One of the major challenges in designing an effective intrusion detection system for identifying abnormal behavior in data is the large number of original features, which can significantly impact the classification performance. A high-dimensional feature space often leads to increased computational complexity, decreased model efficiency, and the risk of overfitting. To overcome this challenge, this study presents an intrusion detection system that integrates an optimized feature selection process. The proposed system employs an Enhanced Hybrid Genetic Algorithm (EHGA) during the classification phase to perform feature selection and dimensionality reduction. The EHGA combines the strengths of genetic algorithms with other optimization techniques to improve recognition efficiency while maintaining classification accuracy. The system’s performance is assessed through extensive simulation experiments conducted on widely used intrusion detection datasets. The experimental results demonstrate that the EHGA-based feature selection process effectively reduces data dimensionality, enhances prediction accuracy, and improves the overall detection performance of the intrusion detection system. This method significantly enhances the feature selection performance of the intrusion detection system, offering a promising solution for improving intrusion detection in cybersecurity applications.

Path planning is a critical component in UAV mission execution. While traditional optimization algorithms are mature and effective, they typically rely on expert knowledge and manual tuning, resulting in high development barriers and limited adaptability. With the growing capabilities of large language models (LLMs) in natural language understanding and code generation, we explore the autonomous generation of UAV path planning algorithms using DeepSeek, a general-purpose LLM developed in China. We propose a prompt-driven framework that guides DeepSeek to generate both structural descriptions and implementation code for optimization algorithms. A simulation environment is built to evaluate the generated strategies in terms of feasibility, logical consistency, and baseline performance, with comparisons to classical approaches. Experimental results show that DeepSeek is capable of producing executable and modular optimization strategies, demonstrating strong potential for intelligent algorithm design. Instead of aiming to surpass existing state-of-the-art methods, this work focuses on reducing development costs and enhancing accessibility in control-oriented algorithm design. Our study presents a novel perspective on automated algorithm generation and highlights the practical applicability of LLMs in robotics and intelligent control.

The Chinese Ocean Salinity Mission (COSM) was successfully launched on November 14, 2024, with the objective of observing global sea surface salinity (SSS). To fulfill this mission, two payloads were onboard, one of which is a key instrument called the microwave imager combined active and passive (MICAP). MICAP comprises L-/C-/K-band 1-D synthetic aperture interferometric radiometers (SAIRs) that share a parabolic reflector, as well as an L-band scatterometer. As evidenced by SMOS, accurately locating low- and mid-level radio frequency interference (RFI) signals for SAIR is challenging due to issues such as relatively low sensitivity and Gibbs oscillations in complex scenarios. Owing to the relatively small number of array elements in 1D-SAIRs and advanced data transmission technology, MICAP has achieved the capability to downlink short-duration array raw sampling data before array signal correlation, providing strong support for identifying low- and mid-level RFI signals in complex scenarios. In this article, a signal-level RFI localization method is proposed. First, the strong RFI signal is eliminated by leveraging the spatial point source characteristics of RFI. Then, low- and mid-level RFI detection and localization are achieved by extracting non-Gaussian RFI signals from Gaussian background signals through the calculation of kurtosis spectra. Simulations demonstrate that the detection rate and localization accuracy for low- and mid-level RFI signals can be significantly improved.

To address the limitations of existing particle swarm optimization algorithms in solving discrete problems, this paper proposes a discrete particle swarm optimization algorithm for vehicle routing problem with time windows. This algorithm enhances the velocity and position updating mechanism using an set-based strategy, making it more efficient in the discrete search process. Additionally, to further balance the algorithm’s global search and local development capabilities, this paper introduces a chaotic mapping algorithm and a nonlinear dynamic adjustment parameter strategy to enhance the algorithm’s convergence speed.

The Ice Cloud Imager (ICI) aboard the second generation European meteorological satellites is the first space-borne submillimeter wave radiometer used for ice cloud remote sensing. Since ice clouds simultaneously contain three ice phase particles - ice, snow and graupel - and the physical distribution characteristics and submillimeter wave radiation properties of the three kinds of particles are different, simultaneously retrieving the physical parameters of the three ice cloud particles from submillimeter brightness temperatures is very challenging. This paper proposes a multi-phase ice cloud particle retrieval algorithm based on convolutional neural networks (CNNs) that can simultaneously retrieve total path and profile of ice, snow and graupel particles from submillimeter brightness temperatures. The retrieval experiments using the simulated ICI brightness temperatures show that the average relative error of retrieved total path of the three kinds of frozen particles is all lower than 57% and those of the content profiles is all lower than 68%.

Path planning is an indispensable part of the application of intelligent mobile robots. Q-learning is a type of reinforcement learning without prior knowledge and is currently a popular path planning method. Although there are numerous research articles on Q-learning for mobile robot path planning, the difficulties of stability and convergence speed of its path planning can hinder the effectiveness of mobile robot applications in reality. This paper presents an improved Q-learning algorithm incorporating the A* algorithm (IQLA). First, a goal heuristic function is introduced to perform an initialisation operation on the Q-table, which guides the intelligent body to move toward the target for accelerating the convergence of the algorithm. Second, an adaptive exploration factor is proposed to improve the action selection strategy, which balances the exploration and exploitation of the environment via intelligence. Furthermore, an adaptive distance search range is proposed to accelerate the convergence of the algorithm. Finally, the A* heuristic evaluation function with weights is incorporated into the Q-learning reward and punishment functions to guide the algorithm to quickly converge to the optimum. This paper validates the performance and effectiveness of the IQLA algorithm over comparison algorithms for mobile robot path planning through simulation and comparison experiments.

Session-based recommendation aims to make recommendations for anonymous users based on limited session data. However, traditional session-based recommendation methods fail to capture complex item transitions and simply represent the user's last clicked item as a short-term preference, neglecting the global sequential information of the session. This approach struggles to consider transitions between contexts and cannot accurately capture the user's true intentions. To address these issues, this paper proposes a session recommendation method based on self-attention residual connections and graph neural Hawkes (SRGNH). This method introduces a duallayer network structure consisting of graph neural self-attention residual connection layers and graph neural Hawkes layers, designed to learn users' long-term and short-term preferences, respectively. SRGNH employs a Gated Graph Neural Network (GGNN) to capture complex interactions between nodes, obtaining latent vectors for each item. It incorporates self-attention networks and residual connections to effectively utilize low-level inspired information for capturing users' long-term preferences. The graph neural Hawkes layer combines the Hawkes process with GGNN to capture the relationship between user item clicks over continuous time, accurately representing users' short-term preferences. To better represent user intent, we linearly combine users' long-term and short-term preferences in the end. Experimental results demonstrate that the proposed SRGNH outperforms other recommendation models on the Diginetica, Yoochoose1/64, and Yoochoose1/4 datasets.

