Practical integration of machine learning into ab initio calculations and workflows: Accelerating the SCF cycle via density matrix predictions Article Swipe
P. V. Stishenko
,
Qian Chen
,
Julia Westermayr
,
Reinhard J. Maurer
,
Andrew J. Logsdail
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.26434/chemrxiv-2025-xn2mp
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.26434/chemrxiv-2025-xn2mp
Data-driven approaches offer great potential for accelerating ab initio electronic structure calculations of molecules and materials but their transferability is often limited due to the vast amount of data needed for training, including when addressing the need to fine-tune universal models for each specific system to be studied. Here, we demonstrate how contributions from system-specific electronic structure machine learning (ESML) models may be combined (“stitched”) to deliver density matrices of entire systems of interest, improving the initial guess for the self-consistent field cycle and delivering gains in computational efficiency. The “stitching” of density matrices is demonstrated for sequential calculations, such as geometry optimization and molecular dynamics, and we show that the synergistic use of ESML models and density matrix extrapolation algorithms can accelerate standard computational calculations. The algorithms are demonstrated for test cases relating to water clusters and a methane clathrate cage, with the benefits discussed. The future opportunities for hybrid quantum mechanical and ML (QM/ML), and also ML/ML paradigms, are broad-ranging with significant computational speed-up attainable.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.26434/chemrxiv-2025-xn2mp
- https://chemrxiv.org/engage/api-gateway/chemrxiv/assets/orp/resource/item/68bb4ff6728bf9025ea86e33/original/practical-integration-of-machine-learning-into-ab-initio-calculations-and-workflows-accelerating-the-scf-cycle-via-density-matrix-predictions.pdf
- OA Status
- gold
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4414100641
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4414100641Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.26434/chemrxiv-2025-xn2mpDigital Object Identifier
- Title
-
Practical integration of machine learning into ab initio calculations and workflows: Accelerating the SCF cycle via density matrix predictionsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-09-10Full publication date if available
- Authors
-
P. V. Stishenko, Qian Chen, Julia Westermayr, Reinhard J. Maurer, Andrew J. LogsdailList of authors in order
- Landing page
-
https://doi.org/10.26434/chemrxiv-2025-xn2mpPublisher landing page
- PDF URL
-
https://chemrxiv.org/engage/api-gateway/chemrxiv/assets/orp/resource/item/68bb4ff6728bf9025ea86e33/original/practical-integration-of-machine-learning-into-ab-initio-calculations-and-workflows-accelerating-the-scf-cycle-via-density-matrix-predictions.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://chemrxiv.org/engage/api-gateway/chemrxiv/assets/orp/resource/item/68bb4ff6728bf9025ea86e33/original/practical-integration-of-machine-learning-into-ab-initio-calculations-and-workflows-accelerating-the-scf-cycle-via-density-matrix-predictions.pdfDirect OA link when available
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4414100641 |
|---|---|
| doi | https://doi.org/10.26434/chemrxiv-2025-xn2mp |
| ids.doi | https://doi.org/10.26434/chemrxiv-2025-xn2mp |
| ids.openalex | https://openalex.org/W4414100641 |
| fwci | 0.0 |
| type | preprint |
| title | Practical integration of machine learning into ab initio calculations and workflows: Accelerating the SCF cycle via density matrix predictions |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11948 |
| topics[0].field.id | https://openalex.org/fields/25 |
| topics[0].field.display_name | Materials Science |
| topics[0].score | 0.9986000061035156 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2505 |
| topics[0].subfield.display_name | Materials Chemistry |
| topics[0].display_name | Machine Learning in Materials Science |
| topics[1].id | https://openalex.org/T11825 |
| topics[1].field.id | https://openalex.org/fields/15 |
| topics[1].field.display_name | Chemical Engineering |
| topics[1].score | 0.9750999808311462 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1503 |
