Image-Driven Multiview Environmental Simulation Modeling and Dynamic Response Mechanisms for Virtual Disaster Drills
Bibliographic record
Abstract
In response to the increasing frequency of natural disasters and public safety incidents, traditional field-based drills face significant challenges in terms of cost, safety, and scene diversity.Virtual simulation technology, however, provides a revolutionary approach for efficient, low-risk disaster drills.Nevertheless, constructing a high-fidelity, interactive virtual training environment and realizing physically credible dynamic disaster responses remain core challenges in this field.Current research in environmental modeling, such as methods like Neural Radiance Fields (NeRF), suffers from slow training and difficulties in integrating physical semantics, while high-fidelity disaster simulations incur enormous computational costs, with simplified models sacrificing realism.To address these issues, this paper focuses on two core areas: "image-driven modeling" and "dynamic response mechanisms."(1) In environmental simulation modeling, this paper innovatively optimizes and applies three-dimensional Gaussian Splatting (3DGS) techniques, enabling rapid reconstruction of geometrically accurate, visually rich, and semantically informed digital twins of scenes from multi-view images via hierarchical spatial partitioning and semantic injection.(2) In dynamic response, a hybrid framework combining physical simulation and AI acceleration is proposed, where graph neural network (GNN)-based proxy models are trained to simulate the physical evolution of disasters such as fires and floods in real time.These models are deeply coupled with particle systems and physics engines in game engines to achieve intelligent, real-time interaction between disasters, environments, and trainee behaviors.The main contributions of this paper are: (1) the introduction of a complete virtual disaster drill technology system that integrates improved 3DGS with AI-accelerated physical simulation, achieving a closed-loop from real-world perception to virtual-world interaction; (2) the introduction of enhanced appearance and geometric priors in environmental modeling, significantly improving the physical consistency and semantic completeness of reconstructed models; and (3) the development of a real-time disaster simulator based on AI proxy models, which breaks computational bottlenecks and enables immersive, interactive drills at large-scale scenes while ensuring physical credibility.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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".