Machine learning for active matter

Real-time 3D tracking of swimming microbes using digital holographic microscopy and deep learning

The three-dimensional swimming tracks of motile microorganisms can be used to identify their species, which holds promise for the rapid identification of bacterial pathogens. The tracks also provide detailed information on the cells' responses to external stimuli such as chemical gradients and physical objects. Digital holographic microscopy (DHM) is a well-established, but computationally intensive method for obtaining three-dimensional cell tracks from video microscopy data. We demonstrate that a common neural network (NN) accelerates the analysis of holographic data by an order of magnitude, enabling its use on single-board computers and in real time. We establish a heuristic relationship between the distance of a cell from the focal plane and the size of the bounding box assigned to it by the NN, allowing us to rapidly localise cells in three dimensions as they swim. This technique opens the possibility of providing real-time feedback in experiments, for example by monitoring and adapting the supply of nutrients to a microbial bioreactor in response to changes in the swimming phenotype of microbes, or for rapid identification of bacterial pathogens in drinking water or clinical samples.

Swarm Autonomy: From Agent Functionalization to Machine Intelligence

Swarm behaviors are common in nature, where individual organisms collaborate via perception, communication, and adaptation. Emulating these dynamics, large groups of active agents can self-organize through localized interactions, giving rise to complex swarm behaviors, which exhibit potential for applications across various domains. This review presents a comprehensive summary and perspective of synthetic swarms, to bridge the gap between the microscale individual agents and potential applications of synthetic swarms. It is begun by examining active agents, the fundamental units of synthetic swarms, to understand the origins of their motility and functionality in the presence of external stimuli. Then inter-agent communications and agent-environment communications that contribute to the swarm generation are summarized. Furthermore, the swarm behaviors reported to date and the emergence of machine intelligence within these behaviors are reviewed. Eventually, the applications enabled by distinct synthetic swarms are summarized. By discussing the emergent machine intelligence in swarm behaviors, insights are offered into the design and deployment of autonomous synthetic swarms for real-world applications.

Modeling the Temperature-Dependent Size Change of Polydisperse Nano-objects using a Deep Generative Model

Modern microscopy techniques can be used to investigate soft nano-objects at the nanometer scale. However, time-consuming microscopy measurements combined with low numbers of observable polydisperse objects often limit the statistics. We propose a method for identifying the most representative objects from their respective point clouds. These point cloud data are obtained, for example, through the localization of single emitters in super-resolution fluorescence microscopy. External stimuli, such as temperature, can cause changes in the shape and properties of adaptive objects. Due to the demanding and time-consuming nature of super-resolution microscopy experiments, only a limited number of temperature steps can be performed. Therefore, we propose a deep generative model that learns the underlying point distribution of temperature-dependent microgels, enabling the reliable generation of unlimited samples with an arbitrary number of localizations. Our method greatly cuts down the data collection effort across diverse experimental conditions, proving invaluable for soft condensed matter studies.

Smart active particles learn and transcend bacterial foraging strategies

Throughout evolution, bacteria and other microorganisms have learned efficient foraging strategies that exploit characteristic properties of their unknown environment. While much research has been devoted to the exploration of statistical models describing the dynamics of foraging bacteria and other (micro-) organisms, little is known, regarding the question of how good the learned strategies actually are. This knowledge gap is largely caused by the absence of methods allowing to systematically develop alternative foraging strategies to compare with. In the present work, we use deep reinforcement learning to show that a smart run-and-tumble agent, which strives to find nutrients for its survival, learns motion patterns that are remarkably similar to the trajectories of chemotactic bacteria. Strikingly, despite this similarity, we also find interesting differences between the learned tumble rate distribution and the one that is commonly assumed for the run and tumble model. We find that these differences equip the agent with significant advantages regarding its foraging and survival capabilities. Our results uncover a generic route to use deep reinforcement learning for discovering search and collection strategies that exploit characteristic but initially unknown features of the environment. These results can be used, e.g., to program future microswimmers, nanorobots, and smart active particles for tasks like searching for cancer cells, micro-waste collection, or environmental remediation.

Multifractal spectral features enhance classification of anomalous diffusion

Anomalous diffusion processes, characterized by their nonstandard scaling of the mean-squared displacement, pose a unique challenge in classification and characterization. In a previous study [Mangalam et al., Phys. Rev. Res. 5, 023144 (2023)2643-156410.1103/PhysRevResearch.5.023144], we established a comprehensive framework for understanding anomalous diffusion using multifractal formalism. The present study delves into the potential of multifractal spectral features for effectively distinguishing anomalous diffusion trajectories from five widely used models: fractional Brownian motion, scaled Brownian motion, continuous-time random walk, annealed transient time motion, and Lévy walk. We generate extensive datasets comprising 10^{6} trajectories from these five anomalous diffusion models and extract multiple multifractal spectra from each trajectory to accomplish this. Our investigation entails a thorough analysis of neural network performance, encompassing features derived from varying numbers of spectra. We also explore the integration of multifractal spectra into traditional feature datasets, enabling us to assess their impact comprehensively. To ensure a statistically meaningful comparison, we categorize features into concept groups and train neural networks using features from each designated group. Notably, several feature groups demonstrate similar levels of accuracy, with the highest performance observed in groups utilizing moving-window characteristics and p varation features. Multifractal spectral features, particularly those derived from three spectra involving different timescales and cutoffs, closely follow, highlighting their robust discriminatory potential. Remarkably, a neural network exclusively trained on features from a single multifractal spectrum exhibits commendable performance, surpassing other feature groups. In summary, our findings underscore the diverse and potent efficacy of multifractal spectral features in enhancing the predictive capacity of machine learning to classify anomalous diffusion processes.

Microbes in porous environments: from active interactions to emergent feedback

Microbes thrive in diverse porous environments-from soil and riverbeds to human lungs and cancer tissues-spanning multiple scales and conditions. Short- to long-term fluctuations in local factors induce spatio-temporal heterogeneities, often leading to physiologically stressful settings. How microbes respond and adapt to such biophysical constraints is an active field of research where considerable insight has been gained over the last decades. With a focus on bacteria, here we review recent advances in self-organization and dispersal in inorganic and organic porous settings, highlighting the role of active interactions and feedback that mediates microbial survival and fitness. We discuss open questions and opportunities for using integrative approaches to advance our understanding of the biophysical strategies which microbes employ at various scales to make porous settings habitable.