| topics[1].subfield.display_name | Catalysis |
| topics[1].display_name | Catalysis and Oxidation Reactions |
| topics[2].id | https://openalex.org/T10002 |
| topics[2].field.id | https://openalex.org/fields/31 |
| topics[2].field.display_name | Physics and Astronomy |
| topics[2].score | 0.9693999886512756 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/3107 |
| topics[2].subfield.display_name | Atomic and Molecular Physics, and Optics |
| topics[2].display_name | Advanced Chemical Physics Studies |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | doi:10.26434/chemrxiv-2025-xn2mp |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://chemrxiv.org/engage/api-gateway/chemrxiv/assets/orp/resource/item/68bb4ff6728bf9025ea86e33/original/practical-integration-of-machine-learning-into-ab-initio-calculations-and-workflows-accelerating-the-scf-cycle-via-density-matrix-predictions.pdf |
| locations[0].version | acceptedVersion |
| locations[0].raw_type | posted-content |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://doi.org/10.26434/chemrxiv-2025-xn2mp |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5091287939 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-4653-9899 |
| authorships[0].author.display_name | P. V. Stishenko |
| authorships[0].countries | GB |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I79510175 |
| authorships[0].affiliations[0].raw_affiliation_string | Cardiff University |
| authorships[0].institutions[0].id | https://openalex.org/I79510175 |
| authorships[0].institutions[0].ror | https://ror.org/03kk7td41 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I79510175 |
| authorships[0].institutions[0].country_code | GB |
| authorships[0].institutions[0].display_name | Cardiff University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Pavel Stishenko |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Cardiff University |
| authorships[1].author.id | https://openalex.org/A5028434644 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-3685-3585 |
| authorships[1].author.display_name | Qian Chen |
| authorships[1].countries | GB |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I39555362 |
| authorships[1].affiliations[0].raw_affiliation_string | University of Warwick |
| authorships[1].institutions[0].id | https://openalex.org/I39555362 |
| authorships[1].institutions[0].ror | https://ror.org/01a77tt86 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I39555362 |
| authorships[1].institutions[0].country_code | GB |
| authorships[1].institutions[0].display_name | University of Warwick |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Chen Qian |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | University of Warwick |
| authorships[2].author.id | https://openalex.org/A5039680751 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-6531-0742 |
| authorships[2].author.display_name | Julia Westermayr |
| authorships[2].countries | DE |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I926574661 |
| authorships[2].affiliations[0].raw_affiliation_string | Leipzig Un |
| authorships[2].institutions[0].id | https://openalex.org/I926574661 |
| authorships[2].institutions[0].ror | https://ror.org/03s7gtk40 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I926574661 |
| authorships[2].institutions[0].country_code | DE |
| authorships[2].institutions[0].display_name | Leipzig University |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Julia Westermayr |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Leipzig Un |
| authorships[3].author.id | https://openalex.org/A5016855366 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-3004-785X |
| authorships[3].author.display_name | Reinhard J. Maurer |
| authorships[3].countries | GB |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I39555362 |
| authorships[3].affiliations[0].raw_affiliation_string | University of Warwick |
| authorships[3].institutions[0].id | https://openalex.org/I39555362 |
| authorships[3].institutions[0].ror | https://ror.org/01a77tt86 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I39555362 |
| authorships[3].institutions[0].country_code | GB |
| authorships[3].institutions[0].display_name | University of Warwick |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Reinhard Maurer |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | University of Warwick |
