Xiaowei Gu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Xiaowei Gu has a total of 108 co-authors. Here are the top co-authors by number of shared publications:
- Plamen Angelov
School of Computing and Communications, Lancaster University, Lancaster, UK
60 shared publications - Qiang Shen
Aberystwyth University
11 shared publications - Ce Zhang
School of Geographical Sciences, University of Bristol, Bristol, UK
6 shared publications - Hongxing Cui
Physical Science and Engineering Division, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
6 shared publications - Azliza Mohd Ali
Universiti Teknologi MARA
4 shared publications - Peter Michael Atkinson
Lancaster Environment Centre, Lancaster University, Lancaster, UK
4 shared publications
Latest Publications
- Open Access
- 9 September 2026
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Machine Learning and Computation
- Vol. 3 (5)
Rapid Joint Downscaling of Multiple Atmospheric Fields to Kilometer Scale With Deep Learning
Predicting weather and climate hazards typically relies on computationally expensive kilometer‐scale numerical models. This study introduces a U‐Net‐based deep learning framework, the Joint Atmospheric fields Downscaling Network (JADNet), for rapid, joint downscaling of multiple atmospheric variables to kilometer resolution. JADNet is trained to map interpolated 25‐km ERA5 (IERA5) reanalysis fields to 4‐km surface fields dynamically downscaled from the latter using the Weather Research and Forecasting model. The proposed model is evaluated against multiple extreme events over the Arabian Peninsula in 2014, including heatwaves, extreme precipitation, extreme surface winds, and a localized Tokar Gap Jet. These case studies indicate that JADNet consistently outperforms IERA5 in reproducing fine‐scale intensity, timing, and spatial patterns. Our results demonstrate that JADNet is a computationally efficient and robust surrogate for traditional dynamical downscaling, offering a powerful tool for scalable high‐resolution weather and climate applications.
- 9 September 2026
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Machine Learning and Computation
- Vol. 3 (5)
Open AccessRapid Joint Downscaling of Multiple Atmospheric Fields to Kilometer Scale With Deep Learning
Predicting weather and climate hazards typically relies on computationally expensive kilometer‐scale numerical models. This study introduces a U‐Net‐based deep learning framework, the Joint Atmospheric fields Downscaling Network (JADNet), for rapid, joint downscaling of multiple atmospheric variables to kilometer resolution. JADNet is trained to map interpolated 25‐km ERA5 (IERA5) reanalysis fields to 4‐km surface fields dynamically downscaled from the latter using the Weather Research and Forecasting model. The proposed model is evaluated against multiple extreme events over the Arabian Peninsula in 2014, including heatwaves, extreme precipitation, extreme surface winds, and a localized Tokar Gap Jet. These case studies indicate that JADNet consistently outperforms IERA5 in reproducing fine‐scale intensity, timing, and spatial patterns. Our results demonstrate that JADNet is a computationally efficient and robust surrogate for traditional dynamical downscaling, offering a powerful tool for scalable high‐resolution weather and climate applications.
- 1 August 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 10 (4) , 3064-3078
A Chunk-Wise Learning Evolving Autonomous Fuzzy System for Intelligent Data Stream Prediction
First-order evolving fuzzy systems (EFSs) typically self-organise and self-evolve their structure and parameters from non-stationary data streams on a sample-by-sample basis to approximate the changing data patterns in real time. However, processing individual data samples sequentially is computationally inefficient for large-scale data streams and makes EFSs more vulnerable to temporal fluctuations in data patterns, causing their prediction performances to deteriorate. To overcome this limitation, a novel chunk-wise learning evolving autonomous fuzzy system (CLEAF) is proposed in this paper. CLEAF identifies the antecedent parameters of fuzzy IF-THEN rules as prototypes from data streams via chunk-wise online clustering, and updates the associated consequent parameters using a modified chunk-wise fuzzily weighted recursive least squares algorithm that treats every data chunk as a single unit for calculation. Thanks to the novel chunk-wise learning mechanism, CLEAF attains greater computational efficiency and achieves better approximation with less fuzzy rules. Furthermore, to better approximate nonlinear, complex problems and further enhance the prediction performance, both the input and target output variables are leveraged in data density calculation for fuzzy rule identification, enabling CLEAF to more effectively capture the underlying data patterns and their overlaps. Numerical experiments on popular benchmark datasets demonstrate the superior computational efficiency and high-level prediction accuracy of CLEAF, outperforming state-of-the-art approaches.
