• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

物理科学中的人工智能：符号回归趋势与展望。

Artificial Intelligence in Physical Sciences: Symbolic Regression Trends and Perspectives.

作者信息

Angelis Dimitrios, Sofos Filippos, Karakasidis Theodoros E

机构信息

Condensed Matter Physics Laboratory, Department of Physics, University of Thessaly, Lamia, 35100 Greece.

出版信息

Arch Comput Methods Eng. 2023 Apr 19:1-21. doi: 10.1007/s11831-023-09922-z.

DOI:10.1007/s11831-023-09922-z
PMID:37359747
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10113133/
Abstract

UNLABELLED

Symbolic regression (SR) is a machine learning-based regression method based on genetic programming principles that integrates techniques and processes from heterogeneous scientific fields and is capable of providing analytical equations purely from data. This remarkable characteristic diminishes the need to incorporate prior knowledge about the investigated system. SR can spot profound and elucidate ambiguous relations that can be generalizable, applicable, explainable and span over most scientific, technological, economical, and social principles. In this review, current state of the art is documented, technical and physical characteristics of SR are presented, the available programming techniques are investigated, fields of application are explored, and future perspectives are discussed.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s11831-023-09922-z.

摘要

未标注

符号回归（SR）是一种基于遗传编程原理的机器学习回归方法，它整合了来自不同科学领域的技术和过程，能够仅从数据中提供分析方程。这一显著特性减少了纳入有关被研究系统的先验知识的需求。SR可以发现深刻的关系，并阐明那些可推广、适用、可解释且涵盖大多数科学、技术、经济和社会原理的模糊关系。在本综述中，记录了当前的技术水平，介绍了SR的技术和物理特性，研究了可用的编程技术，探索了应用领域，并讨论了未来展望。

补充信息

在线版本包含可在10.1007/s11831-023-09922-z获取的补充材料。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98c1/10113133/3e6c512ff068/11831_2023_9922_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98c1/10113133/3544e5588f2d/11831_2023_9922_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98c1/10113133/580822767377/11831_2023_9922_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98c1/10113133/007b0002cd81/11831_2023_9922_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98c1/10113133/7835dfb730c6/11831_2023_9922_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98c1/10113133/ef38dd7bd04b/11831_2023_9922_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98c1/10113133/3e6c512ff068/11831_2023_9922_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98c1/10113133/3544e5588f2d/11831_2023_9922_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98c1/10113133/580822767377/11831_2023_9922_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98c1/10113133/007b0002cd81/11831_2023_9922_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98c1/10113133/7835dfb730c6/11831_2023_9922_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98c1/10113133/ef38dd7bd04b/11831_2023_9922_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/98c1/10113133/3e6c512ff068/11831_2023_9922_Fig6_HTML.jpg

相似文献

1
Artificial Intelligence in Physical Sciences: Symbolic Regression Trends and Perspectives.物理科学中的人工智能：符号回归趋势与展望。
Arch Comput Methods Eng. 2023 Apr 19:1-21. doi: 10.1007/s11831-023-09922-z.
2
A computational framework for physics-informed symbolic regression with straightforward integration of domain knowledge.具有领域知识直接集成的物理信息符号回归的计算框架。
Sci Rep. 2023 Jan 23;13(1):1249. doi: 10.1038/s41598-023-28328-2.
3
Artificial intelligence for improving Nitrogen Dioxide forecasting of Abu Dhabi environment agency ground-based stations.用于改进阿布扎比环境局地面站二氧化氮预测的人工智能
J Big Data. 2023;10(1):92. doi: 10.1186/s40537-023-00754-z. Epub 2023 Jun 2.
4
Research Landscape of Artificial Intelligence and e-Learning: A Bibliometric Research.人工智能与电子学习的研究概况：一项文献计量研究。
Front Psychol. 2022 Feb 16;13:795039. doi: 10.3389/fpsyg.2022.795039. eCollection 2022.
5
Multitree Genetic Programming With Feature-Based Transfer Learning for Symbolic Regression on Incomplete Data.基于特征迁移学习的多树遗传编程用于不完整数据的符号回归
IEEE Trans Cybern. 2024 Jul;54(7):4014-4027. doi: 10.1109/TCYB.2023.3270319. Epub 2024 Jul 11.
6
Explaining protein-protein interactions with knowledge graph-based semantic similarity.用基于知识图的语义相似度解释蛋白质-蛋白质相互作用。
Comput Biol Med. 2024 Mar;170:108076. doi: 10.1016/j.compbiomed.2024.108076. Epub 2024 Feb 1.
7
Artificial Intelligence and Machine Learning in Nuclear Medicine: Future Perspectives.人工智能和机器学习在核医学中的应用：未来展望。
Semin Nucl Med. 2021 Mar;51(2):170-177. doi: 10.1053/j.semnuclmed.2020.08.003. Epub 2020 Sep 12.
8
[Artificial intelligence for future MD].面向未来医学博士的人工智能
G Ital Nefrol. 2018 Dec;35(6).
9
Explainable AI and Reinforcement Learning-A Systematic Review of Current Approaches and Trends.可解释人工智能与强化学习——当前方法与趋势的系统综述
Front Artif Intell. 2021 May 20;4:550030. doi: 10.3389/frai.2021.550030. eCollection 2021.
10
Carbon capture, utilization and sequestration systems design and operation optimization: Assessment and perspectives of artificial intelligence opportunities.碳捕获、利用与封存系统设计及运行优化：人工智能机遇的评估与展望
Sci Total Environ. 2024 Mar 20;917:170085. doi: 10.1016/j.scitotenv.2024.170085. Epub 2024 Jan 13.

