Landslides cause a considerable amount of damage around the world every year. Landslide susceptibility assessments are useful for the mitigation of the associated potential risks to local economic development, land use planning, and decision makers. The main aim of this study was to present a novel hybrid approach of bagging (B)-based kernel logistic regression (KLR), named the BKLR model, for spatial prediction of landslides in the Shangnan County, China. We first selected 15 conditioning factors for landslide susceptibility modeling. Then, the prediction capability of all conditioning factors was evaluated using the least square support vector machine method. Model validation and comparison were performed based on the area under the receiver operating characteristic curve and several statistical-based indexes, including positive predictive rate, negative predictive rate, sensitivity, specificity, kappa index, and root mean square error. Results indicated that the BKLR ensemble model outperformed and outclassed the KLR and the benchmark support vector machine model. Our findings overall confirmed that a combination of the meta model with a decision tree classifier based on a functional algorithm can decrease the over-fitting and variance problems of data, which could enhance the prediction power of the landslide model. The resultant susceptibility maps could be useful for hazard mitigation in the study area and other similar landslide-prone areas.

The main purpose of the present study is to apply three classification models, namely, the index of entropy (IOE) model, the logistic regression (LR) model, and the support vector machine (SVM) model by radial basis function (RBF), to produce landslide susceptibility maps for the Fugu County of Shaanxi Province, China. Firstly, landslide locations were extracted from field investigation and aerial photographs, and a total of 194 landslide polygons were transformed into points to produce a landslide inventory map. Secondly, the landslide points were randomly split into two groups (70/30) for training and validation purposes, respectively. Then, 10 landslide explanatory variables, such as slope aspect, slope angle, altitude, lithology, mean annual precipitation, distance to roads, distance to rivers, distance to faults, land use, and normalized difference vegetation index (NDVI), were selected and the potential multicollinearity problems between these factors were detected by the Pearson Correlation Coefficient (PCC), the variance inflation factor (VIF), and tolerance (TOL). Subsequently, the landslide susceptibility maps for the study region were obtained using the IOE model, the LR–IOE, and the SVM–IOE model. Finally, the performance of these three models was verified and compared using the receiver operating characteristics (ROC) curve. The success rate results showed that the LR–IOE model has the highest accuracy (90.11%), followed by the IOE model (87.43%) and the SVM–IOE model (86.53%). Similarly, the AUC values also showed that the prediction accuracy expresses a similar result, with the LR–IOE model having the highest accuracy (81.84%), followed by the IOE model (76.86%) and the SVM–IOE model (76.61%). Thus, the landslide susceptibility map (LSM) for the study region can provide an effective reference for the Fugu County government to properly address land planning and mitigate landslide risk.

Deep neural networks combined with superpixel segmentation have proven to be superior to high-resolution remote sensing image (HRI) classification. Currently, most HRI classification methods that combine deep learning and superpixel segmentation use stacking on multiple scales to extract contextual information from segmented objects. However, this approach does not take into account the contextual dependencies between each segmented object. To solve this problem, a joint superpixel and Transformer (JST) framework is proposed for HRI classification. In JST, HRI is first segmented into superpixel objects as input, and Transformer is used to model the long-range dependencies. The contextual relationship between each input superpixel object is obtained and the class of analyzed objects is output by designing an encoding and decoding Transformer. Additionally, we explore the effect of semantic range on classification accuracy. JST is also tested by using two HRI datasets with overall classification accuracy, average accuracy and Kappa coefficients of 0.79, 0.70, 0.78 and 0.91, 0.85, 0.89, respectively. The effectiveness of the proposed method is compared qualitatively and quantitatively, and the results achieve competitive and consistently better than the benchmark comparison method.

