Search

In existing global navigation satellite system-interference reflectometry (GNSS-IR) research, only the frequency of signal-to-noise ratio (SNR) oscillations has been used to estimate sea-level height. However, the characteristic parameters of SNR oscillations are not isolated from each other, and a single feature cannot accurately and comprehensively capture the environmental changes of reflecting surface. Our simulation results show that for the nonlinear least squares (NLS), when there is a certain difference between the fitting frequency and the actual frequency of SNR oscillations, the deviation of the phase solution obtained is approximately linear with the frequency difference. Consequently, a linear phase correction GNSS-IR sea-level estimation method is constructed in this study. This method integrates the Lomb–Scargle periodogram (LSP) and NLS to process SNR oscillations, using the phase obtained from NLS to correct the retrieval error of LSP. Through processing SNR data from four sites for nearly half a year, we verified the stability of the relationship between phase and frequency-based retrieval error at different sites in continuous monitoring, and established the relationship model between the two. Then, utilizing the relationship model acquired at different sites, we estimated the sea-level variations for the next 6 months at each site through joint frequency and phase versus reflector height relationships. Experimental results show that the phases acquired from NLS can effectively correct the retrieval error of LSP. Compared with the traditional method using only frequency, the root mean square error and mean absolute error of the retrieval results obtained from the linear phase correction GNSS-IR sea-level estimation method based on LSP-NLS are both reduced by about 60%. This multi-feature fusion technique introduces a new perspective and technical approach for GNSS-IR sea-level estimations. [ABSTRACT FROM AUTHOR]

In the realm of remote sensing image analysis, the task of road extraction poses significant complexities, especially in the context of intricate scenes and diminutive targets. In response to these challenges, we have developed a novel deep learning network, christened CDAU-Net, designed to discern and delineate these features with enhanced precision. This network takes its structural inspiration from the fundamental architecture of U-Net while introducing innovative enhancements: we have integrated CoordConv convolutions into both the initial layer of the U-Net encoder and the terminal layer of the decoder, thereby facilitating a more efficacious processing of spatial information inherent in remote sensing images. Moreover, we have devised a unique mechanism termed the Deep Dual Cross Attention (DDCA), purposed to capture long-range dependencies within images—a critical factor in remote sensing image analysis. Our network replaces the skip-connection component of the U-Net with this newly designed mechanism, dealing with feature maps of the first four scales in the encoder and generating four corresponding outputs. These outputs are subsequently linked with the decoder stage to further capture the remote dependencies present within the remote sensing imagery. We have subjected CDAU-Net to extensive empirical validation, including testing on the Massachusetts Road Dataset and DeepGlobe Road Dataset. Both datasets encompass a diverse range of complex road scenes, making them ideal for evaluating the performance of road extraction algorithms. The experimental results showcase that whether in terms of accuracy, recall rate, or Intersection over Union (IoU) metrics, the CDAU-Net outperforms existing state-of-the-art methods in the task of road extraction. These findings substantiate the effectiveness and superiority of our approach in handling complex scenes and small targets, as well as in capturing long-range dependencies in remote sensing imagery. In sum, the design of CDAU-Net not only enhances the accuracy of road extraction but also presents new perspectives and possibilities for deep learning analysis of remote sensing imagery. [ABSTRACT FROM AUTHOR]

