Cloud Detection Challenge-Methods and Results

Moderate resolution imaging spectrometer (MODIS) images are widely used in land, ocean, and atmospheric monitoring, due to their wide spectral coverage, high temporal resolution, and convenient data acquisition. Accurate cloud detection is critical to the fine processing and application of MODIS images. Owing to spatial resolution limitations and the influence of mixed pixels, most MODIS cloud detection algorithms struggle to effectively recognize of clouds and ground objects. Here, we propose a novel cloud detection method based on land surface reflectance and a multiscale feature convolutional neural network to achieve high-precision cloud detection, particularly for thin clouds and clouds over bright surface. A monthly surface reflectance dataset was constructed by MODIS products (MOD09A1) and employed to provide background information for cloud detection. Difference-based samples were obtained using surface reflectance as well MODIS images of different phases based on difference operations. The multiscale feature network (MFCD-Net) using an atrous spatial pyramid pooling and a channel and spatial attention module integrated low-level spatial features and high-level semantic information to capture multiscale features and generate a high-precision cloud mask. For cloud detection experiments and quantitative analysis, 61 MODIS images acquired at different times on various underlying surface types were used. Cloud detection results were compared to those of UNet, Deeplabv3+, UNet++, PSPNet, and top of atmosphere-based (MFCD-TOA) methods. The proposed method performed well, with the highest overall accuracy (96.55%), precision (92.13%), and recall (88.90%). It improved cloud detection accuracy in various scenarios, reducing thin cloud omission and bright surface misidentification.

Accurate cloud detection is a crucial step in analyzing optical satellite imagery.The increasing application of small satellites equipped only with Visible and Near-Infrared (VNIR) sensors necessitates the evaluation of cloud detection under limited spectral bands.This study focuses on the intercomparison of three cloud detection methodologies-a custom threshold-based method, a machine learning model (Extreme Gradient Boosting; XGBoost), and a deep learning model (U-Net)-using only five VNIR bands from the CloudSEN12+ dataset.As a result, the U-Net model demonstrated higher performance than other approaches, achieving an Overall Accuracy (OA) of 85.6% and an Intersection over Union (IoU) of 65.3%.In particular, the U-Net significantly outperformed others in detecting cloud shadows, achieving an accuracy of 77.4%, nearly double that of XGBoost (46.0%).In spatial analysis, the threshold method misclassified bright surfaces as clouds, and XGBoost generated salt-and-pepper noise at the pixel level.The U-Net accurately detected the complex boundaries of clouds and shadows.Our results indicate that deep learning approaches that leverage spatial information are highly effective for cloud detection with limited spectral bands.This study provides a quantitative baseline to inform the development of operational cloud-detection algorithms for VNIR-only satellite missions.

In this paper, an approach for automatic cloud detection and localization in satellite remote sensing images is introduced. Cloud detection is useful in improving the accuracy of land cover classification in cloudy satellite images. The accurate detection of clouds in satellite images is vital for many atmospheric and terrestrial applications. In this paper we propose an algorithm for automatic cloud detection based on neutrosophic set and wavelet transform. The proposed approach uses both color and texture features for cloud detection. The input image is transformed into Lab color model for extracting the color features and gray scale image for extracting the texture features. Transformed images are converted into neutrosophic domain. An indeterminacy reduction operation is performed for getting better results. Finally a Fuzzy C-means clustering is performed on the true subsets. This gives the cloud detected image. This method is efficient in detecting thick clouds and thin clouds in Landsat images. Result analysis shows that the proposed algorithm can effectively detect the thin cloud. The proposed algorithm gives accurate results in less time complexity.