Accurately categorizing communities within a social network is a crucial aspect of community detection, carrying significant practical relevance. To achieve a higher quality of community division, we combine reinforcement learning methods to learn the distribution characteristics of community nodes during the iteration process of the algorithm, which guides the nodes to migrate to other communities and enhances the algorithm's global search capability. Through a new$\epsilon$-gradient-greedy strategy, which can obtain a node's gradient information relative to its neighbors and achieve higher performance in local search. To speed up the adaptability of the algorithm at the beginning of the iteration and to alleviate the resolution limitation imposed by modularity optimization, this paper employs a triangular subnetwork-based weight assignment method for balancing the weights of each edge in the network. Experimental results on real-world and synthetic network datasets demonstrate that our method's community identification precision outperforms recent community detection algorithms, exhibiting higher accuracy, higher resolution, and adaptability to various network characteristics and structural changes.

The mirrored aperture synthesis (MAS) was proposed to improve the spatial resolution in passive microwave remote sensing. In MAS, the elements in the (H matrix) are the sampled values of the h function. In this article, the h function considering practical factors is derived. These practical factors include the normalized antenna pattern, the reflector reflectivity, the reflector length, and the distance between the array and the scene. The normalized antenna pattern modulates the received signals. The reflector reflectivity affects amplitudes of the reflected signals. The reflector length determines whether the reflected signals can be received. The distance between the array and the scene influences the incident angles of the signals from the same point source in the scene. The distance also influences the path differences between signals. The formulas and related analysis are verified through the numerical simulations and experiments.

L-band Radio Frequency Interferences (RFIs) seriously contaminate remote sensing data. This poses a major challenge in processing microwave radiometric data and can substantially degrade the quality of the data. There is an urgent need to estimate RFI intensity in order to mitigate Gibbs errors caused by RFIs along the sidelobes. The traditional CLEAN algorithm is limited in its ability to account for the interactions among multiple RFIs, which results in biased intensity estimations. In this paper, the RFI brightness temperature model is modified to incorporate the interactions among multiple RFI sources. Building upon this modified model, we establish fundamental equation sets and propose a numerical solution method for calculating RFI intensity. Experiments and simulations based on Soil Moisture and Ocean Salinity (SMOS) data confirm that the method presented in this paper, which we have named MUSID, outperforms the traditional CLEAN algorithm.

For the tilted mirrored aperture synthesis (MAS), it can obtain different fields of view (FOV) by adjusting the inclination angle of the reflector. However, the tilted MAS microwave radiometer system is more complex. The antennas need to receive both direct signals and signals reflected by different reflectors, and reflector errors will affect the performance of the tilted MAS system. At present, there is no effective method to correct various errors in tilted MAS systems (especially reflector errors), which results in poor quality of brightness temperature (BT) image reconstruction for the tilted MAS. In this paper, we design a network to reconstruct BT images based on CNN and Transformer, and present a method to reconstruct the tilted MAS BT image by using this network. Based on the analysis of the FOV and spatial resolution of the tilted MAS system, a method for collecting the measured training dataset is presented. Using the measured training dataset for network training, the network learns the information of different errors in the tilted MAS system, including the error information of different reflectors and the error information of amplitude and phase. The simulation and experimental results show that the proposed method can obtain BT images with higher reconstruction quality than the impulse matrix reconstruction method.

To increase the spatial resolution of passive microwave radiometry, mirrored aperture synthesis (MAS) was presented. In this letter, the method of cosine visibility extension (CVE) is proposed to further enhance the spatial resolution of 1-D MAS. In the CVE method, a convolutional neural network (CNN) is used to learn the distribution of the cosine visibility (CV), specifically the relationship between the low- and high-frequency CV distributions of various scenes. Then, the high-frequency CVs are estimated by the CNN according to the low-frequency CVs obtained by MAS. The high- and low-frequency CVs are combined in MAS image reconstruction to enhance the spatial resolution of MAS. The simulation and experiment indicate that the CVE method can effectively enhance the spatial resolution of MAS.

Radio frequency interferences (RFIs) in the L-band heavily contaminate remote sensing data and bring many challenges to the product quality of synthesis aperture interferometric radiometers. Detecting and localizing RFIs is the urgent need for switching off these RFIs and conducting mitigation algorithms. The localization algorithm based on the brightness temperature (BT) image is limited by the resolution to separate closely spaced RFIs and achieve high localization accuracy in some cases. To achieve super-resolution, the MUSIC method using subspace decomposition technique is suggested. Nevertheless, when the BT image SNR is low, the power of RFI is insufficient to overwhelm the background scene, and the performance of the MUSIC algorithm is unsatisfactory. In this paper, a further improvement is proposed by combining BT image and subspace decomposition. In the BT image domain, background scene cancellation and RFI target enhancement are carried out for enhancing the SNR. In the frequency domain, the MUSIC algorithm is applied utilizing subspace-decomposition to achieve super-resolution localization. Experiments and simulations based on SMOS data validate that the method presented in this paper performs better than both the classical MUSIC algorithm and BT-based localization algorithm in low SNR cases.

The critical advantage of passive microwave imaging is that it can be used in all-day and in low visibility conditions, such as hazes, fogs, clouds, smokes, and sandstorms. In this article, the ground-based passive interferometric microwave sensor (PIMS) is proposed to detect civil aircrafts, especially in low visibility conditions. The fundamental of civil aircraft detection by a ground-based PIMS is introduced and analyzed. Numerical simulations are performed to assess its feasibility and detection performance, and the impact of the low visibility weather is analyzed and discussed. To verify the practicability of civil aircraft detection by the ground-based PIMS, a series of experiments have been performed by a ground-based X-band PIMS, and a data processing procedure is introduced, which contains a target detection algorithm. Experimental results have demonstrated that the civil aircrafts can be accurately detected and consecutively tracked by the ground-based PIMS using the target detection algorithm. Meanwhile, a mirrored TB phenomenon, the TB change, and an application scheme are analyzed and discussed. As a conclusion, the ground-based PIMS can be considered as a powerful complementary tool for civil aircraft detection.

