Data-driven surrogate model with latent data assimilation: Application to wildfire forecasting

Ensemble latent assimilation with deep learning surrogate model: application to drop interaction in a microfluidics device

“…26 To reduce the computational burden, reduced surrogate modelling has been applied on a wide range of dynamical problems, including (CFD), 27,28 air pollution modelling 29,30 and wildfire prediction. 31 It has shown promising results by achieving comparable performance with the high-fidelity models. In the field of ROM, (POD) 32 is a well developed concept.…”

“…Predicting high-dimensional systems in the full physical space can be computationally expensive, if not infeasible 26 . To reduce the computational burden, reduced surrogate modelling has been applied on a wide range of dynamical problems, including computational fluid mechanics (CFD) 27,28 , air pollution modelling 29,30 and wildfire prediction 31 . It has shown promising results by achieving comparable performance with the high-fidelity models.…”

An efficient digital twin based on machine learning SVD autoencoder and generalised latent assimilation for nuclear reactor physics

“…Further more, because of the high-efficiency of the machine learning based ROM forward model, when constructing the inverse model to infer the input parameter with online sensor data, we proposed a relatively naive approach in [36] to approximate the model parameters from an ensemble of samplings generated using LHS around the initial guess. Meanwhile, the latest progress of data assimilation in latent space [61,1,16,27,52] (also called latent assimilation) with machine learning make it possible to further simplify our inverse problem instead of the naive sampling approach. Thus our second contribution in this work it to adopt the generalised latent assimilation to solve the inverse problem, which ensures the high efficiency of the operation digital twin.…”

“…Data-driven models such as data assimilation (DA) approaches can be applied [5,23]. Recently, latent assimilation techniques are introduced in the work of [1,61,27] where the DA is performed after having compressed the state and the observation data into the same latent space. However, as noted in the work [25], it is almost infeasible to compress the full state space and observations into a same latent space in a wide range of DA applications, where only a part of the state are observable.…”

Reduced order digital twin and latent data assimilation for global wildfire prediction

“…However, predictive models trained using large amounts of data do not necessarily guarantee long-term prediction accuracy. In fact, iterative applications of Sequence-to-Sequence (Seq2seq) forecasting models can lead to error accumulation, resulting in incorrect long-term predictions (Cheng et al, 2022a;Cheng et al, 2022b). Researchers have applied data assimilation (DA) methods to address this challenge.…”