Learning how to find targets in the micro-world: the case of intermittent active Brownian particles

Finding the best strategy to minimize the time needed to find a given target is a crucial task both in nature and in reaching decisive technological advances. By considering learning agents able to switch their dynamics between standard and active Brownian motion, here we focus on developing effective target-search behavioral policies for microswimmers navigating a homogeneous environment and searching for targets of unknown position. We exploit projective simulation, a reinforcement learning algorithm, to acquire an efficient stochastic policy represented by the probability of switching the phase, i.e. the navigation mode, in response to the type and the duration of the current phase. Our findings reveal that the target-search efficiency increases with the particle's self-propulsion during the active phase and that, while the optimal duration of the passive case decreases monotonically with the activity, the optimal duration of the active phase displays a non-monotonic behavior.

AI-enhanced biomedical micro/nanorobots in microfluidics

Human beings encompass sophisticated microcirculation and microenvironments, incorporating a broad spectrum of microfluidic systems that adopt fundamental roles in orchestrating physiological mechanisms. In vitro recapitulation of human microenvironments based on lab-on-a-chip technology represents a critical paradigm to better understand the intricate mechanisms. Moreover, the advent of micro/nanorobotics provides brand new perspectives and dynamic tools for elucidating the complex process in microfluidics. Currently, artificial intelligence (AI) has endowed micro/nanorobots (MNRs) with unprecedented benefits, such as material synthesis, optimal design, fabrication, and swarm behavior. Using advanced AI algorithms, the motion control, environment perception, and swarm intelligence of MNRs in microfluidics are significantly enhanced. This emerging interdisciplinary research trend holds great potential to propel biomedical research to the forefront and make valuable contributions to human health. Herein, we initially introduce the AI algorithms integral to the development of MNRs. We briefly revisit the components, designs, and fabrication techniques adopted by robots in microfluidics with an emphasis on the application of AI. Then, we review the latest research pertinent to AI-enhanced MNRs, focusing on their motion control, sensing abilities, and intricate collective behavior in microfluidics. Furthermore, we spotlight biomedical domains that are already witnessing or will undergo game-changing evolution based on AI-enhanced MNRs. Finally, we identify the current challenges that hinder the practical use of the pioneering interdisciplinary technology.

Reprogramming the Transition States to Enhance C-N Cleavage Efficiency of Rhodococcus opacusl-Amino Acid Oxidase

l-Amino acid oxidase (LAAO) is an important biocatalyst used for synthesizing α-keto acids. LAAO from Rhodococcus opacus (RoLAAO) has a broad substrate spectrum; however, its low total turnover number limits its industrial use. To overcome this, we aimed to employ crystal structure-guided density functional theory calculations and molecular dynamic simulations to investigate the catalytic mechanism. Two key steps were identified: S → [TS1] in step 1 and Int1 → [TS2] in step 2. We reprogrammed the transition states [TS1] and [TS2] to reduce the identified energy barrier and obtain a RoLAAO variant capable of catalyzing 19 kinds of l-amino acids to the corresponding high-value α-keto acids with a high total turnover number, yield (≥95.1 g/L), conversion rate (≥95%), and space-time yields ≥142.7 g/L/d in 12-24 h, in a 5 L reactor. Our results indicated the promising potential of the developed RoLAAO variant for use in the industrial production of α-keto acids while providing a potential catalytic-mechanism-guided protein design strategy to achieve the desired physical and catalytic properties of enzymes.

A machine learning approach to robustly determine director fields and analyze defects in active nematics

Active nematics are dense systems of rodlike particles that consume energy to drive motion at the level of the individual particles. They exist in natural systems like biological tissues and artificial materials such as suspensions of self-propelled colloidal particles or synthetic microswimmers. Active nematics have attracted significant attention in recent years due to their spectacular nonequilibrium collective spatiotemporal dynamics, which may enable applications in fields such as robotics, drug delivery, and materials science. The director field, which measures the direction and degree of alignment of the local nematic orientation, is a crucial characteristic of active nematics and is essential for studying topological defects. However, determining the director field is a significant challenge in many experimental systems. Although director fields can be derived from images of active nematics using traditional imaging processing methods, the accuracy of such methods is highly sensitive to the settings of the algorithms. These settings must be tuned from image to image due to experimental noise, intrinsic noise of the imaging technology, and perturbations caused by changes in experimental conditions. This sensitivity currently limits automatic analysis of active nematics. To address this, we developed a machine learning model for extracting reliable director fields from raw experimental images, which enables accurate analysis of topological defects. Application of the algorithm to experimental data demonstrates that the approach is robust and highly generalizable to experimental settings that are different from those in the training data. It could be a promising tool for investigating active nematics and may be generalized to other active matter systems.

Machine learning methods for liquid crystal research: phases, textures, defects and physical properties

Liquid crystal materials, with their unique properties and diverse applications, have long captured the attention of researchers and industries alike. From liquid crystal displays and electro-optical devices to advanced sensors and emerging technologies, the study and application of liquid crystals continue to be of paramount importance in the fields of materials science, chemistry and physics. With the ever-increasing complexity and diversity of liquid crystal materials, researchers face new challenges in understanding their behaviors, properties, and potential applications. On the other hand, machine learning, a rapidly evolving interdisciplinary field at the intersection of computer science and data analysis, has already become a powerful tool for unraveling implicit correlations and predicting new properties of a wide variety of physical and chemical systems and structures. Here we aim to consider how machine learning methods are suitable for solving fundamental problems in the field of liquid crystals and what are the advantages of this artificial intelligence based approach.

Harnessing synthetic active particles for physical reservoir computing

The processing of information is an indispensable property of living systems realized by networks of active processes with enormous complexity. They have inspired many variants of modern machine learning, one of them being reservoir computing, in which stimulating a network of nodes with fading memory enables computations and complex predictions. Reservoirs are implemented on computer hardware, but also on unconventional physical substrates such as mechanical oscillators, spins, or bacteria often summarized as physical reservoir computing. Here we demonstrate physical reservoir computing with a synthetic active microparticle system that self-organizes from an active and passive component into inherently noisy nonlinear dynamical units. The self-organization and dynamical response of the unit are the results of a delayed propulsion of the microswimmer to a passive target. A reservoir of such units with a self-coupling via the delayed response can perform predictive tasks despite the strong noise resulting from the Brownian motion of the microswimmers. To achieve efficient noise suppression, we introduce a special architecture that uses historical reservoir states for output. Our results pave the way for the study of information processing in synthetic self-organized active particle systems.

Machine learning interpretable models of cell mechanics from protein images

Cellular form and function emerge from complex mechanochemical systems within the cytoplasm. Currently, no systematic strategy exists to infer large-scale physical properties of a cell from its molecular components. This is an obstacle to understanding processes such as cell adhesion and migration. Here, we develop a data-driven modeling pipeline to learn the mechanical behavior of adherent cells. We first train neural networks to predict cellular forces from images of cytoskeletal proteins. Strikingly, experimental images of a single focal adhesion (FA) protein, such as zyxin, are sufficient to predict forces and can generalize to unseen biological regimes. Using this observation, we develop two approaches-one constrained by physics and the other agnostic-to construct data-driven continuum models of cellular forces. Both reveal how cellular forces are encoded by two distinct length scales. Beyond adherent cell mechanics, our work serves as a case study for integrating neural networks into predictive models for cell biology.

