellite images for data inputs in Satellite-Derived Bathymetry (SDB). However, the performance of time-series composite images for shallow water bathymetric mapping needs to be assessed, considering the presence of pixel and band dispersion during the composite image construction process. This research aims to study the result of a clean-coastal-water time-series composite Sentinel-2 by using cloud computing preprocessing as input data for SDB in shallow waters, compare the results of SDB from a Sentinel-2 single date image and from the clean-coastal-water time-series composite image using a random forest regressor (RFR) algorithm in terms of accuracy and spatial distribution of the bathymetry, and evaluate the performance and quality of bathymetric maps obtained from a single date image and clean-coastal-water time-series composite Sentinel-2 images based on International Hydrographic Organization standards (IHO). The results show that not all time-series composite processes can produce clean images of interference from clouds, sunglints, bad waters, and pixel wave breaks. The acquisition time range affects the quality of the time-series composite image. The SDB RFR model can handle the complex relationship between the in situ water depth variable and the surface reflectance value of a clean-coastal-water time-series composite image that has pixel and band dispersion. Overall, the SDB RFR model was successfully used to predict bathymetry in shallow waters with accuracy that meets the IHO standard CATZOC requirements, with RMSE and MAE values of less than 0.5 m as well as TVU confidence level values of more than 95% at a depth of 0–5 m resulting from each - respectively clean-coastal-water time-series composite images in shallow waters around Morotai Island.

Changes In Greenness Level In PT Arumin Indonesia's RPT NPLCT Area With Normalized Difference Vegetation Index (NDVI)

The observation focused on PT Arutmin Indonesia's NPLCT RPT area of 98 hectares. These observations are viewed with the help of remote sensing technology and geographic information systems (GIS). This observation aims to analyze changes in greenness levels that occur from 2019 to 2023 using the normalized difference vegetation index (NDVI) method and the materials used sentinel-2A imagery. The goal is to evaluate changes in greenness levels and their interpolation from 2019 to 2023. An area of 98 hectares was monitored using sentinel-2A satellite imagery with a pixel sharpness of 10 meters x 10 meters. The results show sentinel imagery from 2019 to 2020, 38.41 ha experienced reforestation, 1.65 ha experienced deforestation and 58.14 ha did not change. Sentinel-2A image from 2020 to 2021, 79.09 ha experienced reforestation, 1.35 ha experienced deforestation and 17.68 ha did not change. Sentinel-2A image from 2021 to 2022, 1.08 ha experienced reforestation, 79.48 ha experienced deforestation and 17.68 ha did not change. Sentinel-2A imagery from 2022 to 2023, 0.47 ha experienced reforestation, 40.65 ha experienced deforestation and 57.17 ha did not change. The sentinel-2A image changes from 2019 to 2023, 2.27 ha reforested, 20.35 ha deforested and 75.64. These observations highlight the importance of remote sensing technology and geographic information systems (GIS) in monitoring and analyzing land cover change to support conservation, rehabilitation and natural resource management policies in Kotabaru District, South Kalimantan.

Optimal Timing of Carrot Crop Monitoring and Yield Assessment Using Sentinel-2 Images: A Machine-Learning Approach

Remotely sensed images provide effective sources for monitoring crop growth and the early prediction of crop productivity. To monitor carrot crop growth and yield estimation, three 27 ha center-pivot irrigated fields were studied to develop yield prediction models using crop biophysical parameters and vegetation indices (VIs) extracted from Sentinel-2A (S2) multi-temporal satellite data. A machine learning (ML)-based image classification technique, the random forest (RF) algorithm, was used for carrot crop monitoring and yield analysis. The VIs (NDVI, RDVI, GNDVI, SIPI, and GLI), extracted from S2 satellite data for the crop ages of 30, 45, 60, 75, 90, 105, and 120 days after plantation (DAP), and the chlorophyll content, SPAD (Soil Plant Analysis Development) meter readings, were incorporated as predictors for the RF algorithm. The RMSE of the five RF scenarios studied ranged from 7.8 t ha−1 (R2 ≥ 0.82 with Scenario 5) to 26.2 t ha−1 (R2 ≤ 0.46 with Scenario 1). The optimal window for monitoring the carrot crop for yield prediction with the use of S2 images could be achieved between the 60 DAP and 75 DAP with an RMSE of 8.6 t ha−1 (i.e., 12.4%) and 11.4 t ha−1 (16.2%), respectively. The developed RF algorithm can be utilized in carrot crop yield monitoring and decision-making processes for the self-sustainability of carrot production.

