Xiangming Guo
Research Subjects
Xiangming Guo has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Yiwen Wei
School of Physics, Xidian University, Xian, China
7 shared publications - Jinpeng Zhang
National Key Laboratory of Electromagnetic Environment, China Research Institute of Radiowave Propagation, Qingdao, China
6 shared publications - Lixin Guo
Xidian University
6 shared publications - Han-Jie Ji
School of Physics, Xidian University, Xi’an 710071, China
5 shared publications Qing-Liang Li
National Key Laboratory of Electromagnetic Environment, China Research Institute of Radiowave Propagation, Qingdao, China
5 shared publications- Lixia Yang
Anhui University
3 shared publications
Latest Publications
- 23 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 1-19
DenseRefrception: A Densely Connected Perception Framework for Passive Retrieval of Ocean Refractive Environments via GPS Scattered Signals
Accurate ocean ducting environments sensing is crucial for radio communication. Conventionally, ducting profile inversion relied heavily on radar sea returns. Though feasible, this active approach suffers from operational drawback, which severely impedes practical deployment. Global positioning system (GPS) has revolutionized ocean monitoring through its inherent global coverage, all-weather capability, and high precision. GPS signals scattered from the sea surface provide unique yet underutilized information on atmospheric environments. Although duct-induced modulations encode key ducting parameters, direct extraction from these signals poses intractable nonlinear inverse problems due to complex signal-refraction interactions. Leveraging the unparalleled capability of deep learning to approximate highly complex, nonlinear mappings, this study presents a Densely Connected Perception Framework for Atmospheric Ducting Retrieval via GPS Scattered Signals (DenseRefrception). The core breakthrough resides in constructing a sophisticated architecture. This framework innovatively integrates Dense Connectivity to extract discriminative features from scattered GPS signal power, while incorporating multi-head attention and fully-connected networks to establish high-dimensional nonlinear mappings. Through systematic training of a unified multi-dimensional duct parameter learning mechanism, it precisely constructs highly nonlinear functional relationships. By transforming passively collected GPS signals into actionable refractivity intelligence, the DenseRefrception represents a shift towards persistent and clandestine monitoring of the oceanic environment, significantly enhancing situational awareness for maritime platforms.
- 23 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 1-19
DenseRefrception: A Densely Connected Perception Framework for Passive Retrieval of Ocean Refractive Environments via GPS Scattered Signals
Accurate ocean ducting environments sensing is crucial for radio communication. Conventionally, ducting profile inversion relied heavily on radar sea returns. Though feasible, this active approach suffers from operational drawback, which severely impedes practical deployment. Global positioning system (GPS) has revolutionized ocean monitoring through its inherent global coverage, all-weather capability, and high precision. GPS signals scattered from the sea surface provide unique yet underutilized information on atmospheric environments. Although duct-induced modulations encode key ducting parameters, direct extraction from these signals poses intractable nonlinear inverse problems due to complex signal-refraction interactions. Leveraging the unparalleled capability of deep learning to approximate highly complex, nonlinear mappings, this study presents a Densely Connected Perception Framework for Atmospheric Ducting Retrieval via GPS Scattered Signals (DenseRefrception). The core breakthrough resides in constructing a sophisticated architecture. This framework innovatively integrates Dense Connectivity to extract discriminative features from scattered GPS signal power, while incorporating multi-head attention and fully-connected networks to establish high-dimensional nonlinear mappings. Through systematic training of a unified multi-dimensional duct parameter learning mechanism, it precisely constructs highly nonlinear functional relationships. By transforming passively collected GPS signals into actionable refractivity intelligence, the DenseRefrception represents a shift towards persistent and clandestine monitoring of the oceanic environment, significantly enhancing situational awareness for maritime platforms.
- 4 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22 (1545598X) , 1-5
A Bayesian Fusion Framework for Characterizing Marine Ducts Using Multisource Prior Constraints
The study of surface-layer evaporation ducts (EDs) maintains persistent scientific significance due to their critical role in modulating tropospheric propagation. While multiple ED quantification methodologies exist, the inherent complexity of these atmospheric structures radically constrains the observational completeness achievable through singular technologies. To address this limitation, we develop a novel Bayesian fusion framework that systematically integrates multi-source knowledge through probabilistic reasoning to estimate ED from point-to-point propagation loss (PL) observations. This approach reformulates the inverse problem as a maximum likelihood estimation challenge, systematically synthesizing prior ED distributions (derived from diverse knowledge sources) with PL-constrained likelihood functions through a rigorous Bayesian approach. This probabilistic integration enables robust determination of posterior ED distributions while inherently quantifying retrieval uncertainties. Validation experiments using a dedicated dataset confirms the framework’s viability, demonstrating sufficient accuracy to support real-world marine applications.
