Cloud Detection Research Articles

I-MPaFS: enhancing EDoS attack detection in cloud computing through a data-driven approach

Cloud computing offers cost-effective IT solutions but is susceptible to security threats, particularly the Economic Denial of Sustainability (EDoS) attack. EDoS exploits cloud elasticity and the pay-per-use billing model, forcing users to incur unnecessary costs. This research introduces the Integrated Model Prediction and Feature Selection (I-MPaFS) framework to address EDoS attacks. I-MPaFS framework enhances an existing dataset to improve performance, using the generated data to build a Random Forest model for EDoS detection. Our investigation employs the UNSW-NB15, CSE-CIC-IDS18 and NSL-KDD datasets, demonstrating the proposed method’s superiority over existing techniques. The model achieved recall scores of 99.45% on the UNSW-NB15 dataset, 98.19% on the CSE-CIC-IDS18 dataset, and 99.82% on the NSL-KDD dataset, highlighting its reliability and efficacy in safeguarding cloud users from financial exploitation. This study contributes to the field by evaluating current EDoS detection methods, introducing the I-MPaFS framework, validating its performance with benchmark datasets, and comparing its effectiveness against state-of-the-art techniques. The findings affirm the significant potential of I-MPaFS in enhancing cloud security and protecting users from EDoS attacks.

CLOWN: The PASO Cloud Detection for Optimization of Automatic Optical Surveys

Orbiting space objects have become in the last decade a major nuisance impacting ground astronomy and orbiting space assets, from observatories to satellites and space stations. In particular with the rise of the satellite population in Low Earth Orbits, space objects are becoming an even bigger threat and a strong problem to astronomical observations. To tackle these threats, several coordinated surveillance networks composed of dedicated sensors (telescopes, radars, and laser ranging facilities) track and survey space objects, from debris to active satellites. As part of the European Space Surveillance & Tracking network, Portugal is developing the Pampilhosa da Serra Space Observatory, with both radio and optical telescopes dedicated to the Space Situational Awareness domain, deployed at a Dark Sky destination. To optimize telescope survey time, we developed CLOud Watcher at Night (CLOWN), an application interface that automatically monitors clouds in real time. This software can correctly trace cloud positions in the sky and provide accurate pointing information to the observation planning of the optical telescope to avoid cloudy areas. CLOWN only requires the use of an all-sky camera, which is already a norm in observatories with optical telescopes and can be used with any camera, including those for which no information about its model specification do exist. CLOWN does not require great computing power, and it does not require the installation of additional equipment. CLOWN results are very promising and confirm that the app can correctly identify clouds in a variety of different conditions and cloud types.

Swincloud: a hybrid network for cloud detection in thermal infrared remote sensing images

ABSTRACT Cloud cover is a significant factor affecting the effectiveness of satellite-based Earth observations. Existing cloud detection algorithms primarily rely on imaging data from satellite sensors in the visible to near-infrared spectral range, making it challenging to achieve day-and-night cloud monitoring. Convolutional neural networks have shown outstanding performance in previous cloud detection algorithms due to their robust ability to extract local information. However, their inherent inductive bias limits their capacity to learn long-range semantic information. To address these challenges, we proposed SwinCloud, a U-shaped semantic segmentation network based on an enhanced Swin Transformer for cloud detection in the thermal infrared spectral range. Specifically, we augment the Swin Transformer's window attention module with a CNN-based parallel pathway to effectively model global-local information. We employ a feature fusion module before the final upsampling module in the decoder to better integrate low-level spatial information and high-level semantic information. On the Landsat-8 cloud detection dataset, our model outperforms state-of-the-art methods. When transferred to the SDGSAT-TIS cloud detection dataset, the mIOU of experiment results reaches 69.9%, demonstrating the strong transferability of SwinCloud across different sensors. We also applied SwinCloud to cloud detection in the visible bands of Landsat-8. The results demonstrated SwinCloud's generalization capability across different bands.