Unbiased construction of constitutive relations for soft materials from experiments via rheology-informed neural networks

The ability to concisely describe the dynamical behavior of soft materials through closed-form constitutive relations holds the key to accelerated and informed design of materials and processes. The conventional approach is to construct constitutive relations through simplifying assumptions and approximating the time- and rate-dependent stress response of a complex fluid to an imposed deformation. While traditional frameworks have been foundational to our current understanding of soft materials, they often face a twofold existential limitation: i) Constructed on ideal and generalized assumptions, precise recovery of material-specific details is usually serendipitous, if possible, and ii) inherent biases that are involved by making those assumptions commonly come at the cost of new physical insight. This work introduces an approach by leveraging recent advances in scientific machine learning methodologies to discover the governing constitutive equation from experimental data for complex fluids. Our rheology-informed neural network framework is found capable of learning the hidden rheology of a complex fluid through a limited number of experiments. This is followed by construction of an unbiased material-specific constitutive relation that accurately describes a wide range of bulk dynamical behavior of the material. While extremely efficient in closed-form model discovery for a real-world complex system, the model also provides insight into the underpinning physics of the material.

Connecting theory and experiment in cell and tissue mechanics

Understanding complex living systems, which are fundamentally constrained by physical phenomena, requires combining experimental data with theoretical physical and mathematical models. To develop such models, collaborations between experimental cell biologists and theoreticians are increasingly important but these two groups often face challenges achieving mutual understanding. To help navigate these challenges, this Perspective discusses different modelling approaches, including bottom-up hypothesis-driven and top-down data-driven models, and highlights their strengths and applications. Using cell mechanics as an example, we explore the integration of specific physical models with experimental data from the molecular, cellular and tissue level up to multiscale input. We also emphasize the importance of constraining model complexity and outline strategies for crosstalk between experimental design and model development. Furthermore, we highlight how physical models can provide conceptual insights and produce unifying and generalizable frameworks for biological phenomena. Overall, this Perspective aims to promote fruitful collaborations that advance our understanding of complex biological systems.

Characterizing different motility-induced regimes in active matter with machine learning and noise

We examine motility-induced phase separation (MIPS) in two-dimensional run-and-tumble disk systems using both machine learning and noise fluctuation analysis. Our measures suggest that within the MIPS state there are several distinct regimes as a function of density and run time, so that systems with MIPS transitions exhibit an active fluid, an active crystal, and a critical regime. The different regimes can be detected by combining an order parameter extracted from principal component analysis with a cluster stability measurement. The principal component-derived order parameter is maximized in the critical regime, remains low in the active fluid, and has an intermediate value in the active crystal regime. We demonstrate that machine learning can better capture dynamical properties of the MIPS regimes compared to more standard structural measures such as the maximum cluster size. The different regimes can also be characterized via changes in the noise power of the fluctuations in the average speed. In the critical regime, the noise power passes through a maximum and has a broad spectrum with a 1/f^{1.6} signature, similar to the noise observed near depinning transitions or for solids undergoing plastic deformation.

Collective Behaviors of Isotropic Micromotors: From Assembly to Reconstruction and Motion Control under External Fields

Swarms of self-propelled micromotors can mimic the processes of natural systems and construct artificial intelligent materials to perform complex collective behaviors. Compared to self-propelled Janus micromotors, the isotropic colloid motors, also called micromotors or microswimmers, have advantages in self-assembly to form micromotor swarms, which are efficient in resistance to external disturbance and the delivery of large quantity of cargos. In this minireview, we summarize the fundamental principles and interactions for the assembly of isotropic active particles to generate micromotor swarms. Recent discoveries based on either catalytic or external physical field-stimulated micromotor swarms are also presented. Then, the strategy for the reconstruction and motion control of micromotor swarms in complex environments, including narrow channels, maze, raised obstacles, and high steps/low gaps, is summarized. Finally, we outline the future directions of micromotor swarms and the remaining challenges and opportunities.

IBGJO: Improved Binary Golden Jackal Optimization with Chaotic Tent Map and Cosine Similarity for Feature Selection

Feature selection is a crucial process in machine learning and data mining that identifies the most pertinent and valuable features in a dataset. It enhances the efficacy and precision of predictive models by efficiently reducing the number of features. This reduction improves classification accuracy, lessens the computational burden, and enhances overall performance. This study proposes the improved binary golden jackal optimization (IBGJO) algorithm, an extension of the conventional golden jackal optimization (GJO) algorithm. IBGJO serves as a search strategy for wrapper-based feature selection. It comprises three key factors: a population initialization process with a chaotic tent map (CTM) mechanism that enhances exploitation abilities and guarantees population diversity, an adaptive position update mechanism using cosine similarity to prevent premature convergence, and a binary mechanism well-suited for binary feature selection problems. We evaluated IBGJO on 28 classical datasets from the UC Irvine Machine Learning Repository. The results show that the CTM mechanism and the position update strategy based on cosine similarity proposed in IBGJO can significantly improve the Rate of convergence of the conventional GJO algorithm, and the accuracy is also significantly better than other algorithms. Additionally, we evaluate the effectiveness and performance of the enhanced factors. Our empirical results show that the proposed CTM mechanism and the position update strategy based on cosine similarity can help the conventional GJO algorithm converge faster.

Perspectives on adaptive dynamical systems

Adaptivity is a dynamical feature that is omnipresent in nature, socio-economics, and technology. For example, adaptive couplings appear in various real-world systems, such as the power grid, social, and neural networks, and they form the backbone of closed-loop control strategies and machine learning algorithms. In this article, we provide an interdisciplinary perspective on adaptive systems. We reflect on the notion and terminology of adaptivity in different disciplines and discuss which role adaptivity plays for various fields. We highlight common open challenges and give perspectives on future research directions, looking to inspire interdisciplinary approaches.

