Integrating physical units into high-performance AI-driven scientific computing

Αποθηκεύτηκε σε:
Λεπτομέρειες βιβλιογραφικής εγγραφής
Εκδόθηκε σε:Nature Communications vol. 16, no. 1 (2025), p. 3609
Έκδοση:
Nature Publishing Group
Θέματα:
Διαθέσιμο Online:Citation/Abstract
Full Text - PDF
Ετικέτες: Προσθήκη ετικέτας
Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!

MARC

LEADER 00000nab a2200000uu 4500
001 3190953795
003 UK-CbPIL
022 |a 2041-1723 
024 7 |a 10.1038/s41467-025-58626-4  |2 doi 
035 |a 3190953795 
045 2 |b d20250101  |b d20251231 
084 |a 145839  |2 nlm 
245 1 |a Integrating physical units into high-performance AI-driven scientific computing 
260 |b Nature Publishing Group  |c 2025 
513 |a Journal Article 
520 3 |a Artificial intelligence is revolutionizing scientific research across various disciplines. The foundation of scientific research lies in rigorous scientific computing based on standardized physical units. However, current mainstream high-performance numerical computing libraries for artificial intelligence generally lack native support for physical units, significantly impeding the integration of artificial intelligence methodologies into scientific research. To fill this gap, we introduce SAIUnit, a system designed to seamlessly integrate physical units into scientific artificial intelligence libraries, with a focus on compatibility with JAX. SAIUnit offers a comprehensive library of over 2000 physical units and 500 unit-aware mathematical functions. It is fully compatible with JAX transformations, allowing for automatic differentiation, just-in-time compilation, vectorization, and parallelization while maintaining unit consistency. We demonstrate SAIUnit’s applicability and effectiveness across diverse artificial intelligence-driven scientific computing domains, including numerical integration, brain modeling, and physics-informed neural networks. Our results show that by confining unit checking to the compilation phase, SAIUnit enhances the accuracy, reliability, interpretability, and collaborative potential of scientific computations without compromising runtime performance. By bridging the gap between abstract computing frameworks and physical units, SAIUnit represents a crucial step towards more robust and physically grounded artificial intelligence-driven scientific computing.Existing numerical computing libraries lack native support for physical units, limiting their application in rigorous scientific computing. Here, the authors developed SAIUnit, which integrates physical units, and unit-aware mathematical functions and transformations into numerical computing libraries for artificial intelligence-driven scientific computing. 
653 |a Transformations (mathematics) 
653 |a Mathematics 
653 |a Computation 
653 |a Artificial intelligence 
653 |a Neural networks 
653 |a Functions (mathematics) 
653 |a Mathematical functions 
653 |a Numerical integration 
653 |a Libraries 
653 |a Economic 
773 0 |t Nature Communications  |g vol. 16, no. 1 (2025), p. 3609 
786 0 |d ProQuest  |t Health & Medical Collection 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3190953795/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3190953795/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch