Intensity Estimation Method Research Articles

Cyclone Intensity Estimation Using Deep Learning

Cyclone Intensity Estimation based on Deep Learning focuses on cyclone intensity estimation, enhancing early warning systems and empowering decision-makers to take proactive measures to safeguard vulnerable communities and infrastructure, which aims to minimize the devastating impacts of cyclones worldwide. The challenge in cyclone intensity prediction persists due to the complex and dynamic nature of these storms. Traditional methods fall short of capturing rapid changes. This research project leverages the power of deep learning to enhance the accuracy of cyclone intensity prediction by utilizing both satellite images and grayscale representations as input datasets. It involves preprocessing and feature extraction from satellite images captured during cyclonic events. Convolutional Neural Networks (CNN) are employed to automatically learn and extract relevant patterns from these complex datasets. In parallel, grayscale images derived from the original satellite images are utilized to capture essential structure information that contributes to cyclone intensity. The fusion of information from both modalities is achieved through a novel deep learning patterns that go beyond the capabilities of traditional intensity estimation methods, and architecture, fostering a comprehensive understanding of cyclonic patterns that go beyond the capabilities of traditional intensity estimation methods. A new approach seeks to automate cyclone estimation, streamlining timelines and increasing efficiency by merging deep learning with hurricane-focused satellite data. This approach might result in more precise forecasts, Reducing the amount of casualties and property damage in prone areas.

Bridging satellite missions: deep transfer learning for enhanced tropical cyclone intensity estimation

ABSTRACT Geostationary satellites are valuable tools for monitoring the entire lifetime of tropical cyclones (TCs). Although the most widely used method for TC intensity estimation is manual, several automatic methods, particularly artificial intelligence (AI)-based algorithms, have been proposed and have achieved significant performance. However, AI-based techniques often require large amounts of input data, making it challenging to adopt newly introduced data such as those from recently launched satellites. This study proposed a transfer-learning-based TC intensity estimation method to combine different source data. The pre-trained model was built using the Swin Transformer (Swin-T) model, utilizing data from the Communication Ocean and Meteorological Satellite Meteorological Imager sensor, which has been in operation for an extensive period (2011–2021) and provides a large dataset. Subsequently, a transfer learning model was developed by fine-tuning the pre-trained model using the GEO-KOMPSAT-2A Advanced Meteorological Imager, which has been operational since 2019. The transfer learning approach was tested in three different ways depending on the fine-tuning ratio, with the optimal performance achieved when all layers were fine-tuned. The pre-trained model employed TC observations from 2011 to 2017 for training and 2018 for testing, whereas the transfer learning model utilized data from 2019 and 2020 for training and 2021 for testing to evaluate the model performance. The best pre-trained and transfer learning models achieved mean absolute error of 6.46 kts and 6.48 kts, respectively. Our proposed model showed a 7–52% improvement compared to the control models without transfer learning. This implies that the transfer learning approach for TC intensity estimation using different satellite observations is significant. Moreover, by employing a deep learning model visualization approach known as Eigen-class activation map, the spatial characteristics of the developed model were validated according to the intensity levels. This analysis revealed features corresponding to the Dvorak technique, demonstrating the interpretability of the Swin-T-based TC intensity estimation algorithm. This study successfully demonstrated the effectiveness of transfer learning in developing a deep learning-based TC intensity estimation model for newly acquired data.

Video2Haptics: Converting Video Motion to Dynamic Haptic Feedback with Bio-Inspired Event Processing.

In cinematic VR applications, haptic feedback can significantly enhance the sense of reality and immersion for users. The increasing availability of emerging haptic devices opens up possibilities for future cinematic VR applications that allow users to receive haptic feedback while they are watching videos. However, automatically rendering haptic cues from real-time video content, particularly from video motion, is a technically challenging task. In this paper, we propose a novel framework called "Video2Haptics" that leverages the emerging bio-inspired event camera to capture event signals as a lightweight representation of video motion. We then propose efficient event-based visual processing methods to estimate force or intensity from video motion in the event domain, rather than the pixel domain. To demonstrate the application of Video2Haptics, we convert the estimated force or intensity to dynamic vibrotactile feedback on emerging haptic gloves, synchronized with the corresponding video motion. As a result, Video2Haptics allows users not only to view the video but also to perceive the video motion concurrently. Our experimental results show that the proposed event-based processing methods for force and intensity estimation are one to two orders of magnitude faster than conventional methods. Our user study results confirm that the proposed Video2Haptics framework can considerably enhance the users' video experience.