Machine learning (ML)-based methods of landslide susceptibility assessment primarily focus on two dimensions: accuracy and complexity. The complexity is not only influenced by specific model frameworks but also by the type and complexity of the modeling data. Therefore, considering the impact of factor data types on the model's decision-making mechanism holds significant importance in assessing regional landslide characteristics and conducting landslide risk warnings given the achievement of good predictive performance for landslide susceptibility using excellent ML methods. The decision-making mechanism of landslide susceptibility models coupled with different types of factor data in machine learning methods was explained in this study by utilizing the Shapley Additive exPlanations (SHAP) method. Furthermore, a comparative analysis was carried out to examine the differential effects of diverse data types for identical factors on model predictions. The study area selected was Cenxi, Guangxi, where a geographic spatial database was constructed by combining 23 landslide conditioning factors with 214 landslide samples from the region. Initially, the factors were standardized using five conditional probability models, frequency ratio (FR), information value (IV), certainty factor (CF), evidential belief function (EBF), and weights of evidence (WOE), based on the spatial arrangement of landslides. This led to the formation of six types of factor databases using the initial data. Subsequently, two ensemble-based ML methods, random forest (RF) and XGBoost, were utilized to build models for predicting landslide susceptibility. Various evaluation metrics were employed to compare the predictive capabilities of different models and determined the optimal model. Simultaneously, the analysis was conducted using the interpretable SHAP method for intrinsic decision-making mechanisms of different ensemble-based ML models, with a specific focus on explaining and comparing the differential impacts of different types of factor data on prediction results. The results of the study illustrated that the XGBoost-CF model constructed with CF values of factors not only exhibited the best predictive accuracy and stability but also yielded more reasonable results for landslide susceptibility zoning, and was thus identified as the optimal model. The global interpretation results revealed that slope was the most crucial factor influencing landslides, and its interaction with other factors in the study area collectively contributed to landslide occurrences. The differences in the internal decision-making mechanisms of models based on different data types for the same factors primarily manifested in the extent of influence on prediction results and the dependency of factors, providing an explanation for the performance of standardized data in ML models and the reasons behind the higher predictive performance of coupled models based on conditional probability models and ML methods. Through comprehensive analysis of the local interpretation results from different models analyzing the same sample with different sample characteristics, the reasons for model prediction errors can be summarized, thereby providing a reference framework for constructing more accurate and rational landslide susceptibility models and facilitating landslide warning and management. [ABSTRACT FROM AUTHOR]

The retrieval of soil moisture (SM) using the Global Navigation Satellite System-Reflectometry (GNSS-R) technique has become a prominent topic in recent years. Although prior research has reached a spatial resolution of up to 9 km through the Cyclone Global Navigation Satellite System (CYGNSS), it is insufficient to meet the requirements of higher spatial resolutions for hydrological or agricultural applications. In this paper, we present an SM downscaling method that fuses CYGNSS and SMAP SM. This method aims to construct a dataset of CYGNSS observables, auxiliary variables, and SMAP SM (36 km) products. It then establishes their nonlinear relationship at the same scale and finally builds a downscale retrieval model of SM using the eXtreme Gradient Boosting (XGBoost) algorithm. Focusing on the southern United States, the results indicate that the SM downscaling method exhibits robust performance during both the training and testing processes, enabling the generation of a CYGNSS SM product with a 1 day/3 km resolution. Compared to existing methods, the spatial resolution is increased threefold. Furthermore, in situ sites are utilized to validate the downscaled SM, and spatial correlation analysis is conducted using MODIS EVI and MODIS ET products. The CYGNSS SM obtained by the downscaling model exhibits favorable correlations. The high temporal and spatial resolution characteristics of GNSS-R are fully leveraged through the downscaled method proposed. Furthermore, this work provides a new perspective for enhancing the spatial resolution of SM retrieval using the GNSS-R technique. [ABSTRACT FROM AUTHOR]

