The understory terrain is an essential component of forest vertical structure and ecosystem health, providing crucial insights for resource assessment and forestry surveys. This paper proposes a novel method for extracting understory terrain through forest backscattering power profiles and the Modified Cloth Simulation Filtering (MCSF) algorithm. It innovatively reconstructs SAR signals into a three-dimensional point cloud, eliminating side-lobe signals to reduce noise while only retaining the main lobe signals. The MCSF algorithm is subsequently utilized to extract ground and non-ground points based on the vertical distribution of the main lobe signals. The extracted ground points offer a more precise representation of actual terrain conditions. The feasibility of the method was validated utilizing airborne P-band multi-baseline SAR data obtained from the Saihanba test site in Hebei Province. The outcomes clearly indicate that our approach exhibits superior correlation (0.999) and a smaller root mean square error (3.07 m) in comparison to conventional methods when compared with the reference DEM.

In millimeter-wave and terahertz band communication systems, precise beam prediction is crucial for optimizing network performance and enhancing signal transmission efficiency. Traditional beam prediction methods have primarily relied on single-modal data, which often fails to capture the comprehensive environmental information necessary for optimal accuracy. In contrast, multi-modal data-based approaches offer a more promising solution by leveraging the strengths of diverse data sources. However, many existing fusion methods are static, inadequately accounting for variations in information content across different modalities, which can hinder the full utilization of each modality’s advantages. To address these limitations, this paper proposes an advanced multi-modal beam prediction method that integrates multipath-like data augmentation (MLDA), cross-modal feature enhancement (CMFE), and an uncertainty-aware dynamic fusion mechanism. Our approach combines image and radar data to predict beam indices, dynamically adjusting the weights of different modalities to accommodate varying information densities. The proposed method employs ResNet34 for feature extraction from the multi-modal data, followed by a cross-modal feature enhancement module that aggregates complementary information from the image and radar data. Finally, the dynamic fusion mechanism integrates the predictions from the single-modal data. Experimental results demonstrate that our method significantly improves the accuracy and robustness of beam prediction, achieving an overall accuracy of 89.72%. The performance of the proposed method is further validated through comparisons with various existing methods and comprehensive ablation studies, highlighting its superiority in multi-modal assisted beam prediction scenarios.

Synthetic aperture radar tomography (TomoSAR) is a common measurement technique for three-dimensional (3-D) imaging of forested areas. It extends the synthetic aperture principle into the elevation direction, obtains the elevation scattering information of the observed target, and then realizes the 3-D reconstruction. In order to achieve high-resolution imaging, compressed sensing (CS) technology is widely used in TomoSAR. Given that many existing forested area datasets comprise multi-polarization modes, leveraging the complete potential of polarimetric data to achieve high-resolution 3-D recovery of the observed scene is essential. Therefore, this paper proposes a novel L2,1/2 -norm regularization based TomoSAR imaging method of the forested area, which jointly reconstructs the multi-polarization data and utilizes the correlation between each polarization to obtain more accurate 3-D reconstruction results. Experimental results based on real BioSAR 2008 L-band dataset are used to verify the proposed method.

Characterising spatial information as reinforcement of spectral signatures can largely assist the performance in hyperspectral image (HSI) classification. Markov random fields (MRFs) are probabilistic image texture models, and capable of encoding contextual dependencies through charactering local conditional probabilities. As a representative standardised measure of dispersion of image probability distributions, coefficient of variation (CoV) can be a useful tool for characterising spatial heterogeneity. Their parameter derivation processes also share strong compatibility with convolutional neural networks that specifies spatial correlations in local neighbourhoods. In this work, we propose an MRF and CoV based spectral-spatial convolutional network (MRF-CoV-CNN) for HSI classification. MRF models and CoVs are characterised as measures of spatial distributions and further combined with spectral information. Then the proposed MRF-CoV-CNN takes the fused features as input and produces reliable classification results. Comprehensive experiments have been conducted on the Pavia university dataset and the Salinas dataset to evaluate the proposed method both visually and quantitatively.

