Artificial Intelligence-Based, Wavelet-Aided Prediction of Long-Term Outdoor Performance of Perovskite Solar Cells.

The commercial development of perovskite solar cells (PSCs) has been significantly delayed by the constraint of performing time-consuming degradation studies under real outdoor conditions. These are necessary steps to determine the device lifetime, an area where PSCs traditionally suffer. In this work, we demonstrate that the outdoor degradation behavior of PSCs can be predicted by employing accelerated indoor stability analyses. The prediction was possible using a swift and accurate pipeline of machine learning algorithms and mathematical decompositions. By training the algorithms with different indoor stability data sets, we can determine the most relevant stress factors, thereby shedding light on the outdoor degradation pathways. Our methodology is not specific to PSCs and can be extended to other PV technologies where degradation and its mechanisms are crucial elements of their widespread adoption.

Application of Machine Learning Algorithms to Metadynamics for the Elucidation of the Binding Modes and Free Energy Landscape of Drug/Target Interactions: a Case Study.

In the context of drug discovery, computational methods were able to accelerate the challenging process of designing and optimizing a new drug candidate. Amongst the possible atomistic simulation approaches, metadynamics (metaD) has proven very powerful. However, the choice of collective variables (CVs) is not trivial for complex systems. To automate the process of CVs identification, two different machine learning algorithms were applied in this study, namely DeepLDA and Autoencoder, to the metaD simulation of a well-researched drug/target complex, consisting in a pharmacologically relevant non-canonical DNA secondary structure (G-quadruplex) and a metallodrug acting as its stabilizer, as well as solvent molecules.

Utilizing Data-Driven Optimization to Automate the Parametrization of Kinetic Monte Carlo Models.

Kinetic Monte Carlo (kMC) simulations are a popular tool to investigate the dynamic behavior of stochastic systems. However, one major limitation is their relatively high computational costs. In the last three decades, significant effort has been put into developing methodologies to make kMC more efficient, resulting in an enhanced runtime efficiency. Nevertheless, kMC models remain computationally expensive. This is in particular an issue in complex systems with several unknown input parameters where often most of the simulation time is required for finding a suitable parametrization. A potential route for automating the parametrization of kinetic Monte Carlo models arises from coupling kMC with a data-driven approach. In this work, we equip kinetic Monte Carlo simulations with a feedback loop consisting of Gaussian Processes (GPs) and Bayesian optimization (BO) to enable a systematic and data-efficient input parametrization. We utilize the results from fast-converging kMC simulations to construct a database for training a cheap-to-evaluate surrogate model based on Gaussian processes. Combining the surrogate model with a system-specific acquisition function enables us to apply Bayesian optimization for the guided prediction of suitable input parameters. Thus, the amount of trial simulation runs can be considerably reduced facilitating an efficient utilization of arbitrary kMC models. We showcase the effectiveness of our methodology for a physical process of growing industrial relevance: the space-charge layer formation in solid-state electrolytes as it occurs in all-solid-state batteries. Our data-driven approach requires only 1-2 iterations to reconstruct the input parameters from different baseline simulations within the training data set. Moreover, we show that the methodology is even capable of accurately extrapolating into regions outside the training data set which are computationally expensive for direct kMC simulation. Concluding, we demonstrate the high accuracy of the underlying surrogate model via a full parameter space investigation eventually making the original kMC simulation obsolete.

Mass transport and charge transfer through an electrified interface between metallic lithium and solid-state electrolytes.

All-solid-state Li-ion batteries are one of the most promising energy storage devices for future automotive applications as high energy density metallic Li anodes can be safely used. However, introducing solid-state electrolytes needs a better understanding of the forming electrified electrode/electrolyte interface to facilitate the charge and mass transport through it and design ever-high-performance batteries. This study investigates the interface between metallic lithium and solid-state electrolytes. Using spectroscopic ellipsometry, we detected the formation of the space charge depletion layers even in the presence of metallic Li. That is counterintuitive and has been a subject of intense debate in recent years. Using impedance measurements, we obtain key parameters characterizing these layers and, with the help of kinetic Monte Carlo simulations, construct a comprehensive model of the systems to gain insights into the mass transport and the underlying mechanisms of charge accumulation, which is crucial for developing high-performance solid-state batteries.

Machine learning and DFT investigation of CO, CO2 and CH4 adsorption on pristine and defective two-dimensional magnesene.

