Neural networks, while effective for tackling many challengi ng scientific tasks, are not known to perform well out-of-distribution (OOD), i.e., within domains which d iffer from their training data. Understanding neural network OOD generalization is paramount to their suc cessful deployment in experimental workflows, especially when ground-truth knowledge about the experime nt is hard to establish or experimental conditions significantly vary. With inherent access to ground-truth in formation and fine-grained control of underlying distributions, simulation-based data curation facilitate s precise investigation of OOD generalization behavior. Here, we probe generalization with respect to imaging condi tions of neural network segmentation models for high-resolution transmission electron microscopy (HRTEM) imaging of nanoparticles, training and measuring the OOD generalization of over 12,000 neural networks using synthetic data generated via random structure sampling and multislice simulation. Using the HRTEM contra st transfer function, we further develop a framework to compare information content of HRTEM datasets an d quantify OOD domain shifts. We demonstrate that neural network segmentation models enjoy significant performance stability, but will smoothly and predictably worsen as imaging conditions shift from the training distribution. Lastly, we consider limitations of our approach in explaining other OOD shifts, s uch as of the atomic structures, and discuss complementary techniques for understanding generalizatio n in such settings.

We approach the search for optimal element ordering in bimetallic alloy nanoparticles (NPs) as a reinforcement learning (RL) problem, and have built an RL agent that learns to perform such global optimisation using the geometric graph representation of the NPs. To demonstrate the effectiveness, we train an RL agent to perform composition-conserving atomic swap actions on the icosahedral nanoparticle structure. Trained once on randomised $Ag_{X}Au_{309-X}$ compositions and orderings, the agent discovers previously established ground state structure. We show that this optimization is robust to differently ordered initialisations of the same NP compositions. We also demonstrate that a trained policy can extrapolate effectively to NPs of unseen size. However, the efficacy is limited when multiple alloying elements are involved. Our results demonstrate that RL with pre-trained equivariant graph encodings can navigate combinatorial ordering spaces at the nanoparticle scale, and offer a transferable optimisation strategy with the potential to generalise across composition and reduce repeated individual search cost.

The LA Fires Spewed Out Toxic Nanoparticles. Nicholas Spada is one of the only scientists in the world using a nuclear x-ray process to study deadly nanoparticles in wildfire smoke. What he's uncovered in California is a nightmare. Nicholas Spada was used to fielding urgent requests when wildfire smoke blanketed cities. Winter was supposed to be the quiet period when wildfires die down and researchers like Spada perform instrument maintenance, write grant proposals and go home for dinner. Instead, 2025's so-called offseason ignited January 7, when the Santa Ana winds came howling through Los Angeles, bringing gusts upwards of 100 miles per hour, after more than eight months without meaningful rainfall. By nightfall, thousands of homes in Los Angeles' swanky Pacific Palisades neighborhood and the Altadena community north of the city were gone. The next morning, Spada was fielding call after call at the University of California, Davis, from fellow air researchers at universities across the country who were packing instruments and other gear and heading for Los Angeles, many on their own dime. They would be studying urban fires--not normal wildfires or even urban-wildland interface fires--but urban fires in which most of the fuel was manmade: lawn chemicals, asbestos insulation, lead paint, lithium batteries. They asked Spada which instruments to bring, what measurements to take, where to set up downwind and when he would be there. The calls quickly morphed into a WhatsApp group that's still going strong, as results continue to roll in sporadically all these months later. Spada, a trim, energetic man with a close-trimmed beard and reddish hair, is a project scientist at UC Davis' Air Quality Research Center. He is one of only a handful of scientists in the world proficient at using a nuclear method for detecting toxic substances in air particles to understand their impact on human health and the environment.

Motile nanosized particles, or "nanobots", promise more effective and less toxic targeted drug delivery because of their unique scale and precision. We consider the case in which the cancer is "diffuse", dispersed such that there are multiple distinct cancer sites. We investigate the problem of a swarm of nanobots locating these sites and treating them by dropping drug payloads at the sites. To improve the success of the treatment, the drug payloads must be allocated between sites according to their "demands"; this requires extra nanobot coordination. We present a mathematical model of the behavior of the nanobot agents and of their colloidal environment. This includes a movement model for agents based upon experimental findings from actual nanoparticles in which bots noisily ascend and descend chemical gradients. We present three algorithms: The first algorithm, called KM, is the most representative of reality, with agents simply following naturally existing chemical signals that surround each cancer site. The second algorithm, KMA, includes an additional chemical payload which amplifies the existing natural signals. The third algorithm, KMAR, includes another additional chemical payload which counteracts the other signals, instead inducing negative chemotaxis in agents such that they are repelled from sites that are already sufficiently treated. We present simulation results for all algorithms across different types of cancer arrangements. For KM, we show that the treatment is generally successful unless the natural chemical signals are weak, in which case the treatment progresses too slowly. For KMA, we demonstrate a significant improvement in treatment speed but a drop in eventual success, except for concentrated cancer patterns. For KMAR, our results show great performance across all types of cancer patterns, demonstrating robustness and adaptability.

Recent advancements in machine learning have significantly enhanced the precision and efficiency of data-driven methodologies in scientific applications. These methods have found applications in a variety of fields, including physics, medicine, and space sciences, where they help addressing complex challenges which require high-precision measurements. One such application is directional dark matter search experiments that require precise measurements of ions recoiling after their interactions with dark matter particles [1, 2]. Due to their extremely low kinetic energies, in the 1 100 keV range, recoiling ions produce tracks ranging from a few millimeters in gases at low pressure to a few hundreds of nanometers in solids [2, 3]. Taking into account that the required detector mass in practice amounts to several tons, the choice of solid materials as a sensitive medium is advantageous.