- 4 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22 (1545598X) , 1-5
A Bayesian Fusion Framework for Characterizing Marine Ducts Using Multisource Prior Constraints
The study of surface-layer evaporation ducts (EDs) maintains persistent scientific significance due to their critical role in modulating tropospheric propagation. While multiple ED quantification methodologies exist, the inherent complexity of these atmospheric structures radically constrains the observational completeness achievable through singular technologies. To address this limitation, we develop a novel Bayesian fusion framework that systematically integrates multi-source knowledge through probabilistic reasoning to estimate ED from point-to-point propagation loss (PL) observations. This approach reformulates the inverse problem as a maximum likelihood estimation challenge, systematically synthesizing prior ED distributions (derived from diverse knowledge sources) with PL-constrained likelihood functions through a rigorous Bayesian approach. This probabilistic integration enables robust determination of posterior ED distributions while inherently quantifying retrieval uncertainties. Validation experiments using a dedicated dataset confirms the framework’s viability, demonstrating sufficient accuracy to support real-world marine applications.
- 2 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-18
RFCFormer: A Dual-Stream Transformer Architecture Integrating Gramian Angular Field Representations for Retrieving Evaporation Duct Refractivity From Radar Sea Clutter
This study introduces RFCFormer, an innovative framework for retrieving evaporation duct refractivity from radar sea clutter, which synergistically integrates a dual-stream Transformer architecture with Gramian Angular Field (GAF) methodology. The framework first converts the input sea clutter into two distinct GAF matrices, effectively transforming the raw clutter into more manageable sparse matrix representations. This transformation enhances the model’s ability to identify underlying patterns within the sea clutter, improving the accuracy of the mapping between clutter characteristics and duct parameters. The dual-stream Transformer architecture then utilizes parallel processing pathways, where coordinated self-attention mechanisms process the GAF matrices in depth, facilitating the integration of multi-scale clutter features through cross-stream feature fusion. Experimental evaluations show that RFCFormer surpasses existing approaches in both inversion accuracy and generalization capability. Furthermore, the model achieves simultaneous retrieval of four duct parameters while maintaining adaptability to diverse sea states, which conclusively demonstrates its practical utility in real-world marine environments.
- 2 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-18
RFCFormer: A Dual-Stream Transformer Architecture Integrating Gramian Angular Field Representations for Retrieving Evaporation Duct Refractivity From Radar Sea Clutter
This study introduces RFCFormer, an innovative framework for retrieving evaporation duct refractivity from radar sea clutter, which synergistically integrates a dual-stream Transformer architecture with Gramian Angular Field (GAF) methodology. The framework first converts the input sea clutter into two distinct GAF matrices, effectively transforming the raw clutter into more manageable sparse matrix representations. This transformation enhances the model’s ability to identify underlying patterns within the sea clutter, improving the accuracy of the mapping between clutter characteristics and duct parameters. The dual-stream Transformer architecture then utilizes parallel processing pathways, where coordinated self-attention mechanisms process the GAF matrices in depth, facilitating the integration of multi-scale clutter features through cross-stream feature fusion. Experimental evaluations show that RFCFormer surpasses existing approaches in both inversion accuracy and generalization capability. Furthermore, the model achieves simultaneous retrieval of four duct parameters while maintaining adaptability to diverse sea states, which conclusively demonstrates its practical utility in real-world marine environments.
- 29 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Wireless Propagation Letters
- Vol. 24 (8) , 2432-2436
Explainable Deep Learning-Based Prediction of Radar Wave Propagation Loss in Evaporation Ducts and Exploration of Driving Factors
We develop ExPLNet, an explainable deep learning framework for predicting radar wave propagation loss (PL) in non-uniform evaporation ducts, which integrates a hybrid Long Short-Term Memory (LSTM)-Transformer model with SHapley Additive exPlanations (SHAP) technology. ExPLNet employs a data-driven methodology to generate PL predictions by leveraging the LSTM-Transformer framework to discern PL patterns from multi-source driving factors. Subsequently, the SHAP deep explainer module systematically quantifies feature contributions through coalitional game theory, revealing the relative importance of key influencing factors. This architecture simultaneously achieves accurate PL forecasting and physically explainable factor analysis, advancing radio propagation modeling for intelligent communication systems.