Steering undulatory micro-swimmers in a fluid flow through reinforcement learning

This work aims at finding optimal navigation policies for thin, deformable microswimmers that progress in a viscous fluid by propagating a sinusoidal undulation along their slender body. These active filaments are embedded in a prescribed, non-homogeneous flow, in which their swimming undulations have to compete with the drifts, strains, and deformations inflicted by the outer velocity field. Such an intricate situation, where swimming and navigation are tightly bonded, is addressed using various methods of reinforcement learning. Each swimmer has only access to restricted information on its configuration and has to select accordingly an action among a limited set. The optimisation problem then consists in finding the policy leading to the most efficient displacement in a given direction. It is found that usual methods do not converge and this pitfall is interpreted as a combined consequence of the non-Markovianity of the decision process, together with the highly chaotic nature of the dynamics, which is responsible for high variability in learning efficiencies. Still, we provide an alternative method to construct efficient policies, which is based on running several independent realisations of Q-learning. This allows the construction of a set of admissible policies whose properties can be studied in detail and compared to assess their efficiency and robustness.

Learning to cooperate for low-Reynolds-number swimming: a model problem for gait coordination

Biological microswimmers can coordinate their motions to exploit their fluid environment-and each other-to achieve global advantages in their locomotory performance. These cooperative locomotion require delicate adjustments of both individual swimming gaits and spatial arrangements of the swimmers. Here we probe the emergence of such cooperative behaviors among artificial microswimmers endowed with artificial intelligence. We present the first use of a deep reinforcement learning approach to empower the cooperative locomotion of a pair of reconfigurable microswimmers. The AI-advised cooperative policy comprises two stages: an approach stage where the swimmers get in close proximity to fully exploit hydrodynamic interactions, followed a synchronization stage where the swimmers synchronize their locomotory gaits to maximize their overall net propulsion. The synchronized motions allow the swimmer pair to move together coherently with an enhanced locomotion performance unattainable by a single swimmer alone. Our work constitutes a first step toward uncovering intriguing cooperative behaviors of smart artificial microswimmers, demonstrating the vast potential of reinforcement learning towards intelligent autonomous manipulations of multiple microswimmers for their future biomedical and environmental applications.

Quantum Chemistry-Machine Learning Approach for Predicting Properties of Lewis Acid-Lewis Base Adducts

Synthetic design allowing predictive control of charge transfer and other optoelectronic properties of Lewis acid adducts remains elusive. This challenge must be addressed through complementary methods combining experimental with computational insights from first principles. Ab initio calculations for optoelectronic properties can be computationally expensive and less straightforward than those sufficient for simple ground-state properties, especially for adducts of large conjugated molecules and Lewis acids. In this contribution, we show that machine learning (ML) can accurately predict density functional theory (DFT)-calculated charge transfer and even properties associated with excited states of adducts from readily obtained molecular descriptors. Seven ML models, built from a dataset of over 1000 adducts, show exceptional performance in predicting charge transfer and other optoelectronic properties with a Pearson correlation coefficient of up to 0.99. More importantly, the influence of each molecular descriptor on predicted properties can be quantitatively evaluated from ML models. This contributes to the optimization of a priori design of Lewis adducts for future applications, especially in organic electronics.

Machine learning implemented exploration of the adsorption mechanism of carbon dioxide onto porous carbons

Adsorption of CO₂ on porous carbons has been identified as one of the promising methods for carbon capture, which is essential for meeting the sustainable developmental goal (SDG) with respect to climate action, i.e., SDG 13. This research implemented six supervised machine learning (ML) models (gradient boosting decision tree (GBDT), extreme gradient boosting (XGB), light boost gradient machine (LBGM), random forest (RF), categorical boosting (Catboost), and adaptive boosting (Adaboost)) to understand and predict the CO₂ adsorption mechanism and adsorption uptake, respectively. The results recommended that the GBDT outperformed the remaining five ML models for CO₂ adsorption. However, XGB, LBGM, RF, and Catboost also represented the prediction in the acceptable range. The GBDT model indicated the accurate prediction of CO₂ uptake onto the porous carbons considering adsorbent properties and adsorption conditions as model input parameters. Next, two-factor partial dependence plots revealed a lucid explanation of how the combinations of two input features affect the model prediction. Furthermore, SHapley Additive exPlainations (SHAP), a novel explication approach based on ML models, were employed to understand and elucidate the CO₂ adsorption and model prediction. The SHAP explanations, implemented on the GBDT model, revealed the rigorous relationships among the input features and output variables based on the GBDT prediction. Additionally, SHAP provided clear-cut feature importance analysis and individual feature impact on the prediction. SHAP also explained two instances of CO₂ adsorption. Along with the data-driven insightful explanation of CO₂ adsorption onto porous carbons, this study also provides a promising method to predict the clear-cut performance of porous carbons for CO₂ adsorption without performing any experiments and open new avenues for researchers to implement this study in the field of adsorption because a lot of data is being generated.

Optical Manipulation Heats up: Present and Future of Optothermal Manipulation

Optothermal manipulation is a versatile technique that combines optical and thermal forces to control synthetic micro-/nanoparticles and biological entities. This emerging technique overcomes the limitations of traditional optical tweezers, including high laser power, photon and thermal damage to fragile objects, and the requirement of refractive-index contrast between target objects and the surrounding solvents. In this perspective, we discuss how the rich opto-thermo-fluidic multiphysics leads to a variety of working mechanisms and modes of optothermal manipulation in both liquid and solid media, underpinning a broad range of applications in biology, nanotechnology, and robotics. Moreover, we highlight current experimental and modeling challenges in the pursuit of optothermal manipulation and propose future directions and solutions to the challenges.

Blood Glucose Level Time Series Forecasting: Nested Deep Ensemble Learning Lag Fusion

Blood glucose level prediction is a critical aspect of diabetes management. It enables individuals to make informed decisions about their insulin dosing, diet, and physical activity. This, in turn, improves their quality of life and reduces the risk of chronic and acute complications. One conundrum in developing time-series forecasting models for blood glucose level prediction is to determine an appropriate length for look-back windows. On the one hand, studying short histories foists the risk of information incompletion. On the other hand, analysing long histories might induce information redundancy due to the data shift phenomenon. Additionally, optimal lag lengths are inconsistent across individuals because of the domain shift occurrence. Therefore, in bespoke analysis, either optimal lag values should be found for each individual separately or a globally suboptimal lag value should be used for all. The former approach degenerates the analysis's congruency and imposes extra perplexity. With the latter, the fine-tunned lag is not necessarily the optimum option for all individuals. To cope with this challenge, this work suggests an interconnected lag fusion framework based on nested meta-learning analysis that improves the accuracy and precision of predictions for personalised blood glucose level forecasting. The proposed framework is leveraged to generate blood glucose prediction models for patients with type 1 diabetes by scrutinising two well-established publicly available Ohio type 1 diabetes datasets. The models developed undergo vigorous evaluation and statistical analysis from mathematical and clinical perspectives. The results achieved underpin the efficacy of the proposed method in blood glucose level time-series prediction analysis.