An accurate and efficient estimation of eucalyptus plantation areas is of paramount significance for forestry resource management and ecological environment monitoring. Currently, combining multidimensional optical and SAR images with machine learning has become an important method for eucalyptus plantation classification, but there are still some challenges in feature selection. This study proposes a feature selection method that combines multi-temporal Sentinel-1 and Sentinel-2 data with SLPSO (social learning particle swarm optimization) and RFE (Recursive Feature Elimination), which reduces the impact of information redundancy and improves classification accuracy. Specifically, this paper first fuses multi-temporal Sentinel-1 and Sentinel-2 data, and then carries out feature selection by combining SLPSO and RFE to mitigate the effects of information redundancy. Next, based on features such as the spectrum, red-edge indices, texture characteristics, vegetation indices, and backscatter coefficients, the study employs the Simple Non-Iterative Clustering (SNIC) object-oriented method and three different types of machine-learning models: Random Forest (RF), Classification and Regression Trees (CART), and Support Vector Machines (SVM) for the extraction of eucalyptus plantation areas. Each model uses a supervised-learning method, with labeled training data guiding the classification of eucalyptus plantation regions. Lastly, to validate the efficacy of selecting multi-temporal data and the performance of the SLPSO–RFE model in classification, a comparative analysis is undertaken against the classification results derived from single-temporal data and the ReliefF–RFE feature selection scheme. The findings reveal that employing SLPSO–RFE for feature selection significantly elevates the classification precision of eucalyptus plantations across all three classifiers. The overall accuracy rates were noted at 95.48% for SVM, 96% for CART, and 97.97% for RF. When contrasted with classification outcomes from multi-temporal data and ReliefF–RFE, the overall accuracy for the trio of models saw an increase of 10%, 8%, and 8.54%, respectively. The accuracy enhancement was even more pronounced when juxtaposed with results from single-temporal data and ReliefF-RFE, at increments of 15.25%, 13.58%, and 14.54% respectively. The insights from this research carry profound theoretical implications and practical applications, particularly in identifying and extracting eucalyptus plantations leveraging multi-temporal data and feature selection. [ABSTRACT FROM AUTHOR]

Wildfire disasters pose a significant threat to the stability and sustainability of ecosystems. The assessment of wildfire risk based on a seasonal dimension has contributed to improving the spatiotemporal targeting of fire prevention efforts. In this study, Nanning, China, was selected as the research area. The wildfire driving factors were chosen from both seasonal and nonseasonal aspects, and the datasets were divided into five periods: all seasons, spring, summer, autumn, and winter. The light gradient boosting machine (LGBM) was employed to construct wildfire danger models for different periods, evaluating the spatial distribution of high-wildfire-danger areas during these periods and the predictive performance differences. The SHapley Additive exPlanations (SHAP) method was utilized to analyze the differential contributions of various factors to wildfire occurrence in different seasons. Subsequently, the remote sensing ecological index (RSEI) was calculated using four indicators, greenness, heat, wetness, and dryness, to assess the ecological vulnerability in different seasons. Finally, by integrating danger and vulnerability information, wildfire risk models were developed to systematically assess the risk of wildfire disasters causing losses to the ecological environment in different seasons. The results indicate that: (1) The evaluation of wildfire danger based on individual seasons effectively compensates for the shortcomings of analyzing danger across all seasons, exhibiting higher predictive performance and richer details. (2) Wildfires in Nanning primarily occur in spring and winter, while the likelihood of wildfires in summer and autumn is relatively lower. In different seasons, NDVI is the most critical factor influencing wildfire occurrence, while slope is the most important nonseasonal factor. The influence of factors varies among different seasons, with seasonal factors having a more significant impact on wildfire danger. (3) The ecological vulnerability in Nanning exhibits significant differences between different seasons. Compared to spring and winter, the ecological environment is more vulnerable to wildfire disasters during summer and autumn. (4) The highest wildfire risk occurs in spring, posing the greatest threat to the ecological environment, while the lowest wildfire risk is observed in winter. Taking into account information on danger and vulnerability in different seasons enables a more comprehensive assessment of the risk differences in wildfire disasters causing ecological losses. The research findings provide a scientific theoretical basis for relevant departments regarding the prevention, control, and management of seasonal wildfires. [ABSTRACT FROM AUTHOR]

Road extraction from high-resolution satellite images has become a significant focus in the field of remote sensing image analysis. However, factors such as shadow occlusion and spectral confusion hinder the accuracy and consistency of road extraction in satellite images. To overcome these challenges, this paper presents a multi-scale fusion-based road extraction framework, HRU-Net, which exploits the various scales and resolutions of image features generated during the encoding and decoding processes. First, during the encoding phase, we develop a multi-scale feature fusion module with upsampling capabilities (UMR module) to capture fine details, enhancing shadowed areas and road boundaries. Next, in the decoding phase, we design a multi-feature fusion module (MPF module) to obtain multi-scale spatial information, enabling better differentiation between roads and objects with similar spectral characteristics. The network simultaneously integrates multi-scale feature information during the downsampling process, producing high-resolution feature maps through progressive cross-layer connections, thereby enabling more effective high-resolution prediction tasks. We conduct comparative experiments and quantitative evaluations of the proposed HRU-Net framework against existing algorithms (U-Net, ResNet, DeepLabV3, ResUnet, HRNet) using the Massachusetts Road Dataset. On this basis, this paper selects three network models (U-Net, HRNet, and HRU-Net) to conduct comparative experiments and quantitative evaluations on the DeepGlobe Road Dataset. The experimental results demonstrate that the HRU-Net framework outperforms its counterparts in terms of accuracy and mean intersection over union. In summary, the HRU-Net model proposed in this paper skillfully exploits information from different resolution feature maps, effectively addressing the challenges of discontinuous road extraction and reduced accuracy caused by shadow occlusion and spectral confusion factors. In complex satellite image scenarios, the model accurately extracts comprehensive road regions. [ABSTRACT FROM AUTHOR]