[Objective] This study focused on the primary tea-producing regions of Shangluo City (ranging from 108°34′20″ E to 111°1′25″ E and 33°2′30″ N to 34°24′40″ N), which include Shangnan County, Zhen’an County, Zhashui County, Danfeng County, and Shanyang County. The aim was to explore the characteristics and influencing factors of soil nutrient content variation across different tea gardens in the area. The study involved an analysis of various soil nutrient indicators and an investigation of their correlations to assess the nutrient status of tea gardens in Shangluo City. [Method] A total of 228 soil samples from these tea gardens were quantitatively analyzed for pH, soil organic matter (SOM), total nitrogen (TN), total phosphorus (TP), total potassium (TK), available nitrogen (AN), available phosphorus (AP), available potassium (AK), as well as clay, silt, and sand content. Additionally, the soil texture was qualitatively analyzed. Statistical methods including analysis of variance (ANOVA), correlation analysis, principal component analysis (PCA), and regression analysis were performed using SPSS software to examine the relationships between soil nutrients and texture in relation to altitude, latitude, and fertility status. [Results] The results indicated that the pH of tea garden soils in Shangluo City was relatively stable, ranging from 4.3 to 7.6, with the mean of 5.9 and a coefficient of variation of 11.0%. The soil organic matter (SOM) content varied from 7.491 to 81.783 g/kg, exhibiting a moderate variability with a coefficient of variation of 38.75%. The mean values for total nitrogen (TN), available nitrogen (AN), total phosphorus (TP), available phosphorus (AP), total potassium (TK), available potassium (AK), clay, silt, and sand were 1.53 g/kg, 213 mg/kg, 0.85 g/kg, 49.1 mg/kg, 5.5 g/kg, 110 mg/kg, 3.99, 44.89, and 51.11, respectively. AN and AP displayed higher coefficients of variation at 57% and 120.1%, respectively. Significant differences in pH, SOM, TN, TP, TK, silt, and sand were observed at varying elevations, while TN, TP, TK, clay, silt, and sand varied significantly across different latitudes. Principal component analysis (PCA) results revealed that altitude had four principal components with eigenvalues greater than 1, accounting for 71.366% of the total variance, whereas latitude exhibited five principal components with eigenvalues exceeding 1, explaining 76.304% of the total variance. Regression analysis indicated that altitude exerted a stronger influence on soil indicators, as demonstrated by a well-fitting model (Model 4), where the coefficients of principal components 1, 3, and 4 were positive, while that of principal component 2 was negative. In contrast, latitude influenced soil indicators most effectively in Model 3, where the coefficient of principal component 5 was positive, and the coefficients of principal components 1 and 4 were negative. [Conclusions] The variation in soil nutrients and pH in the tea gardens of Shangluo City is closely associated with altitude and latitude. Notably, there is no discernible trend of pH acidification. Therefore, tea garden management should prioritize the rational application of soil nutrients at varying altitudes and focus on enhancing soil texture at different latitudes to adapt to the diverse soil characteristics under these conditions, thereby promoting sustainable development in tea gardens.

Deep neural networks combined with superpixel segmentation have proven to be superior to high-resolution remote sensingimage (HRI) classification. Currently, most HRI classification methods that combine deep learning and superpixel segmentationuse stacking on multiple scales to extract contextual information from segmented objects. However, this approach does nottake into account the contextual dependencies between each segmented object. To solve this problem, a joint superpixel andTransformer (JST) framework is proposed for HRI classification. In JST, HRI is first segmented into superpixel objects as input,and Transformer is used to model the long-range dependencies. The contextual relationship between each input superpixelobject is obtained and the class of analyzed objects is output by designing an encoding and decoding Transformer. Additionally,we explore the effect of semantic range on classification accuracy. JST is also tested by using two HRI datasets with overallclassification accuracy, average accuracy and Kappa coefficients of 0.79, 0.70, 0.78 and 0.91, 0.85, 0.89, respectively. Theeffectiveness of the proposed method is compared qualitatively and quantitatively, and the results achieve competitive andconsistently better than the benchmark comparison method.