- 1 August 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 10 (4) , 3064-3078
A Chunk-Wise Learning Evolving Autonomous Fuzzy System for Intelligent Data Stream Prediction
First-order evolving fuzzy systems (EFSs) typically self-organise and self-evolve their structure and parameters from non-stationary data streams on a sample-by-sample basis to approximate the changing data patterns in real time. However, processing individual data samples sequentially is computationally inefficient for large-scale data streams and makes EFSs more vulnerable to temporal fluctuations in data patterns, causing their prediction performances to deteriorate. To overcome this limitation, a novel chunk-wise learning evolving autonomous fuzzy system (CLEAF) is proposed in this paper. CLEAF identifies the antecedent parameters of fuzzy IF-THEN rules as prototypes from data streams via chunk-wise online clustering, and updates the associated consequent parameters using a modified chunk-wise fuzzily weighted recursive least squares algorithm that treats every data chunk as a single unit for calculation. Thanks to the novel chunk-wise learning mechanism, CLEAF attains greater computational efficiency and achieves better approximation with less fuzzy rules. Furthermore, to better approximate nonlinear, complex problems and further enhance the prediction performance, both the input and target output variables are leveraged in data density calculation for fuzzy rule identification, enabling CLEAF to more effectively capture the underlying data patterns and their overlaps. Numerical experiments on popular benchmark datasets demonstrate the superior computational efficiency and high-level prediction accuracy of CLEAF, outperforming state-of-the-art approaches.
- 7 July 2026
- Published by Elsevier in International Journal of Approximate Reasoning
- Vol. 198
Online fuzzily weighted adaptive boosting for streaming data classification
- 7 July 2026
- Published by Elsevier in International Journal of Approximate Reasoning
- Vol. 198
Online fuzzily weighted adaptive boosting for streaming data classification
- 1 June 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 347
A semi-supervised self-organised prototype tree-based method for few-shot remote sensing scene classification
- 1 June 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 347
A semi-supervised self-organised prototype tree-based method for few-shot remote sensing scene classification
- 14 March 2026
- Published by Springer Nature in Evolving Systems
- Vol. 17 (2) , 44
Adaptive local outlier factor
- 14 March 2026
- Published by Springer Nature in Evolving Systems
- Vol. 17 (2) , 44
Adaptive local outlier factor
- 13 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 1-18
An Autoencoder-Based Framework for Multimodal Fusion in Forecasting Tropical Cyclone-Induced Sea Surface Height Responses
Current physical models often struggle to accurately capture the spatial structure of sea surface height (SSH) changes induced by tropical cyclones (TCs) because they do not adequately account for TC features. To address this limitation, a new multimodal fusion framework, namely FusionNet, is proposed to forecast the spatial structure of SSH changes induced by TCs. By integrating TC features and pre-storm ocean conditions whilst preserving structural information and spatial patterns, the proposed model effectively captures the amplitudes of TC-induced SSH changes across various TC intensity categories, accurately forecasting both troughs and sea level rise along TC tracks. Moreover, FusionNet consistently outperforms the baseline derived from the widely used ocean reanalysis fields in capturing and modelling the spatial variations, as evidenced by results from an independent testing set and a case study of Super Typhoon Mangkhut (2018). Ablation analysis further disclosed the respective contributions of TC features and pre-storm ocean conditions in modelling the physical processes underlying TC-induced SSH responses. Notably, incorporating TC features significantly enhances the model's ability to represent trough amplitudes, particularly near the storm center and across different TC intensity groups.
- 13 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 1-18
An Autoencoder-Based Framework for Multimodal Fusion in Forecasting Tropical Cyclone-Induced Sea Surface Height Responses
Current physical models often struggle to accurately capture the spatial structure of sea surface height (SSH) changes induced by tropical cyclones (TCs) because they do not adequately account for TC features. To address this limitation, a new multimodal fusion framework, namely FusionNet, is proposed to forecast the spatial structure of SSH changes induced by TCs. By integrating TC features and pre-storm ocean conditions whilst preserving structural information and spatial patterns, the proposed model effectively captures the amplitudes of TC-induced SSH changes across various TC intensity categories, accurately forecasting both troughs and sea level rise along TC tracks. Moreover, FusionNet consistently outperforms the baseline derived from the widely used ocean reanalysis fields in capturing and modelling the spatial variations, as evidenced by results from an independent testing set and a case study of Super Typhoon Mangkhut (2018). Ablation analysis further disclosed the respective contributions of TC features and pre-storm ocean conditions in modelling the physical processes underlying TC-induced SSH responses. Notably, incorporating TC features significantly enhances the model's ability to represent trough amplitudes, particularly near the storm center and across different TC intensity groups.
- 7 January 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 190
Self-organising explainable multi-view representation learning for remote sensing scene classification
- 7 January 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 190
Self-organising explainable multi-view representation learning for remote sensing scene classification
- 13 March 2025
- Published by SAGE Publications in Organizational Research Methods
- Vol. 29 (2) , 202-237
Shedding Light on the Black Box: Integrating Prediction Models and Explainability Using Explainable Machine Learning
In contemporary organizational research, when dealing with large heterogeneous datasets and complex relationships, statistical modeling focused on developing substantive explanations typically results in low predictive accuracy. In contrast, machine learning (ML) exhibits remarkable strength for prediction, but suffers from an unexplainable analytical process and output—thus ML is often known as a “black box” approach. The recent development of explainable machine learning (XML) integrates high predictive accuracy with explainability, which combines the advantages inherent in both statistical modeling and ML paradigms. This paper compares XML with statistical modeling and the traditional ML approaches, focusing on an advanced application of XML known as evolving fuzzy system (EFS), which enhances model transparency by clarifying the unique contribution of each modeled predictor. In an illustrative study, we demonstrate two EFS-based XML models and conduct comparative analyses among XML, ML, and statistical models with a commonly-used database in organizational research. Our study offers a thorough description of analysis procedures for implementing XML in organizational research, along with best-practice recommendations for each step as well as Python code to aid future research using XML. Finally, we discuss the benefits of XML for organizational research and its potential development.
- 13 March 2025
- Published by SAGE Publications in Organizational Research Methods
- Vol. 29 (2) , 202-237
Shedding Light on the Black Box: Integrating Prediction Models and Explainability Using Explainable Machine Learning
In contemporary organizational research, when dealing with large heterogeneous datasets and complex relationships, statistical modeling focused on developing substantive explanations typically results in low predictive accuracy. In contrast, machine learning (ML) exhibits remarkable strength for prediction, but suffers from an unexplainable analytical process and output—thus ML is often known as a “black box” approach. The recent development of explainable machine learning (XML) integrates high predictive accuracy with explainability, which combines the advantages inherent in both statistical modeling and ML paradigms. This paper compares XML with statistical modeling and the traditional ML approaches, focusing on an advanced application of XML known as evolving fuzzy system (EFS), which enhances model transparency by clarifying the unique contribution of each modeled predictor. In an illustrative study, we demonstrate two EFS-based XML models and conduct comparative analyses among XML, ML, and statistical models with a commonly-used database in organizational research. Our study offers a thorough description of analysis procedures for implementing XML in organizational research, along with best-practice recommendations for each step as well as Python code to aid future research using XML. Finally, we discuss the benefits of XML for organizational research and its potential development.
- Open Access
- 7 January 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 170
A semi-supervised soft prototype-based autonomous fuzzy ensemble system for network intrusion detection
- 7 January 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 170
Open AccessA semi-supervised soft prototype-based autonomous fuzzy ensemble system for network intrusion detection
- 21 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 32 (11) , 6314-6328
Multilayer Evolving Fuzzy Neural Networks With Self-Adaptive Dimensionality Compression for High-Dimensional Data Classification
High-dimensional data classification is widely considered as a challenging task in machine learning due to the so-called “curse of dimensionality”. In this paper, a novel multilayer jointly evolving and compressing fuzzy neural network (MECFNN) is proposed to learn highly compact multi-level latent representations from high-dimensional data. As a meta-level stacking ensemble system, each layer of MECFNN is based on a single jointly evolving and compressing neural fuzzy inference system (ECNFIS) that self-organises a set of human-interpretable fuzzy rules from input data in a sample-wise manner to perform approximate reasoning. ECNFISs associate a unique compressive projection matrix to each individual fuzzy rule to compress the consequent part into a tighter form, removing redundant information whilst boosting the diversity within the stacking ensemble. The compressive projection matrices of the cascading ECNFISs are self-updating to minimise the prediction errors via error backpropagation together with the consequent parameters, empowering MECFNN to learn more meaningful, discriminative representations from data at multiple levels of abstraction. An adaptive activation control scheme is further introduced in MECFNN to dynamically exclude less activated fuzzy rules, effectively reducing the computational complexity and fostering generalisation. Numerical examples on popular high-dimensional classification problems demonstrate the efficacy of MECFNN.
- 21 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 32 (11) , 6314-6328
Multilayer Evolving Fuzzy Neural Networks With Self-Adaptive Dimensionality Compression for High-Dimensional Data Classification
High-dimensional data classification is widely considered as a challenging task in machine learning due to the so-called “curse of dimensionality”. In this paper, a novel multilayer jointly evolving and compressing fuzzy neural network (MECFNN) is proposed to learn highly compact multi-level latent representations from high-dimensional data. As a meta-level stacking ensemble system, each layer of MECFNN is based on a single jointly evolving and compressing neural fuzzy inference system (ECNFIS) that self-organises a set of human-interpretable fuzzy rules from input data in a sample-wise manner to perform approximate reasoning. ECNFISs associate a unique compressive projection matrix to each individual fuzzy rule to compress the consequent part into a tighter form, removing redundant information whilst boosting the diversity within the stacking ensemble. The compressive projection matrices of the cascading ECNFISs are self-updating to minimise the prediction errors via error backpropagation together with the consequent parameters, empowering MECFNN to learn more meaningful, discriminative representations from data at multiple levels of abstraction. An adaptive activation control scheme is further introduced in MECFNN to dynamically exclude less activated fuzzy rules, effectively reducing the computational complexity and fostering generalisation. Numerical examples on popular high-dimensional classification problems demonstrate the efficacy of MECFNN.