The use of deep learning (DL) based hyperspectral image (HSI) classification has been made remarkable progress in recent years. However, obtaining sufficient labeled samples for training DL models remains a challenge. Transfer learning is effective in addressing the problem of HSI classification with limited labeled samples. However, cross-domain HSI classification using transfer learning remain difficult, as differences in ground object categories between two datasets make it challenging to transfer and learn accurate. To address this issue, we propose a simple yet effective method for HSI classification using Model-Agnostic Meta-Learning (MAML) and Regularized Fine-tuning (MRFSL). Our method uses optimized 3-Dimension Convolutional Neural Networks (3D-CNNs) model, aided by MAML and cutout data augmentation to enable cross-domain transfer learning and carry out the HSI classification with limited target samples. Experiments conducted on three HSI datasets demonstrate that the MRFSL method achieves excellent results compared to existing methods. Specifically, the overall accuracy of our proposed MRFSL method reached 91.81%, 71.04%, and 88.35%, when only five labeled samples for each category were randomly extracted from the Salinas, Indian Pines, and University of Pavia datasets, respectively.

The objective is to estimate forest above-ground biomass (AGB) considering the vertical structures of tropical forest in Mondah test site. Ten DLR F-SAR P-band fully polarized images are utilized to reconstruct the vertical reflectivity through TomoSAR techniques, and then extract multi-feature parameters from vertical profiles of reflectivity, finally these parameters are used for forest AGB estimation with support vector regression (SVR) approach. The results show that the method we proposed for tropical forest AGB estimation is effective and accurate in our test site.

Net Primary Productivity (NPP) is an important part of the carbon cycle of terrestrial ecosystems. The technical advantages and huge potential of remote sensing technology in NPP estimation make it a hot spot in the research field. The vigorous development of many remote sensing fusion algorithms provides fine-resolution remote sensing data support for high-precision NPP dynamic monitoring. In recent years, the expansion of urban areas and climate change have had a great impact on the NPP of vegetation. In accordance with the requirements of large-scale and high-temporal-spatial resolution productivity assessment of urban area, we chose the northern Jiangsu area as the research area and uses three remote sensing data spatiotemporal fusion methods, STARFM, ESTARFM, and STDFA to blend Landsat and MODIS data. Three methods are compared in aspects of NDVI reconstruction ability in large-scale, highly heterogeneous regional application scenarios, the accuracy of NPP estimation through CASA model, and the ability of fine spatial description. The results of the study show that STDFA gets the highest correlation coefficient between its NDVI reconstruction results and MODIS products, which is 0.82. Correlation coefficient of STARFM and ESTARFM are 0.77 and 0.75, respectively. The STARFM is significantly lower in the NPP estimation results among the three methods, meanwhile STDFA performs best in our test site.

The errors of the theoretical model and the simplified SINC model in forest height inversion are analyzed. Simulation results show that the higher the tree height, the lower the kz value, the error between the theoretical and simplified SINC model is greater in inverting the forest height. When kz is 0.03 and forest height is 40 meters, the difference of the inversion height between theoretical and simplified SINC model can reach 1.5 meters. To address this problem, bisection iterative algorithm is utilized to eliminate or minimize the error between theoretical and simplified SINC forest height inversion model based on X-band airborne interferometric synthetic aperture radar (InSAR) coherence data. Lidar$H_{100}$CHM data are used to verify the effectiveness of bisection iterative algorithm. Compared with simplified SINC model, the performance of bisection iterative algorithm is better in retrieving the real value in the theoretical SINC model. The results show that the average height error of the bisection iterative algorithm is 0.5 m lower than that of the simplified SINC model in the inversion of forest parameters in the height range of 15–20 m.

Convolutional neural network (CNN) is one of the most important tools to accomplish high-spatial-resolution remote sensing (HSRRS) image classification tasks with their unique feature extraction and feature expression capabilities. However, the CNN-based classification method is very limited due to the acquisition of HSRRS images is difficult and the sample size is limited. In addition, the extraction of features by a single model is very limited, which limits the further improvement of classification performance. To solve the above problems, we propose ResNet50-InceptionV3 based on deep transfer learning and multi-feature fusion (TLMFFRI) model to apply for high-spatial-resolution remote sensing image classification. First, both ResNet50 and InceptionV3 are trained on the ImageNet dataset. Then, transfer the trained convolutional layers weights to the TLMFFRI model to fuse the features and realize the HSRRS image classification. Finally, we evaluate the method on the HSRRS dataset. Compared with ResNet50 based on transfer learning (TL-ResNet50) and InceptionV3 based on transfer learning (TL-InceptionV3), the proposed method achieved better classification performance.

In this paper, we propose a convolutional neural network (CNN) aided automatic modulation recognition (AMR) method for a multiple antenna system. We also present two specific combination strategies, such as the relative majority voting method and arithmetic mean method to improve the classification performance in comparison with the state of the art. Our results are given to verify that the proposed method dominant exploits features and classify the modulation types with higher accuracy in comparison with the AMR employing high order cumulants (HOC) and artificial neural networks (ANN).