引用本文的文献

1
Graph ODEs and Beyond: A Comprehensive Survey on Integrating Differential Equations with Graph Neural Networks.图常微分方程及其他：关于将微分方程与图神经网络相结合的全面综述。
KDD. 2025 Aug;2025:6118-6128. doi: 10.1145/3711896.3736559. Epub 2025 Aug 3.
2
Physically Consistent Self-Diffusion Coefficient Calculation with Molecular Dynamics and Symbolic Regression.基于分子动力学和符号回归的物理一致自扩散系数计算
Int J Mol Sci. 2025 Jul 14;26(14):6748. doi: 10.3390/ijms26146748.
3
Using graph neural network and symbolic regression to model disordered systems.

本文引用的文献

1
Contemporary Symbolic Regression Methods and their Relative Performance.当代符号回归方法及其相对性能。
Adv Neural Inf Process Syst. 2021 Dec;2021(DB1):1-16.
2
Augmenting astrophysical scaling relations with machine learning: Application to reducing the Sunyaev-Zeldovich flux-mass scatter.利用机器学习增强天体物理比例关系：在降低 Sunyaev-Zeldovich 流量质量离散度中的应用。
Proc Natl Acad Sci U S A. 2023 Mar 21;120(12):e2202074120. doi: 10.1073/pnas.2202074120. Epub 2023 Mar 17.
3
Combining symbolic regression with the Cox proportional hazards model improves prediction of heart failure deaths.
使用图神经网络和符号回归对无序系统进行建模。
Sci Rep. 2025 Jul 1;15(1):22122. doi: 10.1038/s41598-025-05205-8.
4
Dynamics of an epidemic controlled by isolation and quarantine: A probability-based deterministic model.通过隔离和检疫控制的流行病动态：一个基于概率的确定性模型。
Infect Dis Model. 2025 Mar 18;10(3):813-839. doi: 10.1016/j.idm.2025.03.007. eCollection 2025 Sep.
5
Role of data-driven regional growth model in shaping brain folding patterns.数据驱动的区域生长模型在塑造脑回折叠模式中的作用。
Soft Matter. 2025 Jan 22;21(4):729-749. doi: 10.1039/d4sm01194e.
6
Automated data-driven discovery of material models based on symbolic regression: A case study on the human brain cortex.基于符号回归的自动化数据驱动的材料模型发现：以人类大脑皮层为例。
Acta Biomater. 2024 Oct 15;188:276-296. doi: 10.1016/j.actbio.2024.09.005. Epub 2024 Sep 17.
7
Optimization Design of Submerged-Entry-Nozzle Structure Using NSGA-II Genetic Algorithm in Ultra-Large Beam-Blank Continuous-Casting Molds.
Materials (Basel). 2024 Sep 2;17(17):4346. doi: 10.3390/ma17174346.
8
Plant science in the age of simulation intelligence.模拟智能时代的植物科学。
Front Plant Sci. 2024 Jan 16;14:1299208. doi: 10.3389/fpls.2023.1299208. eCollection 2023.
9
Fluid Properties Extraction in Confined Nanochannels with Molecular Dynamics and Symbolic Regression Methods.基于分子动力学和符号回归方法的受限纳米通道内流体性质提取
Micromachines (Basel). 2023 Jul 19;14(7):1446. doi: 10.3390/mi14071446.
将符号回归与 Cox 比例风险模型相结合可以提高心力衰竭死亡预测的准确性。
BMC Med Inform Decis Mak. 2022 Jul 25;22(1):196. doi: 10.1186/s12911-022-01943-1.
4
Symbolic regression development of empirical equations for diffusion in Lennard-Jones fluids.拉努加因流体中扩散的经验方程的符号回归开发。
J Chem Phys. 2022 Jul 7;157(1):014503. doi: 10.1063/5.0093658.
5
Instantaneous Property Prediction and Inverse Design of Plasmonic Nanostructures Using Machine Learning: Current Applications and Future Directions.利用机器学习实现等离子体纳米结构的瞬时特性预测与逆向设计：当前应用与未来方向
Nanomaterials (Basel). 2022 Feb 14;12(4):633. doi: 10.3390/nano12040633.
6
Artificial intelligence and machine learning in design of mechanical materials.人工智能和机器学习在机械材料设计中的应用。
Mater Horiz. 2021 Apr 1;8(4):1153-1172. doi: 10.1039/d0mh01451f. Epub 2021 Jan 7.
7
Materials Informatics for Mechanical Deformation: A Review of Applications and Challenges.机械变形的材料信息学：应用与挑战综述
Materials (Basel). 2021 Oct 2;14(19):5764. doi: 10.3390/ma14195764.
8
Shape-Constrained Symbolic Regression-Improving Extrapolation with Prior Knowledge.形状约束符号回归——利用先验知识提高外推能力。
Evol Comput. 2022 Mar 1;30(1):75-98. doi: 10.1162/evco_a_00294.
9
A Bayesian neural network predicts the dissolution of compact planetary systems.贝叶斯神经网络预测致密行星系统的解体。
Proc Natl Acad Sci U S A. 2021 Oct 5;118(40). doi: 10.1073/pnas.2026053118.
10
Probing the carbon emissions in 30 regions of China based on symbolic regression and Tapio decoupling.基于符号回归和脱钩理论探讨中国 30 个地区的碳排放。
Environ Sci Pollut Res Int. 2022 Jan;29(2):2650-2663. doi: 10.1007/s11356-021-15648-x. Epub 2021 Aug 10.