The tobacco in plateau mountains has the characteristics of fragmented planting, uneven growth, and mixed/interplanting of crops. It is difficult to extract effective features using an object-oriented image analysis method to accurately extract tobacco planting areas. To this end, the advantage of deep learning features self-learning is relied on in this paper. An accurate extraction method of tobacco planting areas based on a deep semantic segmentation model from the unmanned aerial vehicle (UAV) remote sensing images in plateau mountains is proposed in this paper. Firstly, the tobacco semantic segmentation dataset is established using Labelme. Four deep semantic segmentation models of DeeplabV3+, PSPNet, SegNet, and U-Net are used to train the sample data in the dataset. Among them, in order to reduce the model training time, the MobileNet series of lightweight networks are used to replace the original backbone networks of the four network models. Finally, the predictive images are semantically segmented by trained networks, and the mean Intersection over Union (mIoU) is used to evaluate the accuracy. The experimental results show that, using DeeplabV3+, PSPNet, SegNet, and U-Net to perform semantic segmentation on 71 scene prediction images, the mIoU obtained is 0.9436, 0.9118, 0.9392, and 0.9473, respectively, and the accuracy of semantic segmentation is high. The feasibility of the deep semantic segmentation method for extracting tobacco planting surface from UAV remote sensing images has been verified, and the research method can provide a reference for subsequent automatic extraction of tobacco planting areas.

The Xiaojiang Basin ranks among the global regions with the highest density of geological hazards. Landslides, avalanches, and debris flows represent significant threats to the safety of residents and their properties, impeding sustainable development. This study utilized three InSAR techniques to monitor surface deformations in the basin, using the standard deviation of these measurements as a stability threshold to identify potential landslides. A systematic analysis of landslide development characteristics was then conducted. Key findings include the following: (1) The annual average deformation velocity in the basin from 2018 to 2021 ranged from −25.36 to 24.40 mm/year, identifying 212 potential landslides. (2) Deformation analysis of a typical landslide in Caizishan showed consistent detection of significant surface changes by all three InSAR methods. Seasonal deformation linked to summer rainfall exacerbates the movement in elevated landslides. (3) Landslides predominantly occur in fragile geological formations such as sandstone, mudstone, and kamacite on slopes of 20° to 40°. These landslides, typically covering less than 0.1 km², are mostly found on barren and grassland terrains adjacent to lower debris gullies, with a relative elevation difference of under 300 m and an aspect range of 90° to 270°. A high kernel density value of 0.3 or higher was noted, with 86.8% influenced by regional tectonic activities, including fault zones. The results demonstrate that natural environmental factors primarily drive landslides in the Xiaojiang Basin, which pose significant threats to the safety of nearby residents. This study’s insights and outcomes provide valuable references for safeguarding local populations, disaster prevention, and promoting regional sustainable development.

The Hunga Tonga‐Hunga Ha'apai volcanic eruption on 15 January 2022 had a significant impact on the ionosphere‐thermosphere system, resulting in large‐scale ionospheric irregularities with longitudinal and latitudinal asymmetries. Multiple instruments recorded these irregularities, indicating the propagation of a westward wave at an average velocity of 354 ± 8 m/s, which led to plasma irregularities of 0.2 TECu/min. Conversely, an eastward‐propagating wave was detected on the Pacific's east coast, traveling at a speed of 348 ± 6 m/s, with a corresponding decrease in plasma fluctuations to 0.1 TECu/min. In Asia, noticeable plasma irregularities appeared within a few hours after the eruption, and the maximum speed exceeded 1,100 m/s, which cannot be explained by the acoustic wave model. There was also a significant latitudinal asymmetry of ionospheric disturbances in the Asian‐Oceania sector, with the plasma density around Oceania depleted by 2–3 orders of magnitude within the altitudes of ∼150–575 km, while the ion density over Asia was enhanced by 1–2 orders of magnitude, and was uplifted ∼50 km. The plasma temperature was proportional to ion density, indicating the ion temperature reduced ∼500 K and increased 100–200 K around Oceania and Asia, respectively. The equatorial electric field, vertical E × B drifts and thermospheric O/N₂ density ratio also fluctuated significantly following the eruption, indicating the redistribution of charged particles due to the magnetic field mapping effect, which was the main contributor to the asymmetries observed.

To address the issues of high noise in ionospheric Total Electron Content (TEC) time series data, fluctuations in prediction accuracy with changing space environments, and the unclear mechanism and process of selecting space physical parameters for model training, this paper utilizes the random forest and deep denoising autoencoder models to construct a method for assessing the importance of space physical parameters and enhancing ionospheric TEC data. Combining this with an improved Transformer prediction model, a data-driven method for TEC forecasting that takes into account the influence of the space environment is proposed. This method is applied to the Global Ionosphere Map data provided by the Center for Orbit Determination in Europe (CODE) for the solar minimum year of 2018 and the solar maximum year of 2015, and compared with traditional Transformer models and CODE’s 1-day forecast product C1PG. The experimental results show that while the proposed method did not show a significant improvement in accuracy compared to the models that did not consider the space environment in the solar minimum year of 2018, it achieved a noticeable accuracy improvement in the solar maximum year of 2015. The accuracy improvements in terms of the annual root mean square error, annual mean absolute error, and annual correlation coefficient are 4.2%, 4.17%, and 0.132% respectively, indicating a significant enhancement.