Search for: All records

Cyber-physical systems (CPS) play a pivotal role in industrial automation, transportation, and critical infrastructure, where meeting stringent timing constraints is essential to ensure operational safety and efficiency. While reinforcement learning (RL) has shown promise in synthesizing controllers for time-critical applications, existing approaches often prioritize speed (as soon as possible, or ASAP) without explicitly addressing deadline compliance. This misalignment can lead to unsafe or suboptimal behaviors, which are unacceptable in industrial contexts requiring both safety and reliability under hard deadlines. For example, with inappropriate rewards, a control policy for a industrial robot can be encouraged to be less safe but fast instead of being steady and meeting the deadlines. To address this challenge, we investigate the relationship between ASAP behavior and deadline-safe behavior, introducing a novel Markov decision process formulation (R-MDP) that includes time-awareness while preserving the Markov property. We propose a reward design method that systematically encourages deadline compliance and guarantees safety in reach-avoid tasks. Our approach is validated on multiple benchmarks, including linear and nonlinear systems representative of industrial applications, such as DC motor control and real-time attitude control. Experimental results demonstrate the efficacy of our method in achieving deadline-safe control while maintaining system safety, offering a reliable solution for industrial CPS where failure to meet deadlines can have severe consequences. 

Metal superhydrides, known for their high hydrogen content and polyhedral hydrogen cages, are promising candidates for high-temperature superconductivity. Despite extensive studies on binary metal superhydrides, there remains a large, unexplored chemical space, particularly regarding non-integer hydrogen-to-metal ratios. By integrating the "chemical template effect" with machine learning algorithms, we developed a specialized structure discovery workflow that significantly enhances the efficiency of predicting stable superhydrides. Within the compiled dataset used in this work, our method led to the identification of 13 new structural prototypes and 31 stable metal superhydrides, representing a 23% increase in discoveries. The 3D hydrogen clathrates in these compounds are significantly correlated with high superconducting transition temperatures (Tc), and our approach achieves a remarkable 65% increase. Most of these structures contain over 50 atoms per primitive cell, with the I4/m M10H84 prototype having the largest unit cell, containing 94 atoms. Additionally, 19 of the newly identified superhydrides exhibit Tc > 100 K, highlighting the potential for higher Tc materials within the 3D hydrogen clathrate structures. The method also shows good potential to search for ternary superhydrides on a large scale. 

Soil microbial diversity is crucial to sustaining ecosystem productivity and improving carbon sequestration. Global temperature continues to rise, but how climate warming affects microbial diversity and its capacity to sequester soil organic carbon (SOC) remains uncertain. Here, by conducting a global meta-analysis with 251 paired observations from 102 studies, we showed that, on average, warming reduced bacterial and fungal diversity (measured by richness and Shannon index) by 16.0 and 19.7%, respectively, and SOC by 18.1%. The negative responses of both soil bacterial and fungal diversity to warming became more pronounced with increasing warming magnitude, experimental duration, and decreasing soil nitrogen availability. Under the worst-case climate warming scenario (2010 to 2070, 3.4 increase in °C), soil bacterial diversity and fungal diversity are projected to reduce by 56% and 81%, respectively, over 60 y. Importantly, in addition to the direct impact of warming on SOC, warming-induced declines in microbial diversity also contributed to SOC losses. We highlight that prolonged warming could substantially reduce soil microbial diversity and decrease SOC sequestration, accelerating future warming and underscoring the urgent need for decisive actions to mitigate global climate change. 

eXplainable Artificial Intelligence (XAI) has garnered significant attention for enhancing transparency and trust in machine learning models. However, the scopes of most existing explanation techniques focus either on offering a holistic view of the explainee model (global explanation) or on individual instances (local explanation), while the middle ground, i.e., cohort-based explanation, is less explored. Cohort explanations offer insights into the explainee's behavior on a specific group or cohort of instances, enabling a deeper understanding of model decisions within a defined context. In this paper, we discuss the unique challenges and opportunities associated with measuring cohort explanations, define their desired properties, and create a generalized framework for generating cohort explanations based on supervised clustering.