# Achieving Conservation of Energy in Neural Network Emulators for Climate Modeling

arXiv: https://arxiv.org/abs/1906.06622 · HTML: https://mlsanity.com/paper/1906.06622/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2019.

## Built on by (most cited first, 28 of 28)

- [DC3: A learning method for optimization with hard constraints](https://mlsanity.com/paper/2104.12225/) (2021)
- [Machine learning structure preserving brackets for forecasting irreversible processes](https://mlsanity.com/paper/2106.12619/) (2021)
- [Physics-Guided Deep Learning for Dynamical Systems: A Survey](https://mlsanity.com/paper/2107.01272/) (2021)
- [Will Artificial Intelligence supersede Earth System and Climate Models?](https://mlsanity.com/paper/2101.09126/) (2021)
- [Hard-Constrained Deep Learning for Climate Downscaling](https://mlsanity.com/paper/2208.05424/) (2022)
- [Fourier Neural Operators for Arbitrary Resolution Climate Data Downscaling](https://mlsanity.com/paper/2305.14452/) (2023)
- [Differentiable Programming for Earth System Modeling](https://mlsanity.com/paper/2208.13825/) (2022)
- [MC-LSTM: Mass-Conserving LSTM](https://mlsanity.com/paper/2101.05186/) (2021)
- [Towards physically consistent data-driven weather forecasting: Integrating data assimilation with equivariance-preserving deep spatial transformers](https://mlsanity.com/paper/2103.09360/) (2021)
- [DiffESM: Conditional Emulation of Temperature and Precipitation in Earth System Models with 3D Diffusion Models](https://mlsanity.com/paper/2409.11601/) (2024)
- [Multiscale Neural Operator: Learning Fast and Grid-independent PDE Solvers](https://mlsanity.com/paper/2207.11417/) (2022)
- [W-Transformers : A Wavelet-based Transformer Framework for Univariate Time Series Forecasting](https://mlsanity.com/paper/2209.03945/) (2022)
- [Knowledge-augmented Deep Learning and Its Applications: A Survey](https://mlsanity.com/paper/2212.00017/) (2022)
- [DiffESM: Conditional Emulation of Earth System Models with Diffusion Models](https://mlsanity.com/paper/2304.11699/) (2023)
- [Using Machine Learning at Scale in HPC Simulations with SmartSim: An Application to Ocean Climate Modeling](https://mlsanity.com/paper/2104.09355/) (2021)
- [A Review of Machine Learning Methods Applied to Structural Dynamics and Vibroacoustic](https://mlsanity.com/paper/2204.06362/) (2022)
- [CondensNet: Enabling stable long-term climate simulations via hybrid deep learning models with adaptive physical constraints](https://mlsanity.com/paper/2502.13185/) (2025)
- [Calabi-Yau metrics through Grassmannian learning and Donaldson's algorithm](https://mlsanity.com/paper/2410.11284/) (2024)
- [Inductive biases in deep learning models for weather prediction](https://mlsanity.com/paper/2304.04664/) (2023)
- [Hybrid Modeling Design Patterns](https://mlsanity.com/paper/2401.00033/) (2023)
- [AutoPINN: When AutoML Meets Physics-Informed Neural Networks](https://mlsanity.com/paper/2212.04058/) (2022)
- [Physically consistent model learning for reaction-diffusion systems](https://mlsanity.com/paper/2512.14240/) (2025)
- [Physics-Guided Problem Decomposition for Scaling Deep Learning of High-dimensional Eigen-Solvers: The Case of Schr"odinger's Equation](https://mlsanity.com/paper/2202.05994/) (2022)
- [Knowledge-based Deep Learning for Modeling Chaotic Systems](https://mlsanity.com/paper/2209.04259/) (2022)
- [Emergence of Concepts in DNNs?](https://mlsanity.com/paper/2211.06137/) (2022)
- [Downscaling Neural Network for Coastal Simulations](https://mlsanity.com/paper/2408.16553/) (2024)
- [Scientifically-Interpretable Reasoning Network (ScIReN): Discovering Hidden Relationships in the Carbon Cycle and Beyond](https://mlsanity.com/paper/2506.14054/) (2025)
- [Counterfactual Predictions in Scientific Emulators Without Controlled Experiments](https://mlsanity.com/paper/2610.02252/) (2026)

## Abstract (arXiv)

Artificial neural-networks have the potential to emulate cloud processes with higher accuracy than the semi-empirical emulators currently used in climate models. However, neural-network models do not intrinsically conserve energy and mass, which is an obstacle to using them for long-term climate predictions. Here, we propose two methods to enforce linear conservation laws in neural-network emulators of physical models: Constraining (1) the loss function or (2) the architecture of the network itself. Applied to the emulation of explicitly-resolved cloud processes in a prototype multi-scale climate model, we show that architecture constraints can enforce conservation laws to satisfactory numerical precision, while all constraints help the neural-network better generalize to conditions outside of its training set, such as global warming.