Supercooled Water Cloud Detection From Polarized Multi‐Angle Imager Data Using 1.37 μm Water Vapor Polarized Channel

AbstractDetecting supercooled water clouds (SWCs) is essential for enhancing artificial rainfall, preventing aircraft ice accretion, and developing a better understanding of radiative energy balance. The 1.37 μm channel, known as strong water vapor absorbing, was made polarized in the polarized multi‐angle imager (PMAI) onboard FengYun‐3G satellite. The infight data shown that the new 1.37 μm polarized channel could be used to detect SWCs. The cloudbow is observed around the 140° scattering angle in the 1.37 μm polarization image, with a maximum polarization reflectance of approximately 0.04–0.06. The indicated water clouds with spherical particles in the high‐level altitude could be SWCs. Then, the SWCs detected by 1.37 μm polarized channel is verified using polarized reflectance of other channels, the reflectance difference of channels, and thermal infrared bright temperature. The presence of cloudbow in 1.03 and 1.64 μm channels indicate liquid water cloud. The reflectance difference between 1.03 and 1.64 μm of SWCs agree with characteristic of water cloud. The thermal infrared channels from the imager on the same platform indicate cold cloud with the brightness temperature far below 273.16 K. Therefore, the only use of 1.37 μm polarized channel could perform the identification of SWCs. PMAI provides a powerful tool for monitoring supercooled water clouds.

Cloud detection for HY-1C/COCTS over the ocean based on spectral-and-textural-information-guided deep neural network

AbstractGiven that clouds can absorb and scatter radiation signals in the visible and infrared bands, cloud detection is a key preprocessing step for ocean color and sea surface temperature retrievals. In this research, a Spectral-and-Textural-Information-Guided deep neural Network (STIGNet) is designed for cloud detection in global ocean data from the Haiyang-1C (HY-1C)/Chinese Ocean Color and Temperature Scanner (COCTS). Considering the spectral and textural properties of clouds, the model incorporates HY-1C/COCTS spectral data, differences in brightness temperature (BT), local statistical characteristics of BT, and geographical location information–all of which are closely related to cloud features. Notably, an edge learning module is implemented to emphasize edge features during the training process. We construct a HY-1C/COCTS cloud detection dataset to train and test the cloud detection model. In the dataset, labels are generated by combining the Bayesian cloud detection method with a manual mask. Analysis of the resulting cloud detection images indicates that STIGNet exhibits accurate performance across various types of clouds while showing minimal overestimated errors in areas such as ocean fronts or sun glints, where they tend to occur frequently. The ablation experiments performed on physical-based input features and edge learning modules show enhancements in cloud detection accuracy. Evaluation results demonstrate an overall accuracy of 96.64%, with a cloud overestimated error of 1.61% and a cloud missed error of 1.76%. These findings highlight the effectiveness of STIGNet in generating precise cloud masks for HY-1C/COCTS data.

GS–CDNet: a remote sensing image cloud detection method with geographic spatial data integration

ABSTRACT In optical remote sensing images, clouds exhibit irregular scales and boundaries that vary with elevation across diverse geographical locations. To accurately capture the diverse visual patterns of clouds, we propose a cloud image segmentation approach named GS-CDNet (Geographic Spatial Data-Cloud Detection Network), which is based on the integration of geospatial data with multifaceted self-attention feature extraction, multi-scale feature aggregation, and boundary clarification techniques.Firstly, we utilize geographical coordinates from optical remote sensing images to extract a raster DEM (Digital Elevation Model) from SRTM3. This process creates a dataset consisting of elevation images, longitude, and latitude maps as geospatial data, enhancing the model’s capability in spatial positioning for cloud detection. Secondly, the proposed method consists of three interconnected modules within the cloud detection network: the Interleaved Self-Attention module(ISAM) utilizes a variety of self-attention mechanisms in an interleaved manner to extract multi-scale feature information.The Bidirectional Multi-Scale Feature Fusion Module(BIMFM) is responsible for integrating features, enabling a more comprehensive contextual understanding. The Boundary Extraction Module(BEM) utilizes a residual structure to generate a boundary cloud mask, effectively addressing the common issue of boundary blurring in multi-scale cloud masks. Finally, we compared and evaluated GS-CDNet with other cloud detection methods and conducted an ablation study on the key components of the method. The validation of generalization performance demonstrates the exceptional performance of the proposed model in cloud mask generation. Geospatial data and the different modules of the method play a significant role in the model.