Adsorption study of environmentally toxic small gas molecules on two-dimensional (2D) materials plays a significant role in analyzing the performance of sensors. In this work, density functional theory (DFT) and machine learning (ML) techniques have been employed to systematically study the adsorption properties of CO, CO2, and CH4 gas molecules on the pristine and defective planar magnesium monolayer, known as magnesene (2D-Mg). The DFT analysis showed that mechanically robust 2D-Mg retains its metallicity in the presence of both mono and di-vacancy defects. Our observations have shown that 2D-Mg, whether defective or pristine, exhibits distinct adsorption behaviors towards CO, CO2, and CH4 gas molecules, including varying chemisorption and physisorption, charge transfer, and distance from the gas molecules. When analyzing the recovery time of gas molecules at room temperature, it is clear that adsorption energy has a direct correlation with the adsorption-desorption cycles, and CH4 possesses an ultra-low recovery time (15.27 ps) compared to CO2 (1.04 ns) and CO (0.90 µs) molecules. The analysis showed that defects do not have a significant impact on the work function of 2D-Mg. However, the work function decreased upon adsorption of CH4, resulting in improved sensitivity due to changes in the electronic properties. Additionally, we explored supervised ML regression models to evaluate their ability to act as a surrogate for the DFT-based adsorption energy calculation. Using both system statistics and smooth overlap of atomic position (SOAP)-based featurization, we observed that adsorption energies can be predicted with a mean absolute error of 0.10 eV.

Emerging indoor photovoltaics for self-powered and self-aware IoT towards sustainable energy management.

As the number of Internet of Things devices is rapidly increasing, there is an urgent need for sustainable and efficient energy sources and management practices in ambient environments. In response, we developed a high-efficiency ambient photovoltaic based on sustainable non-toxic materials and present a full implementation of a long short-term memory (LSTM) based energy management using on-device prediction on IoT sensors solely powered by ambient light harvesters. The power is supplied by dye-sensitised photovoltaic cells based on a copper(ii/i) electrolyte with an unprecedented power conversion efficiency at 38% and 1.0 V open-circuit voltage at 1000 lux (fluorescent lamp). The on-device LSTM predicts changing deployment environments and adapts the devices' computational load accordingly to perpetually operate the energy-harvesting circuit and avoid power losses or brownouts. Merging ambient light harvesting with artificial intelligence presents the possibility of developing fully autonomous, self-powered sensor devices that can be utilized across industries, health care, home environments, and smart cities.

Rapid Data-Efficient Optimization of Perovskite Nanocrystal Syntheses through Machine Learning Algorithm Fusion.

With the demand for renewable energy and efficient devices rapidly increasing, a need arises to find and optimize novel (nano)materials. With sheer limitless possibilities for material combinations and synthetic procedures, obtaining novel, highly functional materials has been a tedious trial and error process. Recently, machine learning has emerged as a powerful tool to help optimize syntheses; however, most approaches require a substantial amount of input data, limiting their pertinence. Here, three well-known machine-learning models are merged with Bayesian optimization into one to optimize the synthesis of CsPbBr3 nanoplatelets with limited data demand. The algorithm can accurately predict the photoluminescence emission maxima of nanoplatelet dispersions using only the three precursor ratios as input parameters. This allows us to fabricate previously unobtainable seven and eight monolayer-thick nanoplatelets. Moreover, the algorithm dramatically improves the homogeneity of 2-6-monolayer-thick nanoplatelet dispersions, as evidenced by narrower and more symmetric photoluminescence spectra. Decisively, only 200 total syntheses are required to achieve this vast improvement, highlighting how rapidly material properties can be optimized. The algorithm is highly versatile and can incorporate additional synthetic parameters. Accordingly, it is readily applicable to other less-explored nanocrystal syntheses and can help rapidly identify and improve exciting compositions' quality.

Advanced MRI imaging of nerve roots in lumbar radiculopathy due to discoradicular conflict: DWI, DTI, and T2 mapping with clinical and neurophysiological correlations.