| authorships[4].author.id | https://openalex.org/A5064011663 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-2277-415X |
| authorships[4].author.display_name | Andrew J. Logsdail |
| authorships[4].countries | GB |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I79510175 |
| authorships[4].affiliations[0].raw_affiliation_string | Cardiff University |
| authorships[4].institutions[0].id | https://openalex.org/I79510175 |
| authorships[4].institutions[0].ror | https://ror.org/03kk7td41 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I79510175 |
| authorships[4].institutions[0].country_code | GB |
| authorships[4].institutions[0].display_name | Cardiff University |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Andrew Logsdail |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | Cardiff University |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://chemrxiv.org/engage/api-gateway/chemrxiv/assets/orp/resource/item/68bb4ff6728bf9025ea86e33/original/practical-integration-of-machine-learning-into-ab-initio-calculations-and-workflows-accelerating-the-scf-cycle-via-density-matrix-predictions.pdf |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Practical integration of machine learning into ab initio calculations and workflows: Accelerating the SCF cycle via density matrix predictions |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T11948 |
| primary_topic.field.id | https://openalex.org/fields/25 |
| primary_topic.field.display_name | Materials Science |
| primary_topic.score | 0.9986000061035156 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2505 |
| primary_topic.subfield.display_name | Materials Chemistry |
| primary_topic.display_name | Machine Learning in Materials Science |
| related_works | https://openalex.org/W1994111383, https://openalex.org/W1991778621, https://openalex.org/W2044324006, https://openalex.org/W1970435430, https://openalex.org/W1964384985, https://openalex.org/W1990209859, https://openalex.org/W1985888471, https://openalex.org/W2015945838, https://openalex.org/W2058434227, https://openalex.org/W2374466131 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.26434/chemrxiv-2025-xn2mp |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://chemrxiv.org/engage/api-gateway/chemrxiv/assets/orp/resource/item/68bb4ff6728bf9025ea86e33/original/practical-integration-of-machine-learning-into-ab-initio-calculations-and-workflows-accelerating-the-scf-cycle-via-density-matrix-predictions.pdf |
| best_oa_location.version | acceptedVersion |
| best_oa_location.raw_type | posted-content |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | https://doi.org/10.26434/chemrxiv-2025-xn2mp |
| primary_location.id | doi:10.26434/chemrxiv-2025-xn2mp |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://chemrxiv.org/engage/api-gateway/chemrxiv/assets/orp/resource/item/68bb4ff6728bf9025ea86e33/original/practical-integration-of-machine-learning-into-ab-initio-calculations-and-workflows-accelerating-the-scf-cycle-via-density-matrix-predictions.pdf |
| primary_location.version | acceptedVersion |
| primary_location.raw_type | posted-content |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://doi.org/10.26434/chemrxiv-2025-xn2mp |
| publication_date | 2025-09-10 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 138 |
| abstract_inverted_index.ML | 154 |
| abstract_inverted_index.ab | 7 |
| abstract_inverted_index.as | 100 |
| abstract_inverted_index.be | 46, 62 |
| abstract_inverted_index.in | 86 |
| abstract_inverted_index.is | 19, 94 |
| abstract_inverted_index.of | 12, 27, 69, 72, 91, 113 |
| abstract_inverted_index.to | 23, 37, 45, 65, 134 |
| abstract_inverted_index.we | 49, 107 |
| abstract_inverted_index.The | 89, 126, 146 |
| abstract_inverted_index.and | 14, 83, 103, 106, 116, 137, 153, 156 |
| abstract_inverted_index.are | 128, 160 |
| abstract_inverted_index.but | 16 |
| abstract_inverted_index.can | 121 |
| abstract_inverted_index.due | 22 |
| abstract_inverted_index.for | 5, 30, 41, 78, 96, 130, 149 |
| abstract_inverted_index.how | 51 |
| abstract_inverted_index.may | 61 |
| abstract_inverted_index.the | 24, 35, 75, 79, 110, 143 |
| abstract_inverted_index.use | 112 |
| abstract_inverted_index.ESML | 114 |
| abstract_inverted_index.also | 157 |
| abstract_inverted_index.data | 28 |
| abstract_inverted_index.each | 42 |
