scholarly journals Tropical Cyclone Intensity Estimation Using Multi-Dimensional Convolutional Neural Networks from Geostationary Satellite Data

2019 ◽  
Vol 12 (1) ◽  
pp. 108 ◽  
Author(s):  
Juhyun Lee ◽  
Jungho Im ◽  
Dong-Hyun Cha ◽  
Haemi Park ◽  
Seongmun Sim
Keyword(s):  
Neural Networks ◽  
Tropical Cyclone ◽  
Convolutional Neural Networks ◽  
Mean Squared Error ◽  
Single Channel ◽  
Three Dimensional ◽  
Geostationary Satellite ◽  
Lower Atmosphere ◽  
Long Time ◽  
3D Cnn

For a long time, researchers have tried to find a way to analyze tropical cyclone (TC) intensity in real-time. Since there is no standardized method for estimating TC intensity and the most widely used method is a manual algorithm using satellite-based cloud images, there is a bias that varies depending on the TC center and shape. In this study, we adopted convolutional neural networks (CNNs) which are part of a state-of-art approach that analyzes image patterns to estimate TC intensity by mimicking human cloud pattern recognition. Both two dimensional-CNN (2D-CNN) and three-dimensional-CNN (3D-CNN) were used to analyze the relationship between multi-spectral geostationary satellite images and TC intensity. Our best-optimized model produced a root mean squared error (RMSE) of 8.32 kts, resulting in better performance (~35%) than the existing model using the CNN-based approach with a single channel image. Moreover, we analyzed the characteristics of multi-spectral satellite-based TC images according to intensity using a heat map, which is one of the visualization means of CNNs. It shows that the stronger the intensity of the TC, the greater the influence of the TC center in the lower atmosphere. This is consistent with the results from the existing TC initialization method with numerical simulations based on dynamical TC models. Our study suggests the possibility that a deep learning approach can be used to interpret the behavior characteristics of TCs.

scholarly journals 3D Dense Convolutional Neural Networks Utilizing Molecular Topological Features for Accurate Atomization Energy Predictions

2021 ◽  
Author(s):  
Ankur Gupta ◽  
Krishnan Raghavachari
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Dimensional Space ◽  
Three Dimensional ◽  
Molecular Geometry ◽  
Topological Features ◽  
Natural Choice ◽  
Proposed Model ◽  
Localized Orbital ◽  
3D Cnn

<p>Deep learning methods provide a novel way to establish a correlation between two quantities. In this context, computer vision techniques like 3D-Convolutional Neural Networks (3D-CNN) become a natural choice to associate a molecular property with its structure due to the inherent three-dimensional nature of a molecule. However, traditional 3D input data structures are intrinsically sparse in nature, which tend to induce instabilities during the learning process, which in turn may lead to under-fitted results. To address this deficiency, in this project, we propose to use quantum-chemically derived molecular topological features, namely, Localized Orbital Locator (LOL) and Electron Localization Function (ELF), as molecular descriptors, which provide a relatively denser input representation in three-dimensional space. Such topological features provide a detailed picture of the atomic configuration and inter-atomic interactions in the molecule and are thus ideal for predicting properties that are highly dependent on molecular geometry. Herein, we demonstrate the efficacy of our proposed model by applying it to the task of predicting atomization energies for the QM9-G4MP2 dataset, which contains ~134-k molecules. Furthermore, we incorporated the Δ-ML approach into our model, allowing us to reach beyond benchmark accuracy levels (~1.0 kJ mol<sup>−1</sup>).<sup> </sup>We consistently obtain impressive MAEs of the order 0.1 kcal mol<sup>−1</sup> (~ 0.42 kJ mol<sup>−1</sup>) <i>versus</i> G4(MP2) theory using relatively modest models, which could potentially be improved further using additional compute resources.</p>

Video Classification Using 3D Convolutional Neural Network

2021 ◽  
pp. 1-18
Author(s):  
K. Jairam Naik ◽  
Annukriti Soni
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Spatial Information ◽  
Three Dimensional ◽  
Classification Problem ◽  
Video Classification ◽  
Convolutional Networks ◽  
3D Cnn ◽  
Deep Learning Neural Network

Since video includes both temporal and spatial features, it has become a fascinating classification problem. Each frame within a video holds important information called spatial information, as does the context of that frame relative to the frames before it in time called temporal information. Several methods have been invented for video classification, but each one is suffering from its own drawback. One of such method is called convolutional neural networks (CNN) model. It is a category of deep learning neural network model that can turn directly on the underdone inputs. However, such models are recently limited to handling two-dimensional inputs only. This chapter implements a three-dimensional convolutional neural networks (CNN) model for video classification to analyse the classification accuracy gained using the 3D CNN model. The 3D convolutional networks are preferred for video classification since they inherently apply convolutions in the 3D space.

scholarly journals 3D Dense Convolutional Neural Networks Utilizing Molecular Topological Features for Accurate Atomization Energy Predictions

2021 ◽  
Author(s):  
Ankur Gupta ◽  
Krishnan Raghavachari
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Dimensional Space ◽  
Three Dimensional ◽  
Molecular Geometry ◽  
Topological Features ◽  
Natural Choice ◽  
Proposed Model ◽  
Localized Orbital ◽  
3D Cnn