PURPOSE: To evaluate the lumbar nerve root alterations in patients with lumbar disc herniation sciatica using advanced multimodality MRI sequences and the correlations with clinical and neurophysiological findings. MATERIAL AND METHODS: We prospectively evaluated 45 patients suffering from unilateral lumbar radiculopathy due to disco radicular conflict. All patients underwent MRI examinations using a standard MRI protocol and additional advanced MRI sequences (DWI, DTI, and T2 mapping sequences). Relative metrics of ADC, FA, and T2 relaxation times were recorded by placing ROIs at the pre-, foraminal, and post-foraminal level, either at the affected side or the contralateral side, used as control. All patients were also submitted to electromyography testing, recording the spontaneous activity, voluntary activity, F wave amplitude, latency, and motor evoked potentials (MEP) amplitude and latency, both at the level of the tibialis anterior and the gastrocnemius. Clinical features (diseases duration, pain, sensitivity, strength, osteotendinous reflexes) were also recorded. RESULTS: Among clinical features, we found a positive correlation of pain intensity with ADC values of the lumbar nerve roots. The presence of spontaneous activity was correlated with lower ADC values of the affected lumbar nerve root. F wave and MEP latency were correlated with decreased FA values at the foraminal level and increased values at the post-foraminal level. The same neurophysiological measures correlated positively with pre-foraminal T2 mapping values and negatively with post-foraminal T2 mapping values. Increased T2 mapping values at the foraminal level were correlated with disease duration. CONCLUSIONS: Evaluation of lumbar nerve roots using advanced MRI sequences may provide useful clinical information in patients with lumbar radiculopathy, potentially indicating active inflammation/myelinic damage (DTI, T2 mapping) and axonal damage/chronicity (DWI).

Rational design of selenium inserted 1T/2H mixed-phase molybdenum disulfide for energy storage and pollutant degradation applications.

MoS2based materials are recognized as the promising candidate for multifunctional applications due to its unique physicochemical properties. But presence of lower number of active sites, poor electrical conductivity, and less stability of 2H and 1T MoS2inherits its practical applications. Herein, we synthesized the Se inserted mixed-phase 2H/1T MoS2nanosheets with abundant defects sites to achieve improved overall electrochemical activity. Moreover, the chalcogen insertion induces the recombination of photogenerated excitons and enhances the life of carriers. The bifunctional energy storage and photocatalytic pollutant degradation studies of the prepare materials are carried out. Fabricated symmetric solid-state supercapacitor showed an exceptional capacitance of 178 mF cm-2with an excellent energy density of 8µWh cm-2and power density of 137 mW cm-2, with remarkable capacitance retention of 86.34% after successive 8000 charge-discharge cycles. The photocatalytic dye degradation experiments demonstrate that the prepared Se incorporated 1T/2H MoS2is a promising candidate for dye degradation applications. Further, the DFT studies confirmed that the Se inserted MoS2is a promising electrode material for supercapacitor applications with higherCQdue to a larger density of states near Fermi level as compared to pristine MoS2.

Local Temporal Acceleration Scheme to Couple Transport and Reaction Dynamics in Kinetic Monte Carlo Models of Electrochemical Systems.

Kinetic Monte Carlo (kMC) simulations are a well-established tool for investigating the operation of electrochemical systems. Standard kMC algorithms become unfeasible in the presence of processes on vastly different time scales. In electrochemical systems, such time scale disparities often arise between fast transport processes and slow electrochemical reactions. A promising approach to overcome time scale disparities in kMC models is given by temporal acceleration schemes. In this work, we present a local temporal acceleration scheme to bridge the time scale disparity between fast transport and slow reaction dynamics. We combine the superbasin concept with a local, particle-based criterion for the quasi-equilibrium detection and a partitioning of transitions and particles in the system into process chains. Scaling of entire quasi-equilibrated process chains considerably reduces the computational effort without disturbing the relative dynamics of transitions within a process chain. The methodology is outlined for a hybrid organic-aqueous electrolyte device which links fast electronic processes in an organic semiconductor with slow reduction reactions at its interface to the electrolyte. Our approach captures local inhomogeneities such that local physical quantities can be reproduced accurately. Additionally, we show that previous accelerated superbasin algorithms are limited by the presence of spatially varying time scale disparities. Our algorithm achieves an acceleration of several orders of magnitude providing a serious alternative to replace existing multiscale models by stand-alone kMC simulations.

Machine Learning and Optoelectronic Materials Discovery: A Growing Synergy.

Novel optoelectronic materials have the potential to revolutionize the ongoing green transition by both providing more efficient photovoltaic (PV) devices and lowering energy consumption of devices like LEDs and sensors. The lead candidate materials for these applications are both organic semiconductors and more recently perovskites. This Perspective illustrates how novel machine learning techniques can help explore these materials, from speeding up ab initio calculations toward experimental guidance. Furthermore, based on existing work, perspectives around machine-learned molecular dynamics potentials, physically informed neural networks, and generative methods are outlined.

