Search

Hyperspectral image classification is widely applied in several fields. Since existing datasets focus on a single scene, current deep learning-based methods typically divide patches randomly on the same image as training and testing samples. This can result in similar spatial distributions of samples, which may incline the network to learn specific spatial distributions in pursuit of falsely high accuracy. In addition, the large variation between single-scene datasets has led to research in cross-scene hyperspectral classification, focusing on domain adaptation and domain generalization while neglecting the exploration of the generalizability of models to specific variables. This paper proposes two approaches to address these issues. The first approach is to train the model on the original image and then test it on the rotated dataset to simulate cross-scene evaluation. The second approach is constructing a new cross-scene dataset for spatial distribution variations, named GF14-C17&C16, to avoid the problems arising from the existing single-scene datasets. The image conditions in this dataset are basically the same, and only the land cover distribution is different. In response to the spatial distribution variations, this paper proposes a constrained spectral attention mechanism and a constrained spatial attention mechanism to limit the fitting of the model to specific feature distributions. Based on these, this paper also constructs a constrained spectral–spatial attention residual network (CSSARN). Extensive experimental results on two public hyperspectral datasets and the GF14-C17&C16 dataset have demonstrated that CSSARN is more effective than other methods in extracting cross-scene spectral and spatial features. [ABSTRACT FROM AUTHOR]

Cool-season plant growth and development are impacted by high temperatures. As a biostimulant, glycine betaine is responsible for inducing tolerance to both biotic and abiotic stressors. However, the mechanism by which glycine betaine protects cool-season crops against high-temperature stress is not clear. In the present study, under the conditions of high temperatures (35 °C/30 °C day/night), cherry radishes (Raphanus sativus var. radicula Pers.) (Brassicaceae) were cultured for 9, 18, and 27 days, and different concentrations (0, 0.067, 8.79, 11.72, 14.65, and 17.58 mg L−1) of glycine betaine were applied to investigate the influence of glycine betaine on cherry radish biomass, quality, net photosynthetic rate, chlorophyll content, antioxidant enzyme activity, and endogenous hormone content under high-temperature stress. The results showed that, under high-temperature conditions, cherry radishes grew best with the 17.58 mg L−1 glycine betaine treatment. At day 27, comparing the 17.58 mg L−1 glycine betaine treatment with 0 mg L−1 glycine betaine under high-temperature stress, the cherry radish biomass increased by 44.7%, while the soluble protein and vitamin C content increased by 14.4% and 21.6%, respectively, the net photosynthetic rate and chlorophyll a content increased by 7.8% and 44.1%, respectively, and the peroxidase and catalase levels increased by 81.0% and 146.3%, respectively. On day 9, the auxin, abscisic acid, and glycine betaine contents significantly increased by 67.4%, 6.8%, and 32.9%, respectively, in comparing the 17.58 mg L−1 glycine betaine treatment with 0 mg L−1 glycine betaine under high-temperature stress. Therefore, the application of 17.58 mg L−1 betaine to cherry radishes grown under high-temperature stress had positive effects. The appropriate concentration of glycine betaine can improve the resistance of cherry radish to high temperatures and maintain yield. [ABSTRACT FROM AUTHOR]

BACKGROUND The high cost of controlled‐release urea (CRU) has prompted this study to explore whether the amount of CRU can be reduced by adding biostimulants while maintaining or increasing rice yield. A 2 year field experiment was conducted with CRU at three levels (60%, 80%, and 100% of the recommended nitrogen (N) fertilizer) and a novel biostimulant Paecilomyces variotii extract (ZNC), to investigate their synergistic effects on yield, nitrogen use efficiency (NUE), and net profitability of rice. RESULTS: Controlled‐release urea achieved a significantly higher gain yield and NUE than conventional urea with the same N level, which could be attributed to its N supply. Even if the N level of CRU was reduced by 40%, both rice yield and net profit were still significantly higher than for the full amount of urea. Paecilomyces variotii extract sprayed on the surface of CRU at a dose of only 87.5 mL ha−1 exhibited ultra‐high effectiveness by increasing the panicles, the N accumulation, and the rice yield. Controlled‐release urea enriched by ZNC achieved significantly higher gain yield than CRU alone, increasing the yield by 9.2% and 8.7%, respectively, in 2 years under the full recommended N rate. The combination of 80% CRU and ZNC showed no significant difference in rice yield from treatment with 100% CRU, indicating that the rate of CRU could be reduced by ZNC. The application of ZNC further increased NUE, N partial factor productivity, and net profit. CONCLUSION: The CRU and ZNC combination provided a feasible approach for reducing N input while maintaining rice yield and agricultural sustainability. © 2021 Society of Chemical Industry. [ABSTRACT FROM AUTHOR]

One high loess landslide, which was located in Yili Region of Xinjiang, reactivated and caused long-distance road burying and river blocking on April 30, 2019. About 5. 04 X 10 m of loess body was cut out along the high sliding position, and impacted shovel scraping ditch and bank slopes on both sides. However, so far it is difficult to understand the mechanism of unscheduled landslide reactivation. Based on detailed field investigation, remote sensing image identification, meteorological data analysis and loess characteristic test, this paper attempts to determine the formation and evolution history, movement process and reactivation mechanism of loess landslide. The results indicated that in the past this landslide had experienced two large-scale sliding failures, and in the meantime showed different degrees of inherited cumulative deformation failure annually with the development of slope ground fissures and cracks. The rapid snow ablation and infiltration drived by the abnormal temperature rising in spring was the most important influencing factor on deformation evolution of the loess landslide, and the coupling of thawing water and rainstorm in spring was the fundamental reason controlling the occurrence of loess landslides. Based on the successful disaster emergency response process after the disaster occurrence, a multi-department linkage highway disaster emergency response model based on early warning is proposed. Accompanying with the increase of regional grazing activities and climate warming, this loess landslide will have a great potential risk of reactivation sliding in the future. The study can provide a new perspective for researching the formation, evolution and failure mechanism of landslides in frozen regions, and have great significance for serving the traffic construction of One Belt and One Road in Xinjiang. [ABSTRACT FROM AUTHOR]

It is thus essential and critical to enhance phosphorus (P) fertilizer use efficiency of crops to improve agricultural and environmental sustainability. A pot experiment was conducted to examine the impact of different kinds of value-added P-potassium (K)-activator fertilizers (VPAFs) on soil nutrient bioavailability, growth and yield of wheat-maize crops. Compared with that of the control (NPK) treatment, the wheat yields of VPAF treatments increased from 6.59% to 18.61%, and the maize yields increased from −0.22% to 15.58%. In addition, the P fertilizer utilization rate of VPAF treatments increased by an average of 10.87% and 5.75% for wheat and maize, respectively. Therefore, VPAF application in agriculture can introduce multiple benefits including increasing crop yield, improving fertilizer utilization efficiency, enhancing nutrient bioavailability, and reducing pollution. [ABSTRACT FROM AUTHOR]