Cloud Images Research Articles

UATNet: U-Shape Attention-Based Transformer Net for Meteorological Satellite Cloud Recognition

Cloud recognition is a basic task in ground meteorological observation. It is of great significance to accurately identify cloud types from long-time-series satellite cloud images for improving the reliability and accuracy of weather forecasting. However, different from ground-based cloud images with a small observation range and easy operation, satellite cloud images have a wider cloud coverage area and contain more surface features. Hence, it is difficult to effectively extract the structural shape, area size, contour shape, hue, shadow and texture of clouds through traditional deep learning methods. In order to analyze the regional cloud type characteristics effectively, we construct a China region meteorological satellite cloud image dataset named CRMSCD, which consists of nine cloud types and the clear sky (cloudless). In this paper, we propose a novel neural network model, UATNet, which can realize the pixel-level classification of meteorological satellite cloud images. Our model efficiently integrates the spatial and multi-channel information of clouds. Specifically, several transformer blocks with modified self-attention computation (swin transformer blocks) and patch merging operations are used to build a hierarchical transformer, and spatial displacement is introduced to construct long-distance cross-window connections. In addition, we introduce a Channel Cross fusion with Transformer (CCT) to guide the multi-scale channel fusion, and design an Attention-based Squeeze and Excitation (ASE) to effectively connect the fused multi-scale channel information to the decoder features. The experimental results demonstrate that the proposed model achieved 82.33% PA, 67.79% MPA, 54.51% MIoU and 70.96% FWIoU on CRMSCD. Compared with the existing models, our method produces more precise segmentation performance, which demonstrates its superiority on meteorological satellite cloud recognition tasks.

Bulk hydrometeor optical properties for microwave and sub-millimetre radiative transfer in RTTOV-SCATT v13.0

Abstract. Satellite observations of radiation in the microwave and sub-millimetre spectral regions (broadly from 1 to 1000 GHz) can have strong sensitivity to cloud and precipitation particles in the atmosphere. These particles (known as hydrometeors) scatter, absorb, and emit radiation according to their mass, composition, shape, internal structure, and orientation. Hence, microwave and sub-millimetre observations have applications including weather forecasting, geophysical retrievals and model validation. To simulate these observations requires a scattering-capable radiative transfer model and an estimate of the bulk optical properties of the hydrometeors. This article describes the module used to integrate single-particle optical properties over a particle size distribution (PSD) to provide bulk optical properties for the Radiative Transfer for TOVS microwave and sub-millimetre scattering code, RTTOV-SCATT, a widely used fast model. Bulk optical properties can be derived from a range of particle models including Mie spheres (liquid and frozen) and non-spherical ice habits from the Liu and Atmospheric Radiative Transfer Simulator (ARTS) databases, which include pristine crystals, aggregates, and hail. The effects of different PSD and particle options on simulated brightness temperatures are explored, based on an analytical two-stream solution for a homogeneous cloud slab. The hydrometeor scattering “spectrum” below 1000 GHz is described, along with its sensitivities to particle composition (liquid or ice), size and shape. The optical behaviour of frozen particles changes in the frequencies above 200 GHz, moving towards an optically thick and emission-dominated regime more familiar from the infrared. This region is little explored but will soon be covered by the Ice Cloud Imager (ICI).

A Supplementary Module to Improve Accuracy of the Quality Assessment Band in Landsat Cloud Images

Cloud contamination is a serious obstacle for the application of Landsat data. To popularize the applications of Landsat data, each Landsat image includes the corresponding Quality Assessment (QA) band, in which cloud and cloud shadow pixels have been flagged. However, previous studies suggested that Landsat QA band still needs to be modified to fulfill the requirement of Landsat data applications. In this study, we developed a Supplementary Module to improve the original QA band (called QA_SM). On one hand, QA_SM extracts spectral and geometrical features in the target Landsat cloud image from the original QA band. On the other, QA_SM incorporates the temporal change characteristics of clouds and cloud shadows between the target and reference images. We tested the new method at four local sites with different land covers and the Landsat-8 cloud cover validation dataset (“L8_Biome”). The experimental results show that QA_SM performs better than the original QA band and the multi-temporal method ATSA (Automatic Time-Series Analyses). QA_SM decreases omission errors of clouds and shadows in the original QA band effectively but meanwhile does not increase commission errors. Besides, the better performance of QA_SM is less affected by the selections of reference images because QA_SM considers the temporal change of land surface reflectance that is not caused by cloud contamination. By further designing a quantitative assessment experiment, we found that the QA band generated by QA_SM improves cloud-removal performance on Landsat cloud images, suggesting the benefits of the new method to advance the applications of Landsat data.

