Rapid and reliable discrimination of authentic nerve agents in complex environments is a critical, unsolved challenge for security and public safety. Current detection technologies are often limited by bulky instrumentation, prolonged analysis times, or validation restricted to simulants, hindering their real-world threat-monitoring capabilities. Here, we demonstrate a machine learning-enhanced colorimetric sensor array that overcomes these limitations. We employed a systematic data-driven approach using hierarchical clustering, analysis of variance, and correlation analysis to optimally select just six commercially available fluorescent dyes from an initial 29-candidate library. This optimized array was rigorously evaluated against five authentic nerve agents (GA, GB, GD, GF, VX) and a key simulant using a novel dual-mode (Visible/UV) illumination strategy. By quantifying colorimetric responses (RGB-to-ΔE₀₀), our linear discriminant analysis classifier achieved 100% classification accuracy. The sensor provides an instantaneous visual response and maintains discrimination capability down to 10 μM, markedly outperforming the 87.5% accuracy of visible-light-only detection. This study establishes a simple, low-cost, and scalable platform for the rapid, accurate discrimination of multiple authentic nerve agents. By integrating data-driven sensor design with robust visual analysis, our system provides a clear pathway toward next-generation portable technologies for real-time chemical threat surveillance.

Resource-constrained edge processors deployed on unmanned aerial vehicles and wearable platforms require compact, drift-robust gas classification models for a range of environmental and security monitoring applications, including CBRN-motivated scenarios. Existing approaches rely on server-grade architectures incompatible with edge-board-scale deployment, or on classifiers that chemically degrade severely under long-term sensor drift. Each UCI gas class was mapped to a CBRN behavioral category based on physicochemical analogy (molecular functional group, vapor pressure, and metal-oxide semiconductor (MOS) cross-sensitivity pattern), following established precedent. Analyzed were Ammonia (NH₃), Acetaldehyde (CH₃CHO), Acetone ((CH₃)₂CO), Ethylene (C₂H₄), Ethanol (C₂H₅OH), Toluene (C₆H₅CH₃). We propose herein an end-to-end pipeline integrating a novel 1-D convolutional neural network with depth-wise separable convolutions (LiteSensor-Net), INT8 post-training quantization, structured magnitude pruning, and a knowledge-distillation domain-adaptation module (KD–DM) for sensor drift compensation. Using the UCI Gas Sensor Array Drift Dataset (13,910 measurements; 16 metal-oxide sensors; six analyte gases; a 36-month work span). LiteSensor-Net achieved accuracy = 92.63 ± 2.02%, macro-F1 = 0.898, model size = 5.99 kB INT8 pruned, inference latency = 6.3 ms, RAM footprint = 31.7 kB, and energy per inference = 0.04 mJ (all metrics on Raspberry Pi 4B, ARM Cortex-A72). Under chronological forward-chaining evaluation, KD–DM–20 achieved 47.91 ± 18.79% mean accuracy over Batches 2–10, representing a +9.25 pp improvement over uncompensated NC (38.66%). A six-metric benchmark framework—accuracy, macro-F1, model size, inference latency, RAM footprint, and energy per inference—is introduced to standardize edge-AI gas classifier evaluation. The proposed pipeline provides an open-source, deployable foundation for edge-class gas classification systems, with CBRN detection as a motivating application. Full operational validation on certified chemical simulants remains as future work.

Reliable field identification of unknown white powder substances is a persistent analytical challenge in security screening, forensic science, and environmental emergency response.