The physical sciences are replete with dynamical systems that require the resolution of a wide range of length and time scales. This presents significant computational challenges since direct numerical simulation requires discretization at the finest relevant scales, leading to a high-dimensional state space. In this work, we propose an approach to learn stochastic multiscale models in the form of stochastic differential equations directly from observational data. Drawing inspiration from physics-based multiscale modeling approaches, we resolve the macroscale state on a coarse mesh while introducing a microscale latent state to explicitly model unresolved dynamics. We learn the parameters of the multiscale model using a simulator-free amortized variational inference method with a Product of Experts likelihood that enforces scale separation. We present detailed numerical studies to demonstrate that our learned multiscale models achieve superior predictive accuracy compared to under-resolved direct numerical simulation and closure-type models at equivalent resolution, as well as reduced-order modeling approaches.

Plasma systems exhibit complex multiscale dynamics, resolving which poses significant challenges for conventional numerical simulations. Machine learning (ML) offers an alternative by learning data-driven representations of these dynamics. Yet existing ML time-stepping models suffer from error accumulation, instability, and limited long-term forecasting horizons. This paper demonstrates the application of a hierarchical multiscale neural network architecture for autonomous plasma forecasting. The framework integrates multiple neural networks trained across different temporal scales to capture both fine-scale and large-scale behaviors while mitigating compounding error in recursive evaluation. Fine-scale networks accurately resolve fast-evolving features, while coarse-scale networks provide broader temporal context, reducing the frequency of recursive updates and limiting the accumulation of small prediction errors over time. We first evaluate the method using canonical nonlinear dynamical systems and compare its performance against classical single-scale neural networks. The results demonstrate that single-scale neural networks experience rapid divergence due to recursive error accumulation, whereas the multiscale approach improves stability and extends prediction horizons. Next, our ML model is applied to two plasma configurations of high scientific and applied significance, demonstrating its ability to preserve spatial structures and capture multiscale plasma dynamics. By leveraging multiple time-stepping resolutions, the applied framework is shown to outperform conventional single-scale networks for the studied plasma test cases. The results of this work position the hierarchical multiscale neural network as a promising tool for efficient plasma forecasting and digital twin applications.

Multiscale models provide a unique tool for studying complex processes that study events occurring at different scales across space and time. In the context of biological systems, such models can simulate mechanisms happening at the intracellular level such as signaling, and at the extracellular level where cells communicate and coordinate with other cells. They aim to understand the impact of genetic or environmental deregulation observed in complex diseases, describe the interplay between a pathological tissue and the immune system, and suggest strategies to revert the diseased phenotypes. The construction of these multiscale models remains a very complex task, including the choice of the components to consider, the level of details of the processes to simulate, or the fitting of the parameters to the data. One additional difficulty is the expert knowledge needed to program these models in languages such as C++ or Python, which may discourage the participation of non-experts. Simplifying this process through structured description formalisms -- coupled with a graphical interface -- is crucial in making modeling more accessible to the broader scientific community, as well as streamlining the process for advanced users. This article introduces three examples of multiscale models which rely on the framework PhysiBoSS, an add-on of PhysiCell that includes intracellular descriptions as continuous time Boolean models to the agent-based approach. The article demonstrates how to easily construct such models, relying on PhysiCell Studio, the PhysiCell Graphical User Interface. A step-by-step tutorial is provided as a Supplementary Material and all models are provided at: https://physiboss.github.io/tutorial/.

In recent years, battery technology for electric vehicles (EVs) has been a major focus, with a significant emphasis on developing new battery materials and chemistries. However, accurately predicting key battery parameters, such as state-of-charge (SOC) and temperature, remains a challenge for constructing advanced battery management systems (BMS). Existing battery models do not comprehensively cover all parameters affecting battery performance, including non-battery-related factors like ambient temperature, cabin temperature, elevation, and regenerative braking during EV operation. Due to the difficulty of incorporating these auxiliary parameters into traditional models, a data-driven approach is suggested. Time-series-transformers (TSTs), leveraging multiheaded attention and parallelization-friendly architecture, are explored alongside LSTM models. Novel TST architectures, including encoder TST + decoder LSTM and a hybrid TST-LSTM, are also developed and compared against existing models. A dataset comprising 72 driving trips in a BMW i3 (60 Ah) is used to address battery life prediction in EVs, aiming to create accurate TST models that incorporate environmental, battery, vehicle driving, and heating circuit data to predict SOC and battery temperature for future time steps.

Diffusion models have emerged as one of the most promising frameworks for deep generative modeling. In this work, we explore the potential of non-uniform diffusion models. We show that non-uniform diffusion leads to multi-scale diffusion models which have similar structure to this of multi-scale normalizing flows. We experimentally find that in the same or less training time, the multi-scale diffusion model achieves better FID score than the standard uniform diffusion model. More importantly, it generates samples $4.4$ times faster in $128\times 128$ resolution. The speed-up is expected to be higher in higher resolutions where more scales are used. Moreover, we show that non-uniform diffusion leads to a novel estimator for the conditional score function which achieves on par performance with the state-of-the-art conditional denoising estimator. Our theoretical and experimental findings are accompanied by an open source library MSDiff which can facilitate further research of non-uniform diffusion models.

We propose a generalization of neural network sequence models. Instead of predicting one symbol at a time, our multi-scale model makes predictions over multiple, potentially overlapping multi-symbol tokens. A variation of the byte-pair encoding (BPE) compression algorithm is used to learn the dictionary of tokens that the model is trained with. When applied to language modelling, our model has the flexibility of character-level models while maintaining many of the performance benefits of word-level models. Our experiments show that this model performs better than a regular LSTM on language modeling tasks, especially for smaller models.

We present a probabilistic model for natural images which is based on Gaussian scale mixtures and a simple multiscale representation. In contrast to the dominant approach to modeling whole images focusing on Markov random fields, we formulate our model in terms of a directed graphical model. We show that it is able to generate images with interesting higher-order correlations when trained on natural images or samples from an occlusion based model. More importantly, the directed model enables us to perform a principled evaluation. While it is easy to generate visually appealing images, we demonstrate that our model also yields the best performance reported to date when evaluated with respect to the cross-entropy rate, a measure tightly linked to the average log-likelihood.