Comprehensive Evaluation of Factors Affecting Tremor Relapse after MRgFUS Thalamotomy: A Case-Control Study.

OBJECTIVE: To identify possible relevant factors contributing to tremor relapse after MRgFUS thalamotomy in patients with essential tremor (ET) and Parkinson's disease (PD). METHODS: We identified patients with tremor relapse from a series of 79 treatments in a single institution. The demographic and clinical characteristics of the study group patients were compared to those of patients who did not relapse in the same follow-up period. Imaging and procedural factors were compared using a control group matched for clinical and demographic characteristics. RESULTS: Concerning clinical and demographic characteristics, we did not find statistically significant differences in gender and age. Seventy-three percent of patients with tremor relapse were Parkinson's disease patients. Using MRI, we found larger thalamotomy lesions at the 1-year follow-up in the control group with stable outcomes, compared to patients with tremor relapse. In the tractography evaluation, we found a more frequent eccentric position of the DRTt in patients with tremor relapse. CONCLUSIONS: The most relevant determining factors for tremor relapse after MRgFUS thalamotomy appear to be tremor from Parkinson's disease and inaccurate thalamic targeting. Size of the thalamotomy lesion can also influence the outcome of treatment.

Machine Learning Approach to Analyze the Surface Properties of Biological Materials.

Similar to how CRISPR has revolutionized the field of molecular biology, machine learning may drastically boost research in the area of materials science. Machine learning is a fast-evolving method that allows for analyzing big data and unveiling correlations that otherwise would remain undiscovered. It may hold invaluable potential to engineer novel functional materials with desired properties, a field, which is currently limited by time-consuming trial and error approaches and our limited understanding of how different material properties depend on each other. Here, we apply machine learning algorithms to classify complex biological materials based on their microtopography. With this approach, the surfaces of different variants of biofilms and plant leaves can not only be distinguished but also correctly classified according to their wettability. Furthermore, an importance ranking provided by one of the algorithms allows us to identify those surface features that are critical for a successful sample classification. Our study exemplifies how machine learning can contribute to the analysis and categorization of complex surfaces, a tool, which can be highly useful for other areas of materials science, such as damage assessment as well as adhesion or friction studies.

An Instrument for the Characterization and Calibration of Optical Sensors.

This paper presents the development of a hardware/software system for the characterization of the electronic response of optical (camera) sensors such as matrix and linear color and monochrome Charge Coupled Device (CCD) or Complementary Metal Oxide Semiconductor (CMOS). The electronic response of a sensor is required for inspection purposes. It also allows the design and calibration of the integrating device to achieve the desired performance. The proposed instrument equipment fulfills the most recent European Machine Vision Association (EMVA) 1288 standard ver. 3.1: the spatial non uniformity of the illumination ΔE must be under 3%, and the sensor must achieve an f-number of 8.0 concerning the light source. The following main innovations have achieved this: an Ulbricht sphere providing a uniform light distribution (irradiation) of 99.54%; an innovative illuminator with proper positioning of color Light Emitting Diodes (LEDs) and control electronics; and a flexible C# program to analyze the sensor parameters, namely Quantum Efficiency, Overall System Gain, Temporal Dark Noise, Dark Signal Non Uniformity (DSNU1288), Photo Response Non-Uniformity (PRNU1288), Maximum achievable Signal to Noise Ratio (SNRmax), Absolute sensitivity threshold, Saturation Capacity, Dynamic Range, and Dark Current. This new instrument has allowed a camera manufacturer to design, integrate, and inspect numerous devices and camera models (Necta, Celera, and Aria).

Nonequilibrium Thermodynamics of Charge Separation in Organic Solar Cells.

This work presents a novel theoretical description of the nonequilibrium thermodynamics of charge separation in organic solar cells (OSCs). Using stochastic thermodynamics, we take realistic state populations derived from the phonon-assisted dynamics of electron-hole pairs within photoexcited organic bilayers to connect the kinetics with the free energy profile of charge separation. Hereby, we quantify for the first time the difference between nonequilibrium and equilibrium free energy profile. We analyze the impact of energetic disorder and delocalization on free energy, average energy, and entropy. For a high disorder, the free energy profile is well-described as equilibrated. We observe significant deviations from equilibrium for delocalized electron-hole pairs at a small disorder, implying that charge separation in efficient OSCs proceeds via a cold but nonequilibrated pathway. Both a large Gibbs entropy and large initial electron-hole distance provide an efficient charge separation, while a decrease in the free energy barrier does not necessarily enhance charge separation.

