Characterization (materials science)×Artificial neural network
This pair ranks in the top 0.5% of every collision candidate in the corpus. Across held-out years, pairs scoring that well went on to co-publish at 8.2× the base rate, typically within 3 years.
The Frontier Brief for this collision is still being written. The evidence below already reflects the current model run.
Pre-company space. No named players have staked this collision yet — an emerging pairing where the field, not a firm, is the story so far.
43 researchers publish on both sides of this collision without the fields themselves having met. Every name below is counted from papers in the corpus — not inferred.
- Daniele IelminiInstitut de Microelectrònica de Barcelona1/8
- J. Joshua YangUnidades Centrales Científico-Técnicas1/7
- Rampi RamprasadArgonne National Laboratory2/2
- Adnan MehonićJiangsu Key Laboratory for Advanced Metallic Materials1/2
- Mario LanzaJiangsu Key Laboratory for Advanced Metallic Materials1/2
- Anthony Joseph KenyonJiangsu Key Laboratory for Advanced Metallic Materials1/2
- Daniel BrunnerUniversity of Birmingham1/2
- Wenzhong BaoUniversity of Massachusetts Amherst1/2
- Georgy A. ErmolaevInstitute for Functional Intelligent Materials1/1
- Aleksey V. ArseninInstitute for Functional Intelligent Materials1/1
- Chinese Academy of SciencesCN13/114
- Stanford UniversityUS8/133
- Centre National de la Recherche ScientifiqueFR12/62
- Massachusetts Institute of TechnologyUS7/102
- Tsinghua UniversityCN8/81
- National University of SingaporeSG11/47
- Standards for the Characterization of Endurance in Resistive Switching Devices2021 · 265 citations · DOI ↗1
- Materials Informatics Framework for Accelerated Discovery of High-Refractive-Index 2D Materials2026 · 4 citations · DOI ↗1
- Training Deep Neural Networks for the Inverse Design of Nanophotonic Structures2018 · 1,192 citations · DOI ↗2
- Accurate characterization of next-generation thin-film photodetectors2018 · 731 citations · DOI ↗2
Counted from the corpus. Institution counts use best-effort affiliation (every author on a paper is paired with every institution on it), so read them as presence, not headcount.
A premium Deep-Dive is being generated for this collision — check back soon.