Stability of cloud detection methods for Land Surface Temperature (LST) Climate Data Records (CDRs)

The stability of a climate data record (CDR) is essential for evaluating long-term trends in surface temperature using remote sensing products. In the case of a satellite-derived CDR of land surface temperature (LST), this includes the stability of processing steps prior to the estimation of the target climate variable. Instability in the masking of cloud-affected observations can result in non-geophysical trends in a LST CDR. This paper provides an assessment of cloud detection performance stability over a 25-year LST CDR generated using data from the second Along-Track Scanning Radiometer (ATSR-2), the Advanced Along-Track Scanning Radiometer (AATSR), the Moderate Resolution Imaging Spectroradiometer (MODIS) and the Sea and Land Surface Temperature Radiometer (SLSTR). We evaluate three cloud detection methodologies, one fully Bayesian, one naïve probabilistic and the operational threshold-based cloud mask provided with each sensor, at four in-situ ceilometer sites. Of the 12 algorithm-site combinations assessed, only two (17 %) were stable across the full timeseries with respect to both cloud contamination and missed clear-sky observations. Five (42 %) were stable with respect to missed clear-sky observations only. The associated impacts on LST trends in the CDR could be as large as (+/−)0.73 K per decade (0.43 K per decade above the target stability), which means that attention needs to be paid to this aspect of stability in order to understand uncertainty in long-term observed trends. Given that cloud detection stability has not to our knowledge been previously assessed for any target climate variable, this conclusion may apply more broadly to other satellite-derived CDRs.

Harnessing DBSCAN and auto-encoder for hyper intrusion detection in cloud computing

Harnessing DBSCAN and auto-encoder for hyper intrusion detection in cloud computing

DB-Net: dual-branch deep learning network for cloud detection utilizing attention mechanism and cascaded multiscale feature fusion

DB-Net: dual-branch deep learning network for cloud detection utilizing attention mechanism and cascaded multiscale feature fusion

Multi‐Layer Cloud Detection and Distributions Over the Asia–Pacific Region Based on Geostationary Satellite Imagers

AbstractA large portion of cloud scenes over the globe shows multiple layers composed of different phases, in general with ice clouds on the top and liquid water clouds beneath. Such multi‐layer (ML) clouds constitute major challenges in cloud observations and weather and climate modeling. This study improved a threshold algorithm for detecting ice‐over‐water ML clouds using geostationary satellites. Optimal thresholds were established for the spectral characteristics of the Advanced Himawari Imager (AHI) and the Advanced Geostationary Radiation Imager (AGRI), accounting for differences between land and ocean surfaces. Validation with collocated space radar and lidar measurements indicated the identification accuracies of approximately 82% over the land and 76% over the ocean. Annual distributions of ML clouds inferred by AHI and AGRI exhibited strong similarity. Furthermore, 6 years of hourly observations revealed distinct monthly and daily variations in ice‐over‐water clouds over the Asia–Pacific region. The ML cloud monthly variations were similar to those of the seasonal convection cycle, with occurrence frequencies over the typical regions higher in summer (maximum ∼27%) and lower (minimum 6%–10%) in winter. Regarding daily variations, ice‐over‐water clouds occurred more frequently around local noon over most of the six time zones (from UTC + 06 to UTC + 11) throughout all seasons. The refined spatiotemporal distribution of ML clouds, particularly the daily variations, is possible to improve our understanding of cloud vertical distributions and radiative effects, and has the potential to promote subsequent validation and parameterization of cloud overlapping in global climate modeling.

