HlightReaxMD: A Machine Learning-Augmented Multiscale Analysis Framework for Radiation Chemistry Dynamics and Damage Prediction
Bibliographic record
Abstract
Molecular dynamics (MD) simulations are currently widely used to study large-scale displacement cascades based on massive simulation trajectories. However, when the irradiation process involves the complex chemical reactions, effectively analyzing and extracting features from these data becomes a challenge. Here, we introduce a new cross-platform toolkit, HlightReaxMD, designed to directly obtain information about the irradiation damage process and chemical reactions from MD trajectories and further achieve the prediction of irradiation damage. The analysis tools in HlightReaxMD include chemical reaction analysis and calculation of reaction kinetic parameters, analysis of the collision cascade process, and calculation of necessary physicochemical properties. HlightReaxMD supports the analysis of all elements used in reactive force fields by reading ReaxFF potential file parameters and provides an automated solution for tracking atomic-scale collision events and analyzing chemical reaction mechanisms through constructing cascade trees and reaction network paths. A machine learning-driven model using the analysis results has been included in HlightReaxMD, which can predict irradiation damage by considering various factors, rather than relying solely on the Norgett-Robinson-Torrens displacements per atom (NRT-dpa) model. It enables researchers to automatically obtain dynamic processes and reaction information from atomic to microscale defects from terabyte-level trajectory data. Thus, HlightReaxMD can promote systematic research on irradiation effects in materials science.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".