Publications
Publications are organised by category below. (*: corresponding author).
See also my Google Scholar profile.
Review & position papers
- Machine Learning With Data Assimilation and Uncertainty Quantification for Dynamical Systems: A ReviewIEEE/CAA Journal of Automatica Sinica, 10(6), 1361–1387, 2023.
- Machine learning for modelling unstructured grid data in computational physics: A reviewInformation Fusion, 123, 103255, 2025.
- Deep learning for wildfire risk prediction: Integrating remote sensing and environmental dataISPRS Journal of Photogrammetry and Remote Sensing, 227, 632–677, 2025.
- The convergence of machine learning and data assimilation in Earth system sciencenpj Artificial Intelligence, 2(1), 48, 2026.
Selected recent journal publications as 1st author
- Data-driven surrogate model with latent data assimilation: Application to wildfire forecastingJournal of Computational Physics, 464, 111302, 2022.
- Efficient deep data assimilation with sparse observations and time-varying sensorsJournal of Computational Physics, 496, 112581, 2023.
- Generalised Latent Assimilation in Heterogeneous Reduced Spaces with Machine Learning Surrogate ModelsJournal of Scientific Computing, 94(1), 11, 2022.
- A Generative Model for Surrogates of Spatial-Temporal Wildfire NowcastingIEEE Transactions on Emerging Topics in Computational Intelligence, 7(5), 1420–1430, 2023.
- Multi-domain encoder–decoder neural networks for latent data assimilation in dynamical systemsComputer Methods in Applied Mechanics and Engineering, 430, 117201, 2024.
Selected recent journal publications as main supervisor
- Spectral Cross-Domain Neural Network With Soft-Adaptive Threshold Spectral EnhancementIEEE Transactions on Neural Networks and Learning Systems, 36(1), 692–703, 2024.
- Multi-fidelity physics constrained neural networks for dynamical systemsComputer Methods in Applied Mechanics and Engineering, 420, 116758, 2024.
- Explainable AI models for predicting drop coalescence in microfluidics deviceChemical Engineering Journal, 481, 148465, 2024.
- Dynamical system prediction from sparse observations using deep neural networks with Voronoi tessellation and physics constraintComputer Methods in Applied Mechanics and Engineering, 432, 117339, 2025.
- Can foundation language models predict fluid dynamics?Engineering Applications of Artificial Intelligence, 158, 111427, 2025.
Selected top AI conference publications
- Machine learning based surrogate modelling and parameter identification for wildfire forecastingAI for Earth and Space Science Workshop at ICLR, 2022.
- G2D: From Global to Dense Radiography Representation Learning via Vision-Language Pre-trainingAdvances in Neural Information Processing Systems 37 (NeurIPS), 14751–14773, 2024.
- Learning Chaos In A Linear WayInternational Conference on Learning Representations (ICLR), 2025.
- Tensor-Var: Variational Data Assimilation in Tensor Product Feature SpaceProceedings of the 42nd International Conference on Machine Learning (ICML), 267, 70649–70679, 2025.
- Information Shapes Koopman RepresentationInternational Conference on Learning Representations (ICLR), 2026, Oral (top 1.2%).
- BCWildfire: A Long-term Multi-factor Dataset and Deep Learning Benchmark for Boreal Wildfire Risk PredictionProceedings of the AAAI Conference on Artificial Intelligence (AAAI), 40(46), 39486–39494, 2026, Oral (top 4%).
Software publications
- TorchDA: A Python package for performing data assimilation with deep learning forward and transformation functionsComputer Physics Communications, 306, 109359, 2024.
- PyTorchFire: A GPU-accelerated wildfire simulator with Differentiable Cellular AutomataEnvironmental Modelling & Software, 188, 106401, 2025.
Other Journal publications
- Fast-forward prediction of lattice Boltzmann dynamics with physics-informed neural operatorsNature Communications, 17(1), 9243, 2026.
- Predicting spatio-temporal wildfire propagation with dynamic firebreaksNatural Hazards and Earth System Sciences, 26(6), 2871–2895, 2026.
- A probabilistic approach to wildfire spread prediction using a denoising diffusion surrogate modelGeoscientific Model Development, 19(2), 1027–1054, 2026.
- Elucidating the performance of data assimilation neural networks for chaotic dynamicsNonlinear Processes in Geophysics, 33(3), 401–424, 2026.
- Non‐Gaussian Assimilation of Atmospheric and Oceanic Data in Latent Space for Paleoclimate ReconstructionJournal of Advances in Modeling Earth Systems, 18(7), e2026MS005767, 2026.
- Bridging idealized and operational models: an explainable AI framework for Earth system emulatorsnpj Climate and Atmospheric Science, 9(1), 65, 2026.
- Rooftop wind field reconstruction using sparse sensors: From deterministic to generative learning methodsBuilding and Environment, 296, 114480, 2026.