Assessing Consciousness in Patients With Disorders of Consciousness Using a Facial Action Unit Intensity Estimation Method Based on a Hybrid Similar Feature Network

Assessing Consciousness in Patients With Disorders of Consciousness Using a Facial Action Unit Intensity Estimation Method Based on a Hybrid Similar Feature Network

Predicting Short-Term Intensity Change in Tropical Cyclones Using a Convolutional Neural Network

Abstract This study details a two-method, machine learning approach to predict current and short-term intensity change in global tropical cyclones (TCs), “D-MINT” and “D-PRINT.” D-MINT and D-PRINT use infrared imagery and environmental scalar predictors, while D-MINT also employs microwave imagery. Results show that current TC intensity estimates from D-MINT and D-PRINT are more skillful than three established intensity estimation methods routinely used by operational forecasters for North Atlantic and eastern and western North Pacific TCs. Short-term intensity predictions are validated against five operational deterministic guidances at 6-, 12-, 18-, and 24-h lead times. D-MINT and D-PRINT are less skillful than NHC and consensus TC intensity predictions in North Atlantic and eastern North Pacific TCs, but are more skillful than the other guidances for at least half of the lead times. In western North Pacific, north Indian Ocean, and Southern Hemisphere TCs, D-MINT is more skillful than the JTWC and other individual TC intensity forecasts for over half of the lead times. When probabilistically predicting TC rapid intensification (RI), D-MINT is more skillful in North Atlantic and western North Pacific TCs than three operationally used RI guidances, but less skillful for yes–no RI forecasts. In addition, this work demonstrates the importance of microwave imagery, as D-MINT is more skillful than D-PRINT. Since D-MINT and D-PRINT are convolutional neural network models interrogating two-dimensional structures within TC satellite imagery, this study also demonstrates that those features can yield better short-term predictions than existing scalar statistics of satellite imagery in operational models. Finally, a diagnostics tool is revealed to aid the attribution of the D-MINT/D-PRINT intensity predictions. Significance Statement This study develops a method to predict current and short-term forecasts of tropical cyclone (TC) intensity using artificial intelligence. The resultant models use a convolutional neural network (CNN) that can identify two-dimensional features in satellite imagery that are indicative of TC intensity and future intensity change. The performance results indicate that in several TC basins, the CNN approach is generally more skillful than alternative satellite-based estimates of TC intensity as well as operational short-term forecasts of deterministic intensity change and of similar skill to probabilistic rapid intensification forecasts.

Estimating tropical cyclone intensity using dynamic balance convolutional neural network from satellite imagery

Accurate estimation of tropical cyclone (TC) intensity helps to understand the evolution of TCs throughout their life cycle and plays an essential role in mitigating TC impact. Although TC intensity estimation methods based on deep learning have made significant progress, the existing techniques do not apply good methods to overcome the intensity overestimation and underestimation problems caused by the unbalanced distribution of TC data. Therefore, we propose a dynamic balance convolutional neural network to overcome these issues. The model consists of two branches, one branch is the learning of the raw data, and the other is the learning of strong (weak) TCs that account for a few data samples. Finally, the model is dynamically adjusted by adaptive trade-off parameters, gradually from the learning of the raw data to the learning of strong (weak) TCs, thus reducing errors in underestimation (overestimation) of strong (weak) TCs. Furthermore, an attention mechanism is employed to obtain the correlation between channels to improve the accuracy of TC intensity estimation further. We used globally 1285 TC cases from 2003–2016 to train the model and globally 94 TC cases from 2017 as independent test data. The results showed that the root-mean-square error of TC intensity estimation was 8.32 kt, 35% lower than that of the advanced Dvorak technique and 26% lower than that of the deep learning method visual geometry group (VGG). For a subset of 482 samples (from East Pacific and Atlantic) analyzed with reconnaissance observations, a root-mean-square intensity difference of 7.95 kt is achieved. Finally, we explored the model’s feature learning process and the contribution of each component of the satellite image to the TC intensity estimation through model visualization.