Neural networks determination of material elastic constants and structures in nematic complex fluids

Supervised machine learning and artificial neural network approaches can allow for the determination of selected material parameters or structures from a measurable signal without knowing the exact mathematical relationship between them. Here, we demonstrate that material nematic elastic constants and the initial structural material configuration can be found using sequential neural networks applied to the transmmited time-dependent light intensity through the nematic liquid crystal (NLC) sample under crossed polarizers. Specifically, we simulate multiple times the relaxation of the NLC from a random (qeunched) initial state to the equilibirum for random values of elastic constants and, simultaneously, the transmittance of the sample for monochromatic polarized light. The obtained time-dependent light transmittances and the corresponding elastic constants form a training data set on which the neural network is trained, which allows for the determination of the elastic constants, as well as the initial state of the director. Finally, we demonstrate that the neural network trained on numerically generated examples can also be used to determine elastic constants from experimentally measured data, finding good agreement between experiments and neural network predictions.

Fluid interfaces laden by force dipoles: towards active matter-driven microfluidic flows

In recent years, nonlinear microfluidics in combination with lab-on-a-chip devices has opened a new avenue for chemical and biomedical applications such as droplet formation and cell sorting. In this article, we integrate ideas from active matter into a microfluidic setting, where two fluid layers with identical densities but different viscosities flow through a microfluidic channel. Most importantly, the fluid interface is laden with active particles that act with dipolar forces on the adjacent fluids and thereby generate flows. We perform lattice-Boltzmann simulations and combine them with phase field dynamics of the interface and an advection-diffusion equation for the density of active particles. We show that only contractile force dipoles can destabilize the flat fluid interface. It develops a viscous finger from which droplets break up. For interfaces with non-zero surface tension, a critical value of activity equal to the surface tension is necessary to trigger the instability. Since activity depends on the density of force dipoles, the interface can develop steady deformation. Lastly, we demonstrate how to control droplet formation using switchable activity.

Anomaly Detection in Biological Early Warning Systems Using Unsupervised Machine Learning

The use of bivalve mollusks as bioindicators in automated monitoring systems can provide real-time detection of emergency situations associated with the pollution of aquatic environments. The behavioral reactions of Unio pictorum (Linnaeus, 1758) were employed in the development of a comprehensive automated monitoring system for aquatic environments by the authors. The study used experimental data obtained by an automated system from the Chernaya River in the Sevastopol region of the Crimean Peninsula. Four traditional unsupervised machine learning techniques were implemented to detect emergency signals in the activity of bivalves: elliptic envelope, isolation forest (iForest), one-class support vector machine (SVM), and local outlier factor (LOF). The results showed that the use of the elliptic envelope, iForest, and LOF methods with proper hyperparameter tuning can detect anomalies in mollusk activity data without false alarms, with an F1 score of 1. A comparison of anomaly detection times revealed that the iForest method is the most efficient. These findings demonstrate the potential of using bivalve mollusks as bioindicators in automated monitoring systems for the early detection of pollution in aquatic environments.

Using Machine Learning to make nanomaterials sustainable

Sustainable development is a key challenge for contemporary human societies; failure to achieve sustainability could threaten human survival. In this review article, we illustrate how Machine Learning (ML) could support more sustainable development, covering the basics of data gathering through each step of the Environmental Risk Assessment (ERA). The literature provides several examples showing how ML can be employed in most steps of a typical ERA.A key observation is that there are currently no clear guidance for using such autonomous technologies in ERAs or which standards/checks are required. Steering thus seems to be the most important task for supporting the use of ML in the ERA of nano- and smart-materials. Resources should be devoted to developing a strategy for implementing ML in ERA with a strong emphasis on data foundations, methodologies, and the related sensitivities/uncertainties. We should recognise historical errors and biases (e.g., in data) to avoid embedding them during ML programming.

Collective Behaviors of Active Matter Learning from Natural Taxes Across Scales

Taxis orientation is common in microorganisms, and it provides feasible strategies to operate active colloids as small-scale robots. Collective taxes involve numerous units that collectively perform taxis motion, whereby the collective cooperation between individuals enables the group to perform efficiently, adaptively, and robustly. Hence, analyzing and designing collectives is crucial for developing and advancing microswarm toward practical or clinical applications. In this review, natural taxis behaviors are categorized and synthetic microrobotic collectives are discussed as bio-inspired realizations, aiming at closing the gap between taxis strategies of living creatures and those of functional active microswarms. As collective behaviors emerge within a group, the global taxis to external stimuli guides the group to conduct overall tasks, whereas the local taxis between individuals induces synchronization and global patterns. By encoding the local orientations and programming the global stimuli, various paradigms can be introduced for coordinating and controlling such collective microrobots, from the viewpoints of fundamental science and practical applications. Therefore, by discussing the key points and difficulties associated with collective taxes of different paradigms, this review potentially offers insights into mimicking natural collective behaviors and constructing intelligent microrobotic systems for on-demand control and preassigned tasks.

Deep Learning to Reveal the Distribution and Diffusion of Water Molecules in Fuel Cell Catalyst Layers

Water management in the catalyst layers (CLs) of proton-exchange membrane fuel cells is crucial for its commercialization and popularization. However, the high experimental or computational cost in obtaining water distribution and diffusion remains a bottleneck in the existing experimental methods and simulation algorithms, and further mechanistic exploration at the nanoscale is necessary. Herein, we integrate, for the first time, molecular dynamics simulation with our customized analysis framework based on a multiattribute point cloud dataset and an advanced deep learning network. This was achieved through our workflow that generates simulated transport data of water molecules in the CLs as the training and test dataset. Deep learning framework models the multibody solid-liquid system of CLs on a molecular scale and completes the mapping from the Pt/C substrate structure and Nafion aggregates to the density distribution and diffusion coefficient of water molecules. The prediction results are comprehensively analyzed and error evaluated, which reveals the highly anisotropic interaction landscape between 50,000 pairs of interacting nanoparticles and explains the structure and water transport property relationship in the hydrated Nafion film on the molecular scale. Compared to the conventional methods, the proposed deep learning framework shows computational cost efficiency, accuracy, and good visual display. Further, it has a generality potential to model macro- and microscopic mass transport in different components of fuel cells. Our framework is expected to make real-time predictions of the distribution and diffusion of water molecules in CLs as well as establish statistical significance in the structural optimization and design of CLs and other components of fuel cells.

