Pre-trained machine learning (ML) models have shown great performance for awide range of applications, in particular in natural language processing (NLP)and computer vision (CV). Here, we study how pre-training could be used forscientific machine learning (SciML) applications, specifically in the context oftransfer learning. We study the transfer behavior of these models as (i) the pretrainedmodel size is scaled, (ii) the downstream training dataset size is scaled,(iii) the physics parameters are systematically pushed out of distribution, and (iv)how a single model pre-trained on a mixture of different physics problems canbe adapted to various downstream applications.

Machine learning-based modeling of physical systems has experienced increased interest in recent years. Despite some impressive progress, there is still a lack of benchmarks for Scientific ML that are easy to use but still challenging and representative of a wide range of problems. We introduce PDEBENCH, a benchmark suite of time-dependent simulation tasks based on Partial Differential Equations (PDEs). PDEBENCH comprises both code and data to benchmark the performance of novel machine learning models against both classical numerical simulations and machine learning baselines. Our proposed set of benchmark problems contribute the following unique features: (1) A much wider range of PDEs compared to existing benchmarks, ranging from relatively common examples to more realistic and difficult problems; (2) much larger ready-to-use datasets compared to prior work, comprising multiple simulation runs across a larger number of initial and boundary conditions and PDE parameters; (3) more extensible source codes with user-friendly APIs for data generation and baseline results with popular machine learning models (FNO, U-Net, PINN, Gradient-Based Inverse Method). PDEBENCH allows researchers to extend the benchmark freely for their own purposes using a standardized API and to compare the performance of new models to existing baseline methods. We also propose new evaluation metrics with the aim to provide a more holistic understanding of learning methods in the context of Scientific ML. With those metrics we identify tasks which are challenging for recent ML methods and propose these tasks as future challenges for the community.

Scaling laws describe how model performance grows with data, parameters and compute. While large datasets can usually be collected at relatively low cost in domains such as language or vision, scientific machine learning is often limited by the high expense of generating training data through numerical simulations. However, by adjusting modeling assumptions and approximations, simulation fidelity can be traded for computational cost, an aspect absent in other domains. We investigate this trade-off between data fidelity and cost in neural surrogates using low- and high-fidelity Reynolds-Averaged Navier-Stokes (RANS) simulations. Reformulating classical scaling laws, we decompose the dataset axis into compute budget and dataset composition. Our experiments reveal compute-performance scaling behavior and exhibit budget-dependent optimal fidelity mixes for the given dataset configuration. These findings provide the first study of empirical scaling laws for multi-fidelity neural surrogate datasets and offer practical considerations for compute-efficient dataset generation in scientific machine learning.

Universal Differential Equations (UDEs), which blend neural networks with physical differential equations, have emerged as a powerful framework for scientific machine learning (SciML), enabling data-efficient, interpretable, and physically consistent modeling. In the context of smart grid systems, modeling node-wise battery dynamics remains a challenge due to the stochasticity of solar input and variability in household load profiles. Traditional approaches often struggle with generalization and fail to capture unmodeled residual dynamics. This work proposes a UDE-based approach to learn node-specific battery evolution by embedding a neural residual into a physically inspired battery ODE. Synthetic yet realistic solar generation and load demand data are used to simulate battery dynamics over time. The neural component learns to model unobserved or stochastic corrections arising from heterogeneity in node demand and environmental conditions. Comprehensive experiments reveal that the trained UDE aligns closely with ground truth battery trajectories, exhibits smooth convergence behavior, and maintains stability in long-term forecasts. These findings affirm the viability of UDE-based SciML approaches for battery modeling in decentralized energy networks and suggest broader implications for real-time control and optimization in renewable-integrated smart grids.

Pre-trained machine learning (ML) models have shown great performance for awide range of applications, in particular in natural language processing (NLP)and computer vision (CV). Here, we study how pre-training could be used forscientific machine learning (SciML) applications, specifically in the context oftransfer learning. We study the transfer behavior of these models as (i) the pretrainedmodel size is scaled, (ii) the downstream training dataset size is scaled,(iii) the physics parameters are systematically pushed out of distribution, and (iv)how a single model pre-trained on a mixture of different physics problems canbe adapted to various downstream applications. We also find that fine-tuning these modelsyields more performance gains as model size increases, compared to training fromscratch on new downstream tasks. These results hold for a broad range of PDElearning tasks.