DICE: An open-source MATLAB application for quantification and parametrization of digital outcrop model-based fracture datasets

An open-source MATLAB application (app) named Discontinuity Intensity Calculator and Estimator (DICE) was developed in order to quantitatively characterize the fractures, or in more general, discontinuities within a rocky outcrop in three-dimensional (3D) digital data, such as digital outcrop model (DOM). The workflow proposed for the parametrization of the discontinuities consists of the following steps: (1) Analysis and mapping of the fractures detected within the 3D DOMs; (2) Calculation of the orientation, position and dimensions of discontinuities that are represented by best-fit circular planes; (3) Determining the discontinuity parameters (dimension, distribution, spacing and intensity) by the DICE algorithm using different 3D oriented sampling techniques (3D oriented scanline, 3D oriented circular scan window and spherical scan volume). Different sampling methods were bench tested with a synthetic, as well as a natural case study, and compared in order to understand the advantages and limitations of each technique. The 3D oriented circular scan window appears to be the most effective method for fracture intensity estimation with high accuracy (error 0.4%) and stability with variations in scan radius.

DMANet_KF: Tropical Cyclone Intensity Estimation Based on Deep Learning and Kalman Filter From Multispectral Infrared Images

It is very crucial to identify the intensity of tropical cyclone (TC) accurately. In this article, a novel TC intensity estimation method is proposed to estimate the TC intensity from multispectral infrared images in the Northwest Pacific Basin. A deep multisource attention network (DMANet) is proposed to model the dynamics of multispectral infrared images along the spatial dimension. We first introduce a message-passing enhancement module based on the conditional random fields to process multispectral infrared images. Multispectral data transfer the complementary information to refine the features of TC. Second, we utilize a local global attention module to make the model focus on local key features (i.e., the typhoon eye) and obtain deeper global semantic information of TC. The ablation experiment is set up in the same dataset and computing environment to verify the effectiveness of each module. Finally, we use a Kalman filter to correct the error of TC intensity during its lifetime estimated by the DMANet model. After using Kalman filter, the evolution of TC intensity becomes smooth and corresponding root-mean-square error (RMSE) decreases from 9.79 to 7.82 knots. Compared with the best result of the existing TC intensity estimation method, the RMSE of our method is reduced by 9.07%. Therefore, the proposed TC intensity estimation method shows a great potential for accurately estimating the TC intensity.

A Detectable Candidate for the YORP Effect of Asteroids

The YORP (Yarkovsky-O’Keefe-Radzievskii-Paddack) effect is one of the mechanisms of the long-term dynamical evolution of asteroids. Compared with factors such as collision and gravitational perturbation, the YORP is of small magnitude, and the short-time scale observation effect is inconspicuous, which brings great difficulties to the direct measurement of the YORP. From the Asteroid Lightcurve Database, asteroids having a high confidence rotation period were selected for this study. Two subsample groups for identifying potential asteroids slowed by the YORP effect are provided by using the kernel density estimation method and the Kolmogorov-Smirnov test to analyze the rotation rate distribution characteristics of near-Earth asteroids and main belt asteroids; a screening model is proposed based on the light-curve data of seven YORP asteroids with YORP rotation acceleration, combined with the YORP intensity estimation method and the detection conditions of the YORP effect. Finally, ten candidates that can directly detect the YORP effect through light-curve data in the future are listed based on the screening model.