The global navigation satellite system–interferometric reflectometry (GNSS-IR) technique has emerged as an effective coastal sea-level monitoring solution. However, the accuracy and stability of GNSS-IR sea-level estimation based on quadratic fitting are limited by the retrieval range of reflector height (RH range) and satellite-elevation range, reducing the flexibility of this technology. This study introduces a new GNSS-IR sea-level estimation model that combines local mean decomposition (LMD) and Lomb–Scargle periodogram (LSP). LMD can decompose the signal-to-noise ratio (SNR) arc into a series of signal components with different frequencies. The signal components containing information from the sea surface are selected to construct the oscillation term, and its frequency is extracted by LSP. To this end, observational data from SC02 sites in the United States are used to evaluate the accuracy level of the model. Then, the performance of LMD and the influence of noise on retrieval results are analyzed from two aspects: RH ranges and satellite-elevation ranges. Finally, the sea-level variation for one consecutive year is estimated to verify the stability of the model in long-term monitoring. The results show that the oscillation term obtained by LMD has a lower noise level than other signal separation methods, effectively improving the accuracy of retrieval results and avoiding abnormal values. Moreover, it still performs well under loose constraints (a wide RH range and a high-elevation range). In one consecutive year of retrieval results, the new model based on LMD has a significant improvement effect over quadratic fitting, and the root mean square error and mean absolute error of retrieval results obtained in each month on average are improved by 8.34% and 8.87%, respectively. [ABSTRACT FROM AUTHOR]

Research on wildfire risk can quantitatively assess the risk of wildfire damage to the population, economy, and natural ecology. However, existing research has primarily assessed the spatial risk of wildfires across an entire region, neglecting the impact of different land-use types on the assessment outcomes. The purpose of the study is to construct a framework for assessing wildfire risk in different land-use types, aiming to comprehensively assess the risk of wildfire disasters in a region. We conducted a case study in Central China, collecting and classifying historical wildfire samples according to land-use types. The Light Gradient Boosting Machine (LGBM) was employed to construct wildfire susceptibility models for both overall and individual land-use types. Additionally, a subjective and objective combined weighting method using the Analytic Hierarchy Process (AHP) and Entropy Weight Method (EWM) was utilized to build the wildfire vulnerability model. By integrating susceptibility and vulnerability information, we comprehensively assessed the combined risk of wildfire disasters across land-use types. The results demonstrate the following: (1) Assessing wildfire susceptibility based on different land-use types compensated for limitations in analyzing overall wildfire susceptibility, with a higher prediction performance and more detailed susceptibility information. (2) Significant variations in wildfire susceptibility distribution existed among different land-use types, with varying contributions of factors. (3) Using the AHP-EWM combined weighting method effectively addressed limitations of a single method in determining vulnerability. (4) Land-use types exerted a significant impact on wildfire risk assessment in Central China. Assessing wildfire risk for both overall and individual land-use types enhances understanding of spatial risk distribution and specific land use risk. The experimental results validate the feasibility and effectiveness of the proposed evaluation framework, providing guidance for wildfire prevention and control. [ABSTRACT FROM AUTHOR]

