Event prediction is the ability of anticipating future events, i.e., future real-world occurrences, and aims to support the user in deciding on actions that change future events towards a desired state. An event prediction method learns the relation between features of past events and future events. It is applied to newly observed events to predict corresponding future events that are evaluated with respect to the user's desired future state. If the predicted future events do not comply with this state, actions are taken towards achieving desirable future states. Evidently, event prediction is valuable in many application domains such as business and natural disasters. The diversity of application domains results in a diverse range of methods that are scattered across various research areas which, in turn, use different terminology for event prediction methods. Consequently, sharing methods and knowledge for developing future event prediction methods is restricted. To facilitate knowledge sharing on account of a comprehensive classification, integration, and assessment of event prediction methods, we combine taxonomies and take a systems perspective to integrate event prediction methods into a single system, elicit requirements and assess existing work with respect to the requirements. Based on the assessment, we identify open challenges and discuss future research directions.

Process design is a creative task that is currently performed manually by engineers. Artificial intelligence provides new potential to facilitate process design. Specifically, reinforcement learning (RL) has shown some success in automating process design by integrating data-driven models that learn to build process flowsheets with process simulation in an iterative design process. However, one major challenge in the learning process is that the RL agent demands numerous process simulations in rigorous process simulators, thereby requiring long simulation times and expensive computational power. Therefore, typically short-cut simulation methods are employed to accelerate the learning process. Short-cut methods can, however, lead to inaccurate results. We thus propose to utilize transfer learning for process design with RL in combination with rigorous simulation methods. Transfer learning is an established approach from machine learning that stores knowledge gained while solving one problem and reuses this information on a different target domain. We integrate transfer learning in our RL framework for process design and apply it to an illustrative case study comprising equilibrium reactions, azeotropic separation, and recycles, our method can design economically feasible flowsheets with stable interaction with DWSIM. Our results show that transfer learning enables RL to economically design feasible flowsheets with DWSIM, resulting in a flowsheet with an 8% higher revenue. And the learning time can be reduced by a factor of 2.

Using NIR Spectroscopy and don't want to pay for a calibration abo or a subscription based software/service? If you would like Pay per calibration, then CalibrationModel is the solution for you. "Near infrared spectroscopy for blend uniformity monitoring: An innovative qualitative application based on the coefficient of determination" LINK "Research on the secondary structure and hydration water around human serum albumin induced by ethanol with infrared and near-infrared spectroscopy" LINK "Point-of-Care Using Vis-NIR Spectroscopy for White Blood Cell Count Analysis" LINK "Rapid determination of viscosity and viscosity index of lube base oil based on near-infrared spectroscopy and new transformation formula" LINK "A recognition method of mushroom mycelium varieties based on near-infrared spectroscopy and deep learning model" LINK "Fast and nondestructive discrimination of fresh tea leaves at different altitudes based on near infrared spectroscopy and various chemometrics methods" LINK "Detection of early collision and compression bruises for pears based on hyperspectral imaging technology" LINK "Hyperspectral Imaging based Detection of PVC during Sellafield Repackaging Procedures" LINK "Study on the detection of apple soluble solids based on fractal theory and hyperspectral imaging technology" LINK "Ganoderma boninense classification based on near-infrared spectral data using machine learning techniques" LINK "Sensors: Prediction of the Nitrogen Content of Rice Leaf Using Multi-Spectral Images Based on Hybrid Radial Basis Function Neural Network and Partial Least-Squares Regression" LINK "Foods: Detection of the Inoculated Fermentation Process of Apo Pickle Based on a Colorimetric Sensor Array Method" LINK "Analysis of physio-chemical properties of solution grown third order nonlinear optical single crystal: 1, 4-oxazinanium nitrate for photonic applications" LINK "A novel composite colorimetric sensor array for quality characterization of shrimp paste based on indicator displacement assay and etching of silver nanoprisms" LINK "Research on weed identification method in rice fields based on UAV remote sensing" LINK "Flexible Microspectrometers Based on Printed Perovskite Pixels with Graded Bandgaps" spectrometers miniaturization LINK "Improving spectral estimation of soil inorganic carbon in urban and suburban areas by coupling continuous wavelet transform with geographical stratification" LINK "Biomedicines: Fourier Transform Infrared Spectroscopy Reveals Molecular Changes in Blood Vessels of Rats Treated with Pentadecapeptide BPC 157" LINK "Electrochromic Tungsten Oxide Nanofilms and Ionic Liquid Based Ion Conductor for Smart Windows Development: Preparation, Characterization and …" LINK

According to a recent study, machine learning could aid in the creation of new metal types with advantageous characteristics like resistance to rust and high temperatures. A variety of industries could benefit from this; for instance, spacecraft could be improved with metals that function well at lower temperatures, while boats and submarines could benefit from corrosion-resistant metals. Currently, attempts to produce new metals are mostly conducted in laboratories by scientists. Typically, they begin with one well-known element, such as iron, which is readily available and malleable, and then add one or two more to examine how it affects the base material. Trial & error is a hard process that invariably produces more failures than successful outcomes.

It is critical that machine learning (ML) model predictions be trustworthy for high-throughput catalyst discovery approaches. Uncertainty quantification (UQ) methods allow estimation of the trustworthiness of an ML model, but these methods have not been well explored in the field of heterogeneous catalysis. Herein, we investigate different UQ methods applied to a crystal graph convolutional neural network (CGCNN) to predict adsorption energies of molecules on alloys from the Open Catalyst 2020 (OC20) dataset, the largest existing heterogeneous catalyst dataset. We apply three UQ methods to the adsorption energy predictions, namely k-fold ensembling, Monte Carlo dropout, and evidential regression. The effectiveness of each UQ method is assessed based on accuracy, sharpness, dispersion, calibration, and tightness. Evidential regression is demonstrated to be a powerful approach for rapidly obtaining tunable, competitively trustworthy UQ estimates for heterogeneous catalysis applications when using neural networks. Recalibration of model uncertainties is shown to be essential in practical screening applications of catalysts using uncertainties.