Data-Driven Discovery of Active Nematic Hydrodynamics

Active nematics can be modeled using phenomenological continuum theories that account for the dynamics of the nematic director and fluid velocity through partial differential equations (PDEs). While these models provide a statistical description of the experiments, the relevant terms in the PDEs and their parameters are usually identified indirectly. We adapt a recently developed method to automatically identify optimal continuum models for active nematics directly from spatiotemporal data, via sparse regression of the coarse-grained fields onto generic low order PDEs. After extensive benchmarking, we apply the method to experiments with microtubule-based active nematics, finding a surprisingly minimal description of the system. Our approach can be generalized to gain insights into active gels, microswimmers, and diverse other experimental active matter systems.

Mind the matter: Active matter, soft robotics, and the making of bio-inspired artificial intelligence

Philosophical and theoretical debates on the multiple realisability of the cognitive have historically influenced discussions of the possible systems capable of instantiating complex functions like memory, learning, goal-directedness, and decision-making. These debates have had the corollary of undermining, if not altogether neglecting, the materiality and corporeality of cognition-treating material, living processes as "hardware" problems that can be abstracted out and, in principle, implemented in a variety of materials-in particular on digital computers and in the form of state-of-the-art neural networks. In sum, the matter in se has been taken not to matter for cognition. However, in this paper, we argue that the materiality of cognition-and the living, self-organizing processes that it enables-requires a more detailed assessment when understanding the nature of cognition and recreating it in the field of embodied robotics. Or, in slogan form, that the matter matters for cognitive form and function. We pull from the fields of Active Matter Physics, Soft Robotics, and Basal Cognition literature to suggest that the imbrication between material and cognitive processes is closer than standard accounts of multiple realisability suggest. In light of this, we propose upgrading the notion of multiple realisability from the standard version-what we call 1.0-to a more nuanced conception 2.0 to better reflect the recent empirical advancements, while at the same time averting many of the problems that have been raised for it. These fields are actively reshaping the terrain in which we understand materiality and how it enables, mediates, and constrains cognition. We propose that taking the materiality of our embodied, precarious nature seriously furnishes an important research avenue for the development of embodied robots that autonomously value, engage, and interact with the environment in a goal-directed manner, in response to existential needs of survival, persistence, and, ultimately, reproduction. Thus, we argue that by placing further emphasis on the soft, active, and plastic nature of the materials that constitute cognitive embodiment, we can move further in the direction of autonomous embodied robots and Artificial Intelligence.

Automated Experiments of Local Non-Linear Behavior in Ferroelectric Materials

An automated experiment in multimodal imaging to probe structural, chemical, and functional behaviors in complex materials and elucidate the dominant physical mechanisms that control device function is developed and implemented. Here, the emergence of non-linear electromechanical responses in piezoresponse force microscopy (PFM) is explored. Non-linear responses in PFM can originate from multiple mechanisms, including intrinsic material responses often controlled by domain structure, surface topography that affects the mechanical phenomena at the tip-surface junction, and the presence of surface contaminants. Using an automated experiment to probe the origins of non-linear behavior in ferroelectric lead titanate (PTO) and ferroelectric Al_0.93 B_0.07 N films, it is found that PTO shows asymmetric nonlinear behavior across a/c domain walls and a broadened high nonlinear response region around c/c domain walls. In contrast, for Al_0.93 B_0.07 N, well-poled regions show high linear piezoelectric responses, when paired with low non-linear responses regions that are multidomain show low linear responses and high nonlinear responses. It is shown that formulating dissimilar exploration strategies in deep kernel learning as alternative hypotheses allows for establishing the preponderant physical mechanisms behind the non-linear behaviors, suggesting that automated experiments can potentially discern between competing physical mechanisms. This technique can also be extended to electron, probe, and chemical imaging.

Active matter in space

In the last 20 years, active matter has been a highly dynamic field of research, bridging fundamental aspects of non-equilibrium thermodynamics with applications to biology, robotics, and nano-medicine. Active matter systems are composed of units that can harvest and harness energy and information from their environment to generate complex collective behaviours and forms of self-organisation. On Earth, gravity-driven phenomena (such as sedimentation and convection) often dominate or conceal the emergence of these dynamics, especially for soft active matter systems where typical interactions are of the order of the thermal energy. In this review, we explore the ongoing and future efforts to study active matter in space, where low-gravity and microgravity conditions can lift some of these limitations. We envision that these studies will help unify our understanding of active matter systems and, more generally, of far-from-equilibrium physics both on Earth and in space. Furthermore, they will also provide guidance on how to use, process and manufacture active materials for space exploration and colonisation.

Thermodynamics of the Ising Model Encoded in Restricted Boltzmann Machines

The restricted Boltzmann machine (RBM) is a two-layer energy-based model that uses its hidden-visible connections to learn the underlying distribution of visible units, whose interactions are often complicated by high-order correlations. Previous studies on the Ising model of small system sizes have shown that RBMs are able to accurately learn the Boltzmann distribution and reconstruct thermal quantities at temperatures away from the critical point Tc. How the RBM encodes the Boltzmann distribution and captures the phase transition are, however, not well explained. In this work, we perform RBM learning of the 2d and 3d Ising model and carefully examine how the RBM extracts useful probabilistic and physical information from Ising configurations. We find several indicators derived from the weight matrix that could characterize the Ising phase transition. We verify that the hidden encoding of a visible state tends to have an equal number of positive and negative units, whose sequence is randomly assigned during training and can be inferred by analyzing the weight matrix. We also explore the physical meaning of the visible energy and loss function (pseudo-likelihood) of the RBM and show that they could be harnessed to predict the critical point or estimate physical quantities such as entropy.

Machine learning in electron microscopy for advanced nanocharacterization: current developments, available tools and future outlook

In the last few years, electron microscopy has experienced a new methodological paradigm aimed to fix the bottlenecks and overcome the challenges of its analytical workflow. Machine learning and artificial intelligence are answering this call providing powerful resources towards automation, exploration, and development. In this review, we evaluate the state-of-the-art of machine learning applied to electron microscopy (and obliquely, to materials and nano-sciences). We start from the traditional imaging techniques to reach the newest higher-dimensionality ones, also covering the recent advances in spectroscopy and tomography. Additionally, the present review provides a practical guide for microscopists, and in general for material scientists, but not necessarily advanced machine learning practitioners, to straightforwardly apply the offered set of tools to their own research. To conclude, we explore the state-of-the-art of other disciplines with a broader experience in applying artificial intelligence methods to their research (e.g., high-energy physics, astronomy, Earth sciences, and even robotics, videogames, or marketing and finances), in order to narrow down the incoming future of electron microscopy, its challenges and outlook.

