Search

Obtaining accurate and timely crop area information is crucial for crop yield estimates and food security. Because most existing crop mapping models based on remote sensing data have poor generalizability, they cannot be rapidly deployed for crop identification tasks in different regions. Based on a priori knowledge of phenology, we designed an off-center Bayesian deep learning remote sensing crop classification method that can highlight phenological features, combined with an attention mechanism and residual connectivity. In this paper, we first optimize the input image and input features based on a phenology analysis. Then, a convolutional neural network (CNN), recurrent neural network (RNN), and random forest classifier (RFC) were built based on farm data in northeastern Inner Mongolia and applied to perform comparisons with the method proposed here. Then, classification tests were performed on soybean, maize, and rice from four measurement areas in northeastern China to verify the accuracy of the above methods. To further explore the reliability of the method proposed in this paper, an uncertainty analysis was conducted by Bayesian deep learning to analyze the model's learning process and model structure for interpretability. Finally, statistical data collected in Suibin County, Heilongjiang Province, over many years, and Shandong Province in 2020 were used as reference data to verify the applicability of the methods. The experimental results show that the classification accuracy of the three crops reached 90.73% overall and the average F1 and IOU were 89.57% and 81.48%, respectively. Furthermore, the proposed method can be directly applied to crop area estimations in different years in other regions based on its good correlation with official statistics. [ABSTRACT FROM AUTHOR]

With global warming, previous studies have found nonuniformity responses of precipitation because of regional differences. However, climate change affects the mean, extreme, and data structure of precipitation. Quantile regression, which can reflect every part of the trends of data, was used to detect responses of each part of precipitation in China. The V2.0 dataset of daily precipitation grid data (0.5° × 0.5°) from 1961 to 2020 in China was used as practical observation data. Daily precipitation in 2015–2100 from the China Model BCC-CSM2-MR of scenarios SSP2-4.5 and SSP5-8.5 were chosen as future climate changes with moderate and high radiative forcing, respectively. On the basis of the sign consistency of the slope coefficients with quantile regression, the results of quantiles q = 0.3, 0.5, 0.7 and 0.9 were selected to represent low, median, high and flood precipitation, respectively. Precipitation in four seasons was separately analyzed to observe seasonal characteristics in China. For the observation data, precipitation had obviously different responses in the low and high percentiles and was present in mainly spring and summer. In spring, in the middle and lower Yangtze Plains, the low and median precipitation increased, whereas the high and flood precipitation significantly decreased. In summer, Heilongjiang Province and northern Inner Mongolia showed decreasing trends in the low quantile and increasing trends in the high quantile, indicating a completely opposite trend adjustment. These regions deserve more attention. However, obviously different responses in low and high percentiles were not so evident in future climate changes. Self-consistency in model data may weaken the heteroscedastic characteristics of precipitation. [ABSTRACT FROM AUTHOR]

Fresh corn is a kind of herbaceous plant with rich nutritive value and a reasonable composition of fatty acids; however, there is little research on methods for the systemic nutritional evaluation of fatty acids in fresh corn. The aim of the present study was to conduct a comparative analysis of the fatty acid profiles of Chinese Huangnuo 9 sweet-waxy corn from the provinces of Inner Mongolia, Jilin, and Heilongjiang by gas chromatography; to establish a nutritional evaluation system according to the impacts of nutrients from fatty acids on human health; and finally, to evaluate, compare and rank fresh sweet-waxy corn grown in different regions. Tocopherols were detected by liquid chromatography in order to demonstrate the anti-oxidation activity of fresh corn's fatty acids. The fatty acid contents and compositions of the 12 samples from the three regions are significantly different from each other. The nutrient value of the fatty acids in fresh corn was analyzed by factor analysis and a linear structural relation model, followed by the fitting and appraising of the model. The studied fresh sweet-waxy corn 1-4 from Inner Mongolia had the highest γ-tocopherol content and the closest saturated fatty acid:monounsaturated fatty acid:polyunsaturated fatty acid rate to the recommended value. The fatty acid profiles of sweet-waxy corns 2-1, 2-2, and 2-3 were the most diverse, and the comprehensive evaluation result of fresh corn 2-4 was the best; its total fatty acid content was the highest. Fresh corn 3-1 in Heilongjiang had the highest unsaturated fatty acids and lower values in its atherosclerosis index and thrombosis index, which suggested the strongest anti-atherosclerosis and anti-thrombotic ability. This work will give a reference to guide dietary choices and provide data support for dietary recommendations for residents. [ABSTRACT FROM AUTHOR]

Two new species of Diatrype collected in northeast China are described and illustrated based on morphological and molecular evidence. Diatrype larissae from Heilongjiang Province is characterised by having 3–6 perithecia in a stroma, asci polysporous, ascospores allantoid, aseptate, slightly or moderately curved, subhyaline. Diatrype betulaceicola from Inner Mongolia has large stroma with 5–14 perithecia, perithecium immersed, asci polysporous, long-stalked, ascospores allantoid, aseptate, slightly curved, subhyaline. The phylogenies inferred from the data set of nrDNA ITS1-5.8S-ITS2 (ITS) and beta-tubulin (β-tubulin) supported the two new species both as members in the genus Diatrype and distinct species. The morphological similarities and dissimilarities of the new species with phylogenetically close relatives are discussed. A dichotomous identification key to the Diatrype spp. known from China is proposed. [ABSTRACT FROM AUTHOR]