| abstract_inverted_index.from | 53 |
| abstract_inverted_index.need | 36 |
| abstract_inverted_index.show | 108 |
| abstract_inverted_index.such | 99 |
| abstract_inverted_index.test | 131 |
| abstract_inverted_index.that | 109 |
| abstract_inverted_index.vast | 25 |
| abstract_inverted_index.when | 33 |
| abstract_inverted_index.with | 142, 162 |
| abstract_inverted_index.Here, | 48 |
| abstract_inverted_index.ML/ML | 158 |
| abstract_inverted_index.cage, | 141 |
| abstract_inverted_index.cases | 132 |
| abstract_inverted_index.cycle | 82 |
| abstract_inverted_index.field | 81 |
| abstract_inverted_index.gains | 85 |
| abstract_inverted_index.great | 3 |
| abstract_inverted_index.guess | 77 |
| abstract_inverted_index.offer | 2 |
| abstract_inverted_index.often | 20 |
| abstract_inverted_index.their | 17 |
| abstract_inverted_index.water | 135 |
| abstract_inverted_index.(ESML) | 59 |
| abstract_inverted_index.amount | 26 |
| abstract_inverted_index.entire | 70 |
| abstract_inverted_index.future | 147 |
| abstract_inverted_index.hybrid | 150 |
| abstract_inverted_index.initio | 8 |
| abstract_inverted_index.matrix | 118 |
| abstract_inverted_index.models | 40, 60, 115 |
| abstract_inverted_index.needed | 29 |
| abstract_inverted_index.system | 44 |
| abstract_inverted_index.deliver | 66 |
| abstract_inverted_index.density | 67, 92, 117 |
| abstract_inverted_index.initial | 76 |
| abstract_inverted_index.limited | 21 |
| abstract_inverted_index.machine | 57 |
| abstract_inverted_index.methane | 139 |
| abstract_inverted_index.quantum | 151 |
| abstract_inverted_index.systems | 71 |
| abstract_inverted_index.(QM/ML), | 155 |
| abstract_inverted_index.benefits | 144 |
| abstract_inverted_index.clusters | 136 |
| abstract_inverted_index.combined | 63 |
| abstract_inverted_index.geometry | 101 |
| abstract_inverted_index.learning | 58 |
| abstract_inverted_index.matrices | 68, 93 |
| abstract_inverted_index.relating | 133 |
| abstract_inverted_index.specific | 43 |
| abstract_inverted_index.speed-up | 165 |
| abstract_inverted_index.standard | 123 |
| abstract_inverted_index.studied. | 47 |
| abstract_inverted_index.clathrate | 140 |
| abstract_inverted_index.dynamics, | 105 |
| abstract_inverted_index.fine-tune | 38 |
| abstract_inverted_index.improving | 74 |
| abstract_inverted_index.including | 32 |
| abstract_inverted_index.interest, | 73 |
| abstract_inverted_index.materials | 15 |
| abstract_inverted_index.molecular | 104 |
| abstract_inverted_index.molecules | 13 |
| abstract_inverted_index.potential | 4 |
| abstract_inverted_index.structure | 10, 56 |
| abstract_inverted_index.training, | 31 |
| abstract_inverted_index.universal | 39 |
| abstract_inverted_index.accelerate | 122 |
| abstract_inverted_index.addressing | 34 |
| abstract_inverted_index.algorithms | 120, 127 |
| abstract_inverted_index.approaches | 1 |
| abstract_inverted_index.delivering | 84 |
| abstract_inverted_index.discussed. | 145 |
| abstract_inverted_index.electronic | 9, 55 |
| abstract_inverted_index.mechanical | 152 |
| abstract_inverted_index.paradigms, | 159 |
| abstract_inverted_index.sequential | 97 |
| abstract_inverted_index.Data-driven | 0 |
| abstract_inverted_index.attainable. | 166 |
| abstract_inverted_index.demonstrate | 50 |
| abstract_inverted_index.efficiency. | 88 |
| abstract_inverted_index.significant | 163 |
| abstract_inverted_index.synergistic | 111 |
| abstract_inverted_index.accelerating | 6 |
| abstract_inverted_index.calculations | 11 |
| abstract_inverted_index.demonstrated | 95, 129 |
| abstract_inverted_index.optimization | 102 |
| abstract_inverted_index.broad-ranging | 161 |
| abstract_inverted_index.calculations, | 98 |
| abstract_inverted_index.calculations. | 125 |
| abstract_inverted_index.computational | 87, 124, 164 |
| abstract_inverted_index.contributions | 52 |
| abstract_inverted_index.extrapolation | 119 |
| abstract_inverted_index.opportunities | 148 |
| abstract_inverted_index.self-consistent | 80 |
| abstract_inverted_index.system-specific | 54 |
| abstract_inverted_index.transferability | 18 |
| abstract_inverted_index.“stitching” | 90 |
| abstract_inverted_index.(“stitched”) | 64 |
| cited_by_percentile_year | |
| countries_distinct_count | 2 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile.value | 0.38675736 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |