Soil moisture (SM) is a very important physical parameter in land surface processes. The low-resolution microwave products are extremely useful for large-scale studies, but are limited in their ability to resolve landscape-level variability. In this study, to overcome this limitation, we adopted three different deep learning based downscaling methods and performed a comparative analysis. Firstly, a downscaling method based on a deep belief network (DBN) model with a fully connected structure was employed to fit the complex nonlinear relationship between soil moisture and the auxiliary surface parameters. Then, to improve this simple point-to-point relationship, a neighborhood constraint based improved DBN model was developed to consider the effect of local spatial correlation among the surface factors on soil moisture. Finally, to maintain the integrity of the spatial structure in the process of model construction, a residual network (ResNet) model consisting of several residual dense blocks (RDBs) was introduced to use convolutions to obtain more complete and powerful spatial feature maps. The Tibetan Plateau was selected as the study area because of its importance to the global water cycle. The four soil moisture monitoring networks in the research area were used to verify the effectiveness of the proposed methods in the downscaling of soil moisture products, and four quantitative indicators were used to evaluate the effectiveness of the methods. From the verified results, it is shown that the three deep learning methods can maintain a higher correlation and better reduce the bias, on the whole, and the ResNet model, in particular, shows a higher stability. From the perspective of the spatial patterns and details, when compared to back-propagation neural network (BPNN) and random forest (RF) models, the three deep learning methods can provide more feasible spatial patterns and details, as well as reducing the uncertainty in the central regions of the Tibetan Plateau. The ResNet model shows a superior ability to enhance the texture details with lower uncertainty, due to the fact that it can meet the requirements of fitting the soil moisture to complex surfaces. Furthermore, the results of the ResNet model can also effectively capture the temporal changes of the microwave soil moisture product well. 

Downscaling of Soil Moisture Products Using Deep Learning: Comparison and Analysis on Tibetan Plateau

Target detection in the presence of main-lobe deception jamming has received intensive attention. Generally, traditional target detection with additive jamming can be regarded as an adjacent process of jamming suppression and target detection. Since target information can be lost in jamming suppression, the detection performance can degrade severely. Aiming at this issue, an end-to-end anti-jamming target detector is proposed based on convolutional neural network (CNN) in the presence of interrupted-sampling repeater jamming. The CNN method first converts the single-pulse compression filter into a series of feature extraction filters, accumulating the energy of various features in various dimensions and on multiple scales. Then, a feature fusion filter added after the feature extraction stage is utilized to suppress jamming features while simultaneously retaining the actual target features. The two stages can be achieved in the CNN structure, and all the filters in this method are obtained by training the CNN. Numerical simulations show the efficiency of the proposed method.

An End-to-End Anti-Jamming Target Detection Method Based on CNN

Signal structure information-based target detection with a fully convolutional network

While recent years have witnessed an increasing number of commercial applications of unmanned aerial vehicles (UAVs), an imperative problem people have to face is the rapid growth of malicious use. So, it is imperative for security agencies to develop anti-UAV technology. The introduction of deep learning (DL) has a positive influence on radar signal processing, but DL-based methodologies have yet to be widespread in radar target detection because of the lack of unique architecture based on radar echo characteristics and the annotation method of radar data. In this article, a novel Transformer-based architecture is proposed, which transforms the problem of UAV detection into a binary classification task in each range cell. The complex encoder architecture and the Transformer-based extractor are designed to extract the Doppler frequency shift feature and the micro-Doppler signature (mDS) of a UAV simultaneously. The well-designed architecture based on radar echo characteristics can achieve a combination training of echoes with different coherent processing intervals (CPIs). In addition, we provide an annotation method and a data augmentation skill for our real measured dataset. The results of the experiment demonstrate that the proposed method has better detection performance and measuring accuracy under different SNRs in comparison with traditional radar target detection and other DL-based methods. 