Global Property Prediction: A Benchmark Study on Open-Source, Perovskite-like Datasets.

Screening combinatorial space for novel materials, such as perovskite-like ones for photovoltaics, has resulted in a high amount of simulated high-throughput data and analysis thereof. This study proposes a comprehensive comparison of structural fingerprint-based machine learning models on seven open-source databases of perovskite-like materials to predict band gaps and energies. It shows that none of the given methods, including graph neural networks, are able to capture arbitrary databases evenly, while underlining that commonly used metrics are highly database-dependent in typical workflows. In addition, the applicability of variance selection and autoencoders to significantly reduce fingerprint size indicates that models built with common fingerprints only rely on a submanifold of the available fingerprint space.

Implementing a real-time, AI-based, people detection and social distancing measuring system for Covid-19.

COVID-19 is a disease caused by a severe respiratory syndrome coronavirus. It was identified in December 2019 in Wuhan, China. It has resulted in an ongoing pandemic that caused infected cases including many deaths. Coronavirus is primarily spread between people during close contact. Motivating to this notion, this research proposes an artificial intelligence system for social distancing classification of persons using thermal images. By exploiting YOLOv2 (you look at once) approach, a novel deep learning detection technique is developed for detecting and tracking people in indoor and outdoor scenarios. An algorithm is also implemented for measuring and classifying the distance between persons and to automatically check if social distancing rules are respected or not. Hence, this work aims at minimizing the spread of the COVID-19 virus by evaluating if and how persons comply with social distancing rules. The proposed approach is applied to images acquired through thermal cameras, to establish a complete AI system for people tracking, social distancing classification, and body temperature monitoring. The training phase is done with two datasets captured from different thermal cameras. Ground Truth Labeler app is used for labeling the persons in the images. The proposed technique has been deployed in a low-cost embedded system (Jetson Nano) which is composed of a fixed camera. The proposed approach is implemented in a distributed surveillance video system to visualize people from several cameras in one centralized monitoring system. The achieved results show that the proposed method is suitable to set up a surveillance system in smart cities for people detection, social distancing classification, and body temperature analysis.

Stepping Out of Equilibrium: The Quest for Understanding the Role of Non-Equilibrium (Thermo-)Dynamics in Electronic and Electrochemical Processes.

This editorial aims to interest researchers and inspire novel research on the topic of non-equilibrium Thermodynamics and Monte Carlo for Electronic and Electrochemical Processes. We present a brief outline on recent progress and challenges in the study of non-equilibrium dynamics and thermodynamics using numerical Monte Carlo simulations. The aim of this special issue is to collect recent advances and novel techniques of Monte Carlo methods to study non-equilibrium electronic and electrochemical processes at the nanoscale.

Deep Learning Total Energies and Orbital Energies of Large Organic Molecules Using Hybridization of Molecular Fingerprints.

The ability to predict material properties without the need for resource-consuming experimental efforts can immensely accelerate material and drug discovery. Although ab initio methods can be reliable and accurate in making such predictions, they are computationally too expensive on a large scale. The recent advancements in artificial intelligence and machine learning as well as the availability of large quantum mechanics derived datasets enable us to train models on these datasets as a benchmark and to make fast predictions on much larger datasets. The success of these machine learning models highly depends on the machine-readable fingerprints of the molecules that capture their chemical properties as well as topological information. In this work, we propose a common deep learning-based framework to combine different types of molecular fingerprints to enhance prediction accuracy. A graph neural network (GNN), many-body tensor representation (MBTR), and a set of simple molecular descriptors (MD) were used to predict the total energies, highest occupied molecular orbital (HOMO) energies, and lowest unoccupied molecular orbital (LUMO) energies of a dataset containing ∼62k large organic molecules with complex aromatic rings and remarkably diverse functional groups. The results demonstrate that a combination of best performing molecular fingerprints can produce better results than the individual ones. The simple and flexible deep learning framework developed in this work can be easily adapted to incorporate other types of molecular fingerprints.