Cloud Features Research Articles

Enhanced Typhoon Center Localization Using Geostationary Satellite Imagery

AbstractAn accurate center localization in near real‐time is critical for tropical cyclone (TC) monitoring and forecasting. This study presents a robust algorithm for localizing typhoon centers using the Chinese geostationary (GEO) meteorological satellite. The results using the Advanced Geostationary Radiation Imager (AGRI) onboard Fengyun‐4A (FY‐4A) satellite data, achieving a mean absolute error (MAE) of 29.4 km across various typhoon intensities in the Western North Pacific, superior to other baseline methods. By harnessing the multi‐spectral imagery from the FY‐4A and incorporating an attention mechanism, it significantly boosts the deep learning convolutional neural network's ability to identify typhoon cloud features and their centers, even during their initial and weakest stages, which is laudable because these are the most difficult for center fixing even for human analysts. Remarkably, it requires just a single moment satellite imagery to locate the center of typhoon, enabling automated updates of the typhoon centers in near real‐time applications.

Correction to: Regional differences in cloud characteristics at different depth, intensity and horizontal scale over South Asia during Indian summer monsoon using CloudSat and reanalysis data

Correction to: Regional differences in cloud characteristics at different depth, intensity and horizontal scale over South Asia during Indian summer monsoon using CloudSat and reanalysis data

Potential damage area detection of bridges based on single-temporal point cloud

Abstract With advantages of 3D representation, non-contact measurements and intensive sampling capability, it has been a research hotspot to detect the potential damage area of bridges with point cloud by TLS. However, TLS is commonly used to detect a potential damage area by comparing multi-temporal point cloud data, which limits the timeliness of bridge inspection. Therefore, aiming to accurately detect the potential damage areas of bridges with single-temporal point cloud, this paper proposes a normalized normal vector constrained coordinate transformation method. First, the distribution of sharp features is revealed in a single-temporal point cloud at potential damage areas, and a neighborhood growth method constrained by the normal distance is proposed to eliminate the sharp features in point cloud, which is prone to cause incorrect or missing curvature values from point cloud. Second, a normalized normal vector constrained coordinate transformation method is proposed to construct Gaussian curvature model, which can improve the accuracy of point cloud curvature and accurately detect the potential damage areas in bridges. At last, an evaluation criterion is proposed to quantify the bridge condition by integrating the characteristics of small-span concrete bridges in urban areas with actual damage data from the experimental bridges. The experimental results show that the proposed method can effectively detect the potential damage areas of the measured bridges.

Is it possible to generate accurate 3D point clouds with UAS-LIDAR and UAS-RGB photogrammetry without GCPs? A case study on a beach and rocky cliff

ContextRecently, Unoccupied Aerial Systems (UAS) with photographic or Light Detection and Ranging (LIDAR) sensors have incorporated on-board survey-grade Global Navigation Satellite Systems that allow the direct georeferencing of the resulting datasets without Ground Control Points either in Real-Time (RTK) or Post-Processing Kinematic (PPK) modes. These approaches can be useful in hard-to-reach or hazardous areas. However, the resulting 3D models have not been widely tested, as previous studies tend to evaluate only a few points and conclude that systematic errors can be found.ObjectivesWe test the absolute positional accuracy of point clouds produced using UAS with direct-georeferencing systems.MethodsWe test the accuracy and characteristics of point clouds produced using a UAS-LIDAR (with PPK) and a UAS-RGB (Structure-from-Motion or SfM photogrammetry with RTK and PPK) in a challenging environment: a coastline with a composite beach and cliff. The resulting models of each processing were tested using as a benchmark a point cloud surveyed simultaneously by a Terrestrial Laser Scanner.ResultsThe UAS-LIDAR produced the most accurate point cloud, with homogeneous cover and no noise. The systematic bias previously observed in the UAS-RGB RTK approaches are minimized using oblique images. The accuracy observed across the different surveyed landforms varied significantly.ConclusionsThe UAS-LIDAR and UAS-RGB with PPK produced unbiased point clouds, being the latter the most cost-effective method. For the other direct georeferencing systems/approaches, the acquisition of GCP or the co-registration of the resulting point cloud is still necessary.