Si photonic crystal optical antenna serial array and frequency-modulated continuous-wave light detection and ranging action

Photonic crystal waveguide slow-light grating emits a free-space optical beam and steers it widely by changing the optical wavelength or waveguide refractive index. In the reverse process, returned light is coupled into the device again. We have proposed to use this optical transmission and reception antenna as a beam scanner for light detection and ranging (LiDAR). Ideally, a large-aperture antenna can narrow the transmission beam and enhance the reception efficiency. Actually, however, the transmission and reception performance is not scalable owing to waveguide loss even though the waveguide is simply lengthened. A serial array configuration in which the waveguide is divided into multiple antennas is effective for mitigating this problem. In this study, we fabricated such a device using Si photonics technology and obtained a small beam divergence of 0.02° at a telecom wavelength. Then, we observed the ranging operation by adding an optical setup of frequency-modulated continuous-wave (FMCW) LiDAR and confirmed that the divided antenna device improved the reception intensity by 12 dB. Moreover, we fabricated a FMCW LiDAR chip in which the serial array antennas were integrated in parallel with switch trees and Ge photodiodes and obtained point cloud images by two-dimensional beam scanning.

Integrated Architecture Model of Tourism Information Service in Smart Scenic Spots Based on Hybrid Cloud

Tourism industry can promote the prosperity of the local economy. In addition, the booming tourism business in recent years has also led to the development of related industries and services. According to high-tech technologies such as cloud computing, hybrid cloud, and panoramic image, we will plan to design a comprehensive and integrated architecture model of scenic spots that integrates all tourism information and various services, strive to create smart scenic spots, bring the best play experience to tourists, and strive to attract more attention and attention. The results show that (1) the overall average satisfactory approval of UI test is as high as 93%, which can meet the requirements. (2) After the improved panoramic image mosaic method, the correct rate is as high as 93.90%, the effect is 4.90% better than that before the improvement, and the algorithm is more efficient. (3) The scenic spot configuration management effect is excellent, and various situations in the scenic spot are effectively monitored. (4) The average response time per request of the original system is about 161 ms. Compared with the original system, the response time of the new system is reduced by about 57%, and the access success rate is 100%. The system in the experiment runs well and satisfies the integration of tourism information resources and services in scenic spots.

ИСПОЛЬЗОВАНИЕ РЕЗУЛЬТАТОВ КЛАССИФИКАЦИИ ОБЛАЧНОСТИ ПО СПУТНИКОВЫМ ДАННЫМ ДЛЯ РЕШЕНИЯ ЗАДАЧ КЛИМАТОЛОГИИ И МЕТЕОРОЛОГИИ

Algorithms for classifying cloud images based on MODIS and VIIRS satellite data using artificial neural networks and fuzzy logic methods are considered. A combined classification of recognized cloud types is presented. The results of using the cloud classification for solving some problems of climatology and meteorology are analyzed. A statistical model of the image texture for various cloud types and physical parameters of clouds based on two-parameter distributions is proposed. A description of the algorithm for detecting weather fronts and determining their types from satellite data and the results of its testing for the territory of Western Siberia are presented. An approach to studying internal waves in the atmosphere based on the analysis of their cloud manifestation parameters is considered. The results are presented of studying the long-term variability for some of their parameters over the water area of the Kuril Islands. The methodology and results are discussed of studying the long-term variability of the structure of global cloud fields and their parameters over the natural zones of Western Siberia in summer during 2001 to 2019.

Classification of imbalanced cloud image data using deep neural networks: performance improvement through a data science competition

Image data classification using machine learning is an effective method for detecting atmospheric phenomena. However, extreme weather events with a small number of cases cause a decrease in classification prediction accuracy owing to the imbalance in data between the target class and the other classes. To build a highly accurate classification model, I held a data analysis competition to determine the best classification performance for two classes of cloud image data, specifically tropical cyclones including precursors and other classes. For the top models in the competition, minority data oversampling, majority data undersampling, ensemble learning, deep layer neural networks, and cost-effective loss functions were used to improve the classification performance of the imbalanced data. In particular, the best model of 209 submissions succeeded in improving the classification capability by 65.4% over similar conventional methods in a measure of the low false alarm ratio.

Atomic Compass: Detecting 3D Magnetic Field Alignment with Vector Vortex Light.