Carbon emissions are rising at an alarming rate, posing a significant threat to global efforts to mitigate climate change. Electric vehicles have emerged as a promising solution, but their reliance on lithium-ion batteries introduces the critical challenge of battery degradation. Accurate prediction and forecasting of battery degradation over both short and long time spans are essential for optimizing performance, extending battery life, and ensuring effective long-term energy management. This directly influences the reliability, safety, and sustainability of EVs, supporting their widespread adoption and aligning with key UN SDGs. In this paper, we present a novel approach to the prediction and long-term forecasting of battery degradation using Scientific Machine Learning framework which integrates domain knowledge with neural networks, offering more interpretable and scientifically grounded solutions for both predicting short-term battery health and forecasting degradation over extended periods. This hybrid approach captures both known and unknown degradation dynamics, improving predictive accuracy while reducing data requirements. We incorporate ground-truth data to inform our models, ensuring that both the predictions and forecasts reflect practical conditions. The model achieved MSE of 9.90 with the UDE and 11.55 with the NeuralODE, in experimental data, a loss of 1.6986 with the UDE, and a MSE of 2.49 in the NeuralODE, demonstrating the enhanced precision of our approach. This integration of data-driven insights with SciML's strengths in interpretability and scalability allows for robust battery management. By enhancing battery longevity and minimizing waste, our approach contributes to the sustainability of energy systems and accelerates the global transition toward cleaner, more responsible energy solutions, aligning with the UN's SDG agenda.

Machine learning-based modeling of physical systems has experienced increased interest in recent years. Despite some impressive progress, there is still a lack of benchmarks for Scientific ML that are easy to use but still challenging and repre- sentative of a wide range of problems. We introduce PDEBENCH, a benchmark suite of time-dependent simulation tasks based on Partial Differential Equations (PDEs). PDEBENCH comprises both code and data to benchmark the performance of novel machine learning models against both classical numerical simulations and machine learning baselines. Our proposed set of benchmark problems con- tribute the following unique features: (1) A much wider range of PDEs compared to existing benchmarks, ranging from relatively common examples to more real- istic and difficult problems; (2) much larger ready-to-use datasets compared to prior work, comprising multiple simulation runs across a larger number of ini- tial and boundary conditions and PDE parameters; (3) more extensible source codes with user-friendly APIs for data generation and baseline results with popular machine learning models (FNO, U-Net, PINN, Gradient-Based Inverse Method).

Scientific Machine Learning is transforming traditional engineering industries by enhancing the efficiency of existing technologies and accelerating innovation, particularly in modeling chemical reactions. Despite recent advancements, the issue of solving stiff chemically reacting problems within computational fluid dynamics remains a significant issue. In this study we propose a novel approach utilizing a multi-layer-perceptron mixer architecture (MLP-Mixer) to model the time-series of stiff chemical kinetics. We evaluate this method using the ROBER system, a benchmark model in chemical kinetics, to compare its performance with traditional numerical techniques. This study provides insight into the industrial utility of the recently developed MLP-Mixer architecture to model chemical kinetics and provides motivation for such neural architecture to be used as a base for time-series foundation models.

Pre-trained machine learning (ML) models have shown great performance for a wide range of applications, in particular in natural language processing (NLP) and computer vision (CV). Here, we study how pre-training could be used for scientific machine learning (SciML) applications, specifically in the context of transfer learning. We study the transfer behavior of these models as (i) the pre-trained model size is scaled, (ii) the downstream training dataset size is scaled, (iii) the physics parameters are systematically pushed out of distribution, and (iv) how a single model pre-trained on a mixture of different physics problems can be adapted to various downstream applications. We find that-when fine-tuned appropriately-transfer learning can help reach desired accuracy levels with orders of magnitude fewer downstream examples (across different tasks that can even be out-of-distribution) than training from scratch, with consistent behavior across a wide range of downstream examples. We also find that fine-tuning these models yields more performance gains as model size increases, compared to training from scratch on new downstream tasks. These results hold for a broad range of PDE learning tasks. All in all, our results demonstrate the potential of the "pre-train and fine-tune" paradigm for SciML problems, demonstrating a path towards building SciML foundation models. We open-source our code for reproducibility.

In general, large datasets enable deep learning models to perform with good accuracy and generalizability. However, massive high-fidelity simulation datasets (from molecular chemistry, astrophysics, computational fluid dynamics (CFD), etc. can be challenging to curate due to dimensionality and storage constraints. Lossy compression algorithms can help mitigate limitations from storage, as long as the overall data fidelity is preserved. To illustrate this point, we demonstrate that deep learning models, trained and tested on data from a petascale CFD simulation, are robust to errors introduced during lossy compression in a semantic segmentation problem. Our results demonstrate that lossy compression algorithms offer a realistic pathway for exposing high-fidelity scientific data to open-source data repositories for building community datasets. In this paper, we outline, construct, and evaluate the requirements for establishing a big data framework, demonstrated at https://blastnet.github.io/,