Short-term forecast of solar irradiance components using an alternative mathematical approach for the identification of cloud features

Solar energy technologies require precise solar forecasting to reduce power generation losses and protect equipment from irradiance fluctuations. This study introduces an alternative methodology for short-term forecasting of direct normal irradiance (DNI) and global horizontal irradiance (GHI) utilizing ground-based sky images captured by a single device. A low-cost all-sky imager (ASI) was developed, which implements an angular transformation and an optical flow technique to extract cloud features such as shape and velocity. A mathematical model calculates cloud transmittance based on pixel intensity, eliminating complex training steps. Results from a 30-day experimental campaign, incorporating diverse meteorological conditions, were compared against a secondary standard solarimetric station, a smart persistence model, and state-of-the-art approaches. The DNI forecast achieved an RMSE (relative error) of 46.79 W/m2 (11.99%) for 1-min intervals and 90.21 W/m2 (17.54%) for 10-min intervals, while GHI ranged from 31.73 W/m2 (4.68%) to 75.02 W/m2 (13.63%). Pearson correlation coefficients exceeded 0.9 overall, reaching 0.98 and 0.99 for the 1-min DNI and GHI forecasts, and 0.91 and 0.96 for the 10-min DNI and GHI forecasts, respectively, underscoring the system’s accuracy and robustness in complex meteorological scenarios.

Investigations of high-speed projectile impact on symmetric sandwich structures containing solid propellant with core perforations

The response of solid rocket motors (SRMs) to high-speed fragment impacts is crucial for their safety design and operational use in scenarios such as rocket launches and space applications. The visualized Burn to Violent Reaction (BVR) test is used to observe intense reactions induced by high-speed projectile impacts. Employing a two-stage light gas gun and optical diagnostic techniques including high-speed schlieren imaging and direct photography, the impact-induced deflagration/explosion behavior, and reaction growth behavior were investigated. The damage mechanisms of the casing and propellant samples were assessed, and the reaction growth and afterburn effects of the impact-induced fragment cloud were quantitatively analyzed. The results indicate that the ignition delay time is inversely correlated with the impact velocity, decreasing from ms to μs scale. Across a wide range of velocities (1050–2058 m/s), higher projectile velocities induce more sustained and vigorous combustion reactions within the propellant. Furthermore, increasing the propellant air gap to 7.8 cm does not trigger further reactions under the studied configurations. The reaction mechanisms are closely linked to the characteristics of the fragment cloud induced by the impact. The developed Smoothed Particle Hydrodynamics (SPH) method, incorporating material constitutive models, ignition criteria, and reaction growth models, was used to study the influence of projectile velocity on the reaction mechanisms. The simulation results were compared with experimental data, demonstrating satisfactory accuracy.

GLDBF: Global and local dual-branch fusion network for no-reference point cloud quality assessment

No-reference Point Cloud Quality Assessment (NR-PCQA) is a challenge in the field of media quality assessment, such as inability to accurately capture quality-related features due to the unique scattered structure of points and less considering global features and local features jointly in the existing no-reference PCQA metrics. To address these challenges, we propose a Global and Local Dual-Branch Fusion (GLDBF) network for no-reference point cloud quality assessment. Firstly, sparse convolution is used to extract the global quality feature of distorted Point Clouds (PCs). Secondly, graph weighted PointNet++ is proposed to extract the multi-level local features of point cloud, and the offset attention mechanism is further used to enhance local effective features. Transformer-based fusion module is also proposed to fuse multi-level local features. Finally, we joint the global and local dual branch fusion modules via multilayer perceptron to predict the quality score of distorted PCs. Experimental results show that the proposed algorithm can achieves state-of-the-art performance compared with existing methods in assessing the quality of distorted PCs.

