Machine Learning Data Augmentation Strategy for Electron Energy Loss Spectroscopy: Generative Adversarial Networks

Recent advances in machine learning (ML) have highlighted a novel challenge concerning the quality and quantity of data required to effectively train algorithms in supervised ML procedures. This article introduces a data augmentation (DA) strategy for electron energy loss spectroscopy (EELS) data, employing generative adversarial networks (GANs). We present an innovative approach, called the data augmentation generative adversarial network (DAG), which facilitates data generation from a very limited number of spectra, around 100. Throughout this study, we explore the optimal configuration for GANs to produce realistic spectra. Notably, our DAG generates realistic spectra, and the spectra produced by the generator are successfully used in real-world applications to train classifiers based on artificial neural networks (ANNs) and support vector machines (SVMs) that have been successful in classifying experimental EEL spectra.

Comparative of machine learning classification strategies for electron energy loss spectroscopy: Support vector machines and artificial neural networks

Machine Learning (ML) strategies applied to Scanning and conventional Transmission Electron Microscopy have become a valuable tool for analyzing the large volumes of data generated by various S/TEM techniques. In this work, we focus on Electron Energy Loss Spectroscopy (EELS) and study two ML techniques for classifying spectra in detail: Support Vector Machines (SVM) and Artificial Neural Networks (ANN). Firstly, we systematically analyze the optimal configurations and architectures for ANN classifiers using random search and the tree-structured Parzen estimator methods. Secondly, a new kernel strategy is introduced for the soft-margin SVMs, the cosine kernel, which offers a significant advantage over the previously studied kernels and other ML classification strategies. This kernel allows us to bypass the normalization of EEL spectra, achieving accurate classification. This result is highly relevant for the EELS community since we also assess the impact of common normalization techniques on our spectra using Uniform Manifold Approximation and Projection (UMAP), revealing a strong bias introduced in the spectra once normalized. In order to evaluate and study both classification strategies, we focus on determining the oxidation state of transition metals through their EEL spectra, examining which feature is more suitable for oxidation state classification: the oxygen K peak or the transition metal white lines. Subsequently, we compare the resistance to energy loss shifts for both classifiers and present a strategy to improve their resistance. The results of this study suggest the use of soft-margin SVMs for simpler EELS classification tasks with a limited number of spectra, as they provide performance comparable to ANNs while requiring lower computational resources and reduced training times. Conversely, ANNs are better suited for handling complex classification problems with extensive training data.

Direct Evidence of a Graded Magnetic Interface in Bimagnetic Core/Shell Nanoparticles Using Electron Magnetic Circular Dichroism (EMCD)

Interfaces play a crucial role in composite magnetic materials and particularly in bimagnetic core/shell nanoparticles. However, resolving the microscopic magnetic structure of these nanoparticles is rather complex. Here, we investigate the local magnetization of antiferromagnetic/ferrimagnetic FeO/Fe₃O₄ core/shell nanocubes by electron magnetic circular dichroism (EMCD). The electron energy-loss spectroscopy (EELS) compositional analysis of the samples shows the presence of an oxidation gradient at the interface between the FeO core and the Fe₃O₄ shell. The EMCD measurements show that the nanoparticles are composed of four different zones with distinct magnetic moment in a concentric, onion-type, structure. These magnetic areas correlate spatially with the oxidation and composition gradient with the magnetic moment being largest at the surface and decreasing toward the core. The results show that the combination of EELS compositional mapping and EMCD can provide very valuable information on the inner magnetic structure and its correlation to the microstructure of magnetic nanoparticles.

Support vector machine for EELS oxidation state determination

Electron Energy-Loss Spectroscopy (EELS) is a powerful and versatile spectroscopic technique used to study the composition and local optoelectronic properties of nanometric materials. Currently, this technique is generating large amounts of spectra per experiment, producing a huge quantity of data to analyse. Several strategies can be applied in order to classify these data to map physical properties at the nanoscale. In the present study, the Support Vector Machine (SVM) algorithm is applied to EELS, and its effectiveness identifying EEL spectra is assessed. Our results evidence the capacity of SVM to determine the oxidation state of iron and manganese in iron and manganese oxides, based on the ELNES of the white lines of the transition metal. The SVM algorithm is first trained with given datasets and then the resulting models are tested through noisy test data sets. We demonstrate that SVM exhibits a very good performance classifying these EEL spectra, despite the usual level of noise and instrumental energy shifts.

Precise Size Control of the Growth of Fe3O4 Nanocubes over a Wide Size Range Using a Rationally Designed One-Pot Synthesis

The physicochemical properties of spinel oxide magnetic nanoparticles depend critically on both their size and shape. In particular, spinel oxide nanocrystals with cubic morphology have shown superior properties in comparison to their spherical counterparts in a variety of fields, like, for example, biomedicine. Therefore, having an accurate control over the nanoparticle shape and size, while preserving the crystallinity, becomes crucial for many applications. However, despite the increasing interest in spinel oxide nanocubes there are relatively few studies on this morphology due to the difficulty to synthesize perfectly defined cubic nanostructures, especially below 20 nm. Here we present a rationally designed synthesis pathway based on the thermal decomposition of iron(III) acetylacetonate to obtain high quality nanocubes over a wide range of sizes. This pathway enables the synthesis of monodisperse Fe₃O₄ nanocubes with edge length in the 9-80 nm range, with excellent cubic morphology and high crystallinity by only minor adjustments in the synthesis parameters. The accurate size control provides evidence that even 1-2 nm size variations can be critical in determining the functional properties, for example, for improved nuclear magnetic resonance T₂ contrast or enhanced magnetic hyperthermia. The rationale behind the changes introduced in the synthesis procedure (e.g., the use of three solvents or adding Na-oleate) is carefully discussed. The versatility of this synthesis route is demonstrated by expanding its capability to grow other spinel oxides such as Co-ferrites, Mn-ferrites, and Mn₃O₄ of different sizes. The simplicity and adaptability of this synthesis scheme may ease the development of complex oxide nanocubes for a wide variety of applications.