DDCCNet: Physics-enhanced Multitask Neural Networks for Data-driven Coupled-cluster
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912868093394944 |
|---|---|
| author | Pathirage, P. D. Varuna S. Vogiatzis, Konstantinos D. |
| author_facet | Pathirage, P. D. Varuna S. Vogiatzis, Konstantinos D. |
| contents | We present the data-driven coupled-cluster deep network (DDCCNet), a family of multitask, physics-enhanced deep learning architectures designed to predict coupled-cluster singles and doubles (CCSD) amplitudes and correlation energies from lower-level electronic structure methods. The three DDCCNet variants (termed as v1, v2, and v3) progressively incorporate architectural refinements ranging from parallel subnetworks for t_1 and t_2 amplitudes to feature-partitioned blocks and physics-enhanced intermediate prediction layers that are structured in accordance with coupled-cluster equations to enhance physical consistency and multitask learning efficiency. These models jointly learn correlated amplitude patterns while embedding symmetry and orbital-level interactions directly into the network structure. Applied to methanol conformers, CO2 clusters, and small organic molecules, DDCCNet_v2 delivered the most accurate and transferable performance, achieving chemically precise correlation energies across diverse molecular systems. Collectively, DDCCNet establishes a scalable, physically grounded framework that unifies machine learning and ab initio theory for efficient, data-driven electronic structure prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_14073 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DDCCNet: Physics-enhanced Multitask Neural Networks for Data-driven Coupled-cluster Pathirage, P. D. Varuna S. Vogiatzis, Konstantinos D. Chemical Physics We present the data-driven coupled-cluster deep network (DDCCNet), a family of multitask, physics-enhanced deep learning architectures designed to predict coupled-cluster singles and doubles (CCSD) amplitudes and correlation energies from lower-level electronic structure methods. The three DDCCNet variants (termed as v1, v2, and v3) progressively incorporate architectural refinements ranging from parallel subnetworks for t_1 and t_2 amplitudes to feature-partitioned blocks and physics-enhanced intermediate prediction layers that are structured in accordance with coupled-cluster equations to enhance physical consistency and multitask learning efficiency. These models jointly learn correlated amplitude patterns while embedding symmetry and orbital-level interactions directly into the network structure. Applied to methanol conformers, CO2 clusters, and small organic molecules, DDCCNet_v2 delivered the most accurate and transferable performance, achieving chemically precise correlation energies across diverse molecular systems. Collectively, DDCCNet establishes a scalable, physically grounded framework that unifies machine learning and ab initio theory for efficient, data-driven electronic structure prediction. |
| title | DDCCNet: Physics-enhanced Multitask Neural Networks for Data-driven Coupled-cluster |
| topic | Chemical Physics |
| url | https://arxiv.org/abs/2601.14073 |