Nanosecond Photodynamics Simulations of a Cis-Trans Isomerization Are Enabled by Machine Learning

2020 ◽  
Author(s):  
Jingbai Li ◽  
Patrick Reiser ◽  
André Eberhard ◽  
Pascal Friederich ◽  
Steven Lopez
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Excited State ◽  
Adaptive Sampling ◽  
Computational Cost ◽  
Ground Truth ◽  
Absolute Error ◽  
Photochemical Reactions ◽  
Computational Techniques ◽  
Full Potential

<p>Photochemical reactions are being increasingly used to construct complex molecular architectures with mild and straightforward reaction conditions. Computational techniques are increasingly important to understand the reactivities and chemoselectivities of photochemical isomerization reactions because they offer molecular bonding information along the excited-state(s) of photodynamics. These photodynamics simulations are resource-intensive and are typically limited to 1–10 picoseconds and 1,000 trajectories due to high computational cost. Most organic photochemical reactions have excited-state lifetimes exceeding 1 picosecond, which places them outside possible computational studies. Westermeyr <i>et al.</i> demonstrated that a machine learning approach could significantly lengthen photodynamics simulation times for a model system, methylenimmonium cation (CH<sub>2</sub>NH<sub>2</sub><sup>+</sup>).</p><p>We have developed a Python-based code, Python Rapid Artificial Intelligence <i>Ab Initio</i> Molecular Dynamics (PyRAI<sup>2</sup>MD), to accomplish the unprecedented 10 ns <i>cis-trans</i> photodynamics of <i>trans</i>-hexafluoro-2-butene (CF<sub>3</sub>–CH=CH–CF<sub>3</sub>) in 3.5 days. The same simulation would take approximately 58 years with ground-truth multiconfigurational dynamics. We proposed an innovative scheme combining Wigner sampling, geometrical interpolations, and short-time quantum chemical trajectories to effectively sample the initial data, facilitating the adaptive sampling to generate an informative and data-efficient training set with 6,232 data points. Our neural networks achieved chemical accuracy (mean absolute error of 0.032 eV). Our 4,814 trajectories reproduced the S<sub>1</sub> half-life (60.5 fs), the photochemical product ratio (<i>trans</i>: <i>cis</i> = 2.3: 1), and autonomously discovered a pathway towards a carbene. The neural networks have also shown the capability of generalizing the full potential energy surface with chemically incomplete data (<i>trans</i> → <i>cis</i> but not <i>cis</i> → <i>trans</i> pathways) that may offer future automated photochemical reaction discoveries.</p>

Nanosecond Photodynamics Simulations of a Cis-Trans Isomerization Are Enabled by Machine Learning

2020 ◽  
Author(s):  
Jingbai Li ◽  
Patrick Reiser ◽  
André Eberhard ◽  
Pascal Friederich ◽  
Steven Lopez
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Excited State ◽  
Adaptive Sampling ◽  
Computational Cost ◽  
Ground Truth ◽  
Absolute Error ◽  
Photochemical Reactions ◽  
Computational Techniques ◽  
Full Potential

<p>Photochemical reactions are being increasingly used to construct complex molecular architectures with mild and straightforward reaction conditions. Computational techniques are increasingly important to understand the reactivities and chemoselectivities of photochemical isomerization reactions because they offer molecular bonding information along the excited-state(s) of photodynamics. These photodynamics simulations are resource-intensive and are typically limited to 1–10 picoseconds and 1,000 trajectories due to high computational cost. Most organic photochemical reactions have excited-state lifetimes exceeding 1 picosecond, which places them outside possible computational studies. Westermeyr <i>et al.</i> demonstrated that a machine learning approach could significantly lengthen photodynamics simulation times for a model system, methylenimmonium cation (CH<sub>2</sub>NH<sub>2</sub><sup>+</sup>).</p><p>We have developed a Python-based code, Python Rapid Artificial Intelligence <i>Ab Initio</i> Molecular Dynamics (PyRAI<sup>2</sup>MD), to accomplish the unprecedented 10 ns <i>cis-trans</i> photodynamics of <i>trans</i>-hexafluoro-2-butene (CF<sub>3</sub>–CH=CH–CF<sub>3</sub>) in 3.5 days. The same simulation would take approximately 58 years with ground-truth multiconfigurational dynamics. We proposed an innovative scheme combining Wigner sampling, geometrical interpolations, and short-time quantum chemical trajectories to effectively sample the initial data, facilitating the adaptive sampling to generate an informative and data-efficient training set with 6,232 data points. Our neural networks achieved chemical accuracy (mean absolute error of 0.032 eV). Our 4,814 trajectories reproduced the S<sub>1</sub> half-life (60.5 fs), the photochemical product ratio (<i>trans</i>: <i>cis</i> = 2.3: 1), and autonomously discovered a pathway towards a carbene. The neural networks have also shown the capability of generalizing the full potential energy surface with chemically incomplete data (<i>trans</i> → <i>cis</i> but not <i>cis</i> → <i>trans</i> pathways) that may offer future automated photochemical reaction discoveries.</p>

