# Domain adaption and physical constrains transfer learning for shale gas production

arXiv: https://arxiv.org/abs/2312.10920 · HTML: https://mlsanity.com/paper/2312.10920/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 55 references that are in the map.
- First posted on arXiv 18 Dec 2023.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [Transformer in Transformer](https://mlsanity.com/paper/2103.00112/) (2021)
- [Transformers in Time Series: A Survey](https://mlsanity.com/paper/2202.07125/) (2022)
- [AdaRNN: Adaptive Learning and Forecasting of Time Series](https://mlsanity.com/paper/2108.04443/) (2021)
- [Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination](https://mlsanity.com/paper/2112.11701/) (2021)
- [Mixing ADAM and SGD: a Combined Optimization Method](https://mlsanity.com/paper/2011.08042/) (2020)
- [Low-Resource Text Classification using Domain-Adversarial Learning](https://mlsanity.com/paper/1807.05195/) (2018)
- [TgDLF2.0: Theory-guided deep-learning for electrical load forecasting via Transformer and transfer learning](https://mlsanity.com/paper/2210.02448/) (2022)
- [Interpretability and causal discovery of the machine learning models to predict the production of CBM wells after hydraulic fracturing](https://mlsanity.com/paper/2212.10718/) (2022)

## Abstract (arXiv)

Effective prediction of shale gas production is crucial for strategic reservoir development. However, in new shale gas blocks, two main challenges are encountered: (1) the occurrence of negative transfer due to insufficient data, and (2) the limited interpretability of deep learning (DL) models. To tackle these problems, we propose a novel transfer learning methodology that utilizes domain adaptation and physical constraints. This methodology effectively employs historical data from the source domain to reduce negative transfer from the data distribution perspective, while also using physical constraints to build a robust and reliable prediction model that integrates various types of data. The methodology starts by dividing the production data from the source domain into multiple subdomains, thereby enhancing data diversity. It then uses Maximum Mean Discrepancy (MMD) and global average distance measures to decide on the feasibility of transfer. Through domain adaptation, we integrate all transferable knowledge, resulting in a more comprehensive target model. Lastly, by incorporating drilling, completion, and geological data as physical constraints, we develop a hybrid model. This model, a combination of a multi-layer perceptron (MLP) and a Transformer (Transformer-MLP), is designed to maximize interpretability. Experimental validation in China's southwestern region confirms the method's effectiveness.