- 29 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Wireless Propagation Letters
- Vol. 24 (8) , 2432-2436
Explainable Deep Learning-Based Prediction of Radar Wave Propagation Loss in Evaporation Ducts and Exploration of Driving Factors
We develop ExPLNet, an explainable deep learning framework for predicting radar wave propagation loss (PL) in non-uniform evaporation ducts, which integrates a hybrid Long Short-Term Memory (LSTM)-Transformer model with SHapley Additive exPlanations (SHAP) technology. ExPLNet employs a data-driven methodology to generate PL predictions by leveraging the LSTM-Transformer framework to discern PL patterns from multi-source driving factors. Subsequently, the SHAP deep explainer module systematically quantifies feature contributions through coalitional game theory, revealing the relative importance of key influencing factors. This architecture simultaneously achieves accurate PL forecasting and physically explainable factor analysis, advancing radio propagation modeling for intelligent communication systems.
- Open Access
- 2 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 10067-10082
IPILT–OHPL: An Over-the-Horizon Propagation Loss Prediction Model Established by Incorporating Prior Information Into the LSTM–Transformer Structure
The evaporation duct is a prevalent atmospheric structure in the marine lower troposphere with significant regional nonuniformity. This structure can trap radio waves inside its layer and enable them to propagate over the horizon with less loss. Therefore, accurately predicting the over-the-horizon propagation loss (OHPL) is important for optimizing the performance of radio-electronic systems. Considering the OHPL characteristics in nonuniform evaporation ducts, this article establishes an OHPL prediction model by incorporating prior information into the long short-term memory (LSTM)–transformer structure (IPILT–OHPL). The combination of the LSTM network and transformer is used to construct the LSTM–transformer, aimed at leveraging their respective strengths to extract important features of OHPL effectively. In addition, to improve the prediction accuracy, this article incorporates the evaporation duct height as an environmental prior information into the LSTM–transformer. Finally, this article comprehensively evaluates IPILT–OHPL model performance in different application scenarios. The evaluation results show that the established model not only has high prediction accuracy but also strong generalization ability, which provides a new method for efficiently predicting the OHPL in nonuniform evaporation ducts.
- 2 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 10067-10082
Open AccessIPILT–OHPL: An Over-the-Horizon Propagation Loss Prediction Model Established by Incorporating Prior Information Into the LSTM–Transformer Structure
The evaporation duct is a prevalent atmospheric structure in the marine lower troposphere with significant regional nonuniformity. This structure can trap radio waves inside its layer and enable them to propagate over the horizon with less loss. Therefore, accurately predicting the over-the-horizon propagation loss (OHPL) is important for optimizing the performance of radio-electronic systems. Considering the OHPL characteristics in nonuniform evaporation ducts, this article establishes an OHPL prediction model by incorporating prior information into the long short-term memory (LSTM)–transformer structure (IPILT–OHPL). The combination of the LSTM network and transformer is used to construct the LSTM–transformer, aimed at leveraging their respective strengths to extract important features of OHPL effectively. In addition, to improve the prediction accuracy, this article incorporates the evaporation duct height as an environmental prior information into the LSTM–transformer. Finally, this article comprehensively evaluates IPILT–OHPL model performance in different application scenarios. The evaluation results show that the established model not only has high prediction accuracy but also strong generalization ability, which provides a new method for efficiently predicting the OHPL in nonuniform evaporation ducts.
- 19 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 71 (8) , 6859-6868
Study of the Deterministic Transmission Loss Prediction Model for Troposcatter
Troposcatter transmission loss prediction models are based mainly on ITU-R’s empirical models. However, the available troposcatter propagation models do not enable the real-time calculation of the transmission loss for a specific propagation link. Therefore, the primary purpose of this study is to develop a deterministic troposcatter transmission loss prediction model to realize the real-time calculation or prediction of the transmission loss. In this study, the turbulent scattering cross-section, the refractive turbulence structure constant and the radar equation were introduced to our approach, and the troposcatter transmission loss prediction model was established based on the geometry of the troposcatter circuit. In addition, a weighted method for taking the value of the refractive turbulence structure constant, generated from the WRF schema, was proposed, based on the ray tracing method. Furthermore, the proposed model was validated with the experimental measurement of troposcatter, which verifies the proposed model’s availability and reliability.