Cloud detection is fundamental for accurate weather monitoring, often achieved through remote sensing technology, such as satellite imagery or radar. This study explores the use of lidar ceilometer backscatter data, a rich but noisy source of atmospheric information, to enhance cloud detection. Leveraging data acquired from a Lufft CHM 15k ceilometer over three months near Mount Etna, Italy, we gathered a novel dataset comprising time-height plots derived from backscatter profiles. The Weather Research and Forecasting (WRF) model was used for ground-truth data labeling, ensuring reliable model validation. We benchmarked state-of-the-art deep learning architectures, including CNN-based models (e.g., ResNet50, VGG16, InceptionV3, EfficientNet) and the Vision Transformer (ViT), on our collected dataset. Among these, ResNet50 achieved the highest accuracy ( $$89.57\%$$ 89.57 % ), closely followed by ViT ( $$89.36\%$$ 89.36 % ), showcasing the efficacy of residual learning and transformer-based approaches in extracting complex patterns from atmospheric data. Our results highlight the potential of lidar-based systems for accurate cloud detection, complementing other remote sensing technologies. Our work contributes to the field by introducing a publicly available dataset and providing comprehensive benchmarking results that establish a baseline for future research. This study also opens avenues for broader applications of ceilometer data, such as the detection of pollutants and other atmospheric phenomena. Our dataset is publicly available at https://zenodo.org/records/10616434.

The deep convolutional neural network has made significant progress in cloud detection. However, the compromise between having a compact model and high accuracy has always been a challenging task in cloud detection for large-scale remote sensing imagery. A promising method to tackle this problem is knowledge distillation, which usually lets the compact model mimic the cumbersome model’s output to get better generalization. However, vanilla knowledge distillation methods cannot properly distill the characteristics of clouds in remote sensing images. In this paper, we propose a novel self-attention knowledge distillation approach for compact and accurate cloud detection, named Bidirectional Self-Attention Distillation (Bi-SAD). Bi-SAD lets a model learn from itself without adding additional parameters or supervision. With bidirectional layer-wise features learning, the model can get a better representation of the cloud’s textural information and semantic information, so that the cloud’s boundaries become more detailed and the predictions become more reliable. Experiments on a dataset acquired by GaoFen-1 satellite show that our Bi-SAD has a great balance between compactness and accuracy, and outperforms vanilla distillation methods. Compared with state-of-the-art cloud detection models, the parameter size and FLOPs are reduced by 100 times and 400 times, respectively, with a small drop in accuracy.

Cloud contamination is a critical source of errors in the data assimilation of hyperspectral infrared radiance (IR). Therefore, it is necessary to filter out cloudy observations. In this study, we review and summarize the principles and research progress of cloud detection methods for the hyperspectral IR in the past two decades. Based on the impact of IR data utilization on cloud detection results, cloud detection methods are categorized into five types, namely clear field-of-view (FOV) detection, clear channel detection, three-dimensional cloud detection, cloud-clearing and deep learning methods. Clear FOV methods and clear channel methods aim to identify the purely clear FOVs and spectral channels that are not affected by clouds, respectively. Cloud-clearing methods are used to reconstruct clear-column radiance for cloudy observations. Deep learning cloud detection methods can quickly learn the mapping relationship between infrared hyperspectral radiation characteristics and FOV cloud distribution from a large amount of infrared radiative information with known FOV cloud labels. In this paper, we discuss and provide an outlook on the key issues in current hyperspectral IR cloud detection. Specifically, we analyze and summarize the factors affecting cloud detection, such as surface background information, vertical cloud distribution, hyperspectral IR channel selection, improvements in cloud detection algorithms and model applicability. The results indicate the use of deep learning methods offer advantages in detection accuracy and algorithm efficiency of hyperspectral IR cloud detection.