Robust algorithm for automatic surface-based outlier detection in MBES point clouds

Bathymetric multibeam echosounder systems (MBES) provide high-resolution mapping of underwater topography but are highly susceptible to errors due to harsh environmental conditions and the measurement process. Traditionally, manual post-processing is required to ensure data quality, a time-consuming, expensive, and subjective task. To address this issue, we propose a surface-based algorithm for pre-processing and cleaning MBES data that reduces manual intervention and improves consistency. A surface-based algorithm models the underwater topography as a surface instead of processing individual points. By assuming a continuous surface for underwater geometry, the algorithm easily identifies observations that deviate significantly from this model. The method combines a hierarchical B-spline surface with iterative robust estimation to automate data cleaning. Preliminary results on example datasets show a balanced outlier detection accuracy of 0.99, with manual processing time reduced from 2 days to just 30 min.

Horse Herd optimization with deep learning based intrusion detection in cloud computing environment

Horse Herd optimization with deep learning based intrusion detection in cloud computing environment

Quartz Clouds in the Dayside Atmosphere of the Quintessential Hot Jupiter HD 189733 b

Recent mid-infrared observations with JWST's Mid-Infrared Instrument Low Resolution Spectrometer (MIRI LRS) have resulted in the first direct detections of absorption features from silicate clouds in the transmission spectra of two transiting exoplanets, WASP-17 b and WASP-107 b. In this Letter, we measure the mid-infrared (5–12 μm) dayside emission spectrum of the benchmark hot Jupiter HD 189733 b with MIRI LRS by combining data from two secondary-eclipse observations. We confirm the previous detection of H2O absorption at 6.5 μm from Spitzer's Infrared Spectrograph (IRS) and additionally detect H2S as well as an absorption feature at 8.7 μm in both secondary-eclipse observations. The excess absorption at 8.7 μm can be explained by the presence of small (∼0.01 μm) grains of SiO2[s] in the uppermost layers of HD 189733 b’s dayside atmosphere. This is the first direct detection of silicate clouds in HD 189733 b’s atmosphere, and the first detection of a distinct absorption feature from silicate clouds on the dayside of any hot Jupiter. We find that models including SiO2[s] are preferred by 6–7σ over clear models and those with other potential cloud species. The high-altitude location of these silicate particles is best explained by formation in the hottest regions of HD 189733 b’s dayside atmosphere near the substellar point. We additionally find that HD 189733 b’s emission spectrum longward of 9 μm displays residual features not well captured by our current atmospheric models. When combined with other JWST observations of HD 189733 b’s transmission and emission spectra at shorter wavelengths, these observations will provide us with the most detailed picture to date of the atmospheric composition and cloud properties of this benchmark hot Jupiter.

An open dataset for individual tree detection in UAV LiDAR point clouds and RGB orthophotos in dense mixed forests

We present an open access dataset for development, evaluation, and comparison of algorithms for individual tree detection in dense mixed forests. The dataset consists of a detailed field inventory and overlapping UAV LiDAR and RGB orthophoto, which make it possible to develop algorithms that fuse multimodal data to improve detection results. Along with the dataset, we describe and implement a basic local maxima filtering baseline and an algorithm for automatically matching detection results to the ground truth trees for detection algorithm evaluation.

An Efficient Observational Strategy for the Detection of the Oort Cloud

The Oort cloud is presumably a pristine relic of the solar system formation. Detection of the Oort cloud may provide information regarding the stellar environment in which the Sun was born and on the planetesimal population during the outer planets’ formation phase. The best suggested approach for detecting Oort cloud objects in situ, is by searching for subsecond occultations of distant stars by these objects. Following Brown & Webster, we discuss the possibility of detecting Oort cloud objects by observing near the quadrature direction. Due to the Earth’s projected velocity, the occultations are longer near the quadrature direction and are therefore easier to detect, but have lower rate. We show that, for ≲1 m size telescopes, the increased exposure time will result in about one to 3 orders of magnitude increase in the number of detectable stars that have an angular size smaller than the Fresnel scale and are therefore suitable for an occultation search. We discuss the ability of this method to detect Oort cloud objects using existing survey telescopes, and we estimate the detection rate as a function of the power-law index of the size distribution of the Oort cloud objects and their distance from the Sun. We show that occultations detected using ≈1 s integration by ≲1 m telescopes at the optimal region near the quadrature points will be marginally dominated by Oort cloud objects rather than Kuiper belt objects.