We describe and demonstrate how 3D magnetic field alignment can be inferred from single absorption images of an atomic cloud. While optically pumped magnetometers conventionally rely on temporal measurement of the Larmor precession of atomic dipoles, here a cold atomic vapor provides a spatial interface between vector light and external magnetic fields. Using a vector vortex beam, we inscribe structured atomic spin polarization in a cloud of cold rubidium atoms and record images of the resulting absorption patterns. The polar angle of an external magnetic field can then be deduced with spatial Fourier analysis. This effect presents an alternative concept for detecting magnetic vector fields and demonstrates, more generally, how introducing spatial phases between atomic energy levels can translate transient effects to the spatial domain.

The Development of Multi-scale Data Management for CityGML-based 3D Buildings

The CityGML model is now the norm for smart city or digital twin city development for better planning, management, risk-related modelling and other applications. CityGML comes with five levels of detail (LoD), mainly constructed from point cloud measurements and images of several systems, resulting in a variety of accuracies and detailed models. The LoDs, also known as pre-defined multi-scale models, require large storage-memory-graphic consumption compared to single scale models. Furthermore, these multi-scales have redundancy in geometries, attributes, are costly in terms of time and workload in updating tasks, and are difficult to view in a single viewer. It is essential for data owners to engage with a suitable multi-scale spatial management solution in minimizes the drawbacks of the current implementation. The proper construction, control and management of multi-scale models are needed to encourage and expedite data sharing among data owners, agencies, stakeholders and public users for efficient information retrieval and analyses. This paper discusses the construction of the CityGML model with different LoDs using several datasets. A scale unique ID is introduced to connect all respective LoDs for cross-LoD information queries within a single viewer. The paper also highlights the benefits of intermediate outputs and limitations of the proposed solution, as well as suggestions for the future.

Intelligent classification of ground-based visible cloud images using a transfer convolutional neural network and fine-tuning

Here a classification method for ground-based visible images is proposed based on a transfer convolutional neural network (TCNN). This approach combines the ability of deep learning (DL) and transfer learning (TL). A sample database containing all ten cloud types was used; this database was expanded four-fold using enhancement processing. AlexNet was chosen as the basic convolutional neural network (CNN), with the ImageNet database being used for pre-transfer. The optimal method, once determined by layer-by-layer fine-tuning, was used to test the classification effects for ten cloud types. The proposed method achieved 92.3% recognition accuracy for all ten ground-based cloud types.

Revisiting the size of nonspherical particles recorded by optical array probes with a new method based on the convex hull

In recent years, the Cloud Imaging Probe (CIP) and Precipitation Imaging Probe (PIP) produced by Droplet Measurement Technologies (DMT) have been introduced by a number of meteorological research and operation centers in China. The supporting software provided by DMT, i.e., PADS (Particle Analysis and Display System), cannot output detailed information on each individual particle, which definitely limits the in-depth utilization of cloud and precipitation particle image data in China. In this paper, particle-by-particle information was extracted by decompressing the CIP and PIP original particle image data, based on which a new definition of the dimension for nonspherical particles is proposed by using the area of the convex hull enclosing a particle to obtain the equivalent diameter of a circle with equal area. Based on the data detected during one flight in Inner Mongolia, the particle size distribution obtained using the new particle size definition and that used by the other four existing definitions are compared. The results show that the particle number concentration calculated using different particle size definitions can vary by up to an order of magnitude. The result obtained based on the new particle size definition is closest to that calculated with the area-equivalent diameter definition.摘要 国内许多气象部门已引进美国DMT公司的云粒子图像探头 (CIP) 和降水粒子图像探头 (PIP) . 由于其配套软件不能输出逐个粒子的详细信息, 在很大程度上限制了对云降水粒子图像探测数据的深入挖掘. 通过解析CIP和PIP原始数据, 提出了一种基于包围粒子凸多边形的面积求取粒子尺度的新定义. 利用在内蒙古的一次航测数据, 对比分析了基于新定义及已有的四种粒子尺度定义求取的粒子尺度谱分布.

Classification Using 3D Point Cloud and 2D Image on Abstract Objects

While classification using machine learning is exceptionally successful with 2D images, it is more challenging to classify 3D objects. However, 3D objects classification is critical because of its application in autonomous vehicles and robotics. This paper compared neural networks with similar structures using 3D point clouds and 2D images on the same objects. We also generated objects with abstract design and input them into the neural networks we created. We find clear disadvantages with classifying abstract objects compared to ordinary objects for both neural networks. We believe having contextual information will help to address this problem. We also observed that the neural network based on images performs worse than that based on point clouds. However, image based classification takes less time to train compared to point cloud based classification.