Unlocking the potential of nanomaterials in medicine and environmental science hinges on understanding their interactions with proteins, a complex decision space where AI is poised to make a transformative impact. However, progress has been hindered by limited datasets and the restricted generalizability of existing models. Here, we propose NanoPro-3M, the largest nanomaterial-protein interaction dataset to date, comprising over 3.2 million samples and 37,000 unique proteins. Leveraging this, we present NanoProFormer, a foundational model that predicts nanomaterial-protein affinities through multimodal representation learning, demonstrating strong generalization, handling missing features, and unseen nanomaterials or proteins. We show that multimodal modeling significantly outperforms single-modality approaches and identifies key determinants of corona formation. Furthermore, we demonstrate its applicability to a range of downstream tasks through zero-shot inference and fine-tuning. Together, this work establishes a solid foundation for high-performance and generalized prediction of nanomaterial-protein interaction endpoints, reducing experimental reliance and accelerating various in vitro applications.

Deploying motile nanosized particles, also known as ``nanobots'', in the human body promises to improve selectivity in drug delivery and reduce side effects. We consider a swarm of nanobots locating a single cancerous region and treating it by releasing an onboard payload of drugs at the site. At nanoscale, the computation, communication, sensing, and locomotion capabilities of individual agents are extremely limited, noisy, and/or nonexistent. We present a general model to formally describe the individual and collective behavior of agents in a colloidal environment, such as the bloodstream, for cancer detection and treatment by nanobots. This includes a feasible and precise model of agent locomotion, inspired by actual nanoparticles that, in the presence of an external chemical gradient, move towards areas of higher concentration by means of self-propulsion. We present two variants of our general model: The first assumes an endogenous chemical gradient that is fixed over time and centered at the targeted cancer site; the second is a more speculative and dynamic variant in which agents themselves create and amplify a chemical gradient centered at the cancer site. In both settings, agents can sense the gradient and ascend it noisily, locating the cancer site more quickly than via simple Brownian motion. For the first variant of the model, we present simulation results to show the behavior of agents under our locomotion model, as well as {analytical results} to bound the time it takes for the agents to reach the cancer site. For the second variant, simulation results highlight the collective benefit in having agents issue their own chemical signal. While arguably more speculative in its agent capability assumptions, this variant shows a significant improvement in runtime performance over the first variant, resulting from its chemical signal amplification mechanism.

Microscopy is a primary source of information on materials structure and functionality at nanometer and atomic scales. The data generated is often well-structured, enriched with metadata and sample histories, though not always consistent in detail or format. The adoption of Data Management Plans (DMPs) by major funding agencies promotes preservation and access. However, deriving insights remains difficult due to the lack of standardized code ecosystems, benchmarks, and integration strategies. As a result, data usage is inefficient and analysis time is extensive. In addition to post-acquisition analysis, new APIs from major microscope manufacturers enable real-time, ML-based analytics for automated decision-making and ML-agent-controlled microscope operation. Yet, a gap remains between the ML and microscopy communities, limiting the impact of these methods on physics, materials discovery, and optimization. Hackathons help bridge this divide by fostering collaboration between ML researchers and microscopy experts. They encourage the development of novel solutions that apply ML to microscopy, while preparing a future workforce for instrumentation, materials science, and applied ML. This hackathon produced benchmark datasets and digital twins of microscopes to support community growth and standardized workflows. All related code is available at GitHub: https://github.com/KalininGroup/Mic-hackathon-2024-codes-publication/tree/1.0.0.1

Accurate determination of three-dimensional (3D) atomic structures is crucial for understanding and controlling the properties of nanomaterials. Atomic electron tomography (AET) offers non-destructive atomic imaging with picometer-level precision, enabling the resolution of defects, interfaces, and strain fields in 3D, as well as the observation of dynamic structural evolution. However, reconstruction artifacts arising from geometric limitations and electron dose constraints can hinder reliable atomic structure determination. Recent progress has integrated deep learning, especially convolutional neural networks, into AET workflows to improve reconstruction fidelity. This review highlights recent advances in neural network-assisted AET, emphasizing its role in overcoming persistent challenges in 3D atomic imaging. By significantly enhancing the accuracy of both surface and bulk structural characterization, these methods are advancing the frontiers of nanoscience and enabling new opportunities in materials research and technology.

Nanomaterial research is becoming a vital area for energy, medicine, and materials science, and accurate analysis of the nanoparticle topology is essential to determine their properties. Unfortunately, the lack of high-quality annotated datasets drastically hinders the creation of strong segmentation models for nanoscale imaging. To alleviate this problem, we introduce F-ANcGAN, an attention-enhanced cycle consistent generative adversarial system that can be trained using a limited number of data samples and generates realistic scanning electron microscopy (SEM) images directly from segmentation maps. Our model uses a Style U-Net generator and a U-Net segmentation network equipped with self-attention to capture structural relationships and applies augmentation methods to increase the variety of the dataset. The architecture reached a raw FID score of 17.65 for TiO$_2$ dataset generation, with a further reduction in FID score to nearly 10.39 by using efficient post-processing techniques. By facilitating scalable high-fidelity synthetic dataset generation, our approach can improve the effectiveness of downstream segmentation task training, overcoming severe data shortage issues in nanoparticle analysis, thus extending its applications to resource-limited fields.