Snow Detection in Gaofen-1 Multi-Spectral Images Based on Swin-Transformer and U-Shaped Dual-Branch Encoder Structure Network with Geographic Information

Snow detection is imperative in remote sensing for various applications, including climate change monitoring, water resources management, and disaster warning. Recognizing the limitations of current deep learning algorithms in cloud and snow boundary segmentation, as well as issues like detail snow information loss and mountainous snow omission, this paper presents a novel snow detection network based on Swin-Transformer and U-shaped dual-branch encoder structure with geographic information (SD-GeoSTUNet), aiming to address the above issues. Initially, the SD-GeoSTUNet incorporates the CNN branch and Swin-Transformer branch to extract features in parallel and the Feature Aggregation Module (FAM) is designed to facilitate the detail feature aggregation via two branches. Simultaneously, an Edge-enhanced Convolution (EeConv) is introduced to promote snow boundary contour extraction in the CNN branch. In particular, auxiliary geographic information, including altitude, longitude, latitude, slope, and aspect, is encoded in the Swin-Transformer branch to enhance snow detection in mountainous regions. Experiments conducted on Levir_CS, a large-scale cloud and snow dataset originating from Gaofen-1, demonstrate that SD-GeoSTUNet achieves optimal performance with the values of 78.08%, 85.07%, and 92.89% for IoU_s, F1_s, and MPA, respectively, leading to superior cloud and snow boundary segmentation and thin cloud and snow detection. Further, ablation experiments reveal that integrating slope and aspect information effectively alleviates the omission of snow detection in mountainous areas and significantly exhibits the best vision under complex terrain. The proposed model can be used for remote sensing data with geographic information to achieve more accurate snow extraction, which is conducive to promoting the research of hydrology and agriculture with different geospatial characteristics.

In situ observations of supercooled liquid water clouds over Dome C, Antarctica, by balloon-borne sondes

Abstract. Clouds in Antarctica are key elements that affect radiative forcing and thus Antarctic climate evolution. Although the vast majority of clouds are composed of ice crystals, a non-negligible fraction constitutes supercooled liquid water (SLW; water held in liquid form below 0 °C). Numerical weather prediction models have great difficulty in forecasting SLW clouds over Antarctica, favouring ice at the expense of liquid water and therefore incorrectly estimating the cloud radiative forcing. Remote-sensing observations of SLW clouds have been carried out for several years at Concordia Station (75° S, 123° E; 3233 m above mean sea level), combining active lidar measurements (SLW cloud detection) and passive HAMSTRAD microwave measurements (liquid water path, LWP). The present project aimed at in situ observations of SLW clouds using sondes developed by the company Anasphere, specifically designed for SLW content (SLWC) measurements. These SLWC sondes were coupled to standard meteorological pressure–temperature–humidity sondes from Vaisala and released under meteorological balloons. During the 2021–2022 summer campaign, 15 launches were made, of which 7 were scientifically exploitable above a height of 400 m above ground level, a threshold height imposed by the time the SLWC sonde takes to stabilize after launch. The three main outcomes from our analyses are as follows: (a) the first in situ observations so far of SLW clouds in Antarctica with SLWC sondes; (b) on average, the consistency of SLW cloud heights as observed by in situ sondes and remote-sensing lidar; and (c) the liquid water path (vertically integrated SLWC) deduced by the sondes being generally equal to or greater than the LWP remotely sensed by HAMSTRAD. In general, the SLW clouds were observed in a layer close to saturation (U > 80 %) or saturated (U ∼ 100 %–105 %) just below or at the lowermost part of the entrainment zone, or capping inversion zone, which exists at the top of the planetary boundary layer and is characterized by an inflection point in the potential temperature vertical profile. Our results are consistent with the theoretical view that SLW clouds form and remain at the top of the planetary boundary layer.