Application of Sentinel-2A Images for Land Cover Classification Using NDVI in Jember Regency

The advancement of remote sensing technology has led to the development of sophisticated image processing methods that yield highly accurate land cover classification information, minimizing misinterpretations. The Normalized Difference Vegetation Index (NDVI) is a widely utilized method in remote sensing for measuring green vegetation. A significant portion of the Jember Regency area is covered by vegetation. This study aimed to identify various land cover types in the Jember Regency area, quantify the area for each classification, and establish the NDVI value ranges for each type of cover. Sentinel-2 was employed as the primary data source, and the NDVI method was utilized for land cover classification in the Jember Regency. The region exhibited diverse land cover types. Data from Sentinel-2A captured in June and October 2019 were chosen due to their accessibility, open-source nature, and adequate spectral, spatial, and temporal resolution. The classification in this study encompassed five classes: water bodies, settlements, dry fields, irrigated paddy fields, and forests. Error analysis was conducted using a confusion matrix with the Overall and Kappa algorithms. The accuracy results for June indicated a Kappa Accuracy of 37.7% and Overall Accuracy of 54.5%. In October, the Kappa Accuracy increased to 39.9%, and the Overall Accuracy reached 56.5%. In conclusion, the NDVI method did not meet the criteria for accurately interpreting land cover classification.

The Influence of Amplitude Stability Index Values in Mapping Land Movements on Sipora Island

Sipora Island in the Mentawai Islands Regency is prone to land movement disasters that can damage and cause losses to the people who live on Sipora Island, plus very little data base related to land movement maps on the island. To reduce the risk that will arise, it is necessary to map land movement using the PS-InSAR method, using 48 scenes of Sentinel-1A images and comparing the amplitude stability index parameters 0.65, 0.75, and 0.85 to get differences in the distribution of land movement points and the number of land movement points on the island of Sipora, to see the relationship between the value of the amplitude of the stability index is done fisher test, amplitude stability index parameters 0.65 and 0.75 can map points with subsidence value up to -99mm / year while the amplitude stability index parameter 0.85 can map points with subsidence value -87mm / year all parameters have a maximum uplift value of 5mm / year. The number of points obtained with an amplitude stability index of 0.65 is 27561, 0.75 is 961 and 0.85 is 255. The distribution of land movement points parameter value amplitude stability index 0.65 covers the entire surface of the island of Sipora, the distribution of land movement points amplitude stability index 0.75 focuses on the north and south of the island and the distribution of land movement points amplitude stability index 0.85 in the northern part of the island. The difference parameters of amplitude stability index 0.65, 0.75 and 0.85.

Non-Linear PSInSAR Analysis of Deformation Patterns in Islamabad/Rawalpindi Region: Unveiling Tectonics and Earthquake-Driven Changes

The standard Permanent Scatterer Interferometric Synthetic Aperture Radar (PSInSAR) technique, which is commonly used for surface motion analysis, assumes linear deformation velocities. While effective for monitoring urban subsidence over short periods, it falls short when dealing with non-linear, earthquake-related deformations over extended timeframes. To address this limitation, we use a non-linear PSInSAR technique, which is an enhancement of PSInSAR, to identify non-linear deformation patterns. We processed Sentinel-1A images from ascending and descending orbits in the Islamabad/Rawalpindi region from December 2015 to January 2023 using non-linear PSInSAR. By calculating the differences in deformation, we analyzed surface movements and assessed the impact of the 2017 earthquake on urban areas. Our findings reveal that the earthquake significantly increased the deformation in ascending and descending orbit tracks, with an average deformation of up to 70 mm/yr and a line-of-sight movement of up to 30 mm/yr. Our observations indicate that the deformation is directed towards the line of sight in the north and south of the deformed area, suggesting subsidence between the two uplifting faults, potentially linked to a concealed fault line along the deformation zone boundary. This contradicts previous arguments, suggesting that water extraction is the leading cause of deformation. Our analysis with non-linear PSInSAR demonstrates that tectonics play a significant role in deformation, providing valuable insights into tectonic-activity-induced deformations in urban areas over the long term.

Time-series InSAR reveals new insights into land subsidence in the Yellow River Delta, China

In the past decade, the synthetic aperture radar interferometry (InSAR) technique has been extensively employed in deltas, making it possible to obtain more subsidence signals. However, the spatiotemporal nonlinearity of land subsidence often results in inaccurate estimations. Based on 72 Sentinel-1A images captured from 2016 to 2021 and the time-series persistent scatterer-interferometric SAR (PS-InSAR) method, we comprehensively analyze the temporal and spatial dynamics of recent land subsidence in the Yellow River Delta (YRD). The findings suggest a notable spatial shift in the subsidence funnel area within this delta region over the past 6 years (2016–2021), with gradual westward movement from the salt fields in the northeast to those in the central north. Additionally, with 2020 as the demarcation point, there was a notable change in magnitude, initially exhibiting acceleration at −333 mm/yr, followed by deceleration at −231 mm/yr and culminating in renewed acceleration at −413 mm/yr. The subsidence characteristics may be attributed to changes in the underground brine reserves, leading to consolidation of the confined aquifer. Furthermore, the ground subsidence trend suddenly slowed at the end of 2019, which we speculate is related to the significant reduction in human activities caused by COVID-19 prevention and control measures.