scholarly journals CircConv: A Structured Convolution with Low Complexity

2019 ◽  
Vol 33 ◽  
pp. 4287-4294
Author(s):  
Siyu Liao ◽  
Bo Yuan
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Computational Cost ◽  
Low Complexity ◽  
Deep Convolutional Neural Networks ◽  
Significant Saving ◽  
Machine Learning Applications ◽  
Fast Multiplication ◽  
Large Model

Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications. However, the large model sizes of DNNs yield high demands on computation resource and weight storage, thereby limiting the practical deployment of DNNs. To overcome these limitations, this paper proposes to impose the circulant structure to the construction of convolutional layers, and hence leads to circulant convolutional layers (CircConvs) and circulant CNNs. The circulant structure and models can be either trained from scratch or re-trained from a pre-trained non-circulant model, thereby making it very flexible for different training environments. Through extensive experiments, such strong structureimposing approach is proved to be able to substantially reduce the number of parameters of convolutional layers and enable significant saving of computational cost by using fast multiplication of the circulant tensor.

New insights on the ESIPT process based on solid-state data and state-of-the-art computational methods

2021 ◽  
Author(s):  
Jean Nunes Laner ◽  
Henrique de Castro Silva Junior ◽  
Fabiano Severo Rodembusch ◽  
Eduardo Ceretta Moreira
Keyword(s):  
Excited State ◽  
Solid State ◽  
Proton Transfer ◽  
State Of The Art ◽  
Computational Cost ◽  
Intramolecular Proton Transfer ◽  
High Accuracy ◽  
Computational Techniques ◽  
Vibrational Properties ◽  
State Data

Updated computational techniques to investigate the excited-state intramolecular proton transfer (ESIPT) process obtaining theoretical electronic and vibrational properties in the solid-state with high accuracy at a small computational cost.

scholarly journals Automated lumen segmentation using multi-frame convolutional neural networks in intravascular ultrasound datasets

2020 ◽  
Vol 1 (1) ◽  
pp. 75-82
Author(s):  
Paulo G P Ziemer ◽  
Carlos A Bulant ◽  
José I Orlando ◽  
Gonzalo D Maso Talou ◽  
Luis A Mansilla Álvarez ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Intravascular Ultrasound ◽  
Ground Truth ◽  
Lumen Area ◽  
Manual Delineation ◽  
Trained Personnel ◽  
Lumen Segmentation ◽  
Automated Pipeline

Abstract Aims Assessment of minimum lumen areas in intravascular ultrasound (IVUS) pullbacks is time-consuming and demands adequately trained personnel. In this work, we introduce a novel and fully automated pipeline to segment the lumen boundary in IVUS datasets. Methods and results First, an automated gating is applied to select end-diastolic frames and bypass saw-tooth artefacts. Second, within a machine learning (ML) environment, we automatically segment the lumen boundary using a multi-frame (MF) convolutional neural network (MFCNN). Finally, we use the theory of Gaussian processes (GPs) to regress the final lumen boundary. The dataset consisted of 85 IVUS pullbacks (52 patients). The dataset was partitioned at the pullback-level using 73 pullbacks for training (20 586 frames), 6 pullbacks for validation (1692 frames), and 6 for testing (1692 frames). The degree of overlapping, between the ground truth and ML contours, median (interquartile range, IQR) systematically increased from 0.896 (0.874–0.933) for MF1 to 0.925 (0.911–0.948) for MF11. The median (IQR) of the distance error was also reduced from 3.83 (2.94–4.98)% for MF1 to 3.02 (2.25–3.95)% for MF11-GP. The corresponding median (IQR) in the lumen area error remained between 5.49 (2.50–10.50)% for MF1 and 5.12 (2.15–9.00)% for MF11-GP. The dispersion in the relative distance and area errors consistently decreased as we increased the number of frames, and also when the GP regressor was coupled to the MFCNN output. Conclusion These results demonstrate that the proposed ML approach is suitable to effectively segment the lumen boundary in IVUS scans, reducing the burden of costly and time-consuming manual delineation.