This study develops a new sea surface temperature (SST) retrieval algorithm based on statistical regression that utilizes WindSat satellite data and in situ SST quality monitor (iQuam) buoy data. The proposed algorithm introduces new rules to remove abnormal brightness temperatures (TB) due to land, sea ice, radio frequency interference (RFI), and sun glint. Besides, SST data from 2019 to 2022 are generated from the HY-2B satellite’s scanning microwave radiometer (SMR) using a two-step retrieval method. Our study reveals that wind speed (WS), cloud liquid water (LW), and wind direction have significant crosstalk effects on SST retrieval, which increases exponentially when the cloud LW exceeds 0.1 mm. The crosstalk effect can be significantly reduced by incorporating WS fitting in the SST retrieval algorithm. By fitting iQuam SST data, the multiple localizing sea surface WS and latitude algorithms are developed, significantly reducing the impact of crosstalk parameters on SST retrieval and improving the SST retrieval accuracy. Also, the algorithm performed well in correcting the nonlinear response of TB and SST. The results reveal that the retrieval algorithm eliminates bias across different WSs, water vapor (WV), and cloud LW ranges and performs consistently on ascending and descending orbits. The overall bias of the SMR four-year SST product is$-0.004\,\,^{\circ }\text{C}$, with a standard deviation (STD) of 0.588 °C, posing a substantial improvement over the existing product with a bias of$-0.022\,\,^{\circ }\text{C}$and an STD of 0.803 °C. Moreover, the four-year fluctuation of STD is very small, indicating excellent stability of the retrieval algorithm.

In this paper, Mirrored Aperture Synthesis with tilting reflectors (MAS-T) is proposed to improve spatial resolution with fewer antennas for passive microwave remote sensing. The principle of MAS-T is given. The initial experimental results demonstrate that MAS-T can achieve higher spatial resolution with the same antenna array compared with conventional aperture synthesis.

Mirrored aperture synthesis (MAS) has been proposed as a novel interferometry to achieve higher spatial resolution in passive microwave remote sensing. The phase and amplitude errors for MAS are a crucial problem that has yet to be analyzed. In this letter, a model for the phase and amplitude errors is established. A correction method based on an external source is proposed to correct the phase and amplitude errors. An analysis of the position of the external source is performed by computing its impact on the radiometric accuracy of a reference scene. The imaginary parts of the cross correlations for MAS are analyzed for the first time. Simulations and experiments are carried out to demonstrate the effectiveness of the correction method.

In this letter, 1-D mirrored aperture synthesis with two tilted reflectors (1-D MAS-T) is proposed to improve the spatial resolution of an antenna array without extending its size. The principle of 1-D MAS-T is given. The size of the reflector is analyzed, and detailed calculation formulae is derived. Numerical simulations and experiments are carried out to illustrate the performance of 1-D MAS-T. The results demonstrate that 1-D MAS-T can achieve a higher spatial resolution than conventional aperture synthesis with the same antenna array.

The arrangement of the antenna array of the mirrored aperture synthesis (MAS) determines the transformation matrix for solving the cosine visibilities. When the transformation matrix is rank deficient, the solved cosine visibilities will introduce the rank-deficient error. For the two-dimensional mirrored aperture synthesis (2-D MAS), the existing literature has discussed the relationship between the arrangement of the antenna array and the rank-deficient error but has not proposed an array that can achieve a full rank transformation matrix, which is call the rank-full array (RFA). Based on a new method for calculating the rank of the transformation matrix and the literature on one-dimensional (1-D) RFAs, this paper proves that 2-D RFA cannot be obtained when the reflectors are all metal, and by introducing a reflector made of magnetic conductor, 2-D RFA can be obtained. Besides, this paper obtained the existence conditions for 2-D RFA. Based on those conditions, two methods are proposed to obtain 2-D RFAs.

The antenna array arrangement determines the rank of the transformation matrix in 1-D mirrored aperture synthesis (1-D MAS). Only when the transformation matrix is of full rank can cosine visibilities be precisely solved from the transformation equations. However, the existing literature states that full rank cannot be realized with the default perpendicular polarization of antennas. In this letter, the transformation matrices of arrays with various polarizations of antennas are discussed, and a type of full array with a full-rank transformation matrix is found. Based on these results, the existence conditions for an array with a full-rank transformation matrix are obtained. In addition, a search algorithm with a shorter search time than the existing algorithm is designed to find low-redundancy arrays with a full-rank transformation matrix. The simulations verify that cosine visibilities are precisely solved from the transformation equations for the array with a full-rank transformation matrix.

The mirrored aperture synthesis radiometer (MASR) has been proposed for high-resolution observation in recent years. Since the MASR is a kind of linear system, the matrix reconstruction method should be an alternative for image reconstruction of a practical MASR. However, the matrix reconstruction method is neither theoretically analyzed nor experimentally validated at present, and the performance of the matrix reconstruction method for a MASR in practical applications is still unknown. In this letter, the H-matrix reconstruction method including the truncated singular value decomposition (SVD) and Tikhonov regularization, not yet applied to a MASR, is introduced. Then, the numerical simulations and imaging experiments are performed to validate the presented method, and the performance of the presented method is also shown. Finally, the comparisons between the presented method and the cosine-transform-based iterative method are made in the view of imaging experiments. The H-matrix reconstruction method is more convenient in the situation of a small MASR with a small alias-free field of view (FOV).

The demand for high-precision sea surface temperature (SST) has been growing rapidly in recent years because SST is one of the key parameters to describe the thermal state of the sea surface. This article analyzes the differences between microwave remote sensing and infrared remote sensing for SST, including the spatial resolution difference and the penetration depth difference. In order to improve the accuracy of retrieved SST, this article proposes a joint inversion algorithm for SST from combining microwave brightness temperature (BT) and infrared BT, which has also taken the influence of wind speed and atmosphere into consideration. Experiments confirm that SST data obtained from the joint inversion algorithm are more accurate than those obtained from the existing inversion algorithms.

Finding out and turning off the radio-frequency interference (RFI) sources as many as possible is an important work for synthetic aperture interferometric radiometer (SAIR). While the impact of strong RFIs on reconstructed brightness temperature (BT) image is clearly observable, the presence of low- or moderate-level RFIs is often hard to be aware of, leaving the RFI detection and localization a difficult problem. In this article, an improved RFI detection method is proposed by making use of the point-source ripple to give prominence to the RFIs presented in the SAIR imagery. The method tests based on Soil Moisture and Ocean Salinity satellite (SMOS) visibility samples and the performance evaluations by numerical simulations validate the correctness and effectiveness of the developed method.