Mangrove mapping and monitoring using remote sensing techniques towards climate change resilience

Mangroves are amongst the richest ecosystems in the world providing valuable goods and services to millions of people while enhancing the resilience of coastal communities against climate change induced hazards, especially island nations. However, these mangroves are severely affected by many anthropogenic activities. Therefore, understanding the spatial variability of mangroves in island nations is highly essential in the events of ongoing climatic change. Thus, this study assessed the use of remote sensing techniques and GIS to map and monitor mangrove cover change at selected sites, namely Le Morne and Ferney, on the tropical island of Mauritius. Freely available 2013 SPOT-5 and 2023 Sentinel 2A images were retrieved and processed using ArcGIS Pro tools and SNAP; mangroves were mapped based on Google Earth Pro historical imagery and ground truthing at the respective sites. Following the application of selected vegetation indices, GLCM and PCA analysis, mosaicked images were classified using the Random Trees algorithm. Kappa values of all the classified images were in the 90 s; Le Morne showed a significant increase in mangrove cover over the decadal scale with main class change from mudflat to mangroves. This study demonstrates how geo-spatial tools are crucial for monitoring mangroves as they provide spatially explicit and time sensitive information. Decision makers, researchers, and relevant stakeholders can utilize this data to bolster tailored mitigation and adaptation strategies at specific sites, thereby enhancing resilience to climate change.

Internal solitary waves observation and feature extraction based on wavelet transform by Sentinel-1A in Lombok Strait, Indonesia

Lombok Strait is an essential pathway in trans-oceanic water mass transport. Due to this water mass transport flowing over Indonesian waters, the current is known as Indonesian Throughflow (ITF), which plays a role in the transfer of warm water masses from the Pacific to the Indian Ocean annually. Lombok Strait has intensive characteristics of the internal waves (IWs) generation because of the strong current that passes through the complex bathymetry along the strait area. IWs with large amplitude and nonlinear properties are known as Internal Solitary Waves (ISW) that can be detected by Synthetic Aperture Radar (SAR) images. A Wavelet Transform method for ISW feature extraction was applied to SAR images by Sentinel-1A (C-band). ISW packet characteristics can be distinguished from other phenomena based on their geometrical structure and shape. ISW packet pattern consists of light and dark lines which decrease intensity from front to rear. SAR observation detected 5 parameters (phase speed, soliton numbers, wavelength, first crest length, and propagation direction). The arc-like ISW in the Lombok Strait propagated to the North of the sill with average phase speeds of about 2.13 m/s and was frequently detected during the northwest monsoon (NWM). The detected soliton number is less than 6 solitons per packet with a wavelength of about 1 – 4 km, and the first crest length varies from about 12.16 km to more than 100 km. ISW detected in Sentinel-1A images were located at the bathymetry about 800 meters around the Lombok Strait area.

Feature optimization combined with UPerNet-Twins model for eucalyptus extraction from Sentinel-2A image

To improve the extraction accuracy of eucalyptus from Sentinel-2A image, two key factors of feature construction and extraction model are considered. The original band spectrum, custom vegetation index, red edge spectral index, and texture features are obtained from the image. The Relief F-PSO-SVM model is used to screen out the best feature subset. A UPerNet-Twins combination model is used to realize the high-precision extraction of eucalyptus for the study area. The experiments show that the original spectrum plays a significant role in the extraction of eucalyptus. In addition, the texture features, vegetation index, and red edge spectral index are helpful to the extraction of eucalyptus, which are increased by about 5.84%, 3.81%, and 3.00%, respectively, compared with the IOU of the original spectrum. Moreover, the IOU of the optimal feature subset obtained by feature selection is increased by about 2.22% compared with the original feature set. The UPerNet-Twins combination model has the highest extraction accuracy of eucalyptus with an IOU of 0.8496 compared with DeeplabV3+, PspNet-UNet, FCN, UperNet, and UperNet-Vision Transformers models.

Postfire Forest Regrowth Algorithm Using Tasseled-Cap-Retrieved Indices

Wildfires are a common disturbance factor worldwide, especially over the last decade due to global climate change. Monitoring postfire forest regrowth provides fundamental information needed to enhance the management and support of ecosystem recovery after fires. The purpose of this study is to propose an algorithm for postfire forest regrowth monitoring using tasseled-cap-derived indices. A complex approach is used for its implementation, for which a model is developed based on three components—Disturbance Index (DI), Vector of Instantaneous Condition (VIC), and Direction Angle (DA). The final product—postfire regrowth (PFIR)—allows for a quantitative assessment of the intensity of regrowth. The proposed methodology is based on the linear orthogonal transformation of multispectral satellite images—tasseled cap transformation (TCT)—that increases the degree of identification of the three main components that change during a fire—soil, vegetation, and water/moisture—and implies a higher accuracy of the assessments. The results provide a thematic raster representing the intensity of the regrowth classes, which are defined after the PFIR threshold values are determined (HRI—high regrowth intensity; MRI—moderate regrowth intensity; and LRI—low regrowth intensity). The accuracy assessment procedure is conducted using very-high-resolution (VHR) aerial and satellite data from World View (WV) sensors, as well as multispectral Sentinel 2A images. Three different forest test sites affected by fire in Bulgaria are examined. The results show that the classified thematic raster maps are distinguished by a good performance in monitoring the regrowth dynamics, with an average overall accuracy of 62.1% for all three test sites, ranging from 73.9% to 48.4% for the individual forests.