This work proposes a forest model based on Gamma distribution to better describe the forest vertical structure for height inversion using P-band polarimetric synthetic aperture radar interferometry (Pol-InSAR) data. The proposed model takes into account the forest vertical heterogeneity and asymmetry, to which volume interferometric coherence is sensitive. The interferometric coherence associated with a volume where the vertical backscattered power varies following a Gamma distribution is derived. The effect of scattering center height standard deviation and mean elevation to the volume interferometric coherence is investigated. Finally, the strategy of multi-baseline on the proposed model for forest height inversion using P-band Pol-InSAR data is proposed.

The goal of this paper is to investigate the influence of temporal decorrelation on InSAR / Pol-INSAR and T-SAR in boreal forest. The P-, L-band Pol-InSAR data collected in campaign BioSAR 2008 was used in our study. The impact of temporal decorrelation on InSAR / Pol-InSAR and T-SAR is reflected by coherences, phases and vertical backscattering power. Markov model is applied to describe the quantitative impact of time decorrelation, and correlation, time decorrelation constant is identified by GA. And the influence of temporal decorrelation on T-SAR is also related with coherences and phases. The backscattering power represents more ambiguous with longer time interval than that with shorter time interval for single baseline.

With the advantages of the simpler transmitter architecture requirements, the wider swath capability and lower data rate, compact polarimetric (CP) synthetic aperture radar (SAR) was proposed in recent ten years to substitute or compensate the disadvantage of the full polarization mode SAR, especially on widening the swath width. CP mode is transmitted with one polarization and received with both of them. As there are only two channels, the decomposition methods and theories which were used for full polarization can not directly apply into it. According to the characteristics of CP mode, the decomposition theory based on partial polarized waves were developed, like the degree of polarization and phase difference (m - δ) decomposition, the degree of polarization and scattering angle (m - α), the degree polarization and the Poincare ellipticity parameter (m - χ) decomposition. Since α and χ are mutual complementary angle, the result of these two decomposition is same. Since the main purpose of decomposition is to classify the different objects, this paper focus on the classification result difference of m - δ and m - α, the interpretation of these results and how to improve the classification based on the better decomposition results. In this paper, the classification results of these two decomposition methods were compared with full polarization classification result. The classification overall accuracy of m - α is 97.17%, whereas m - δ is 88.28%. The kappa coefficient for the former is 0.8500, the latter is 0.8207. Since the volume scattering component is same, the differences were caused by surface scattering component and dihedral component. The statistics of these two components shown that α has better accumulativeness than δ, which lead to the higher classification accuracy. Both of these two method result in higher assessment of volume scattering.

The aim of this paper is to analyze the feasibility of hemi-boreal forest above ground biomass (AGB) estimation based on Tomo-SAR technique. Repeat-path multi-baseline P-band Pol-InSAR data collected during March and May, 2007 in Remningstorp test site is used. The result shows that the correlation coefficient (R) of P-band HH backscattering coefficient reaches 0.87 with the in-situ forest biomass. The R of P-band VV backscattering power at 5m and 10m is 0.71, 0.72 with the in-situ forest biomass, respectively.

The objective of this study is to estimate forest above ground biomass (AGB) of the whole areas covered with forest basing on Polarization coherence tomography (PCT) and polarimetric interferometric segmentation. Two scenes of DLR E-SAR L band quad-polarization images were acquired in Traunstein test site. Results show that there is no saturation using this method even when the biomass ups to 500tons/ha and parameters extracted from PCT is easier to implement in practice.

The primary aim of this study was to extract DEM using Polarimetric SAR Interferometry (Pol-InSAR) ALOS/PALSAR data. We make use of three Pol-InSAR coherence optimization methods, including Singular Value Decomposition, Numerical Radius and Phase Diversity ways, to extract DEM with processing of filtering, unwrapped phase, base-line estimation and so on. At the end, compare optimized results with the single polarimetric interferometry such as HH, HV and VV. It has been observed that optimization ways can reduce the interferometric noise, reduce the phase unwrapping residuals, and improve the precision of the DEM extraction. Meanwhile, Numerical Radius approach has a better result than Singular Value Decomposition and Phase Diversity ways; Interferogram with integrated Contoured Median and Goldstein two-step filter method can further improve and optimize the quality of the interferogram, reduce residual mostly, improve the precision of the DEM, but if two-step filter window setting big will affect the area of non-water-covers while improve the water-covers area.