Normalized difference vegetation index (NDVI) time series data, derived from optical images, play a crucial role for crop mapping and growth monitoring. Nevertheless, optical images frequently exhibit spatial and temporal discontinuities due to cloudy and rainy weather conditions. Existing algorithms for reconstructing NDVI time series using multi-source remote sensing data still face several challenges. In this study, we proposed a novel method, an enhanced gap-filling and Whittaker smoothing (EGF-WS), to reconstruct NDVI time series (EGF-NDVI) using Google Earth Engine. In EGF-WS, NDVI calculated from MODIS, Landsat-8, and Sentinel-2 satellites were combined to generate high-resolution and continuous NDVI time series data. The MODIS NDVI was employed as reference data to fill missing pixels in the Sentinel–Landsat NDVI (SL-NDVI) using the gap-filling method. Subsequently, the filled NDVI was smoothed using a Whittaker smoothing filter to reduce residual noise in the SL-NDVI time series. With reference to the all-round performance assessment (APA) metrics, the performance of EGF-WS was compared with the conventional gap-filling and Savitzky–Golay filter approach (GF-SG) in Fusui County of Guangxi Zhuang Autonomous Region. The experimental results have demonstrated that the EGF-WS can capture more accurate spatial details compared with GF-SG. Moreover, EGF-NDVI of Fusui County exhibited a low root mean square error (RMSE) and a high coefficient of determination (R2). In conclusion, EGF-WS holds significant promise in providing NDVI time series images with a spatial resolution of 10 m and a temporal resolution of 8 days, thereby benefiting crop mapping, land use change monitoring, and various ecosystems, among other applications. [ABSTRACT FROM AUTHOR]

The frequent occurrence and spread of wildfires pose a serious threat to the ecological environment and urban development. Therefore, assessing regional wildfire susceptibility is crucial for the early prevention of wildfires and formulation of disaster management decisions. However, current research on wildfire susceptibility primarily focuses on improving the accuracy of models, while lacking in-depth study of the causes and mechanisms of wildfires, as well as the impact and losses they cause to the ecological environment and urban development. This situation not only increases the uncertainty of model predictions but also greatly reduces the specificity and practical significance of the models. We propose a comprehensive evaluation framework to analyze the spatial distribution of wildfire susceptibility and the effects of influencing factors, while assessing the risks of wildfire damage to the local ecological environment and urban development. In this study, we used wildfire information from the period 2013–2022 and data from 17 susceptibility factors in the city of Guilin as the basis, and utilized eight machine learning algorithms, namely logistic regression (LR), artificial neural network (ANN), K-nearest neighbor (KNN), support vector regression (SVR), random forest (RF), gradient boosting decision tree (GBDT), light gradient boosting machine (LGBM), and eXtreme gradient boosting (XGBoost), to assess wildfire susceptibility. By evaluating multiple indicators, we obtained the optimal model and used the Shapley Additive Explanations (SHAP) method to explain the effects of the factors and the decision-making mechanism of the model. In addition, we collected and calculated corresponding indicators, with the Remote Sensing Ecological Index (RSEI) representing ecological vulnerability and the Night-Time Lights Index (NTLI) representing urban development vulnerability. The coupling results of the two represent the comprehensive vulnerability of the ecology and city. Finally, by integrating wildfire susceptibility and vulnerability information, we assessed the risk of wildfire disasters in Guilin to reveal the overall distribution characteristics of wildfire disaster risk in Guilin. The results show that the AUC values of the eight models range from 0.809 to 0.927, with accuracy values ranging from 0.735 to 0.863 and RMSE values ranging from 0.327 to 0.423. Taking into account all the performance indicators, the XGBoost model provides the best results, with AUC, accuracy, and RMSE values of 0.927, 0.863, and 0.327, respectively. This indicates that the XGBoost model has the best predictive performance. The high-susceptibility areas are located in the central, northeast, south, and southwest regions of the study area. The factors of temperature, soil type, land use, distance to roads, and slope have the most significant impact on wildfire susceptibility. Based on the results of the ecological vulnerability and urban development vulnerability assessments, potential wildfire risk areas can be identified and assessed comprehensively and reasonably. The research results of this article not only can improve the specificity and practical significance of wildfire prediction models but also provide important reference for the prevention and response of wildfires. [ABSTRACT FROM AUTHOR]