First impressions make up an integral part of our interactions with other humans by providing an instantaneous judgment of the trustworthiness, dominance and attractiveness of an individual prior to engaging in any other form of interaction. Unfortunately, this can lead to unintentional bias in situations that have serious consequences, whether it be in judicial proceedings, career advancement, or politics. The ability to automatically recognize social traits presents a number of highly useful applications: from minimizing bias in social interactions to providing insight into how our own facial attributes are interpreted by others. However, while first impressions are well-studied in the field of psychology, automated methods for predicting social traits are largely non-existent. In this work, we demonstrate the feasibility of two automated approaches—multi-label classification (MLC) and multi-output regression (MOR)—for first impression recognition from faces. We demonstrate that both approaches are able to predict social traits with better than chance accuracy, but there is still significant room for improvement. We evaluate ethical concerns and detail application areas for future work in this direction.

Engineers are increasingly faced with the question of sustainable design of processes, industrial networks and supply chains. Conventional steady-state methodologies prevalent for sustainability assessment are inadequate to address the dynamic complexities of multiscale systems with which this community deals. This review systematically examines the evolution of sustainability assessment frameworks, highlighting the limitations of static approaches in capturing the nonlinearity, feed- back loops, and temporal variability inherent across the multiple scales. We explore the transition to dynamic, data-driven methodologies, emphasizing the integration of hybrid mechanistic-machine learning models that bridge first-principles knowledge with data. Further, we highlight the importance of transdisciplinary concepts from ecological sciences such as non-linear dynamics and resilience to the design of industrial networks and supply chains. The perspective uncovers how these dynamic phenomena influence system stability, adaptability, and long-term sustainability by incorporating concepts such as time delays, hysteresis, and time-variant characteristics. We further examine stability landscapes and adaptive cycles to demonstrate how resilience thinking redefines process design and control strategies in the face of global uncertainties. The emergence of advanced computational tools, such as spatial-temporal deep learning architectures and adaptive process control strategies, is reshaping the sustainability of manufacturing supply chains. These innovations enable robust performance under dynamic conditions while aligning with circular economy objectives. By synthesizing resilience principles with dynamic sustainability assessments, this review establishes a transformative paradigm for chemical process network design, offering both theoretical insights and practical strategies to advance sustainability in chemical engineering practice and the future trajectory of research.

Machine learning presents opportunities to improve the scale-specific accuracy of mechanistic models in a data-driven manner. Here we demonstrate the use of a machine learning technique called Sparse Identification of Nonlinear Dynamics (SINDy) to improve a simple mechanistic model of algal growth. Time-series measurements of the microalga Chlorella Vulgaris were generated under controlled photobioreactor conditions at the University of Technology Sydney. A simple mechanistic growth model based on intensity of light and temperature was integrated over time and compared to the time-series data. While the mechanistic model broadly captured the overall growth trend, discrepancies remained between the model and data due to the model's simplicity and non-ideal behavior of real-world measurement. SINDy was applied to model the residual error by identifying an error derivative correction term. Addition of this SINDy-informed error dynamics term shows improvement to model accuracy while maintaining interpretability of the underlying mechanistic framework. This work demonstrates the potential for machine learning techniques like SINDy to aid simple mechanistic models in scale-specific predictive accuracy.