scholarly journals Improved Training of Deep Convolutional Networks via Minimum-Variance Regularized Adaptive Sampling

2021 ◽  
Author(s):  
Alfonso Rojas-Domínguez ◽  
Ivvan Valdez ◽  
Manuel Ornelas-Rodríguez ◽  
Martín Carpio
Keyword(s):  
Neural Networks ◽  
Adaptive Sampling ◽  
Sampling Method ◽  
Deep Neural Networks ◽  
Computational Cost ◽  
Stochastic Gradient Descent ◽  
Experimental Comparison ◽  
Great Success ◽  
Convolutional Networks ◽  
Training Examples

Abstract Fostered by technological and theoretical developments, deep neural networks have achieved great success in many applications, but their training by means of mini-batch stochastic gradient descent (SGD) can be very costly due to the possibly tens of millions of parameters to be optimized and the large amounts of training examples that must be processed. Said computational cost is exacerbated by the inefficiency of the uniform sampling method typically used by SGD to form the training mini-batches: since not all training examples are equally relevant for training, sampling these under a uniform distribution is far from optimal. A better strategy is to form the mini-batches by sampling the training examples under a distribution where the probability of being selected is proportional to the relevance of each individual example. This can be achieved through Importance Sampling (IS), which also achieves the minimization of the gradients’ variance w.r.t. the network parameters, further improving convergence. In this paper, an IS-based adaptive sampling method is studied that exploits side information to construct the required probability distribution. Said method is modified to enable its application to deep neural networks, and the improved method is dubbed Regularized Adaptive Sampling (RAS). Experimental comparison (using deep convolutional networks for classification of the MNIST and CIFAR-10 datasets) of RAS against SGD and against another sampling method in the state of the art, shows that RAS achieves relative improvements of the training process, without incurring significant overhead or affecting the accuracy of the networks.

scholarly journals An End-to-End Machine Learning based Unified Architecture for Non-Intrusive Load Monitoring

2021 ◽  
Vol 11 (3) ◽  
pp. 7217-7222
Author(s):  
S. Wali ◽  
M. H. U. Haq ◽  
M. Kazmi ◽  
S. A. Qazi
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Power Consumption ◽  
Computational Cost ◽  
Absolute Error ◽  
Load Monitoring ◽  
Load Disaggregation ◽  
End To End ◽  
Cost Efficient ◽  
Gated Recurrent Units

Non-Intrusive Load Monitoring (NILM) or load disaggregation aims to analyze power consumption by decomposing the energy measured at the aggregate level into constituent appliances level. The conventional load disaggregation framework consists of signal processing and machine learning-based pipelined architectures, respectively for explicit feature extraction and decision making. Manual feature selection in such load disaggregation frameworks leads to biased decisions that eventually reduce system performance. This paper presents an efficient End-to-End (E2E) approach-based unified architecture using Gated Recurrent Units (GRU) for NILM. The proposed approach eliminates explicit feature engineering and has a unified classification and prediction model for appliance power. This eventually reduces the computational cost and enhances response time. The performance of the proposed system is compared with conventional algorithms' with the use of recall, precision, accuracy, F1 score, the relative error in total energy and Mean Absolute Error (MAE). These evaluation metrics are calculated on the power consumption of top priority appliances of Reference Energy Disaggregation Dataset (REDD). The proposed architecture with an overall accuracy of 91.2 and MAE of 25.23 outperforms conventional methods for all electrical appliances. It has been showcased through a series of experiments that feature extraction and event-based approaches for NILM can readily be replaced with E2E deep learning techniques allowing simpler and cost-efficient implementation pathways.

scholarly journals Stacked Ensemble Machine Learning for Range-Separation Parameters

2021 ◽  
Author(s):  
Cheng-Wei Ju ◽  
Ethan French ◽  
Nadav Geva ◽  
Alexander Kohn ◽  
Zhou Lin
Keyword(s):  
Machine Learning ◽  
First Principles ◽  
Density Functional ◽  
Computational Cost ◽  
Structural Diversity ◽  
Absolute Error ◽  
Hartree Fock ◽  
Separation Parameter ◽  
Ensemble Machine Learning ◽  
Organic Semiconducting Molecules

