# Physics-Guided Foundation Model for Scientific Discovery: An Application to Aquatic Science

arXiv: https://arxiv.org/abs/2502.06084 · HTML: https://mlsanity.com/paper/2502.06084/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 34 references that are in the map.
- First posted on arXiv 10 Feb 2025.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT](https://mlsanity.com/paper/2302.09419/) (2023)
- [Towards Learning Universal, Regional, and Local Hydrological Behaviors via Machine-Learning Applied to Large-Sample Datasets](https://mlsanity.com/paper/1907.08456/) (2019)
- [Physics Guided RNNs for Modeling Dynamical Systems: A Case Study in Simulating Lake Temperature Profiles](https://mlsanity.com/paper/1810.13075/) (2018)
- [AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction](https://mlsanity.com/paper/2003.11235/) (2020)
- [Towards Automated Neural Interaction Discovery for Click-Through Rate Prediction](https://mlsanity.com/paper/2007.06434/) (2020)
- [Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation](https://mlsanity.com/paper/2408.09698/) (2024)
- [Predicting Water Temperature Dynamics of Unmonitored Lakes with Meta Transfer Learning](https://mlsanity.com/paper/2011.05369/) (2020)
- [Adaptive Process-Guided Learning: An Application in Predicting Lake DO Concentrations](https://mlsanity.com/paper/2411.12973/) (2024)
- [When are Foundation Models Effective? Understanding the Suitability for Pixel-Level Classification Using Multispectral Imagery](https://mlsanity.com/paper/2404.11797/) (2024)
- [SimFair: Physics-Guided Fairness-Aware Learning with Simulation Models](https://mlsanity.com/paper/2401.15270/) (2024)
- [Evolution-based Feature Selection for Predicting Dissolved Oxygen Concentrations in Lakes](https://mlsanity.com/paper/2403.18923/) (2024)

## Built on by (most cited first, 12 of 12)

- [Towards a Physics Foundation Model](https://mlsanity.com/paper/2509.13805/) (2025)
- [RAG for Geoscience: What We Expect, Gaps and Opportunities](https://mlsanity.com/paper/2508.11246/) (2025)
- [Science Is Falling Behind the Frontier: Foundation Model Adoption Across Half a Million Papers](https://mlsanity.com/paper/2511.21739/) (2025)
- [Foundation Models for Environmental Science: A Survey of Emerging Frontiers](https://mlsanity.com/paper/2504.04280/) (2025)
- [A Survey of Foundation Models for Environmental Science](https://mlsanity.com/paper/2503.03142/) (2025)
- [Learning to Retrieve for Environmental Knowledge Discovery: An Augmentation-Adaptive Self-Supervised Learning Framework](https://mlsanity.com/paper/2509.14563/) (2025)
- [TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning](https://mlsanity.com/paper/2607.08940/) (2026)
- [GREAT: Generalizable Representation Enhancement via Auxiliary Transformations for Zero-Shot Environmental Prediction](https://mlsanity.com/paper/2511.13469/) (2025)
- [Geo-Aware Models for Stream Temperature Prediction across Different Spatial Regions and Scales](https://mlsanity.com/paper/2510.09500/) (2025)
- [CHAM-net: A Contrastive Hierarchical Adaptive Meta-network for Robust Global Methane Flux Prediction](https://mlsanity.com/paper/2606.00338/) (2026)
- [LakeFM: Toward a Foundation Model for Aquatic Ecosystems Using Irregular Multivariate Multi-depth Time Series Data](https://mlsanity.com/paper/2606.11268/) (2026)
- [PIER: Physics-Informed Environmental Retrieval for Time-Series Modeling](https://mlsanity.com/paper/2607.20230/) (2026)

## Abstract (arXiv)

Physics-guided machine learning (PGML) has become a prevalent approach in studying scientific systems due to its ability to integrate scientific theories for enhancing machine learning (ML) models. However, most PGML approaches are tailored to isolated and relatively simple tasks, which limits their applicability to complex systems involving multiple interacting processes and numerous influencing features. In this paper, we propose a textitPhysics-Guided Foundation Model (PGFM) that combines pre-trained ML models and physics-based models and leverages their complementary strengths to improve the modeling of multiple coupled processes. To effectively conduct pre-training, we construct a simulated environmental system that encompasses a wide range of influencing features and various simulated variables generated by physics-based models. The model is pre-trained in this system to adaptively select important feature interactions guided by multi-task objectives. We then fine-tune the model for each specific task using true observations, while maintaining consistency with established physical theories, such as the principles of mass and energy conservation. We demonstrate the effectiveness of this methodology in modeling water temperature and dissolved oxygen dynamics in real-world lakes. The proposed PGFM is also broadly applicable to a range of scientific fields where physics-based models are being used.