Leveraging Simulation and Deep Learning for Enhanced Health and Safety

Dear Colleagues,

The Special Issue Leveraging Simulation and Deep Learning for Enhanced Health and Safety aims to gather cutting-edge research that combines advanced artificial intelligence techniques with high-fidelity simulation to solve safety-critical problems across domains such as property prediction, public health, agriculture, cyber-security, and autonomous transportation.

Focus and Scope.
This Special Issue centers on AI methods—including deep learning, computer vision, causal inference, statistical modeling, and risk-aware reinforcement learning—that are explicitly engineered for health-and-safety-related tasks. We welcome theoretical contributions, empirical studies, and system demonstrations that achieve the following:

1. Fuse simulation with real-world data to accelerate model training, stress-test edge cases, or generate rare-event scenarios (e.g., pathogen spread models, cyber-attack emulation, corner-case driving incidents).
2. Advance AI safety and interpretability, including explainable AI (XAI) frameworks that expose causal pathways or quantify uncertainty in safety-critical recommendations.
3. Translate insights into practice, for example, crop-health monitoring that reduces pesticide load, AI-driven anomaly detection that hardens critical infrastructure, or risk-aware autopilot controllers that meet regulatory standards.
4. Assess the societal, ethical, and regulatory implications of deploying simulation-augmented AI in sensitive environments.

Papers may span novel architecture, benchmarking datasets, evaluation protocols, or interdisciplinary case studies and should articulate clear pathways from algorithmic innovation to measurable safety or health gains.

Purpose and Contribution to the Literature.
While prior work has advanced either simulation techniques (digital twins, agent-based models) or AI algorithms (deep neural networks, causal discovery) in isolation, few studies examine their synergy for safety augmentation across sectors. The existing literature tends to be siloed—papers on autonomous driving seldom cross-reference medical AI safety frameworks, and agricultural decision support rarely leverages cyber-security risk analytics. This Special Issue therefore aims to achieve the following:

• Bridge disciplines by showcasing transferable methodologies—e.g., causality-guided computer vision equally applicable to crop disease detection and industrial hazard monitoring.
• Extend AI safety discourse beyond theoretical alignment by grounding it in domain-specific risk simulations and real-world validations.
• Fill empirical gaps through curated studies that quantify safety benefits under realistic constraints, supplementing predominantly benchmark-driven AI literature.
• Set a research agenda for integrated simulation–AI pipelines that satisfy regulatory rigor, improving trust in AI and accelerating its adoption in mission-critical contexts.

By situating diverse yet convergent work in a single forum, this Special Issue aims to catalyze the establishment of a new cross-sector community dedicated to AI systems that are not just intelligent, but also verifiably safe, robust, and societally beneficial.

Dr. Pingfan Hu
Dr. He Wen
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. AI is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• deep learning
• simulation-based modeling
• AI safety
• explainable AI (XAI)
• risk simulation
• causal inference
• computer vision
• digital twins
• safety-critical systems
• property prediction