High-throughput virtual materials and drug discovery based on density functional theory has achieved tremendous success in recent decades, but its power on organic semiconducting molecules suffered catastrophically from the self-interaction error until the optimally tuned range-separated hybrid (OT-RSH) exchange-correlation functionals were developed. The accurate but expensive �first-principles OT-RSH transitions from a short-range (semi-)local functional to a long-range Hartree-Fock exchange at a distance characterized by the inverse of a molecule-specific, non-empirically-determined range-separation parameter (ω). In the present study, we proposed a promising stacked ensemble machine learning (SEML) model that provides an accelerated alternative of OT-RSH based on system-dependent structural and electronic configurations. We trained ML-ωPBE, the first functional in our series, using a database of 1,970 organic semiconducting molecules with sufficient structural diversity, and assessed its accuracy and efficiency using another 1,956 molecules. Compared with the �first-principles OT-ωPBE, our ML-ωPBE reached a mean absolute error of 0:00504a_0^{-1} for the optimal value of ω, reduced the computational cost for the test set by 2.66 orders of magnitude, and achieved comparable predictive powers in various optical properties.

Machine Learning Techniques for Estimating Amount of Coolant Required in Shipping of Temperature Sensitive Products

2020 ◽  
Vol 10 (10) ◽  
pp. 67-70
Author(s):  
Divya Choudhary ◽  
Siripong Malasri
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Absolute Error ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Threshold Temperature ◽  
Support Vector ◽  
Temperature Sensitive ◽  
Learning Techniques ◽  
The Neural Networks

This paper implements and compares machine learning algorithms to predict the amount of coolant required during transportation of temperature sensitive products. The machine learning models use trip duration, product threshold temperature and ambient temperature as the independent variables to predict the weight of gel packs need to keep the temperature of the product below its threshold temperature value. The weight of the gel packs can be translated to number of gel packs required. Regression using Neural Networks, Support Vector Regression, Gradient Boosted Regression and Elastic Net Regression are compared. The Neural Networks based model performs the best in terms of its mean absolute error value and r-squared values. A Neural Network model is then deployed on as webservice to score allowing for client application to make rest calls to estimate gel pack weights

scholarly journals Artificial Neural Networks and Machine Learning techniques applied to Ground Penetrating Radar: A review

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Xisto L. Travassos ◽  
Sérgio L. Avila ◽  
Nathan Ida
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Ground Penetrating Radar ◽  
Data Interpretation ◽  
Machine Learning Techniques ◽  
Computational Techniques ◽  
Data Detection ◽  
Artificial Neural ◽  
Ground Penetrating

Ground Penetrating Radar is a multidisciplinary Nondestructive Evaluation technique that requires knowledge of electromagnetic wave propagation, material properties and antenna theory. Under some circumstances this tool may require auxiliary algorithms to improve the interpretation of the collected data. Detection, location and definition of target’s geometrical and physical properties with a low false alarm rate are the objectives of these signal post-processing methods. Basic approaches are focused in the first two objectives while more robust and complex techniques deal with all objectives at once. This work reviews the use of Artificial Neural Networks and Machine Learning for data interpretation of Ground Penetrating Radar surveys. We show that these computational techniques have progressed GPR forward from locating and testing to imaging and diagnosis approaches.

scholarly journals Principal Component Analysis and Machine Learning Approaches for Photovoltaic Power Prediction: A Comparative Study

2021 ◽  
Vol 11 (17) ◽  
pp. 7943
Author(s):  
Souhaila Chahboun ◽  
Mohamed Maaroufi
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Industrial Revolution ◽  
Performance Metrics ◽  
Principal Component ◽  
Support Vector ◽  
Full Potential ◽  
Learning Approaches ◽  
Power Prediction ◽  
Intelligent Sensors

Nowadays, in the context of the industrial revolution 4.0, considerable volumes of data are being generated continuously from intelligent sensors and connected objects. The proper understanding and use of these amounts of data are crucial levers of performance and innovation. Machine learning is the technology that allows the full potential of big datasets to be exploited. As a branch of artificial intelligence, it enables us to discover patterns and make predictions from data based on statistics, data mining, and predictive analysis. The key goal of this study was to use machine learning approaches to forecast the hourly power produced by photovoltaic panels. A comparison analysis of various predictive models including elastic net, support vector regression, random forest, and Bayesian regularized neural networks was carried out to identify the models providing the best predicting results. The principal components analysis used to reduce the dimensionality of the input data revealed six main factor components that could explain up to 91.95% of the variation in all variables. Finally, performance metrics demonstrated that Bayesian regularized neural networks achieved the best results, giving an accuracy of R2 = 99.99% and RMSE = 0.002 kW.

Sign in / Sign up

Export Citation Format

Share Document