The Wide Field of View (WFV) imaging system equipped on the GaoFen-6 (GF-6) optical remote sensing satellite can acquire an image with a swath width 800 km and a resolution of 16 m, which is the largest Earth observation swath width among similar satellites in the world. With the advantages of the high spatial resolution and the wide field of view, GF-6 WFV images are widely used in agricultural resources monitoring, forestry resources investigation, and disaster relief. However, the existence of clouds is inevitable problem in GF-6 WFV images, which influences their availability. To quickly and accurately detect cloud areas in GF-6 WFV images, a cloud detection method for GF-6 WFV images based on the spectrum and variance of superpixels is proposed in the paper. First, the GF-6 WFV image is down-sampled. The simple linear iterative clustering algorithm is used to segment down-sampled images to obtain superpixels. The initial cloud detection result is obtained based on the spectrum of superpixels. Second, the initial cloud detection result is refined based on the variance of superpixels to eliminate the influence of cloud-like ground objects. Finally, the refined cloud detection result is post-processed using the region growing algorithm and expansion algorithm. The post-processed cloud detection result is up-sampled to obtain cloud detection result of the GF-6 WFV image. The experimental results show that the recall and precision of the proposed method are 84.61% and 88.46%, respectively, providing good cloud detection results for GF-6 WFV images.

The existence of clouds has seriously affected the application of remote sensing data. Therefore, accurate cloud detection is of great significance in remote sensing image processing and application. Traditional cloud detection methods are complex to operate and often require the additional ancillary information. An automatic cloud detection method based on convolutional neural network (CNN) is proposed in this study. The method utilizes a convolutional network structure to classify training samples for cloud and non-cloud. In order to make full use of image information, images of different band numbers are applied to evaluate the influence of the spectrum on cloud detection. Experiments and verification on Landsat 8 images show that the proposed method based on CNN can comprehensively and automatically detect different types of clouds on different surface types, and the cloud detection result using 7 bands is the optimal. The algorithm takes full advantage of image information and does not rely on thermal infrared information, which has practical application value for improving image utilization and subsequent retrieval of remote sensing parameters.

Improved cloud detection in GOES scenes over the oceans

Accurate cloud detection is critical for spaceborne photon-counting light detection and ranging (LiDAR) systems like ICESat-2. This study presents the Normalized Difference Cloud Index (NDCI), a new radiometric algorithm for high-resolution daytime cloud identification. By conceptualizing the LiDAR system as an ultra-narrowband radiometer, the NDCI synergistically integrates active laser backscatter and passive solar background radiance. This approach amplifies atmospheric scattering signatures while suppressing interference from heterogeneous surface reflectance, providing a physically consistent framework that requires only standard ATL03 photon data. Validation across cryospheric, arid, and coastal regions demonstrates robust performance, with F1 scores consistently exceeding 0.81. Through regional threshold optimization via receiver operating characteristic (ROC) analysis, the algorithm achieves an F1 score of 0.97 and an area under the curve (AUC) of 0.99 over the Greenland ice sheet. A key advantage of the NDCI is its applicability to ICESat-2 weak beams, which currently lack dedicated operational cloud flags, thereby addressing spatial inconsistencies in multi-beam atmospheric screening. The NDCI provides a potential approach for cloud filtering in existing and future spaceborne photon-counting LiDAR data processing. Nevertheless, the NDCI algorithm has certain limitations. Due to its foundation on the Lambertian reflection model, its detection sensitivity to optically thin clouds is diminished over calm water surfaces under specular reflection. Additionally, the algorithm relies on accurate surface signal photon identification, and signal extraction errors in complex, rugged terrain may give rise to false positives in cloud detection.

Cloud detection is a basic and important task in many high level applications of remote sensing technology. Accurate cloud detection is a challenging task. On the one hand, clouds are normally exhibited at different sizes and thicknesses. On the other hand, the boundary between the clouds and their background is usually not sharp. To address the two challenges, we present a deep learning based strategy, i.e., Gradual Boundary Net, which generates a cloud mask for detecting clouds in one cloudy image. The Gradual Boundary Net consists of two stages: (a) coarse location stage and (b) gradual boundary refinement stage. At the coarse location stage, the feature extraction network with four encoders and a cascade partial decoder (CPD) is implemented to obtain the coarse score map for locating the clouds with different sizes and thicknesses roughly. At the gradual boundary refinement stage, the coarse score map is gradually refined by a erasing and fusion strategy with several gradual boundary attention modules (GBAMs). The refined cloud mask is obtained after the two stages. The experimental results validate that our Gradual Boundary Net performs well and achieves outstanding results. The code for implementing the proposed Gradual Boundary Net is available at https://github.com/kang-wu/Gradual-Boundary-Net.