- 19 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 71 (8) , 6859-6868
Study of the Deterministic Transmission Loss Prediction Model for Troposcatter
Troposcatter transmission loss prediction models are based mainly on ITU-R’s empirical models. However, the available troposcatter propagation models do not enable the real-time calculation of the transmission loss for a specific propagation link. Therefore, the primary purpose of this study is to develop a deterministic troposcatter transmission loss prediction model to realize the real-time calculation or prediction of the transmission loss. In this study, the turbulent scattering cross-section, the refractive turbulence structure constant and the radar equation were introduced to our approach, and the troposcatter transmission loss prediction model was established based on the geometry of the troposcatter circuit. In addition, a weighted method for taking the value of the refractive turbulence structure constant, generated from the WRF schema, was proposed, based on the ray tracing method. Furthermore, the proposed model was validated with the experimental measurement of troposcatter, which verifies the proposed model’s availability and reliability.
- 19 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 71 (7) , 6060-6071
A Comparative Study of Rough Sea Surface and Evaporation Duct Models on Radio Wave Propagation
Microwave and millimeter-wave propagations near the sea surface are greatly affected by the vertical atmospheric refractivity profile and the sea surface. To accurately simulate or predict the performance of ship radar systems, the evaporation duct model and rough sea surface models are usually incorporated into the parabolic equation to model electromagnetic wave propagation. The Paulus-Jeske (PJ) model and Naval Postgraduate School (NPS) model are the most widely used to make the vertical atmospheric refractivity profile, and the roughness sea surface is modeled with the effective reflection coefficient of the rough surface or the generation of the rough sea surface. There are four widely used rough sea surface approximations called Ament, Miller-Brown, Shadowed, and Hybrid for rough sea surface modeling. In this study, numerical simulation is first used to compare the different rough sea surface modeling methods. Then, evaporation duct measurement data and C-band propagation experimental data are used to compare the evaporation duct models and the four rough sea surface models that are combined with evaporation duct models for propagation loss prediction. The simulation results show that the shadowing of radio waves by the rough sea surface and sea surface structure are important factors affecting the transmission of radio waves in evaporation ducts, and the difference in the path loss predicted by different rough sea surface approximations may exceed 10 dB at the same location. In particular, the frequency and wind speed will increase. In addition, the experimental data show that the evaporation duct can be better diagnosed using different evaporation duct models at different atmospheric stabilities. When the air-sea temperature difference is positive, the PJ evaporation duct is recommended; otherwise, the NPS model is better, and the results of the Shadowed and Hybrid rough sea surface models are in better agreement with the observations.
- 19 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 71 (7) , 6060-6071
A Comparative Study of Rough Sea Surface and Evaporation Duct Models on Radio Wave Propagation
Microwave and millimeter-wave propagations near the sea surface are greatly affected by the vertical atmospheric refractivity profile and the sea surface. To accurately simulate or predict the performance of ship radar systems, the evaporation duct model and rough sea surface models are usually incorporated into the parabolic equation to model electromagnetic wave propagation. The Paulus-Jeske (PJ) model and Naval Postgraduate School (NPS) model are the most widely used to make the vertical atmospheric refractivity profile, and the roughness sea surface is modeled with the effective reflection coefficient of the rough surface or the generation of the rough sea surface. There are four widely used rough sea surface approximations called Ament, Miller-Brown, Shadowed, and Hybrid for rough sea surface modeling. In this study, numerical simulation is first used to compare the different rough sea surface modeling methods. Then, evaporation duct measurement data and C-band propagation experimental data are used to compare the evaporation duct models and the four rough sea surface models that are combined with evaporation duct models for propagation loss prediction. The simulation results show that the shadowing of radio waves by the rough sea surface and sea surface structure are important factors affecting the transmission of radio waves in evaporation ducts, and the difference in the path loss predicted by different rough sea surface approximations may exceed 10 dB at the same location. In particular, the frequency and wind speed will increase. In addition, the experimental data show that the evaporation duct can be better diagnosed using different evaporation duct models at different atmospheric stabilities. When the air-sea temperature difference is positive, the PJ evaporation duct is recommended; otherwise, the NPS model is better, and the results of the Shadowed and Hybrid rough sea surface models are in better agreement with the observations.