<p>Deep learning methods provide a novel way to establish a correlation between two quantities. In this context, computer vision techniques like 3D-Convolutional Neural Networks (3D-CNN) become a natural choice to associate a molecular property with its structure due to the inherent three-dimensional nature of a molecule. However, traditional 3D input data structures are intrinsically sparse in nature, which tend to induce instabilities during the learning process, which in turn may lead to under-fitted results. To address this deficiency, in this project, we propose to use quantum-chemically derived molecular topological features, namely, Localized Orbital Locator (LOL) and Electron Localization Function (ELF), as molecular descriptors, which provide a relatively denser input representation in three-dimensional space. Such topological features provide a detailed picture of the atomic configuration and inter-atomic interactions in the molecule and are thus ideal for predicting properties that are highly dependent on molecular geometry. Herein, we demonstrate the efficacy of our proposed model by applying it to the task of predicting atomization energies for the QM9-G4MP2 dataset, which contains ~134-k molecules. Furthermore, we incorporated the Δ-ML approach into our model, allowing us to reach beyond benchmark accuracy levels (~1.0 kJ mol<sup>−1</sup>).<sup> </sup>We consistently obtain impressive MAEs of the order 0.1 kcal mol<sup>−1</sup> (~ 0.42 kJ mol<sup>−1</sup>) <i>versus</i> G4(MP2) theory using relatively modest models, which could potentially be improved further using additional compute resources.</p>

scholarly journals Generation and Annotation of Simulation-Real Ship Images for Convolutional Neural Networks Training and Testing

2021 ◽  
Vol 11 (13) ◽  
pp. 5931
Author(s):  
Ji’an You ◽  
Zhaozheng Hu ◽  
Chao Peng ◽  
Zhiqiang Wang
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Image Annotation ◽  
Three Dimensional ◽  
Image Data ◽  
Detection Algorithm ◽  
Simulation Software ◽  
High Quality ◽  
Annotation Method ◽  
Detection Of Objects

Large amounts of high-quality image data are the basis and premise of the high accuracy detection of objects in the field of convolutional neural networks (CNN). It is challenging to collect various high-quality ship image data based on the marine environment. A novel method based on CNN is proposed to generate a large number of high-quality ship images to address this. We obtained ship images with different perspectives and different sizes by adjusting the ships’ postures and sizes in three-dimensional (3D) simulation software, then 3D ship data were transformed into 2D ship image according to the principle of pinhole imaging. We selected specific experimental scenes as background images, and the target ships of the 2D ship images were superimposed onto the background images to generate “Simulation–Real” ship images (named SRS images hereafter). Additionally, an image annotation method based on SRS images was designed. Finally, the target detection algorithm based on CNN was used to train and test the generated SRS images. The proposed method is suitable for generating a large number of high-quality ship image samples and annotation data of corresponding ship images quickly to significantly improve the accuracy of ship detection. The annotation method proposed is superior to the annotation methods that label images with the image annotation software of Label-me and Label-img in terms of labeling the SRS images.

scholarly journals Identification of Mode Shapes of a Composite Cylinder Using Convolutional Neural Networks

Materials ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 2801
Author(s):  
Bartosz Miller ◽  
Leonard Ziemiański
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Composite Structures ◽  
Three Dimensional ◽  
Mode Shapes ◽  
Identification Algorithm ◽  
Material Degradation ◽  
Local Material ◽  
Noisy Input ◽  
Shape Vector

The aim of the following paper is to discuss a newly developed approach for the identification of vibration mode shapes of multilayer composite structures. To overcome the limitations of the approaches based on image analysis (two-dimensional structures, high spatial resolution of mode shapes description), convolutional neural networks (CNNs) are applied to create a three-dimensional mode shapes identification algorithm with a significantly reduced number of mode shape vector coordinates. The CNN-based procedure is accurate, effective, and robust to noisy input data. The appearance of local damage is not an obstacle. The change of the material and the occurrence of local material degradation do not affect the accuracy of the method. Moreover, the application of the proposed identification method allows identifying the material degradation occurrence.

scholarly journals Tree Species Classification of Drone Hyperspectral and RGB Imagery with Deep Learning Convolutional Neural Networks

2020 ◽  
Vol 12 (7) ◽  
pp. 1070 ◽  
Author(s):  
Somayeh Nezami ◽  
Ehsan Khoramshahi ◽  
Olli Nevalainen ◽  
Ilkka Pölönen ◽  
Eija Honkavaara
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Tree Species ◽  
Classification Accuracy ◽  
Performance Metrics ◽  
Test Site ◽  
Biomass Estimation ◽  
Species Classification ◽  
Tree Species Classification ◽  
3D Cnn

Interest in drone solutions in forestry applications is growing. Using drones, datasets can be captured flexibly and at high spatial and temporal resolutions when needed. In forestry applications, fundamental tasks include the detection of individual trees, tree species classification, biomass estimation, etc. Deep neural networks (DNN) have shown superior results when comparing with conventional machine learning methods such as multi-layer perceptron (MLP) in cases of huge input data. The objective of this research is to investigate 3D convolutional neural networks (3D-CNN) to classify three major tree species in a boreal forest: pine, spruce, and birch. The proposed 3D-CNN models were employed to classify tree species in a test site in Finland. The classifiers were trained with a dataset of 3039 manually labelled trees. Then the accuracies were assessed by employing independent datasets of 803 records. To find the most efficient set of feature combination, we compare the performances of 3D-CNN models trained with hyperspectral (HS) channels, Red-Green-Blue (RGB) channels, and canopy height model (CHM), separately and combined. It is demonstrated that the proposed 3D-CNN model with RGB and HS layers produces the highest classification accuracy. The producer accuracy of the best 3D-CNN classifier on the test dataset were 99.6%, 94.8%, and 97.4% for pines, spruces, and birches, respectively. The best 3D-CNN classifier produced ~5% better classification accuracy than the MLP with all layers. Our results suggest that the proposed method provides excellent classification results with acceptable performance metrics for HS datasets. Our results show that pine class was detectable in most layers. Spruce was most detectable in RGB data, while birch was most detectable in the HS layers. Furthermore, the RGB datasets provide acceptable results for many low-accuracy applications.

Sign in / Sign up

Export Citation Format

Share Document