The presence of unauthorized radio frequency interference (RFI) sources seriously affects the retrieval of brightness temperature of a synthetic aperture interferometric radiometer (SAIR). Postobservation RFI geolocation is important for improving the RFI situation hereafter and mitigating the impact of the identified RFIs. Previous works have demonstrated the potential of using high-/super-resolution direction-of-arrival (DOA) estimation techniques to achieve accurate localization of RFI sources in SAIR imagery. In this article, a multiple snapshot difference method is proposed to further reduce the RFI source geolocation bias. The covariance matrices of the consecutive snapshots with power changed RFIs are picked out and subtracted to cancel out the background scene. A MUSIC-based DOA algorithm is developed. Numerical simulations validate the theoretical correctness and the practical effectiveness of the proposed method.

Setting two reflectors perpendicular to each other and an array produces mirrored aperture synthesis (MAS), which obtains a higher spatial resolution than aperture synthesis (AS) for the same antenna array. The proposal of the MAS theory and the experimental verification suggest that the spatial resolution can be improved by setting the reflector. This paper proposes a method in which four tilted planar reflectors are set around an antenna array. This method is named two-dimensional (2-D) mirrored aperture synthesis with four tilted planar reflectors (2-D MAS-T). Because 2-D MAS-T uses more reflectors than MAS, the spatial resolution is further improved. The principle of 2-D MAS-T with an antenna array is given in this paper. The relationship between the size of the reflectors, the spatial resolution and the field of view (FOV) is obtained. The simulation and experimental results demonstrate that 2-D MAS-T can achieve a higher spatial resolution with the same antenna array than 2-D AS and 2-D MAS.

In mirrored aperture synthesis (MAS), the existing brightness temperature image reconstruction methods include inverse cosine transform and impulse matrix reconstruction methods. However, the quality of the MAS brightness temperature images reconstructed by the existing methods is still poor and needs to be improved. This article proposes a method of MAS brightness temperature image reconstruction with deep convolutional neural network (CNN). The network includes two fully connected (FC) layers, multiple convolutional layers, and deconvolutional layers, which realize the image reconstruction for MAS. This method uses deep CNN to learn the MAS image reconstruction mapping and system errors, so as to improve the performance of the brightness temperature image reconstruction. Both simulation and experimental results verify that the performance of the proposed MAS-CNN method is better than the existing MAS image reconstruction methods.

Lane detection plays a key role in autonomous driving. While car cameras always take streaming videos on the way, current lane detection works mainly focus on individual images (frames) by ignoring dynamics along the video. In this work, we collect a new video instance lane detection (VIL-100) dataset, which contains 100 videos with in total 10,000 frames, acquired from different real traffic scenarios. All the frames in each video are manually annotated to a high-quality instance-level lane annotation, and a set of frame-level and video-level metrics are included for quantitative performance evaluation. Moreover, we propose a new baseline model, named multi-level memory aggregation network (MMA-Net), for video instance lane detection. In our approach, the representation of current frame is enhanced by attentively aggregating both local and global memory features from other frames. Experiments on the new collected dataset show that the proposed MMA-Net outperforms state-of-the-art lane detection methods and video object segmentation methods. We release our dataset and code at https://github.com/yujun0-0/MMA-Net.

Fitness games recently attract much attention these years due to its combination of playability and athleticism. However, most fitness games are entertainment for a single person, with only a few deliver distinctive experiences for multiplayers. Enabling interaction between multiple players would be more enjoyable due to exciting cooperation among players. Considering a Big Stomach Challenge for two players, a certain amount of food can be only eaten when a mouth size, represented by the distance between players is reached collaboratively. Similarly, a certain type of food can only be picked up when the food grabbing speed, denoted by the approaching speed between players, is fast enough. Such games require accurate ranging and speed estimation in a relatively long distance (1-15 m) to deliver a good gaming experience. However, existing ranging schemes cannot meet the above requirements. They either cannot work under Doppler channels or have to strike a balance between accuracy and operational range, prohibiting a heuristic implementation for the above games. To this end, we design MotionBeep, a novel acoustic ranging scheme that achieves centimeter-level ranging and dm/s-level speed estimation accuracy under representative indoor and outdoor scenes within 15 m. In MotionBeep, we design a new working paradigm and incorporates a state-space model to maintain accurate ranging in both static and dynamic channels. We have implemented a system prototype and evaluate its performance in representative environments. Evaluation results demonstrate that MotionBeep achieves a median of centimeter accuracy with up to 15 m even under Doppler effect.

In 2-D mirrored aperture synthesis (2-D MAS), the array configuration determines the rank of the transformation matrix, which can affect the accuracy of the solved cosine visibilities. Ultimately, errors in solved cosine visibilities degrade the quality of reconstructed brightness temperature images. In this letter, the maximum rank of the transformation matrix is analyzed and proven by mathematical induction. An array optimization model of 2-D MAS based on the “maximum-rank” criterion is established, and optimal arrays are presented. Finally, the simulations and experiments are carried out to demonstrate the effectiveness of the optimization model.

In two-dimensional mirrored aperture synthesis (2-D MAS), the rank of the transformation matrix can affect the accuracy of the solved cosine visibilities; therefore, it has an impact on the accuracy of the reconstructed brightness temperature image. In this article, the influence of the rank deficient on the accuracy of the reconstructed brightness temperature image of 2-D MAS is discussed. An analysis of the rank-deficient error is performed by computing its impact on the radiometric accuracy for a reference scene. Two correction methods based on multiple measurements are proposed to correct the rank-deficient error. The simulations and experiments are carried out to demonstrate the effectiveness of the proposed methods.

To monitor sea surface salinity (SSS) in coastal zones with high temporal and spatial resolution, an L-band phased array radiometer is developed. However, it is well known that the L-band radiometers suffer from serious radio frequency interference (RFI) effects. To mitigate the RFI effects, an RFI detection and mitigation algorithm is proposed for the L-band phased array radiometer. The experiments in coastal zones are performed to assess the performance of the RFI algorithm. The results indicate that the detection and mitigation algorithm exhibits good performance and can effectively mitigate the RFI effects.