GF-4 high-resolution texture and FY-4A multispectral data fusion: Two case studies for enhancing early convective cloud detection

Early detection of convective clouds is vital for minimizing hazardous impacts. Forecasting convective initiation (CI) using current multispectral geostationary meteorological satellites is often challenged by high false-alarm rates and missed detections caused by limited resolution. In contrast, high-resolution earth observation satellites offer more detailed texture information, improving early detection capabilities. The authors propose a novel methodology that integrates the advanced features of China's latest-generation satellites, Gaofen-4 (GF-4) and Fengyun-4A (FY-4A). This fusion method retains GF's high-resolution details and FY-4A's multispectral information. Two cases from different observational scenarios and weather conditions under GF-4's staring mode were carried out to compare the CI forecast results based on fused data and solely on FY-4A data. The fused data demonstrated superior performance in detecting smaller-scale convective clouds, enabling earlier forecasting with a lead time of 15–30 minutes, and more accurate location identification. Integrating high-resolution earth observation satellites into early convective cloud detection provides valuable insights for forecasters and decision-makers, particularly given the current resolution limitations of geostationary meteorological satellites.摘要对流云的早期探测对于降低天气致灾风险至关重要. 当前静止气象卫星受其分辨率的限制, 在预测对流初生 (CI) 时仍存在较高的虚警率和漏报率. 对比而言, 高分辨率的地球观测卫星能够提供更丰富的纹理细节, 有助于提升对流云早期探测的能力. 作者提出了一种创新性的方法, 融合GF-4的高分辨率细节和FY-4A的多光谱信息, 以优化对流云的早期识别和预测. 通过对GF-4凝视模式下两种不同天气条件和观测场景的案例分析, 融合数据在探测更小尺度的对流云方面具有明显优势, 一定程度解决漏报难题, 另一方面能够将对流初生的可探测时间提前, 更精确表现对流爆发位置和更准确刻画对流发展过程. 在当前静止气象卫星分辨率受限的条件下, 这种高分辨率地球观测卫星数据的融合应用能够为气象预报员和决策者提供更有价值的观测视角.

Lightweight U-Net based on depthwise separable convolution for cloud detection onboard nanosatellite

Lightweight U-Net based on depthwise separable convolution for cloud detection onboard nanosatellite

Unambiguous detection of mesospheric CO2 clouds on Mars using 2.7 μm absorption band from the ACS/TGO solar occultations

Mesospheric CO2 clouds are one of two types of carbon dioxide clouds known on Mars. We present observations of mesospheric CO2 clouds made by Atmospheric Chemistry Suite (ACS) onboard the ESA-Roscosmos ExoMars Trace Gas Orbiter (TGO). We analyzed 1663 solar occultation sessions of Thermal InfraRed (TIRVIM) and Middle InfraRed (MIR) channels of ACS covering more than two Martian years that contain spectra of 2.7 μm carbon dioxide ice absorption band. That allowed us to unambiguously discriminate carbon dioxide ice aerosols from mineral dust and water ice aerosols, not relying on the information of atmospheric thermal conditions. CO2 clouds were detected in eleven solar occultation observations at altitudes from 39 km to 90 km. In five cases, there were two or three layers of CO2 clouds that were vertically separated by 5–15 km gaps. Effective radius of CO2 aerosol particles is in the range of 0.1–2.2 μm. Spectra produced by the smallest particles indicate a need for a better resolved CO2 ice refractive index. Nadir optical depth of CO2 clouds is in the range 5 × 10−4–4 × 10−2 at both 2.7 μm and 0.8 μm. Asymmetrical diurnal distribution of detections observed by ACS is potentially due to local time variations of temperature induced by thermal tides. Two out of five cases of carbon dioxide cloud detections made by the TIRVIM instrument reveal the simultaneous presence of CO2 ice and H2O ice aerosols. Temperature profiles measured by the Near InfraRed (NIR) channel of ACS are used to calculate CO2 saturation ratio S at locations of carbon dioxide clouds. Supersaturation S > 1 is detected in only 6 out of 19 cases of CO2 cloud layers; extremely low values of S < 0.1 are found in 9 out of 19 cases.