Remote sensing data plays an important role in classifying land use/land cover (LULC) information from various sensors having different spectral, spatial and temporal resolutions. The fusion of an optical image and a synthetic aperture radar (SAR) image is significant for the study of LULC change and simulation in cloudy mountain areas. This paper proposes a novel feature-level fusion framework, in which the Landsat operational land imager (OLI) images with different cloud covers, and a fully polarized Advanced Land Observing Satellite-2 (ALOS-2) image are selected to conduct LULC classification experiments. We take the karst mountain in Chongqing as a study area, following which the features of the spectrum, texture, and space of the optical and SAR images are extracted, respectively, supplemented by the normalized difference vegetation index (NDVI), elevation, slope and other relevant information. Furthermore, the fused feature image is subjected to object-oriented multi-scale segmentation, subsequently, an improved support vector machine (SVM) model is used to conduct the experiment. The results showed that the proposed framework has the advantages of multi-source data feature fusion, high classification performance and can be applied in mountain areas. The overall accuracy (OA) was more than 85%, with the Kappa coefficient values of 0.845. In terms of forest, gardenland, water, and artificial surfaces, the precision of fusion image was higher compared to single data source. In addition, ALOS-2 data have a comparative advantage in the extraction of shrubland, water, and artificial surfaces. This work aims to provide a reference for selecting the suitable data and methods for LULC classification in cloudy mountain areas. When in cloudy mountain areas, the fusion features of images should be preferred, during the period of low cloudiness, the Landsat OLI data should be selected, when no optical remote sensing data are available, and the fully polarized ALOS-2 data are an appropriate substitute.

Estimates of regional net primary productivity (NPP) are useful in modeling regional and global carbon cycles, especially in karst areas. This work developed a new method to study NPP characteristics and changes in Chongqing, a typical karst area. To estimate NPP accurately, the model which integrated an ecosystem process model (CEVSA) with a light use efficiency model (GLOPEM) called GLOPEM-CEVSA was applied. The fraction of photosynthetically active radiation (fPAR) was derived from remote sensing data inversion based on moderate resolution imaging spectroradiometer atmospheric and land products. Validation analyses showed that the PAR and NPP values, which were simulated by the model, matched the observed data well. The values of other relevant NPP models, as well as the MOD17A3 NPP products (NPP MOD17), were compared. In terms of spatial distribution, NPP decreased from northeast to southwest in the Chongqing region. The annual average NPP in the study area was approximately 534 gC/m²a (Std. = 175.53) from 2001 to 2011, with obvious seasonal variation characteristics. The NPP from April to October accounted for 80.1% of the annual NPP, while that from June to August accounted for 43.2%. NPP changed with the fraction of absorbed PAR, and NPP was also significantly correlated to precipitation and temperature at monthly temporal scales, and showed stronger sensitivity to interannual variation in temperature.

Deep learning is an important research method in the remote sensing field. However, samples of remote sensing images are relatively few in real life, and those with markers are scarce. Many neural networks represented by Generative Adversarial Networks (GANs) can learn from real samples to generate pseudosamples, rather than traditional methods that often require more time and man-power to obtain samples. However, the generated pseudosamples often have poor realism and cannot be reliably used as the basis for various analyses and applications in the field of remote sensing. To address the abovementioned problems, a pseudolabeled sample generation method is proposed in this work and applied to scene classification of remote sensing images. The improved unconditional generative model that can be learned from a single natural image (Improved SinGAN) with an attention mechanism can effectively generate enough pseudolabeled samples from a single remote sensing scene image sample. Pseudosamples generated by the improved SinGAN model have stronger realism and relatively less training time, and the extracted features are easily recognized in the classification network. The improved SinGAN can better identify sub-jects from images with complex ground scenes compared with the original network. This mechanism solves the problem of geographic errors of generated pseudosamples. This study incorporated the generated pseudosamples into training data for the classification experiment. The result showed that the SinGAN model with the integration of the attention mechanism can better guarantee feature extraction of the training data. Thus, the quality of the generated samples is improved and the classification accuracy and stability of the classification network are also enhanced.

Deep learning can extract complex and high-dimensional characteristic information with its deep structure, effectively exploring the complex relationship between landslides and their numerous influencing factors, and ultimately, more accurately predict future landslide disasters. This study builds a landslide susceptibility mapping (LSM) method based on deep learning, compares the frequency ratio (FR) sampling method with a buffer random sampling method, and performs resampling operations of landslide and non-landslide samples to explore the applicability of deep learning in LSM. In addition, six indices, precision, accuracy, recall, ROC, and the harmonic mean F1 of accuracy and recall were selected for quantitative comparison. The results show that both the resampling method proposed in this paper and the non-landslide sample selection method based on FR can significantly improve the accuracy of the model, with the area under curve (AUC) increasing by 1.34–8.82% and 3.98–7.20%, respectively, and the AUC value can be improved by 5.32–9.66% by combining the FR selection and resampling methods. Furthermore, all the deep learning models constructed in this study can obtain accurate and reliable landslide susceptibility analysis results compared to traditional models.

The use of remote sensing technology to monitor farmland is currently the mainstream method for crop research. However, in cloudy and misty regions, the use of optical remote sensing image is limited. Synthetic aperture radar (SAR) technology has many advantages, including high resolution, multi-mode, and multi-polarization. Moreover, it can penetrate clouds and mists, can be used for all-weather and all-time Earth observation, and is sensitive to the shape of ground objects. Therefore, it is widely used in agricultural monitoring. In this study, the polarization backscattering coefficient on time-series SAR images during the rice-growing period was analyzed. The rice identification results and accuracy of InSAR technology were compared with those of three schemes (single-time-phase SAR, multi-time-phase SAR, and combination of multi-time-phase SAR and InSAR). Results show that VV and VH polarization coherence coefficients can well distinguish artificial buildings. In particular, VV polarization coherence coefficients can well distinguish rice from water and vegetation in August and September, whereas VH polarization coherence coefficients can well distinguish rice from water and vegetation in August and October. The rice identification accuracy of single-time series Sentinel-1 SAR image (78%) is lower than that of multi-time series SAR image combined with InSAR technology (81%). In this study, Guanghan City, a cloudy region, was used as the study site, and a good verification result was obtained.

In recent years, the scale of rural land transfer has gradually expanded, and the phenomenon of non-grain-oriented cultivated land has emerged. Obtaining crop planting information is of the utmost importance to guaranteeing national food security; however, the acquisition of the spatial distribution of crops in large-scale areas often has the disadvantages of excessive calculation and low accuracy. Therefore, the IO-Growth method, which takes the growth stage every 10 days as the index and combines the spectral features of crops to refine the effective interval of conventional wavebands for object-oriented classification, was proposed. The results were as follows: (1) the IO-Growth method obtained classification results with an overall accuracy and F1 score of 0.92, and both values increased by 6.98% compared to the method applied without growth stages; (2) the IO-Growth method reduced 288 features to only 5 features, namely Sentinel-2: Red Edge1, normalized difference vegetation index, Red, short-wave infrared2, and Aerosols, on the 261st to 270th days, which greatly improved the utilization rate of the wavebands; (3) the rise of geographic data processing platforms makes it simple to complete computations with massive data in a short time. The results showed that the IO-Growth method is suitable for large-scale vegetation mapping.