Radio frequency interferences (RFIs) are present in the data collected by a synthetic aperture interferometric radiometer (SAIR), and these would seriously affect the retrieval of brightness temperature (BT), if not properly handled. Due to the truncated Fourier characteristic, RFIs create ripples that extend over a large set of pixels of the whole image, which is difficult to cancel out their impacts at the BT domain. The current strategy relies on removing the unwanted sources at the visibility level (Fourier domain) with a set of synthetic visibilities of the RFI sources for a given snapshot. However, a major problem is that, as unauthorized emissions, the energies of RFIs are typically unknown and the estimation to the sources' temperature could be inaccurate without credible prior information. In this article, a subspace algorithm is proposed to handle the RFI mitigation problem by exploiting RFI's point-source characteristic, where the visibilities related to the RFIs are excluded from that of the BT scene through an orthogonal design without the need of knowing the sources' power. Both the numerical simulations and the proof-of-concept experiment validate the theoretical correctness and the practical effectiveness of our proposed method.

The mirrored aperture synthesis radiometer (MASR) has been proposed as a promising technique for Earth observation. However, considering the system imperfections, the cosine visibility function and the brightness temperature distribution do not constitute a cosine transform pair. The method to improve the quality of reconstructed brightness temperature images for a practical MASR has not yet been developed. In this article, the complete formulation of cosine visibility functions in a practical MASR is derived to better understand the measurement of a MASR with non-negligible effects of the system imperfections. The array factor of a practical MASR is analyzed. Then, the alias-free field of view (FOV) for a MASR is presented, and an iterative method is proposed to reconstruct the brightness temperature image in the alias-free FOV to reduce the computational burden. The numerical simulation and experimental results demonstrate that the proposed method can be applied to practical MASRs and that the reconstruction quality is significantly improved by the proposed method. Finally, the H-matrix inversion method is discussed as an alternative reconstruction method for a practical MASR. Compared with the H-matrix inversion method, the proposed method is more convenient for practical applications.

Ship detection is important for a wide range of applications. In this article, an airborne passive interferometric microwave sensor (PIMS) is proposed as a powerful complementary tool for ship detection. The fundamental of ship detection by the airborne PIMS is introduced. A specification called “the detection factor” is addressed to quantitatively assess the performance of the airborne PIMS for ship detection. The detection probability is discussed and addressed based on the constant false-alarm rate (CFAR). Numerical simulations are performed to demonstrate the feasibility of ship detection by the airborne PIMS. The impacts of the atmosphere and the sea wind on the performance of the airborne PIMS for ship detection are also addressed in terms of theoretical analyses and numerical simulations. The airborne experiments are also carried out by an X-band PIMS to verify the practicability of ship detection by the airborne PIMS in a sunny weather and a cloudy weather. The data processing procedure and a ship detection algorithm in the experiments are introduced. The airborne experimental results reveal that the ships can be effectively detected and tracked by the airborne X-band PIMS in a sunny weather and a cloudy weather. It demonstrates the practicability of ship detection by the airborne PIMS. The ship detection probability is also analyzed, which agrees well with the theoretical detection probability.

Aperture synthesis technique is able to provide high spatial resolution without requiring very large and massive real aperture. Recently, in addition to the well-known aperture synthesis radiometer, the concept of mirrored aperture synthesis has been proposed, and the experiments has been carried out to validate this technique. However, the field of view (FOV) of a mirrored aperture synthesis radiometer (MASR) has not been analyzed. In this paper, the FOV of an one-dimensional MASR is analyzed based on the symmetric convolution. A simulation and experiment are carried out to validate the derived FOV. The FOV of a two-dimensional MASR can be analyzed in the same way.

Indoor localization has witnessed a rapid development in the past few decades. Tremendous solutions have been put forwarded in the literature and the localization accuracy has reach an unprecedent centimeter-level. Among the available approaches, acoustic-enabled solutions have attracted much attention. They customarily achieve decimeter-level localization accuracy with affordable infrastructure costs. However, there still exist several open issues for the acoustic-based approaches which prohibit their wide-scale adoptions. First, although extra infrastructures (i.e., beacons) are economical, deployment, and maintenance can incur excessive labor cost. Second, current approaches have much latency to obtain a location fix, making it infeasible for mobile target tracking. Third, the localization performance of current solutions degrades easily by the near-far problem, multipath effect, and device diversity. To address these issues, this paper presents an asynchronous acoustic-based localization system with participatory sensing. We leverage the collaborative efforts of the participatory users who are relatively stationary in indoor environments as virtual anchors (VAs) to eliminate the predeployment and post-maintenance costs incurred in traditional anchor-based solutions. To mitigate the latency to obtain a location fix, we design an orthogonal ranging mechanism to enable concurrent beacon message transmission, which is $2\boldsymbol \times $ faster than previous work in obtaining a location fix. Moreover, we propose a robust method to address the near-far problem and device diversity, and we conquer the multipath problem via a genetic algorithm-based approach. Our VA-based system is self-deployable, cost-effective, and robust to environmental dynamics. We have implemented and evaluated a system prototype, demonstrating a median accuracy of 0.98 m in typical indoor settings.

The spatial resolution is still a problem in passive microwave remote sensing, especially in low frequency. In recent years, the satellite formation flying has been proposed. Based on this technique, a large array is able to be synthesized in orbit to achieve higher spatial resolution. However, it is a big challenge for the control system to constrain all the satellites in a coplane in orbit. The 3-D array configuration is a good choice for a synthesized array based on satellite formation flying. In this paper, the complete formulation of visibility functions, including system imperfections, in a 3-D aperture synthesis radiometer (3-D ASR) is derived. The array factor of a 3-D ASR is defined. The reconstructed modified brightness temperature (BT) is a 3-D linear convolution of the modified BT and the array factor. Based on this relationship, the reconstruction method for a practical 3-D ASR is studied. The numerical results demonstrate that the reconstruction method is correct and stable. Finally, a discussion is given to analyze several existing methods that were proposed to reconstruct BT image for 3-D arrays in radio astronomy and earth observation. Compared with these existing methods, our imaging method is more suitable for earth observation based on the technique of satellites formation flying in low earth orbit. In addition, according to the derivations, some mature techniques that were developed for 2-D ASRs may be applied to 3-D ASRs.