In this paper, we propose an automatic and effective cloud detection algorithm for color aerial photographs. Based on the properties derived from observations and statistical results on a large number of color aerial photographs with cloud layers, we present a novel progressive refinement scheme for detecting clouds in the color aerial photographs. We first construct a significance map which highlights the difference between cloud regions and noncloud regions. Based on the significance map and the proposed optimal threshold setting, we obtain a coarse cloud detection result which classifies the input aerial photograph into the candidate cloud regions and noncloud regions. In order to accurately detect the cloud regions from the candidate cloud regions, we then construct a robust detail map derived from a multiscale bilateral decomposition to guide us in removing noncloud regions from the candidate cloud regions. Finally, we further perform a guided feathering to achieve our final cloud detection result, which detects semitransparent cloud pixels around the boundaries of cloud regions. The proposed method is evaluated in terms of both visual and quantitative comparisons, and the evaluation results show that our proposed method works well for the cloud detection of color aerial photographs.

Introducing two Random Forest based methods for cloud detection in remote sensing images

Clouds are an important component of weather and climate change and have a significant impact on ecology, weather forecasting and aviation safety. Cloud detection is a preprocessing step in many satellite image processing and remote sensing inversion. Clouds not only cover the subsurface, but also absorb and scatter solar radiation, which affects the remote sensing analysis and study of the surface and reduces the utilization of data. Accurate detection of cloud-covered areas in satellite images can effectively reduce the interference of cloud cover on remote sensing data application. The Fengyun-4B Satellite is the latest generation of geostationary meteorological satellites in China, with significant performance advantages. In this paper, a land cloud detection algorithm for AGRI sensors is constructed based on the existing cloud detection algorithm using the AGRI full disk data of Fengyun 4B Satellite. Through the analysis of cloud detection product quality, the algorithm threshold is optimized to significantly improve the accuracy of cloud detection. The experimental results show that the algorithm has good overall cloud detection performance in full disk imagery, especially in the thick cloud region, but there are some misclassifications in the high brightness surface region such as the Tibetan Plateau. This study expands the application scenarios of domestic geostationary meteorological satellites, and provides new technical support for meteorological monitoring and remote sensing applications.

The cloud covers most of the Earth's space and plays an important role in the Earth's energy balance. Moreover, the cloud is one of the most vital and active factors in the weather and climate. In addition, the cloud usually covers ground information, which causes many problems and difficulties in the processing of image registration and fusion. So cloud detection is very significant and necessary. DSCOVR (deep space climate observatory) satellite was launched in 2015. The new EPIC (earth polychromatic imaging camera) data from it has some special characteristics, such as the hemisphere scale and the wide range of band spectrum (from ultraviolet bands, visible bands to infrared bands). Hence, we propose a new cloud detection method for EPIC data in the way of normalized difference cloud index (NDCI). In our method, first, we analyze the different reflection characteristics of different bands, especially the new ultraviolet bands, and select appropriate bands to detect clouds. Combined with the applications of EPIC data bands, 340nm, 388nm, 680nm and 780nm are identified as the main research bands. Secondly, we analyze the reflection characteristics of clouds including thin clouds and residual clouds. Based on the above two aspects, we define the cloud index (CI) to detect clouds, which effectively reduces the influence of underlying surface on the cloud detection results. In order to verify the effectiveness of the proposed cloud detection method, other three cloud detection methods are compared, including the visible light cloud detection method, SVM cloud detection method and traditional NDCI cloud detection method. The experimental results show that our proposed method effectively detects thin clouds and residual clouds that are not detected by other methods, even in winter and in summer.