Echoformer: Transformer Architecture Based on Radar Echo Characteristics for UAV Detection

The multivariate range function of the high-speed maneuvering target induces modulations on both the envelop and phase, i.e., the range cell migration (RCM) and Doppler frequency migration (DFM) which degrade the long-time coherent integration used for detection and localization. To solve this problem, many long-time coherent integration methods have been proposed. Based on mechanisms of typical methods, this paper names two signal processing modes, i.e., processing unification (PU) mode and processing separation (PS) mode, and presents their general forms. Thereafter, based on the principle of the PS mode, a novel long-time coherent integration method, known as the generalized dechirp-keystone transform (GDKT), is proposed for radar high-speed maneuvering target detection and localization. The computational cost, energy integration, peak-to-sidelobe level (PSL), resolution, and anti-noise performance of the GDKT are analyzed and compared with those of the maximum likelihood estimation (MLE) method and keystone transform-dechirp (KTD) method. With mathematical analyses and numerical simulations, we validate two main superiorities of the GDKT, including (1) the statistically optimal anti-noise performance, and (2) the low computational cost. The real radar data is also used to validate the GDKT. It is worthwhile noting that, based on closed analytical formulae of the MLE method, KTD method, and GDKT, several doubts in radar high-speed maneuvering target detection and localization are mathematically interpreted, such as the blind speed sidelobe (BSSL) and the relationship between the PU and PS modes.

Generalized Dechirp-Keystone Transform for Radar High-Speed Maneuvering Target Detection and Localization

This article addresses the coherent integration problem for detecting a highly maneuvering radar target with the range migration (RM) and Doppler frequency migration (DFM). Although many research efforts have been devoted toward this problem, how to strike a good balance between the detection performance and the computational complexity is still a challenge yet. In the algorithm, proposed in this article, a neural network is first developed to directly infer the target trajectory from the radar echo, and then the target energy distributed along the inferred trajectory is accumulated via the dechirp technique for detection. Since the proposed algorithm corrects the RM and compensates the DFM via the data-driven and model-driven approaches, respectively, we argue that the proposed algorithm operates in a model-and-data-driven approach. Besides, we fully integrate the domain knowledge into the development of the neural network, and simulation results suggest that this practice helps improve the detection performance of the proposed algorithm. Finally, numerical experiments are provided to show the high detection performance and computational efficiency of the proposed algorithm. Furthermore, we visualize the learned information of the neural network and find that it accords with our domain knowledge, demonstrating the rationality of the neural network's predictions.

Model-and-Data-Driven Method for Radar Highly Maneuvering Target Detection

Deep neural network-aided coherent integration method for maneuvering target detection

Maneuvering target detection in random pulse repetition interval radar via resampling-keystone transform

Facing high-speed targets, the traditional radar target detection framework may suffer from performance degradation due to the signal-to-noise ratio loss caused by Doppler mismatches, especially for phase coded waveforms. In this paper, an end-to-end sliding residual network detector (SRND), which is derived from the likelihood ratio test, is proposed to detect high-speed targets in additive white Gaussian noise environments with a single radar echo pulse. The SRND uses a residual network with an efficient depth to increasingly capture the representations of target echoes, and we partially show this process through visualization. The SRND is robust to target velocities because the employed residual network utilizes layers of convolutional filters to match with target echoes of both low-speed and high-speed targets. Besides, with a waveform adapter, the SRND is compatible with different waveforms, that is to say, the SRND needs to be trained only once and then can cope with different phase modulations of waveforms. More importantly, the SRND, which is trained with computer-generated data only, can deal with not only simulated data but also measured data. Numerical experiments are given to demonstrate the superior detection performance of the SRND over the traditional detector.

/pdf/sliding-residual-network-for-high-speed-target-detection-in-12fmv3lbbl.pdf

Sliding Residual Network for High-Speed Target Detection in Additive White Gaussian Noise Environments

The invention discloses a maximal distance striding loss constrained radar waveform design method. Distance striding loss is included in waveform optimization, and mismatching between echo signals anda matching filter is reduced. The design method is realized by determining an initial value of a phase code vector of the waveform of a phase modulated polyphase code radar, carrying out constraint-free optimization design on the phase code vector, determining a formula of the maximal distance striding loss when there is no distortion, and optimizing the maximal distance striding loss of the phase code vector when there is no distortion. According to the established formula of the maximal distance striding loss when there is no distortion, the distance striding loss is included in waveform optimization, a tolerance selection scheme of the distance striding loss is provided, and the waveform design efficiency is improved. The waveform with high autocorrelation characteristics, high frequency spectrum convergence degree and high Doppler tolerance is designed, and the waveform includes a lower distance striding loss under the same condition. The method of the invention is applied to waveform design of the phase modulated polyphase code radar.

Maximal distance striding loss constrained radar waveform design method

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Chunlei Wang

Author Tools

Chat about Author