The Images of Nature in Wordsworth’s and Al-Bohtory’s Poetry: A Comparative Study of Selected Poems

This study tackles the representation of nature in poetry, mainly in Wordsworth’s and Al-Bohtory’s poems. This study is based on the theoretical and analytical approaches of Russian Formalism that focuses on studying the linguistic aspects of the literary texts. Russian Formalism studies texts through “structures, imagery, syntax, rhyme scheme, paradox, personification and other literary devices” (Bressler, 2011, p. 49). The significance of the study lies in its purpose to introduce a comparison between two different poets whose cultural backgrounds, languages, traditions and societies are different. Wordsworth sees nature as the perfect place for tranquility and pleasure. He emphasizes that man and nature as basically adapted to each other, and the mind of man as the machine of depicting nature. Wordsworth states that this pleasure comes from the human’s interaction with nature in its fascinating images of Spring, flowers, clouds, horses, rivers, castles, seas, gardens, and animals generally. Al-Bohtory also presents nature as a place of pleasure and peace; he accentuates the profound relationship between nature and man, and how nature is admired by humans in its beautiful views. He explains that the beautiful images of nature affect the human’s mind and soul. Al-Bohtory portrays most of his poems in marvelous images of nature, such as Spring, horses, clouds, rivers, animals, castles, seas, and flowers. These two poets seek to glorify nature and its magnificent impact on humans’ life and pleasure.

Troposphere‐Mesosphere Coupling by Convectively Forced Gravity Waves During Southern Hemisphere Monsoon Season as Viewed by AIM/CIPS

AbstractA new data set consisting of Rayleigh Albedo Anomaly variance data resulting from measurements by the Cloud Imaging and Particle Size instrument on the Aeronomy for Ice in the Mesosphere satellite is introduced, and is used to illustrate the lower‐mesospheric (50–55 km) gravity wave (GW) response to tropospheric convection during Southern Hemisphere monsoon season (December‐February). The correspond to GWs with vertical wavelengths 15 km and horizontal wavelengths between about 23 and 600 km. It is shown that these scales encompass most of the convectively generated GW spectrum at 50–55 km altitude due to both plume overshoot and diabatic heating, and include those GWs most likely to impact the overlying ionosphere‐thermosphere‐mesosphere system. The GWs originate from convective sources associated with the African and South American land masses, the maritime continent/Australia, and the South Pacific Convergence Zone. The regions of enhanced convection are identified according to half‐hourly rainfall rate (RR) distributions from the Global Precipitation Measurement mission. The GW exhibits spatial, inter‐monthly, and inter‐annual variabilities connected with RR and propagation conditions. A ∼ southward shift of longitudinal structures in with respect to RR longitudinal structures is interpreted in terms of wave focusing toward the middle atmosphere summer easterly jet core. For the South American Monsoon System, a linear regression analysis shows variability to be expressible in terms of upper‐stratosphere zonal wind speeds (correlation coefficient R = −0.91) with magnitude of RR playing a much lesser role (R = 0.16).

Improved Measurements of Molecular Cloud Distances Based on Global Search

Abstract The principle of the background-eliminated extinction-parallax (BEEP) method is examining the extinction difference between on- and off-cloud regions to reveal the extinction jump caused by molecular clouds, thereby revealing the distance in complex dust environments. The BEEP method requires high-quality images of molecular clouds and high-precision stellar parallaxes and extinction data, which can be provided by the Milky Way Imaging Scroll Painting (MWISP) CO survey and the Gaia DR2 catalog, as well as supplementary A V extinction data. In this work, the BEEP method is further improved (BEEP-II) to measure molecular cloud distances in a global search manner. Applying the BEEP-II method to three regions mapped by the MWISP CO survey, we collectively measured 238 distances for 234 molecular clouds. Compared with previous BEEP results, the BEEP-II method measures distances efficiently, particularly for those molecular clouds with large angular size or in complicated environments, making it suitable for distance measurements of molecular clouds in large samples.

A Feature Based Laser SLAM Using Rasterized Images of 3D Point Cloud

An accurate and computationally efficient SLAM algorithm is vital for autonomous vehicles. Most modern SLAM systems use feature detection approaches to limit computational requirements. Feature detection through a 3D point cloud can be a computationally challenging task. In this paper, we propose a feature-based SLAM algorithm using 2D image projections of the 3D laser point cloud. We use a camera parameters matrix to rasterize the 3D point cloud to an image. Then ORB feature detector is applied to these images. The proposed method gives repeatable and stable features in a variety of environments. Based on such features, we can estimate the 6dof pose of the robot. For loop detection, we employ a 2-step approach, i.e., nearest key-frame detection and loop candidate verification by matching features extracted from rasterized LIDAR images. We evaluate the proposed system with implementation on the KITTI dataset. Through experimental results, we show that the algorithm presented in this paper can substantially reduce the computational cost of feature detection from the point cloud and the whole SLAM system while giving accurate results.