Automatic flower cluster estimation in apple orchards using aerial and ground based point clouds

Chemical and mechanical thinning processes have long been used in stone and pome fruit production. During the thinning of apple flowers, growers use chemicals to regulate the tree load. Hand thinning is applied after the June drop to prune trees with excess crop load. The process of thinning can be unpredictable especially in biennial bearing cultivars. Thus, incentives to optimise chemical usage and to reduce expensive manual labour is ever increasing. Ground based machine vision systems have grown in popularity in orchard management due to the level of detail as well as plant coverage they can inspect with. Additionally, unmanned aerial vehicles (UAV) -based remote sensing technology is becoming a popular non-invasive quality inspection solution. This work proposes a framework for combining UAV and ground based RGB image data to detect flowering intensity in a Dutch Elstar apple orchard. The framework, based on point cloud reconstruction, presents automatic point cloud handling techniques as well as automated unsupervised flowering intensity estimation methods. Two linear regression models based on unsupervised machine learning methods were trained and validated from the framework that estimate flowering intensity in the orchard with both models having R 2 > 0.65, RRMSE < 20% and p-stat < 0.005 for the correlation between the image derived flower index and the flower cluster number counted in field. The proposed methods provide a novel strategy for guiding flower thinning using simple RGB images and location data only. Moreover, the proposed methods also reveal the flexibility of intra-tree inspection by checking its sub-volumes. • Automatic flower cluster estimation at the tree level with a R 2 = 0.7, RMSE < 20. • Ground and aerial point clouds have better performance when combined. • Novel strategy developed for guiding flower thinning in orchard management. • Dataset with aerial and ground images, and field sampling data released.

Facial Action Unit Detection Using Attention and Relation Learning

Attention mechanism has recently attracted increasing attentions in the field of facial action unit (AU) detection. By finding the region of interest of each AU with the attention mechanism, AU-related local features can be captured. Most of the existing attention based AU detection works use prior knowledge to predefine fixed attentions or refine the predefined attentions within a small range, which limits their capacity to model various AUs. In this paper, we propose an end-to-end deep learning based attention and relation learning framework for AU detection with only AU labels, which has not been explored before. In particular, multi-scale features shared by each AU are learned first, and then both channel-wise and spatial attentions are adaptively learned to select and extract AU-related local features. Moreover, pixel-level relations for AUs are further captured to refine spatial attentions so as to extract more relevant local features. Without changing the network architecture, our framework can be easily extended for AU intensity estimation. Extensive experiments show that our framework (i) soundly outperforms the state-of-the-art methods for both AU detection and AU intensity estimation on the challenging BP4D, DISFA, FERA 2015, and BP4D+ benchmarks, (ii) can adaptively capture the correlated regions of each AU, and (iii) also works well under severe occlusions and large poses.

Cloud Physical and Climatological Factors for the Determination of Rain Intensity

The focus of this research is to develop a general method for estimation of rain intensity for application in various geographical regions. In a world with a changing climate, a high importance is attributed to the potential threats caused by increased temperature and rainfall intensity levels. The rainfall intensity climate is here interpreted by a combination of cloud physical factors affecting rain intensity and further developed by the use of climate data and rain intensity statistics. A formula was developed that estimates extreme rainfall and the frequency of these extremes with durations in the intervals of 5 min to 24 h. The obtained estimates are compared in this article with results from statistical methods for the extreme value analysis of measurements. The comparison shows about 90% of the explained variance. The coefficients in the formula are connected with climatological predictors based on the climatological norms of temperature and rainfall. Rain intensity maps over Sweden were produced using the developed formula. Examples of the function of the formula are also given for six European countries. The application of the formula in connection with the probable maximum precipitation (PMP) is presented, where the return period of extreme rainfall is a key factor. The formula is tested with an assumed increased warming of the atmosphere of 1 to 5 °C, and the result indicates an increase of 5.9% of the rainfall amount per each warming degree in intense rainfall.

Electric and Magnetic Field Estimation Under Overhead Transmission Lines Using Artificial Neural Networks

In this paper, a novel method for electric field intensity and magnetic flux density estimation in the vicinity of the high voltage overhead transmission lines is proposed. The proposed method is based on two fully connected feed-forward neural networks to independently estimate electric field intensity and magnetic flux density. The artificial neural networks are trained using the scaled conjugate gradient algorithm. Training datasets corresponds to different overhead transmission line configurations that are generated using an algorithm that is especially developed for this purpose. The target values for the electric field intensity and magnetic flux density datasets are calculated using the charge simulation method and Biot-Savart law based method, respectively. This data is generated for fixed applied voltage and current intensity values. In instances when the applied voltage and current intensity values differ from those used in the artificial neural network training, the electric field intensity and magnetic flux density results are appropriately scaled. In order to verify the validity of the proposed method, a comparative analysis of the proposed method with the charge simulation method for electric field intensity calculation and Biot-Savart law-based method for magnetic flux density calculation is presented. Furthermore, the results of the proposed method are compared to measurement results obtained in the vicinity of two 400 kV transmission lines. The performance analysis results showed that proposed method can produce accurate electric field intensity and magnetic flux density estimation results for different overhead transmission line configurations.