- 10 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 71 (12) , 9799-9813
Environmental Knowledge-Driven Over-the-Horizon Propagation Loss Prediction Based on Short- and Long-Term Parallel Double-Flow TrellisNets
Accurate perceptual knowledge of atmospheric characteristics in the propagation path is of great significance for the design of communication systems. However, the atmosphere above the ocean is inhomogeneous, which brings challenges to accurate prediction of propagation loss. Moreover, the atmospheric refractive index distribution model calculated from atmospheric data requires at least two stations with near-sea meteorological data. In real maritime over-the-horizon communication or detection, only one station transmits and receives meteorological data, and the received meteorological data and propagation loss have large temporal noise. To address these issues, first, a denoising model based on the one-dimensional convolution autoencoder (1DCAE) is constructed to filter out the temporal noise of input environmental meteorological data and propagation loss. Second, to accurately predict the influence of environmental factors on the prediction of propagation loss, a deep-learning framework called short- and long- term parallel double-flow TrellisNets (SL-TrellisNets) is proposed to predict the loss. Finally, the extensive experiments demonstrated that the root mean square and mean absolute errors of the proposed 1DCAE are dramatically reduced. Our proposed SL-TrellisNets outperforms the other state-of-the-art techniques in terms of propagation loss prediction. In addition, we analyzed the impact of the environmental factors on the accuracy of over-the-horizon propagation loss prediction.
- 10 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 71 (12) , 9799-9813
Environmental Knowledge-Driven Over-the-Horizon Propagation Loss Prediction Based on Short- and Long-Term Parallel Double-Flow TrellisNets
Accurate perceptual knowledge of atmospheric characteristics in the propagation path is of great significance for the design of communication systems. However, the atmosphere above the ocean is inhomogeneous, which brings challenges to accurate prediction of propagation loss. Moreover, the atmospheric refractive index distribution model calculated from atmospheric data requires at least two stations with near-sea meteorological data. In real maritime over-the-horizon communication or detection, only one station transmits and receives meteorological data, and the received meteorological data and propagation loss have large temporal noise. To address these issues, first, a denoising model based on the one-dimensional convolution autoencoder (1DCAE) is constructed to filter out the temporal noise of input environmental meteorological data and propagation loss. Second, to accurately predict the influence of environmental factors on the prediction of propagation loss, a deep-learning framework called short- and long- term parallel double-flow TrellisNets (SL-TrellisNets) is proposed to predict the loss. Finally, the extensive experiments demonstrated that the root mean square and mean absolute errors of the proposed 1DCAE are dramatically reduced. Our proposed SL-TrellisNets outperforms the other state-of-the-art techniques in terms of propagation loss prediction. In addition, we analyzed the impact of the environmental factors on the accuracy of over-the-horizon propagation loss prediction.
- 15 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Wireless Propagation Letters
- Vol. 21 (12) , 2312-2316
A Model for Calculating Electromagnetic Scattering From Target in Evaporation Duct
In this paper, we proposed a new model to solve the scattering problem from target in evaporation duct. Firstly, the traditional 2D subsection ray tracing(SRT) method is extended to 3D case. Then the 3D SRT is used to obtain the propagation direction and attenuation of the transmitted electromagnetic(EM) wave from antenna. Secondly, shooting and bouncing rays(SBR) is used in the simulation of complex target scattering. Different from traditional SBR, the launched rays are not planed wave. A virtual transmitting plane is established to obtain the amplitude and direction of these rays in evaporation duct in front of the target. The transmitting plane in evaporation duct can be regard as the incident field of SBR method. What's more, the new model based on SBR is accelerated by CUDA and OptiX from Nvidia to deal with the tremendous number of rays. Finally, the scattering EM field and power distributions in evaporation duct environment are calculated and discussed in the last section.
- 15 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Wireless Propagation Letters
- Vol. 21 (12) , 2312-2316
A Model for Calculating Electromagnetic Scattering From Target in Evaporation Duct
In this paper, we proposed a new model to solve the scattering problem from target in evaporation duct. Firstly, the traditional 2D subsection ray tracing(SRT) method is extended to 3D case. Then the 3D SRT is used to obtain the propagation direction and attenuation of the transmitted electromagnetic(EM) wave from antenna. Secondly, shooting and bouncing rays(SBR) is used in the simulation of complex target scattering. Different from traditional SBR, the launched rays are not planed wave. A virtual transmitting plane is established to obtain the amplitude and direction of these rays in evaporation duct in front of the target. The transmitting plane in evaporation duct can be regard as the incident field of SBR method. What's more, the new model based on SBR is accelerated by CUDA and OptiX from Nvidia to deal with the tremendous number of rays. Finally, the scattering EM field and power distributions in evaporation duct environment are calculated and discussed in the last section.
- 24 August 2019
- Published by Springer Nature in Journal of Ocean University of China
- Vol. 18 (5) , 1022-1030
A Comparison Study of Sensitivity on PJ and NPS Models in China Seas
- 24 August 2019
- Published by Springer Nature in Journal of Ocean University of China
- Vol. 18 (5) , 1022-1030
A Comparison Study of Sensitivity on PJ and NPS Models in China Seas