Speaker
Description
Radiation shielding is a key enabler for robust and adaptable systems in current commercial and future exploration missions. Increasing requirements for performance, mass efficiency, and reliability across space radiation environments, from LEO and GEO to deep space and planetary surfaces, are driving the development of advanced materials.
At EmTDLab, a deep-tech advanced materials company, we have developed a proprietary computational materials discovery platform, Symade.ai (Systematic Materials Discovery Engine), aimed at accelerating the identification and optimisation of material compositions for radiation shielding applications in both single and multilayer configurations. The platform combines a core evolutionary algorithm that accelerates the screening of thousands of material compositions in hours, with a physics-informed framework embedding radiation-matter interaction models. The core engine is aided with machine learning acceleration surrogates that enable a full thermodynamic prediction of materials stability, density, and elastic properties. This enables predictive evaluation of novel material response across hundreds of thousands of candidate compositions, including metal alloys, ceramics, and polymers. Materials are evaluated against multi-objective criteria, including radiation shielding performance, mechanical properties, and areal density constraints. In multilayer configurations, the optimisation is extended to hybrid architectures, enabling the combination of newly identified materials with existing industry-standard solutions. Compared to traditional experimental or incremental approaches, Symade.ai enables systematic, high-throughput screening, supporting the identification of promising materials candidates for experimental validation.
Symade.ai has enabled the identification of novel metal alloy compositions that simultaneously achieve significant radiation dose reduction compared to aluminium over representative 6-year Low Earth Orbit (LEO) missions while maintaining mechanical strength. These results are further supported by GEANT4 simulations, validating the predictive capability of the platform. The resulting performance gains are particularly relevant for mass-constrained configurations such as shield-on-chip, where minimising thickness while maximising attenuation is critical. In addition, three compositions identified by Symade.ai have been successfully manufactured, confirming that the platform identifies materials that are both computationally optimised and experimentally realisable.
SYMADE.ai is a validated ICME (Integrated Computation Materials Engineer) platform developed in collaboration with the European Space Agency (ESA). Ongoing developments extend the framework to additional space environments (e.g., GEO, Moon, Deep Space) and degradation mechanisms, such as atomic oxygen exposure and saline corrosion, further supporting the design of robust, multifunctional materials for future exploration missions.