The concept, principle, and method of microwave radiometric imaging with mirrored aperture synthesis (MAS) were proposed by the Huazhong University of Science and Technology (HUST), Wuhan, China. MAS can achieve higher spatial resolution without extending the size of the antenna array. However, the MAS principle has not been sufficiently validated by practical experiments. To solve this problem, an innovative experiment system of MAS at the V-band (MAS-V) has been developed by HUST. Experiments on the interference fringe pattern, spatial resolution, as well as the imaging of an electric warmer and the absorbing material in the styrofoam box filled with liquid nitrogen are performed. The initial experimental results demonstrate that MAS can achieve higher spatial resolution with the same antenna array compared with the conventional AS. For MAS, the experimental results are consistent with theory and simulation results.

A numerical simulator for analysis of the geostationary orbit multispectral passive microwave (Geo-MW) mapping and sounding is described, which mainly includes upwelling brightness temperatures forward, microwave radiometer payload simulation and atmospheric profile retrieval. This simulator allows evaluation and optimization of the ability of microwave sensors to retrieve atmospheric temperature and humidity profile. In this paper, end to end simulation study of a Geo-MW radiometer observation at selected frequencies from 50 to 425 GHz with a real-aperture antenna is performed and the accuracy of the brightness temperature measurement and the atmospheric temperature and humidity profile sounding are quantitatively analyzed and evaluated.

Mirrored aperture synthesis (MAS) has been proposed to utilize a few antennas to provide high spatial resolution for atmospheric remote sensing. In order to verify the fundamentals of mirrored aperture synthesis (MAS) further, a prototype working at V band was developed in the past two years. In this paper, the prototype is briefly introduced, and then some indoor experiments and the experimental results for one-dimensional MAS based on the prototype are presented, mainly including the fringe pattern experiment for verifying the correlation output and the imaging experiment based on two point sources for evaluating the spatial resolution of MAS.

Mirrored Aperture Synthesis (MAS) was proposed to improve spatial resolution for passive microwave remote sensing. However, the MAS theory needs experimental verification. In this paper, an Experimental System of MAS (MAS-V) at V frequency band is introduced, which is developed for verifying the principle and performance of MAS. MAS-V is composed of an antenna array, reflectors, a receiving channel array, a synchronous acquisition subsystem, a computing server, and a rotatory platform. The initial experimental results demonstrate that the principle of MAS is valid. The experimental spatial resolutions are consistent with the theoretic spatial resolutions.

In this letter, 1-D mirrored aperture synthesis with a rotating reflector (1-D MAS-R) is proposed to improve the spatial resolution and reduce the number of required antennas for passive microwave remote sensing. The principle of the 1-D MAS-R with an antenna array is given, and from the principle, the 1-D MAS-R with only one antenna can also reconstruct the image of the scene. Simulation results demonstrate the validity of the 1-D MAS-R even with only one antenna, and the spatial resolution is improved by increasing the distance between the reflector and the antenna or antenna array.

Rotating mirrored aperture synthesis (RMAS) has been proposed as a new method for high spatial resolution earth observation from the geostationary orbit. However, in previous researches, the reflector sizes are assumed to be infinite so that all antennas in the antenna array can receive the reflection signals. This assumption is obviously unacceptable in practical applications. How to estimate the reflector sizes is still a problem. In this letter, the principle of RMAS is briefly reviewed. Then, the reflector sizes of an RMAS radiometer are analyzed based on solid geometry, and detailed calculation formulae are derived. A numerical example is given for calculating the reflector sizes of an RMAS radiometer applied in the geostationary orbit.

The mirrored aperture synthesis radiometer (MASR) has been proposed as a new technique for high-resolution observation. Compared with ASRs, MASRs have the advantage of lower system complexity. However, the relationship between MASRs and ASRs has not been studied. In order to thoroughly study MASRs, it is necessary to establish the relationship between MASRs and ASRs. In this letter, the array factor of 1-D MASRs in the discrete cosine transform domain (DCT-domain) is defined. The reconstructed image for a 1-D MASR is a symmetric convolution of the observed brightness temperature distribution and the defined array factor in the DCT domain. Since a symmetric convolution can be turned into a linear convolution, the relationship between 1-D MASRs and 1-D ASRs can be established. A 1-D MASR is equivalent to a 1-D ASR that has a mirrored window. Additionally, for the equivalent 1-D ASR, its observed scene is a symmetrically extended real scene. This established relationship is validated by the simulation results. In practical applications, a MASR can be understood as an ASR.

For Soil Moisture And Ocean Salinity (SMOS) data, significant errors exist near coastal areas because of the contamination by the nearby land. For analyzing the origin of the land contamination, in this letter, it is found, from the global map of SMOS data error, that although the SMOS data error due to land contamination near coasts varies in different regions, the characteristic that the error increases significantly in proximity to land is similar in global scope. The detailed analysis of SMOS brightness temperature (TB) error in the selected area reveals a decreasing trend with the increase of the distance to coast (DC). An SMOS TB measurement model according to geophysical parameters of the selected area and SMOS/microwave imaging radiometer aperture synthesis antenna array is established to analyze the origin of the TB error variation due to land contamination. The simulation results, which agree with the SMOS TB data analysis, show that within 40 km of DC, TB error is large and decreases sharply from ~60 to ~4 K with the increase of DC, since the mainlobe of the antenna array is departing from land to ocean; during 40-400 km of DC, TB error decreases smoothly from ~4 to ~0.15 K, since the lower near sidelobes are observing and leaving land; TB error slightly decreases to 0 from 400 to 800 km when the lower far sidelobes leave land. The study of the origin of land contamination on ocean TB will be helpful for improving the observation of salinity near coastal areas.

Mirrored aperture synthesis (MAS) can improve spatial resolution compared with conventional aperture synthesis (AS). In this paper, for 1D MAS and 2D MAS, the array optimization models with the autocorrelation are established. The optimal array configurations based on the models are presented. The simulation results demonstrate that the optimal array configurations have good performance in imaging and can achieve higher spatial resolution than other MAS array configurations with the same antenna number.

For one dimensional large aperture synthesis radiometers (ASRs), the low redundancy linear arrays (LRLAs) are usually the choice for the reason of the lowest system complexity. However, the number of LRLAs is very few, which makes the antenna arrangement of LRLAs inflexible. In this paper, the array configuration optimization for AFF-based nonuniform array is proposed. The AFF-based nonuniform array after the array configuration optimization is called the optimized nonuniform array (ONA). The method how to find out the ONAs is introduced. In numerical results, some examples of ONA are given. The numerical result demonstrates that the performance of ONAs is almost equivalent to LRLAs. Since the antenna positions of ONA are non-integers, in fact, the number of ONAs is infinite in theory, which can be a supplement to the LRLAs in practical applications.