Explicit basis function kernel methods for cloud segmentation in infrared sky images

Photovoltaic systems are sensitive to cloud shadow projection, which needs to be forecasted to reduce the noise impacting the intra-hour forecast of global solar irradiance. We present a comparison between different kernel discriminative models for cloud detection. The models are solved in the primal formulation to make them feasible in real-time applications. The performances are compared using the j-statistic. The infrared cloud images have been preprocessed to remove debris, which increases the performance of the analyzed methods. The use of the pixels’ neighboring features also leads to a performance improvement. Discriminative models solved in the primal yield a dramatically lower computing time along with high performance in the segmentation.

A Point Cloud Fusion Method for Space Target 3D Laser Point Cloud and Visible Light Image Reconstruction Point Cloud

In this paper, a high-precision spatial target lidar for 3D reconstruction of point cloud and visible light image 3D reconstruction point cloud fusion method is proposed. This fusion method uses the solved 3D reconstruction to invert the camera pose and 3D point cloud model centroid position optimization initial value selection. The registration accuracy and registration efficiency of the ICP algorithm are improved. At the same time, according to the characteristics of the two sets of point clouds, the Euclidean distance threshold is used to delete the noise points of the 3D point cloud edge, and the high-precision 3D reconstruction point with the scale information fusion is obtained. cloud. The simulation experiment of the spatial target simulation model shows that the fusion method can effectively improve the point cloud density, fill the reconstruction vulnerability, and improve the point cloud accuracy of the spatial target 3D reconstruction.

Construction of multi-modal perception model of communicative robot in non-structural cyber physical system environment based on optimized BT-SVM model

With the rapid development of intelligent control technology, computer technology, bionics, artificial intelligence and other disciplines, more and more attention has been paid to the research of intelligent mobile robot technology, and autonomous positioning is the basis for mobile robots to conduct autonomous navigation and exploration research. Sensors assist each other to provide a wealth of perception information about the internal state of the robot and the external surrounding environment. This paper proposes a method for optimizing the Support Vector Machine (SVM) multi-classifier with a binary tree structure, which improves the accuracy of multi-modal tactile signal recognition. The improved particle swarm clustering algorithm is used to optimize the binary tree structure, reduce the error accumulation of the binary tree structure SVM multi-classifier, and further improve the accuracy of multi-modal tactile signal recognition. The effect of the method in this paper is verified by robot grasping experiments. The results show that the use of multi-modal information of two-dimensional images and three-dimensional point cloud images can effectively identify and locate target objects of different shapes. Compared with the processing method of two-dimensional or point cloud monomodal image information, the positioning error can be reduced by 54.8%, and the direction error can be reduced by 50.8%, which has better robustness and accuracy. The simulation results show that the improved PSOBT-SVM model has the best classification effect for artificial features, PCA features and spatio-temporal correlation features. The improved PSOBT-SVM optimizes the classification accuracy without changing the number of SVM classifiers, and proves its accuracy in classifying multimodal tactile signals.

Reconstruction of a leaking gas cloud from a passive FTIR scanning remote-sensing imaging system.

The concentration-path-length product (CL) image of the leaking gas cloud measured by the passive Fourier transform infrared (FTIR) scanning remote-sensing imaging system has a low resolution. Gas cloud diffusion is affected by wind speed and direction, which makes it difficult to trace the source of a leakage. Therefore, we propose a method to reconstruct the CL image of the leaking gas cloud applied to the passive FTIR scanning remote-sensing imaging system. First, bicubic interpolation is employed to upsample the low-resolution CL image of gas clouds. Second, the maximum noise-equivalent concentration-path-length (NECL) product is used as a threshold to segment the high-resolution gas cloud image. Third, image morphology processing and the evaluation criteria of the leaking gas cloud are applied to detect the leaking gas cloud. Finally, the high-resolution CL image of the leaking gas cloud is superimposed onto the background image. The effectiveness of the reconstruction method is proven by the SF6 remote-sensing experiment and simulation. The results show that the proposed method should be effectively implemented to reconstruct the high-resolution CL image of the leaking gas cloud. The reconstructed leaking gas cloud plume, as well as the location of the leakage source, are quite obvious. The reconstruction method has been successfully applied to passive FTIR scanning remote-sensing imaging systems, with high accuracy, in real time, and with robustness.