Noise Intensity Estimation Method Based on PCA and Weak Textured Block Selection for Neutron Image

Noise intensity estimation has a very important application in image denoising. In image processing, the denoising method can achieve an ideal denoising effect under the assumption that the Gaussian noise intensity in the image is known. But in real denoising applications, especially the neutron image, the noise level is unknown, which will greatly affect the denoising effect of neutron image processing. In this paper, a method which combined the principal component analysis with weak texture block selection is proposed for noise intensity estimation of neutron images. The experimental results show that the proposed method can accurately estimate the Gaussian noise in the neutron image. Compared with the existing noise intensity estimation methods, the qualitative and quantitative results show that the proposed method has higher accuracy and stability.

Comparison of Urban Heat Island Intensity Estimation Methods Using Urbanized WRF in Berlin, Germany

In this study, we present a meso-scale simulation of the urban microclimate in Berlin, Germany, using the Weather Research and Forecasting (WRF) numerical weather prediction platform. The objective of the study is to derive an accurate estimate of the near-surface urban heat island (UHI) intensity. The simulation is conducted over a two-week summer period. We compare different physical schemes, different urban canopy schemes and different methods for estimating the UHI intensity. The urban fraction of each urban category is derived using the Copernicus Impervious Density data and the Corine Land Cover data. High-resolution City Geography Markup Language (CityGML) data is used to estimate the building height densities required by the multi-layer urban canopy model (UCM). Within the single-layer UCM, we implement an anthropogenic heat profile based on the large scale urban consumption of energy (LUCY) model. The optimal model configuration combines the WRF Single Moment Five-Class (WSM5) microphysics scheme, the Bougeault–Lacarrère planetary boundary layer scheme, the eta similarity (Mellor–Yamada–Janjic) surface layer scheme, the Noah Multi-Parameterization land surface model, the Dudhia and Rapid Radiative Transfer Model (RRTM) radiation schemes, and the multi-layer UCM (including the building energy model). Our simulated UHI intensity results agree well with measurements with a root mean squared error of 0.86K and a mean bias error of 0.20K. After model validation, we proceed to compare several UHI intensity calculation methods, including the ‘ring rural reference’ (RRR) method and the ‘virtual rural reference’ (VRR) method. The VRR mthod is also known as the ‘urban increment’ method. We suggest and argument that the VRR approach is superior.

A Novel Tensor Network for Tropical Cyclone Intensity Estimation

Tropical cyclone (TC) intensity estimation is an important task in meteorological research. Meanwhile, TC intensity estimation performance can be improved by developing advanced machine learning techniques using the newly emerged high-quality multispectral images (MSIs) acquired by FY-4 meteorological satellite of China. To this end, this article proposes a novel model, tensor-based convolutional neural network (TCNN). Not only being a deep network entirely formulated in tensor algebra, but TCNN also establishes the mathematical connections between tensor decomposition and CNN operations with tensor contraction. Moreover, TCNN adopts a multitask structure, which consists of a classification network for intensity categorization and a regression network for wind speed estimation. It allows the regression network to leverage the outcome of the classification network, thus ensuring intensity estimation accuracy. In addition, two alternative TCNN models, coupled TCNN (C-TCNN) and Tucker TCNN (T-TCNN), are designed to automatically deal with invalid band data in the FY-4 MSIs, which has been a practical issue with the data. Experimental results prove that the proposed network is accurate and functional. They also demonstrate the advantages of TCNN over other TC intensity estimation methods, showing that C-TCNN and T-TCNN outperform several classic models and the state-of-the-art models based on CNN.