Mirrored Aperture Synthesis (MAS) was proposed to improve spatial resolution with fewer antennas for passive microwave remote sensing. In this paper, an Experiment System of MAS (ESMAS) at 36.4GHz is introduced, which is designed for verifying the principle and performance of MAS. ESMAS is composed of an antenna array, four reflectors, a receiving channel array, a synchronous acquisition subsystem, a processor, and a rotatory platform. The initial experiment results are given.

To assimilate satellite-based passive microwave observation over heavy clouds and precipitation into numerical weather prediction (NWP) systems and thus to improve the performance of it has become an intensely studied topic. These attempts rely on the development of a radiative transfer (RT) model that accounts for particle scattering and accurately simulates the observation process at an acceptable computational speed. In this paper, two existing RT models (the RTTOV and the DOTLRT) are tested and the accuracies are evaluated by comparing the simulated brightness temperature with real observational data of a satellite-based sounder ATMS. RTTOV is much more well-known and widely applied, however, since these two models use different solvers to deal with the scattering effect, whether it is possible to improve the performance of RT model is still open to discussion.

Aperture synthesis with high spatial resolution would seriously increase the hardware requirements and system complexity. To reduce the system complexity, Rotating mirrored aperture synthesis (RMAS) that combines the antenna array rotation with mirrored aperture synthesis was proposed to reduce the number of antennas. In this paper, the sieving method is presented to optimize the array configuration for RMAS. The initial simulation results demonstrate the validity of the proposed method and the optimized array of RMAS can reconstruct the brightness temperature of the observed scene with fewer antennas.

For SMOS data, significant errors exist in coastal areas because of the contamination by the nearby land. In this paper, the analysis of SMOS brightness temperature (TB) data in coastal area of South China Sea (SCS) reveals a decreasing trend with the increase of the distance to coast. A SMOS TB measurement model according to geophysical parameters and SMOS/MIRAS antenna array is established. The simulation shows that TB is large within 40 km since land is much warmer than ocean and is observed by the mainlobe of the antenna array. Then the simulation result of land contamination is used for correction of SMOS measured TB data in coastal area of SCS. Then the corrected TB is applied for sea surface salinity (SSS) retrieval, which reduces SSS outliers and improves the accuracy of SSS in coastal area of SCS.

In aperture synthesis radiometers (ASRs), the mutual coupling effect between antennas is a key problem, which degrades the performance of ASRs and should be compensated. In this paper, an improved compensation method is proposed for ASRs, which is based on the receiving mutual impedance. The proposed method is verified by a one-dimension 5-channel L-band ASR. The experimental results show that the proposed method is superior over the existing method based on the transmitting mutual impedance, and is more appropriate to compensate the mutual coupling effect for ASRs.

Nonuniform aperture synthesis radiometers (NASRs) have the advantage of flexibility in practical applications. However, the main limitation of NASRs for Earth observation is the poor reconstruction quality. In this letter, the array factor of 1-D NASR is analyzed. Array factor forming (AFF) is introduced to improve the reconstruction quality of 1-D NASRs. The limitations of the AFF on array configurations are given. The NASR that meets the given limitations is called the optimizable NASR (ONASR). The numerical results and experimental results demonstrate that the AFF is able to improve the reconstruction quality of 1-D ONASRs. To assess the performance of the AFF thoroughly, the comparisons are made against the linear interpolation and the regularized G-matrix method. Meanwhile, the comparisons between the AFF-based 1-D ONASRs and the 1-D uniform ASRs are also made. The comparison results demonstrate that the AFF can obtain better reconstruction quality than the linear interpolation and the regularized G-matrix method. Additionally, the comparison results also demonstrate that the reconstruction quality of AFF-based 1-D ONASRs can approach that of 1-D uniform ASRs.

The calibration of aperture synthesis radiometers (ASRs) with large arrays by internal noise injection suffers from high increased mass and volume and is not capable to deal with the out-of-plane distortion of antenna arrays. In this letter, a hybrid calibration method is proposed, which combines the redundant baselines and reduced noise injection. The hybrid method needs only a small noise injection network and can deal with the out-of-plane distortion of antenna arrays. The performance of the hybrid method depends on the noise injection element distribution, which is analyzed and given based on minimizing the root mean square of all residual amplitude and phase errors. Simulation results demonstrate its performance. The proposed hybrid method is particularly helpful to the calibration of ASRs with large arrays in geostationary orbit.

The numerical simulations of imaging technology for analysis of geostationary multispectral passive microwave observation is described. This paper compares the abilities of three candidate passive microwave sensors to image the upwelling atmospheric brightness temperature. Presented are scattering-based simulations of a land falling hurricane that illustrate the imaging capabilities of a filled-aperture antenna instrument refer to GEM, a Y-shaped aperture synthesis array instrument refer to GeoSTAR and a Ring-shaped aperture synthesis array instrument refer to GIMS.

Aperture synthesis technique can provide high spatial resolution without requiring very large and massive real aperture. However, large aperture synthesis systems are very complicated. In this paper, Rotating Mirrored Aperture Synthesis (RMAS) is proposed, which combines rotating and mirrored aperture synthesis to improve spatial resolution with fewer antennas. The principle of RMAS is presented. The initial simulation result shows the RMAS system can approximately reproduce the brightness temperature image of the observed scene.

Nonuniform aperture synthesis radiometers (NASRs) are emerging in Earth remote sensing. The main disadvantage of NASRs is the complexity of the image reconstruction. In this letter, the gridding method is introduced as an efficient method to reconstruct brightness temperature images for NASRs. In the gridding method, a Voronoi diagram is applied to dividing the sampling region in the spatial frequency domain into a number of small cells, and the area of each cell is regarded as the density compensation factor. Meanwhile, a method is proposed to produce the outermost Voronoi cells for the outermost visibility samples. The errors induced by using the gridding method are analyzed. The nonuniformity factor (NF) is defined to indicate the nonuniformity of a sampling pattern. The numerical results verify that the gridding method can be applied to image reconstruction for NASRs and that the accuracy of reconstructed images is dependent on NF. The comparison between the gridding method and the nonuniform fast Fourier transform algorithm shows that the gridding method has lower computational complexity.