Dual-path aggregation transformer network for super-resolution with images occlusions and variability

While Transformer-based approaches have recently achieved notable success in super-resolution, their extensive computational requirements impede widespread practical adoption. High-resolution meteorological satellite cloud imagery is essential for weather analysis and forecasting. Enhancing image resolution through super-resolution techniques facilitates the accurate identification and localization of geographic features by meteorological systems. However, current super-resolution methods fail to restore the intricacies of cloud formations and complex regions fully. This research introduces a novel dual-path aggregation Transformer network (DPAT) tailored to enhance the super-resolution of meteorological satellite cloud images. The DPAT network adeptly captures cloud imagery's subtle details and textures, effectively addressing occlusions and the variability inherent in satellite imagery. It bolsters the model's ability to manage the complex attributes of cloud images through the introduction of the Dual-path Aggregation Self-Attention (DASA) mechanism and the Multi-scale Feature Aggregation Block (MFAB), thereby enhancing performance in processing intricate cloud features. The DASA mechanism synthesizes features across spatial, depth, and channel dimensions via a dual-path approach, thoroughly exploiting feature correlations. The MFAB, designed to supplant the multilayer perceptron, incorporates shift convolution and a multi-scale interaction block to augment feature information, compensating for the deficiency in local information absorption due to fixed receptive fields. Experimental outcomes indicate that DPAT delivers superior super-resolution outcomes. With a parameter count of only 32% of the Enhanced Deep Residual Network (EDSR) or 77% of the Image Restoration using Shift Window Transformer (SwinIR), DPAT matches SwinIR's performance on the satellite cloud dataset. Moreover, DPAT balances accuracy and parameter economy across various datasets. This technology is expected to improve image super-resolution capabilities in multiple fields such as human action recognition and industrial recognition, and indirectly improve the accuracy of image perception tasks.

A Base-Map-Guided Global Localization Solution for Heterogeneous Robots Using a Co-View Context Descriptor

With the continuous advancement of autonomous driving technology, an increasing number of high-definition (HD) maps have been generated and stored in geospatial databases. These HD maps can provide strong localization support for mobile robots equipped with light detection and ranging (LiDAR) sensors. However, the global localization of heterogeneous robots under complex environments remains challenging. Most of the existing point cloud global localization methods perform poorly due to the different perspective views of heterogeneous robots. Leveraging existing HD maps, this paper proposes a base-map-guided heterogeneous robots localization solution. A novel co-view context descriptor with rotational invariance is developed to represent the characteristics of heterogeneous point clouds in a unified manner. The pre-set base map is divided into virtual scans, each of which generates a candidate co-view context descriptor. These descriptors are assigned to robots before operations. By matching the query co-view context descriptors of a working robot with the assigned candidate descriptors, the coarse localization is achieved. Finally, the refined localization is done through point cloud registration. The proposed solution can be applied to both single-robot and multi-robot global localization scenarios, especially when communication is impaired. The heterogeneous datasets used for the experiments cover both indoor and outdoor scenarios, utilizing various scanning modes. The average rotation and translation errors are within 1° and 0.30 m, indicating the proposed solution can provide reliable localization support despite communication failures, even across heterogeneous robots.

Deep Plug-and-Play Non-Iterative Cluster for 3D Global Feature Extraction

Efficient and accurate point cloud feature extraction is crucial for critical tasks such as 3D recognition and semantic segmentation. However, existing global feature extraction methods for 3D data often require designing different models for different input types (point clouds, voxels, and maps). This article proposes an efficient plug-and-play non-iterative clustering method (NICM) to establish a unified point cloud global feature extraction paradigm suitable for any input type to solve the above problems. The core idea of the NICM is to construct the connection between a single point and other global points based only on the cosine similarity between center points to achieve global feature extraction, which has linear complexity characteristics and can be combined with any existing feature extraction model. Additionally, to better integrate the features extracted by NICM and the original model, this article designs an adaptive feature fusion module is designed based on the gate unit, which retains similar features and effectively fuses dissimilar features based on their importance to downstream tasks. We have applied our method to downstream tasks such as point cloud recognition, part segmentation and scene segmentation. Sufficient experiments have proven that our method can provide comprehensive and robust features for the original model, and effectively improve the performance of downstream tasks.