- Spatiotemporal system forecasting with irregular time steps via masked autoencoderPhysica D: Nonlinear Phenomena, 492, 135189, 2026.
- Improving long-term autoregressive spatiotemporal predictions: A proof of concept with fluid dynamicsComputer Methods in Applied Mechanics and Engineering, 447, 118332, 2025.
- AI-Empowered Latent Four-dimensional Variational Data Assimilation for River Discharge ForecastingIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 18, 24676–24689, 2025.
- Latent data assimilation with non‐explicit observation operator in hydrologyQuarterly Journal of the Royal Meteorological Society, 151(772), e5009, 2025.
- Spatially-aware diffusion models with cross-attention for global field reconstruction with sparse observationsComputer Methods in Applied Mechanics and Engineering, 435, 117623, 2025.
- ViTAE-SL: A vision transformer-based autoencoder and spatial interpolation learner for field reconstructionComputer Physics Communications, 308, 109464, 2025.
- Fire-Image-DenseNet (FIDN) for predicting wildfire burnt area using remote sensing dataComputers & Geosciences, 195, 105783, 2025.
- Optimisation of microfluidic synthesis of silver nanoparticles via data-driven inverse modellingChemical Engineering Research and Design, 216, 523–530, 2025.
- Deep Learning Surrogate Models of JULES-INFERNO for Wildfire Prediction on a Global ScaleIEEE Transactions on Emerging Topics in Computational Intelligence, 9(1), 444–454, 2024.
- Explainable AI model for predicting equivalent viscous damping in dual frame–wall resilient systemJournal of Building Engineering, 96, 110564, 2024.
- Exploring unseen 3D scenarios of physics variables using machine learning-based synthetic data: An application to wave energy convertersEnvironmental Modelling & Software, 177, 106051, 2024.
- Liquid–Liquid Dispersion Performance Prediction and Uncertainty Quantification Using Recurrent Neural NetworksIndustrial & Engineering Chemistry Research, 63(17), 7853–7875, 2024.
- Reactor field reconstruction from sparse and movable sensors using Voronoi tessellation-assisted convolutional neural networksNuclear Science and Techniques, 35(5), 43, 2024.
- Reduced-order digital twin and latent data assimilation for global wildfire predictionNatural Hazards and Earth System Sciences, 23(5), 1755–1768, 2023.
- Predicting drop coalescence in microfluidic device with a deep learning generative modelPhysical Chemistry Chemical Physics, 25(23), 15744–15755, 2023.
- Accurate identification and measurement of the precipitate area by two-stage deep neural networks in novel chromium-based alloysPhysical Chemistry Chemical Physics, 25(23), 15970–15987, 2023.
- Optimization of microfluidic synthesis of silver nanoparticles: A generic approach using machine learningChemical Engineering Research and Design, 193, 65–74, 2023.
- A non‐linear non‐intrusive reduced order model of fluid flow by auto‐encoder and self‐attention deep learning methodsInternational Journal for Numerical Methods in Engineering, 124(13), 3087–3111, 2023.
- Parameter Flexible Wildfire Prediction Using Machine Learning Techniques: Forward and Inverse ModellingRemote Sensing, 14(13), 3228, 2022.
- Observation error covariance specification in dynamical systems for data assimilation using recurrent neural networksNeural Computing and Applications, 34(16), 13149–13167, 2022.
- Ensemble latent assimilation with deep learning surrogate model: application to drop interaction in a microfluidics deviceLab on a Chip, 22(17), 3187–3202, 2022.
- Computational fluid dynamics simulations of phase separation in dispersed oil-water pipe flowsChemical Engineering Science, 267, 118310, 2022.
- An efficient digital twin based on machine learning SVD autoencoder and generalised latent assimilation for nuclear reactor physicsAnnals of Nuclear Energy, 179, 109431, 2022.
- Data-Enabled Physics-Informed Machine Learning for Reduced-Order Modeling Digital Twin: Application to Nuclear Reactor PhysicsNuclear Science and Engineering, 196(6), 668–693, 2022.
- Observation data compression for variational assimilation of dynamical systemsJournal of Computational Science, 53, 101405, 2021.
- A Graph Clustering Approach to Localization for Adaptive Covariance Tuning in Data Assimilation Based on State-Observation MappingMathematical Geosciences, 53(8), 1751–1780, 2021.
- Error covariance tuning in variational data assimilation: application to an operating hydrological modelStochastic Environmental Research and Risk Assessment, 35(5), 1019–1038, 2020.
- Background error covariance iterative updating with invariant observation measures for data assimilationStochastic Environmental Research and Risk Assessment, 33(11-12), 2033–2051, 2019.
- Rock–paper–scissors dynamics from random walks on temporal multiplex networksJournal of Complex Networks, 8(2), cnz027, 2019.
Last updated: 20 October 2026.