In order to quantitatively interpret topographic effect on Chang'E (CE) microwave data, a detailed method to compute brightness temperature (TB) over a lunar crater is proposed, which incorporated the effect of surface tilts. The method improves the effective solar irradiance model of the lunar surface to obtain the temperature profile of the lunar crater. The calculated TB at 37 GHz with the proposed computation method, which is based on three digital elevation models (DEMs) from different sources, are consistent with the observed TB from the CE-2 microwave radiometer. The simulated behavior of TB across crater Hercules reproduces the TB undulation observed by CE in a single swath. TB is significantly affected by the lunar dust of a lunar crater and affected by albedo and emissivity in a lesser degree. Based on the explanation with simplified models, the TB variation over a crater is proved to be significantly affected, through physical temperature, by the crater shape described by DEMs. With the simplified crater model, the amplitude of the TB oscillatory curves is proved to depend on the crater shape.

Mirrored interferometric aperture synthesis (MIAS) can reduce the complexity of large IAS systems. In this paper, UV sampling, spatial resolution, sensitivity, and image reconstruction of 1-D MIAS are analyzed, which are not addressed before. Numerical simulation and experiments are carried out to illustrate the performances of MIAS. The results demonstrate the validity of MIAS and the improvement of spatial resolution.

A novel compact size dual-band dual-polarized antenna array for MIMO WLAN is reported. The array element comprises a periodic antenna with bowtie dipoles and a printed dipole antenna with a reflector and a director. The presented design is characterized by dual-band operation, good front-to-back ratios, average gains of 4 and 5 dBi over the 2.4 and 5.2 GHz bands respectively. A prototype 12-element array exhibits dual broad bandwidth and low mutual coupling among 2.25GHz-2.6GHz and 4.95GHz-6GHz. The measured results indicate the array is suitable for 802.11a/b/g/n systems employing MIMO and beam selection techniques.

The calibration of aperture synthesis radiometers (ASRs) by the standard method of noise injection would seriously increase hardware requirements and system complexity. To reduce the network of noise injection, redundant space calibration (RSC) method has been considered. However the number of error phases is larger than the number of independent equations. In this paper, an external calibration method with 120-degree antenna array rotation for geostationary ASR with staggered Y-shaped array is proposed. More redundant baselines are produced by rotation. The equations by rotation and by RSC are combined for solving the phase errors. Basic procedure on this method and preliminary simulation are introduced. As another advantage, if twice 120-degree rotation is taken, one of the antenna arms can be removed from staggered Y-shaped arrays with the missing baselines supplied by the rotations. In this way, the number of antenna elements can be reduced by 1/3.

The on-board calibration of aperture synthesis radiometers (ASRs) with large arrays by the standard method of noise injection would seriously increase hardware requirements and system complexity. To avoid the use of noise injection, an external phase calibration method with antenna array rotation is proposed in this letter, which uses the observation scene as reference without needing for an external calibrator. The relationship of the visibility samples before and after the rotation is established and used to solve for the instrumental phase errors. The proposed method has been proved to be valid by simulations as well as some preliminary experimental results. It is applicable to geostationary ASRs with rotating array such as the geostationary atmospheric sounder.

Aperture synthesis technique can provide high spatial resolution without requiring very large and massive real aperture. However, for a large aperture synthesis system, which will involve hundreds of antennas and thousands of correlators, system and its calibration are very complicated. In this letter, mirrored interferometric aperture synthesis (MIAS) is proposed, which can achieve the same spatial resolution as a large traditional aperture synthesis system but needs fewer antennas. First, the imaging principle of MIAS is presented. A new concept, named Cosine Visibility, is proposed to replace the visibility function used in traditional aperture synthesis. The relationship between the brightness temperature and the cosine visibility is a Cosine Transform. Inverse Cosine Transform can be applied to reconstruct the image of brightness temperature. Then, an example for MIAS is given, and a method is proposed to handle the problems of baselines missing and the rank defect associated with the underdetermined linear equations which relate the cross correlation between signals collected by pairs of antennas with the cosine visibility. Moreover, MIAS with a small array can provide higher and higher spatial resolution by combining more and more linear equations with the help of adjusting the distance from the array to the reflector. The simulation results demonstrate the validity of MIAS and the improvement of spatial resolution. The study in this letter provides a means to reduce the complexity of system and calibration of large traditional aperture synthesis systems.

In this letter, a 16-element imaging radiometer using the digital beamforming technique is described. The system operates in the Ka-band in order to have high spatial resolution. The principle of an image reconstructing system is described. A series of experimental results is reported to demonstrate the effect of the system architecture.

In the above titled paper (ibid., vol. 7, no. 2, pp. 329-332, Apr. 10), we omitted the sources of funding for our work. That is provided here. We also add an additional author, Xiaohu Ge, who assumes now the role of corresponding author.

A general platform for millimeter wave synthetic aperture radiometers is introduced in this paper. The platform consists of hardware and simulation software, and has a flexible and open structure. Simulation and experiment results show the platform is suitable for simulation of synthetic aperture radiometer performance, algorithm performance, error influence on radiometer performance, and calibration performance. The platform can be used for radiometry simulation and design of synthetic aperture radiometers.

Efficient load balancing algorithm is indispensable to serve more mobile stations in the heterogeneous wireless networks. In this paper, we propose a dynamic load balancing algorithm based on sojourn time for heterogeneous multitier wireless networks consisting of macrocell cellular network and microcell cellular network. The sojourn time is calculated by the velocity, direction of motion and position of mobile station. This algorithm is able to balance load by transferring some ongoing calls with longer sojourn time from overloaded cells to overlapping under-loaded heterogeneous cells. The number of transferred ongoing calls per load balancing period is calculated by the new calls arrival rate of overloaded cells and the workload states of overlapping cells. In addition, high-speed mobile stations can hand off from macrocells to microcells and slow mobile stations can hand off from microcells to macrocells, which can decrease the call dropping probability. Simulation results show that call blocking probability, call dropping probability and overall system utilization using our proposed dynamic load balancing algorithm are improved significantly.

Studies on microwave radiation of many targets, such as air, ocean, ice, snow, vegetation, rock, sand, and so on, lead to the radiometric models of the targets. The model uses one or more formulas to represent the radiation of one target. A neural network (NN) is introduced to represent the antenna temperature (AT) or brightness temperature (BT) of the seven types of plane targets: water, concrete road, asphalt road, loess, grassland, crushed stone, and vegetation. The same NN can simulate the relationship of AT (or BT) to observation angle, surface temperature, and polarization of the seven types of plane targets. The agreement between the prediction of NN and the measured AT (or inverted BT) shows that the same NN can give good prediction of the AT (or BT) of the seven types of plane targets.