Ruthenium-bearing intermetallics (Ru-IMCs) featured with well-defined structures and variable compositions offer new opportunities to develop ammonia synthesis catalysts under mild conditions. However, their complex phase nature and the numerous controlling parameters pose major challenges for catalyst design and exploration. Herein, we demonstrate that a combination of machine learning (ML) and model mining techniques can effectively address these challenges. Based on the combination techniques, we generate a two-dimensional activity volcano plot with adsorption energies of N₂ and N, and identify the radius of atom coordinating to Ru as a key parameter. The well-designed Sc_1/8Nd_7/8Ru₂ reaches as high as 8.18 mmol m⁻² h⁻¹ at 0.1 MPa and 400 °C. Density functional theory (DFT) calculations combined with N₂-TPD and FT-IR studies reveal that Ru‒N interaction is controlled by the d-p orbital hybridization between Ru and N. These findings underscore the importance of ML towards material design on exploring IMCs for ammonia synthesis.

Synchrotron radiation sources are widely used in interdisciplinary research, generating an enormous amount of data while posing serious challenges to the storage, processing, and analysis capabilities of the large-scale scientific facilities worldwide. A flexible and scalable computing architecture, suitable for complex application scenarios, combined with efficient and intelligent scheduling strategies, plays a key role in addressing these issues. In this work, we present a novel cloud–edge hybrid intelligent system (CEHIS), which was architected, developed, and deployed by the Big Data Science Center (BDSC) at the Shanghai Synchrotron Radiation Facility (SSRF) and meets the computational needs of the large-scale scientific facilities. Our methodical simulations demonstrate that the CEHIS is more efficient and performs better than the cloud-based model. Here, we have applied a deep reinforcement learning approach to the task scheduling system, finding that it effectively reduces the total time required for the task completion. Our findings prove that the cloud–edge hybrid intelligent architectures are a viable solution to address the requirements and conditions of the modern synchrotron radiation facilities, further enhancing their data processing and analysis capabilities.