Machine learning-assisted evaluation of potential biochars for pharmaceutical removal from water

A popular approach to select optimal adsorbents is to perform parallel experiments on adsorbents based on an initially decided goal such as specified product purity, efficiency, or binding capacity. To screen optimal adsorbents, we focused on the max adsorption capacity of the candidates at equilibrium in this work because the adsorption capacity of each adsorbent is strongly dependent on certain conditions. A data-driven machine learning tool for predicting the max adsorption capacity (Q_m) of 19 pharmaceutical compounds on 88 biochars was developed. The range of values of Q_m (mean 48.29 mg/g) was remarkably large, with a high number of outliers and large variability. Modified biochars enhanced the Q_m and surface area values compared with the original biochar, with a statistically significant difference (Chi-square value = 7.21-18.25, P < 0.005). K- nearest neighbors (KNN) was found to be the most optimal algorithm with a root mean square error (RMSE) of 23.48 followed by random forest and Cubist with RMSE of 26.91 and 29.56, respectively, whereas linear regression and regularization were the worst algorithms. KNN model achieved R² of 0.92 and RMSE of 16.62 for the testing data. A web app was developed to facilitate the use of the KNN model, providing a reliable solution for saving time and money in unnecessary lab-scale adsorption experiments while selecting appropriate biochars for pharmaceutical adsorption.

Probing the rules of cell coordination in live tissues by interpretable machine learning based on graph neural networks

Robustness in developing and homeostatic tissues is supported by various types of spatiotemporal cell-to-cell interactions. Although live imaging and cell tracking are powerful in providing direct evidence of cell coordination rules, extracting and comparing these rules across many tissues with potentially different length and timescales of coordination requires a versatile framework of analysis. Here we demonstrate that graph neural network (GNN) models are suited for this purpose, by showing how they can be applied to predict cell fate in tissues and utilized to infer the cell interactions governing the multicellular dynamics. Analyzing the live mammalian epidermis data, where spatiotemporal graphs constructed from cell tracks and cell contacts are given as inputs, GNN discovers distinct neighbor cell fate coordination rules that depend on the region of the body. This approach demonstrates how the GNN framework is powerful in inferring general cell interaction rules from live data without prior knowledge of the signaling involved.

During development and homeostasis, cells coordinate with each other to grow, deform, and maintain the tissues. Even with the modern high-throughput cell profiling technologies and high-resolution microscopy, it is still challenging to infer how cell coordination affects the dynamics such as cell fate choice, due to the complexity of the problem and the limited methods to perform perturbation experiments. We here propose a versatile framework of analysis utilizing an interpretable machine learning method based on graph neural network (GNN) which infers the cell-to-cell interaction rules from live images of multicellular dynamics. From the spatiotemporal graphs generated from live images of skin stem cells, we identified previously unaddressed neighbor fate coupling as well as rules consistent with past findings. We further found distinct interaction rules in a different skin region of the body, indicating that our method is useful in probing the diverse mechanism behind the robustness and flexibility in multicellular systems. The GNN framework is applicable for interaction rule discovery for general multicellular dynamics as well as in a wide range of systems where modeling by stochastic interacting agents is effective.

Variational methods and deep Ritz method for active elastic solids

Variational methods have been widely used in soft matter physics for both static and dynamic problems. These methods are mostly based on two variational principles: the variational principle of minimum free energy (MFEVP) and Onsager's variational principle (OVP). Our interests lie in the applications of these variational methods to active matter physics. In our former work [H. Wang, T. Qian and X. Xu, Soft Matter, 2021, 17, 3634-3653], we have explored the applications of OVP-based variational methods for the modeling of active matter dynamics. In the present work, we explore variational (or energy) methods that are based on MFEVP for static problems in active elastic solids. We show that MFEVP can be used not only to derive equilibrium equations, but also to develop approximate solution methods, such as the Ritz method, for active solid statics. Moreover, the power of the Ritz-type method can be further enhanced using deep learning methods if we use deep neural networks to construct the trial functions of the variational problems. We then apply these variational methods and the deep Ritz method to study the spontaneous bending and contraction of a thin active circular plate that is induced by internal asymmetric active contraction. The circular plate is found to be bent towards its contracting side. The study of such a simple toy system gives implications for understanding the morphogenesis of solid-like confluent cell monolayers. In addition, we introduce a so-called activogravity length to characterize the importance of gravitational forces relative to internal active contraction in driving the bending of the active plate. When the lateral plate dimension is larger than the activogravity length (about 100 micron), gravitational forces become important. Such gravitaxis behaviors at multicellular scales may play significant roles in the morphogenesis and in the up-down symmetry broken during tissue development.

A distributed nanocluster based multi-agent evolutionary network

As an important approach of distributed artificial intelligence, multi-agent system provides an efficient way to solve large-scale computational problems through high-parallelism processing with nonlinear interactions between the agents. However, the huge capacity and complex distribution of the individual agents make it difficult for efficient hardware construction. Here, we propose and demonstrate a multi-agent hardware system that deploys distributed Ag nanoclusters as physical agents and their electrochemical dissolution, growth and evolution dynamics under electric field for high-parallelism exploration of the solution space. The collaboration and competition between the Ag nanoclusters allow information to be effectively expressed and processed, which therefore replaces cumbrous exhaustive operations with self-organization of Ag physical network based on the positive feedback of information interaction, leading to significantly reduced computational complexity. The proposed multi-agent network can be scaled up with parallel and serial integration structures, and demonstrates efficient solution of graph and optimization problems. An artificial potential field with superimposed attractive/repulsive components and varied ion velocity is realized, showing gradient descent route planning with self-adaptive obstacle avoidance. This multi-agent network is expected to serve as a physics-empowered parallel computing hardware.

Designing an efficient multi-agent hardware system to solve large-scale computational problems through high-parallelism processing with nonlinear interactions remains a challenge. Here, the authors demonstrate that a multi-agent hardware system deploying distributed Ag nanoclusters as physical agents enables parallel, complex computing.

From predicting to learning dissipation from pair correlations of active liquids

Active systems, which are driven out of equilibrium by local non-conservative forces, can adopt unique behaviors and configurations. Towards designing such materials, an important challenge is to precisely connect the static structure of active systems to the dissipation of energy induced by the local driving. Here, we use tools from liquid-state theories and machine learning to take on these challenges. We first demonstrate analytically for an isotropic active matter system that dissipation and pair correlations are closely related when driving forces behave like an active temperature. We then extend a nonequilibrium mean-field framework for predicting these pair correlations which, unlike most existing approaches, is applicable even for strongly interacting particles and far from equilibrium, to predict dissipation in these systems. Based on this theory, we reveal analytically a robust relation between dissipation and structure which holds even as the system approaches a nonequilibrium phase transition. Finally, we construct a neural network which maps static configurations of particles to their dissipation rate without any prior knowledge of the underlying dynamics. Our results open novel perspectives on the interplay between dissipation and organization out-of-equilibrium.