For environmental, sustainable economic and political reasons, recycling processes are becoming increasingly important, aiming at a much higher use of secondary raw materials. Currently, for the copper and aluminium industries, no method for the non-destructive online analysis of heterogeneous materials are available. The Prompt Gamma Neutron Activation Analysis (PGNAA) has the potential to overcome this challenge. A difficulty when using PGNAA for online classification arises from the small amount of noisy data, due to short-term measurements. In this case, classical evaluation methods using detailed peak by peak analysis fail. Therefore, we propose to view spectral data as probability distributions. Then, we can classify material using maximum log-likelihood with respect to kernel density estimation and use discrete sampling to optimize hyperparameters. For measurements of pure aluminium alloys we achieve near perfect classification of aluminium alloys under 0.25 second.

Materials informatics (MI), which uses artificial intelligence and data analysis techniques to improve the efficiency of materials development, is attracting increasing interest from industry. One of its main applications is the rapid development of new high-performance compounds. Recently, several deep generative models have been proposed to suggest candidate compounds that are expected to satisfy the desired performance. However, they usually have the problem of requiring a large amount of experimental datasets for training to achieve sufficient accuracy. In actual cases, it is often possible to accumulate only about 1000 experimental data at most. Therefore, the authors proposed a deep generative model with nested two variational autoencoders (VAEs). The outer VAE learns the structural features of compounds using large-scale public data, while the inner VAE learns the relationship between the latent variables of the outer VAE and the properties from small-scale experimental data. To generate high performance compounds beyond the range of the training data, the authors also proposed a loss function that amplifies the correlation between a component of latent variables of the inner VAE and material properties. The results indicated that this loss function contributes to improve the probability of generating high-performance candidates. Furthermore, as a result of verification test with an actual customer in chemical industry, it was confirmed that the proposed method is effective in reducing the number of experiments to $1/4$ compared to a conventional method.

Recent breakthroughs in computing power have made it feasible to use machine learning and deep learning to advance scientific computing in many fields, including fluid mechanics, solid mechanics, materials science, etc. Neural networks, in particular, play a central role in this hybridization. Due to their intrinsic architecture, conventional neural networks cannot be successfully trained and scoped when data is sparse, which is the case in many scientific and engineering domains. Nonetheless, neural networks provide a solid foundation to respect physics-driven or knowledge-based constraints during training. Generally speaking, there are three distinct neural network frameworks to enforce the underlying physics: (i) physics-guided neural networks (PgNNs), (ii) physics-informed neural networks (PiNNs), and (iii) physics-encoded neural networks (PeNNs). These methods provide distinct advantages for accelerating the numerical modeling of complex multiscale multi-physics phenomena. In addition, the recent developments in neural operators (NOs) add another dimension to these new simulation paradigms, especially when the real-time prediction of complex multi-physics systems is required. All these models also come with their own unique drawbacks and limitations that call for further fundamental research. This study aims to present a review of the four neural network frameworks (i.e., PgNNs, PiNNs, PeNNs, and NOs) used in scientific computing research. The state-of-the-art architectures and their applications are reviewed, limitations are discussed, and future research opportunities in terms of improving algorithms, considering causalities, expanding applications, and coupling scientific and deep learning solvers are presented. This critical review provides researchers and engineers with a solid starting point to comprehend how to integrate different layers of physics into neural networks.

In mining, grade control generally focuses on blast hole sampling and the estimation of ore control block models with little or no attention given to how the materials are being excavated from the ground. In the process of loading trucks, the underlying variability of the individual bucket load will determine the variability of truck payload. Hence, accurate material movement demands a good knowledge of the excavation process and the buckets interaction with the environment. However, equipment frequently goes into off nominal states due to unexpected delays, disturbances or faults. The large amount of such disturbances causes information loss that reduces the statistical power and biases estimates, leading to increased uncertainty in the production. A reliable method that inferences the missing knowledge about the interaction between the machine and the environment from the available data sources, is vital to accurately model the material movement. In this study, a twostep method was implemented that performed unsupervised clustering and then predicted the missing information. The first method is DBSCAN based spatial clustering which divides the diggers and buckets positional data into connected loading segments. Clear patterns of segmented bucket dig positions were observed. The second model utilized Gaussian process regression which was trained with the clustered data and the model was then used to infer the mean locations of the test clusters. Bucket dig locations were then simulated at the inferred mean locations for different durations and compared against the known bucket dig locations. This method was tested at an open pit mine in the Pilbara of Western Australia. The results demonstrate the advantage of the proposed method in inferencing the missing information of bucket environment interactions and therefore enables miners to continuously track the material movement.

The U.K. Government is seemingly backtracking on plans that would have allowed text and data mining "for any purpose," plans designed to position the U.K. as a "global AI superpower." The news emerges following months of blowback from creative industries concerned about what impact the rules might have on protected works. Text and data mining, for the uninitiated, is an essential component of just about every AI application, allowing researchers and developers to leverage disparate datasets to train their algorithms. But gaining access to a sufficient amount of data is not a straight-forward endeavor, given that data is often owned by organizations or individuals that might not want third-parties to have access to their data. Or, they may only make said data available under a commercial license, making it prohibitively expensive to harness.