MSSA: Multi-Representation Semantics-Augmented Set Abstraction for 3D Object Detection

Accurate recognition and localization of 3D objects is a fundamental research problem in 3D computer vision. Benefiting from transformation-free point cloud processing and flexible receptive fields, point-based methods have become accurate in 3D point cloud modeling, but still fall behind voxel-based competitors in 3D detection. We observe that the set abstraction module, commonly utilized by point-based methods for downsampling points, tends to retain excessive irrelevant background information, thus hindering the effective learning of features for object detection tasks. To address this issue, we propose MSSA, a Multi-representation Semantics-augmented Set Abstraction for 3D object detection. Specifically, we first design a backbone network to encode different representation features of point clouds, which extracts point-wise features through PointNet to preserve fine-grained geometric structure features, and adopts VoxelNet to extract voxel features and BEV features to enhance the semantic features of key points. Second, to efficiently fuse different representation features of keypoints, we propose a Point feature-guided Voxel feature and BEV feature fusion (PVB-Fusion) module to adaptively fuse multi-representation features and remove noise. At last, a novel Multi-representation Semantic-guided Farthest Point Sampling (MS-FPS) algorithm is designed to help set abstraction modules progressively downsample point clouds, thereby improving instance recall and detection performance with more important foreground points. We evaluate MSSA on the widely used KITTI dataset and the more challenging nuScenes dataset. Experimental results show that compared to PointRCNN, our method improves the AP of “moderate” level for three classes of objects by 7.02%, 6.76%, and 5.44%, respectively. Compared to the advanced point-voxel-based method PV-RCNN, our method improves the AP of “moderate” level by 1.23%, 2.84%, and 0.55% for the three classes, respectively.

Analysis of Macro- and Microphysical Characteristics of Ice Clouds over the Tibetan Plateau Using CloudSat/CALIPSO Data

Utilizing CloudSat/CALIPSO satellite data and ERA5 reanalysis data from 2007 to 2016, this study analyzed the distributions of optical and physical characteristics and change characteristics of ice clouds over the Tibetan Plateau (TP). The results show that the frequency of ice clouds in the cold season (November to March) on the plateau is over 80%, while in the warm season (May to September) it is around 60%. The average cloud base height of ice clouds in the warm season is 3–5 km, and mostly around 2 km in the cold season. The average cloud top height in the warm season is around 5–8 km, while in the cold season it is mainly around 4.5 km. The average thickness of ice clouds in both seasons is around 2 km. The statistical results of microphysical characteristics show that the ice water content is around 10−1 to 103 mg/m3, and the effective radius of ice clouds is mainly in the range of 10–90 μm. Both have their highest frequency in the west of the TP and lowest in the northeast. A comprehensive analysis of the change in temperature, water vapor, and ice cloud occurrence frequency shows that the rate of increase in water vapor in the warm season is greater than that in the cold season, while the rates of increase in both surface temperature and ice cloud occurrence are smaller than in the cold season. The rate of increase in temperature in the warm season is around 0.038 °C/yr, and that in the cold season is around 0.095 °C/yr. The growth rate of thin ice clouds in the warm season is around 0.15% per year, while that in the cold season is as high as 1% per year. The results suggest that the surface temperature change may be related to the occurrence frequency of thin ice clouds, with the notable increase in temperature during the cold season possibly being associated with a significant increase in the occurrence frequency of thin ice clouds.

Comparative analysis of cloud properties over drought- and flood-prone regions of western India using machine learning techniques

