The integration of satellite data with deep learning has revolutionized various tasks in remote sensing, including classification, object detection, and semantic segmentation. Cloud segmentation in high-resolution satellite imagery is a critical application within this domain, yet progress in developing advanced algorithms for this task has been hindered by the scarcity of specialized datasets and annotation tools. This study addresses this challenge by introducing CloudLabel, a semi-automatic annotation technique leveraging region growing and morphological algorithms including flood fill, connected components, and guided filter. CloudLabel v1.0 streamlines the annotation process for high-resolution satellite images, thereby addressing the limitations of existing annotation platforms which are not specifically adapted to cloud segmentation, and enabling the efficient creation of high-quality cloud segmentation datasets. Notably, we have curated the Annotated Dataset for Training Cloud Segmentation (ADTCS) comprising 32,065 images (512 × 512) for cloud segmentation based on CloudLabel. The ADTCS dataset facilitates algorithmic advancement in cloud segmentation, characterized by uniform cloud coverage distribution and high image entropy (mainly 5–7). These features enable deep learning models to capture comprehensive cloud characteristics, enhancing recognition accuracy and reducing ground object misclassification. This contribution significantly advances remote sensing applications and cloud segmentation algorithms.

This study introduces an advanced ensemble methodology employing lightweight neural network models for identifying severe convective clouds from FY-4B geostationary meteorological satellite imagery. We have constructed a FY-4B based severe convective cloud dataset by a combination of algorithms and expert judgment. Through the ablation study of a model ensembling combination of multiple specialized lightweight architectures—ENet, ESPNet, Fast-SCNN, ICNet, and MobileNetV2—the optimal EFNet (ENet- and Fast-SCNN-based network) not only achieves real-time processing capabilities but also ensures high accuracy in severe weather detection. EFNet consistently outperformed traditional, heavier models across several key performance indicators: achieving an accuracy of 0.9941, precision of 0.9391, recall of 0.9201, F1 score of 0.9295, and computing time of 18.65 s over the test dataset of 300 images (~0.06 s per 512 × 512 pic). ENet shows high precision but misses subtle clouds, while Fast-SCNN has high sensitivity but lower precision, leading to misclassifications. EFNet’s ensemble approach balances these traits, enhancing overall predictive accuracy. The ensemble method of lightweight models effectively aggregates the diverse strengths of the individual models, optimizing both speed and predictive performance.

When vortex electromagnetic waves propagate through a turbulent atmosphere, the amplitude and phase of the electromagnetic waves are disturbed, creating the scintillation effect. According to the scintillation index of vortex waves, a new method of retrieving the turbulent refraction structure parameter was proposed using a genetic algorithm, and the feasibility of this method was verified by simulated experiments. The numerical results showed that the inversed value obtained by the genetic algorithm was close to the real parameter when the turbulent inner scale and outer scale were fixed. However, there was a gap between the inversed value and the real parameter when only the turbulent outer scale was fixed. These results suggest that vortex wave data can be used for turbulent refraction structure parameter inversion, and they provide new research directions for atmospheric remote sensing.

Mars atmospheric dynamics are crucial for understanding its climate and weather patterns, especially over plateaus. Previous studies have explored localized atmospheric heating mechanisms over Mars plateaus only to a little extent. The local atmospheric heating dynamics over the Tharsis plateau, especially during global dust storms (GDSs), have not been quantitatively analyzed before. Based on reanalysis datasets, our analysis reveals that the central highlands of Tharsis experience ~130 K diurnal temperature fluctuations, driven by intense daytime convective activity. Surface temperature and near-surface air temperatures show fluctuations approximately 25 K and 20 K higher than those at similar latitudes, respectively. We quantify a super-adiabatic lapse rate around noon that suggests strong atmospheric instability, previously unquantified in this region. By dusk, the atmosphere stabilizes, presenting a homogenized condition. At aphelion, sensible heating and adiabatic terms control the atmospheric heating, while, at perihelion, radiative and sensible heating predominate. Notably, the onset of GDS significantly alters this dynamic, reducing the ground–air temperature gap from 17 K to 5 K and enhancing diabatic heating (adiabatic cooling) in the mid-to-lower (mid-to-upper) troposphere, with increases in radiative components up to 60 W/m².

In the field of remote sensing image analysis, the issue of cloud interference in high-resolution images has always been a challenging problem, with traditional methods often facing limitations in addressing this challenge. To this end, this study proposes an innovative solution by integrating radiative feature analysis with cutting-edge deep learning technologies, developing a refined cloud segmentation method. The core innovation lies in the development of FFASPPDANet (Feature Fusion Atrous Spatial Pyramid Pooling Dual Attention Network), a feature fusion dual attention network improved through atrous spatial convolution pooling to enhance the model’s ability to recognize cloud features. Moreover, we introduce a probabilistic thresholding method based on pixel radiation spectrum fusion, further improving the accuracy and reliability of cloud segmentation, resulting in the “FFASPPDANet+” algorithm. Experimental validation shows that FFASPPDANet+ performs exceptionally well in various complex scenarios, achieving a 99.27% accuracy rate in water bodies, a 96.79% accuracy rate in complex urban settings, and a 95.82% accuracy rate in a random test set. This research not only enhances the efficiency and accuracy of cloud segmentation in high-resolution remote sensing images but also provides a new direction and application example for the integration of deep learning with radiative algorithms.

In the atmospheric system of Mars, vertical interactions are crucial, yet quantitative studies addressing this issue remain scarce. Based on simulations using the Mars PCM-LMDZ, we present the first frequency-domain quantitative analysis of the vertical interactions among Martian atmospheric dust, zonal circulation, and the migrating diurnal tide (DW1), employing Partial Directed Coherence (PDC) techniques to quantify the strength of associations between different variables. Our findings reveal a chain of influence where sub-seasonal-scale dust signals in the troposphere, through the Doppler effect of middle atmospheric zonal winds, transmit modulated energy to the DW1 in the upper mesosphere, thereby facilitating interlayer atmospheric interactions. The radiative heating from dust activities enhances the residual mean meridional circulation, which, under the influence of the Coriolis force, further accelerates the westerlies. Although gravity wave activity also contributes to the acceleration of the westerlies, its forcing generally remains below 5 m/s, which is relatively weak compared to the impact of intense dust activities in the warm scenario experiments (approximately 20 m/s). Overall, this study quantifies the interactions among atmospheric layers by means of PDC technology and analytically demonstrates how dust energy is transferred to mesospheric tides by shaping the zonal winds in between.