ConflictNET: End-to-End Learning for Speech-Based Conflict Intensity Estimation

Computational paralinguistics aims to infer human emotions, personality traits and behavioural patterns from speech signals. In particular, verbal conflict is an important example of human-interaction behaviour, whose detection would enable monitoring and feedback in a variety of applications. The majority of methods for detection and intensity estimation of verbal conflict apply off-the-shelf classifiers/regressors to generic hand-crafted acoustic features. Generating conflict-specific features requires refinement steps and the availability of metadata, such as the number of speakers and their speech overlap duration. Moreover, most techniques treat feature extraction and regression as independent modules, which require separate training and parameter tuning. To address these limitations, we propose the first end-to-end convolutional-recurrent neural network architecture that learns conflict-specific features directly from raw speech waveforms, without using explicit domain knowledge or metadata. Additionally, to selectively focus the model on portions of speech containing verbal conflict instances, we include a global attention interface that learns the alignment between layers of the recurrent network. Experimental results on the SSPNet Conflict Corpus show that our end-to-end architecture achieves state-of-the-art performance in terms of Pearson Correlation Coefficient.

An Adaptive Bayesian Source Separation Method for Intensity Estimation of Facial AUs

Automated measurement of the intensity of spontaneous facial Action Units (AU) defined by the Facial Action Coding System (FACS) in video sequences is a challenging problem. This paper proposes a person-adaptive methodology for the intensity estimation of spontaneous AUs. We formulate this problem as a source separation problem where we consider the observed AUs as the source signals to be separated from each other and other information given by a sequence of facial images. We first compute an initial estimation of the sources, called observations, using sparse linear regression functions. We then develop and apply a Bayesian source separation method that recruits the prior information of the sources to iteratively improve the initial estimations/observations in an adaptive fashion. Furthermore, our approach adaptively uses some testing information (but not the ground-truth labels) to improve the performance of the approach (i.e., Person-Adaptive model). Our experimental results on DISFA, UNBC-McMaster and FERA2015 databases show that this approach is very promising for automated measurement of the intensity of spontaneous facial AUs.

Methods and approaches of Complexity Theory and Fuzzy Logic for intensity of university research in terms of Creative Work to be estimated

This article describes the main approaches to research in terms of creative labor regulation and time study. Definition of a creative labor and brain-work product as a subject of regulation and work intensity estimation was developed. The method for creative brain-work intensity estimation was based on complexity theory, which enables the evaluation of the complexity of creative brain-work results and time expenditure. Because of the appropriateness of linguistic expert assessments while labor intensive creative work is carried out, the methods and approaches of fuzzy logic were suggested to assess the Competence Complexity of the creative work product. Based on statistical and expert models, a regression was built to estimate time expenditure dependence of the creative brain-work expected outcomes on Competence Complexity. The resulting dependency allows the estimation of the time spent on the research project based on the estimation of the expected project results.

Creative Work Estimation and Creative Projects Time Study on the Basis of Complexity Theory and Fuzzy Logic Approaches

Представлены результаты оценки трудоемкости и норм времени интеллектуального творческого труда на основе теории сложности, позволяющей оценить компетенционную сложность продукта исследовательского труда. В качестве продукта исследовательского, творческого труда предложено считать новые знания, компетенционная сложность которых состоит из сложности знания, новизны знания и коммерческого потенциала. Авторами обоснована возможность использования подходов и принципов теории сложности при нормировании творческого труда с учетом того, что его продуктом являются новые знания. Ввиду целесообразности применения экспертных оценок при определении трудоемкости творческого труда предложено при оценке компетенционной сложности продукта творческого труда использовать методы и подходы нечеткой логики. Построена зависимость трудоемкости исследовательской деятельности от компетенционной сложности, которая позволяет оценить временные затраты, необходимые на реализацию исследовательского проекта с заданной компетенционной сложностью ожидаемого результата. Представлены результаты оценки трудоемкости и нормирования научно-исследовательского труда как творческого труда, и в рамках нечеткой логики сформулированы основные термы, позволяющие учесть специфику и структуру творческой задачи, что дает возможность осуществить количественную оценку в целях дальнейшей монетизации результатов творческого труда.