ABSTRACT Cloud properties are pivotal in analyzing rainfall patterns globally, especially in monsoon-dependent countries such as India. The impact of climate change becomes more important in regions susceptible to hydrometeorological events due to different monsoon regimes. To examine regional heterogeneity of cloud properties, this study investigates long-term trends and predictive capabilities for cloud properties in drought-prone and flood-prone regions of western India, utilizing satellite data and employing various machine learning (ML) models to comprehend intricate data patterns and enhance predictive accuracy. The results show higher mean and variability in cloud parameters over the flood-prone area due to favorable rain conditions, reflecting higher cloud microphysical and optical properties. These parameters negatively correlate with some cloud macrophysical properties along with the aerosol property in the drought-prone area. Additionally, a moderate correlation exists between certain cloud characteristics of one region and another. Employing ML algorithms for regression analysis and comparing them for cloud effective radius across regions shows promising results, with random forest (RF) demonstrating high coefficient of determination (0.86, 0.93) and low root mean squared error (0.76, 1.15) due to its robustness and high accuracy. This research enhances the understanding of regional heterogeneity in India and shows that ML can be helpful in predicting future cloud dynamics and climate variables identifying the most suitable model.

Ground-LIO: enhanced LiDAR-inertial odometry for ground robots based on ground optimization

Abstract In the field of LiDAR-based Simultaneous Localization and Mapping, the potential of ground point clouds to enhance pose estimation in mobile robots has yet to be fully realized. This paper focuses on leveraging ground point clouds to improve the performance of LiDAR-Inertial Odometry (LIO) systems for ground-based mobile robots. We begin by analyzing the characteristics of ground point clouds and the typical types of noise that affect their extraction and utilization. Ground point clouds are then extracted from denoised data. Given the generally local planar nature of ground point clouds, we propose a segmentation-and-refitting approach to process them. This method reduces the computational burden of residual calculation in pose estimation by avoiding redundant plane fitting. Additionally, we introduce a data structure designed for the efficient management and utilization of ground point clouds obtained through segmentation and refitting. This structure is particularly suited to the ground point cloud data produced by our method, enabling efficient access and registration through the continuous maintenance and consolidation of local plane parameters. Our method has been integrated into advanced LIO systems (Bai et al 2022 IEEE Robot. Autom. Lett. 7 4861–8), and experimental results on challenging datasets demonstrate its promising performance.

A global analysis of the fractal properties of clouds revealing anisotropy of turbulence across scales

Abstract. The deterministic motions of clouds and turbulence, despite their chaotic nature, have nonetheless been shown to follow simple statistical power-law scalings: a fractal dimension D relates individual cloud perimeters p to a measurement resolution, and turbulent fluctuations scale with the air parcel separation distance through the Hurst exponent, ℋ. However, it remains uncertain whether atmospheric turbulence is best characterized by a split isotropy that is three-dimensional (3D) with H=1/3 at small scales and two-dimensional (2D) with ℋ=1 at large scales or by a wide-range anisotropic scaling with an intermediate value of ℋ. Here, we introduce an “ensemble fractal dimension” De – analogous to D – that relates the total cloud perimeter per domain area 𝒫 as seen from space to the measurement resolution, and we show theoretically how turbulent dimensionality and cloud edge geometry can be linked through H=De-1. Observationally and numerically, we find the scaling De∼5/3 or H∼2/3, spanning 5 orders of magnitude of scale. Remarkably, the same scaling relationship links two “limiting case” estimates of 𝒫 evaluated at resolutions corresponding to the planetary scale and the Kolmogorov microscale, which span 10 orders of magnitude. Our results are nearly consistent with a previously proposed “23/9D” anisotropic turbulent scaling and suggest that the geometric characteristics of clouds and turbulence in the atmosphere can be easily tied to well-known planetary physical parameters.

Multi-feature enhancement based on sparse networks for single-stage 3D object detection

In the field of autonomous driving, the accuracy and real-time requirements for 3D object detection technology continue to improve, which is directly related to the commercialization process and market popularity of autonomous vehicles. Despite the efficiency of pillar-based coding for onboard systems, it falls short in terms of accuracy and the reduction of incorrect positives. In this paper, we will examine how to solve the problem of high incorrect rate and low accuracy of existing methods. Firstly, a MAP coding module is introduced to optimize previous point cloud feature coding modules, allowing for the efficient extraction of fine-grained features from point cloud data. Then, we introduce an innovative sparse dual attention (SDA) to efficiently filter out irrelevant details in feature extraction, thereby improving the pertinence and efficiency of information extraction. Finally, to address the potential loss of information from single local feature extraction, a local and global fusion module (CTGC) is introduced. Our method has proactively demonstrated its efficiency and accuracy through rigorous experimentation across diverse datasets. Analysis of the results leads to the conclusion that our solutions provide accurate and robust detection results. Code will be available at https://github.com/lcy199905/MyOpenPCDet.git.