Automated machine learning for differentiation of hepatocellular carcinoma from intrahepatic cholangiocarcinoma on multiphasic MRI

With modern management of primary liver cancer shifting towards non-invasive diagnostics, accurate tumor classification on medical imaging is increasingly critical for disease surveillance and appropriate targeting of therapy. Recent advancements in machine learning raise the possibility of automated tools that can accelerate workflow, enhance performance, and increase the accessibility of artificial intelligence to clinical researchers. We explore the use of an automated Tree-Based Optimization Tool that leverages a genetic programming algorithm for differentiation of the two common primary liver cancers on multiphasic MRI. Manual and automated analyses were performed to select an optimal machine learning model, with an accuracy of 73–75% (95% CI 0.59–0.85), sensitivity of 70–75% (95% CI 0.48–0.89), and specificity of 71–79% (95% CI 0.52–0.90) on manual optimization, and an accuracy of 73–75% (95% CI 0.59–0.85), sensitivity of 65–75% (95% CI 0.43–0.89) and specificity of 75–79% (95% CI 0.56–0.90) for automated machine learning. We found that automated machine learning performance was similar to that of manual optimization, and it could classify hepatocellular carcinoma and intrahepatic cholangiocarcinoma with an sensitivity and specificity comparable to that of radiologists. However, automated machine learning performance was poor on a subset of scans that met LI-RADS criteria for LR-M. Exploration of additional feature selection and classifier methods with automated machine learning to improve performance on LR-M cases as well as prospective validation in the clinical setting are needed prior to implementation.

Learning the rules of collective cell migration using deep attention networks

Collective, coordinated cellular motions underpin key processes in all multicellular organisms, yet it has been difficult to simultaneously express the ‘rules’ behind these motions in clear, interpretable forms that effectively capture high-dimensional cell-cell interaction dynamics in a manner that is intuitive to the researcher. Here we apply deep attention networks to analyze several canonical living tissues systems and present the underlying collective migration rules for each tissue type using only cell migration trajectory data. We use these networks to learn the behaviors of key tissue types with distinct collective behaviors—epithelial, endothelial, and metastatic breast cancer cells—and show how the results complement traditional biophysical approaches. In particular, we present attention maps indicating the relative influence of neighboring cells to the learned turning decisions of a ‘focal cell’–the primary cell of interest in a collective setting. Colloquially, we refer to this learned relative influence as ‘attention’, as it serves as a proxy for the physical parameters modifying the focal cell’s future motion as a function of each neighbor cell. These attention networks reveal distinct patterns of influence and attention unique to each model tissue. Endothelial cells exhibit tightly focused attention on their immediate forward-most neighbors, while cells in more expansile epithelial tissues are more broadly influenced by neighbors in a relatively large forward sector. Attention maps of ensembles of more mesenchymal, metastatic cells reveal completely symmetric attention patterns, indicating the lack of any particular coordination or direction of interest. Moreover, we show how attention networks are capable of detecting and learning how these rules change based on biophysical context, such as location within the tissue and cellular crowding. That these results require only cellular trajectories and no modeling assumptions highlights the potential of attention networks for providing further biological insights into complex cellular systems.

Collective behaviors are crucial to the function of multicellular life, with large-scale, coordinated cell migration enabling processes spanning organ formation to coordinated skin healing. However, we lack effective tools to discover and cleanly express collective rules at the level of an individual cell. Here, we employ a carefully structured neural network to extract collective information directly from cell trajectory data. The network is trained on data from various systems, including canonical collective cell systems (HUVEC and MDCK cells) which display visually distinct forms of collective motion, and metastatic cancer cells (MDA-MB-231) which are highly uncoordinated. Using these trained networks, we can produce attention maps for each system, which indicate how a cell within a tissue takes in information from its surrounding neighbors, as a function of weights assigned to those neighbors. Thus for a cell type in which cells tend to follow the path of the cell in front, the attention maps will display high weights for cells spatially forward of the focal cell. We present results in terms of additional metrics, such as accuracy plots and number of interacting cells, and encourage future development of improved metrics.

Scale-invariant representation of machine learning

The success of machine learning has resulted from its structured representation of data. Similar data have close internal representations as compressed codes for classification or emerged labels for clustering. We observe that the frequency of internal codes or labels follows power laws in both supervised and unsupervised learning models. This scale-invariant distribution implies that machine learning largely compresses frequent typical data, and simultaneously, differentiates many atypical data as outliers. In this study, we derive the process by which these power laws can naturally arise in machine learning. In terms of information theory, the scale-invariant representation corresponds to a maximally uncertain data grouping among possible representations that guarantee a given learning accuracy.

Heat-Mediated Optical Manipulation

Progress in optical manipulation has stimulated remarkable advances in a wide range of fields, including materials science, robotics, medical engineering, and nanotechnology. This Review focuses on an emerging class of optical manipulation techniques, termed heat-mediated optical manipulation. In comparison to conventional optical tweezers that rely on a tightly focused laser beam to trap objects, heat-mediated optical manipulation techniques exploit tailorable optothermo-matter interactions and rich mass transport dynamics to enable versatile control of matter of various compositions, shapes, and sizes. In addition to conventional tweezing, more distinct manipulation modes, including optothermal pulling, nudging, rotating, swimming, oscillating, and walking, have been demonstrated to enhance the functionalities using simple and low-power optics. We start with an introduction to basic physics involved in heat-mediated optical manipulation, highlighting major working mechanisms underpinning a variety of manipulation techniques. Next, we categorize the heat-mediated optical manipulation techniques based on different working mechanisms and discuss working modes, capabilities, and applications for each technique. We conclude this Review with our outlook on current challenges and future opportunities in this rapidly evolving field of heat-mediated optical manipulation.

Reinforcement learning reveals fundamental limits on the mixing of active particles

The control of far-from-equilibrium physical systems, including active materials, requires advanced control strategies due to the non-linear dynamics and long-range interactions between particles, preventing explicit solutions to optimal control problems. In such situations, Reinforcement Learning (RL) has emerged as an approach to derive suitable control strategies. However, for active matter systems, it is an important open question how the mathematical structure and the physical properties determine the tractability of RL. In this paper, we demonstrate that RL can only find good mixing strategies for active matter systems that combine attractive and repulsive interactions. Using analytic results from dynamical systems theory, we show that combining both interaction types is indeed necessary for the existence of mixing-inducing hyperbolic dynamics and therefore the ability of RL to find homogeneous mixing strategies. In particular, we show that for drag-dominated translational-invariant particle systems, mixing relies on combined attractive and repulsive interactions. Therefore, our work demonstrates which experimental developments need to be made to make protein-based active matter applicable, and it provides some classification of microscopic interactions based on macroscopic behavior.