EIDU-Net: edge-preserved inception DenseGCN U-Net for LiDAR point cloud segmentation

With the development of laser scanners and machine learning, point cloud semantic segmentation plays a significant role in autonomous driving, scene reconstruction, human-computer interaction, and other fields. In recent years, point cloud semantic segmentation based on deep learning has become one of the key research directions in point cloud processing. Due to the limited ability to exploit geometric details and contextual information in point clouds, most methods that adopt encoder-decoder architecture lose local structural information easily, especially detailed features, and extract features insufficiently. To address this issue, the edge-preserving inception DenseGCN U-Net (entitled as EIDU-Net) is proposed. EIDU-Net makes full use of the complementation between geometric details in the original point cloud and high-level features. The edge-preserved graph pooling (EGP) layer, the key module of the EIDU-Net, is designed to retain additional edge feature information from the original point cloud during pooling operations. Accordingly, the edge-preserved graph unpooling (EGU) layer can restore the feature graph more efficiently based on the additionally retained edge features. Extensive experiments demonstrate that our proposed EIDU-Net has remarkable improvements on semantic segmentation tasks under whatever S3DIS or Terracotta Warrior fragments. Our code is publicly available at https://github.com/caoxin918/EIDU-Net.

Regional differences in cloud characteristics at different depth, intensity and horizontal scale over South Asia during Indian summer monsoon using CloudSat and reanalysis data

Regional differences in cloud characteristics at different depth, intensity and horizontal scale over South Asia during Indian summer monsoon using CloudSat and reanalysis data

Weakly supervised 3D point cloud semantic segmentation for architectural heritage using teacher-guided consistency and contrast learning

Point cloud semantic segmentation is significant for managing and protecting architectural heritage. Currently, fully supervised methods require a large amount of annotated data, while weakly supervised methods are difficult to transfer directly to architectural heritage. This paper proposes an end-to-end teacher-guided consistency and contrastive learning weakly supervised (TCCWS) framework for architectural heritage point cloud semantic segmentation, which can fully utilize limited labeled points to train network. Specifically, a teacher-student framework is designed to generate pseudo labels and a pseudo label dividing module is proposed to distinguish reliable and ambiguous point sets. Based on it, a consistency and contrastive learning strategy is designed to fully utilize supervision signals to learn the features of point clouds. The framework is tested on the ArCH dataset and self-collected point cloud, which demonstrates that the proposed method can achieve effective semantic segmentation of architectural heritage using only 0.1 % of annotated points.

Cloud characteristics and their role in the 2024 United Arab Emirates extreme rainfall events

ABSTRACT Intensified by climate change, extreme rainfall events are frequently increasing and have become severe particularly in tropical and subtropical regions. On 16 April 2024, the United Arab Emirates (UAE) experienced a record-breaking flood event, characterized by ~ 250 mm of rain within a 24-hour period and surpassed the previous record of 1949. Later, on 2 May 2024, another rainfall event occurred but with low rainfall (~20 mm in 12 hours). These consecutive incidents raised a need to understand convective mechanism, so present study focus to analyse it using various cloud properties over Dubai. Our findings inferred that the April event was mostly driven by extensive cloud such as cumulonimbus which stretched up to ~ 16 km, with prominent features of high optical thickness (~150), small-sized cloud droplets (~23.89 µm), and considerable liquid water content (~2185 g/m−2). Further, we found high (~400–1800 J kg−1) and comparatively low (~0–700 J kg−1) potential energies, which trigerred convection on April 16 and May 02 respectively. Thus our study gained insights related to occurrence of convective activities at regional level using atmospheric and cloud parameters. These outcomes can be used as an input in climate models to improve weather patterns even in arid environments like Dubai, where cloud seeding is a regular practice.