Search

Examining the features of vegetation change and analyzing its driving forces across an extensive time series in Xinjiang are pivotal for the ecological environment. This research can offer a crucial point of reference for regional ecological conservation endeavors. We calculated the fractional vegetation cover (FVC) using MOD13Q1 data accessed through the Google Earth Engine (GEE) platform. To discern the characteristics of vegetation changes and forecast future trends, we employed time series analysis, coefficient of variation, and the Hurst exponent. The correlation between climate factors and FVC was investigated through correlation analysis. Simultaneously, to determine the relative impact of meteorological change and anthropogenic actions on FVC, we utilized multiple regression residual analysis. Furthermore, adhering to China’s ecological functional zone classification, Xinjiang was segmented into five ecological zones: R1 Altai Mountains-Junggar West Mountain Forest and Grassland Ecoregion, R2 Junggar Basin Desert Ecoregion, R3 Tianshan Mountains Mountain Forest and Grassland Ecoregion, R4 Tarim Basin-Eastern Frontier Desert Ecoregion, and R5 Pamir-Kunlun Mountains-Altan Mountains Alpine Desert and Grassland Ecoregion. A comparative analysis of these five regions was subsequently conducted. The results showed the following: (1) During the first two decades of the 21st century, the overall FVC in Xinjiang primarily exhibited a trend of growth, exhibiting a rate of increase of 4 × 10−4 y−1. The multi-year average FVC was 0.223. The mean value of the multi-year FVC was 0.223, and the mean values of different ecological zones showed the following order: R1 > R3 > R2 > R5 > R4. (2) The predominant spatial pattern of FVC across Xinjiang’s landscape is characterized by higher coverage in the northwest and lower in the southeast. In this region, 66.63% of the terrain exhibits deteriorating vegetation, while 11% of the region exhibits a notable rise in plant growth. Future changes in FVC will be dominated by a decreasing trend. Regarding the coefficient of variation outcomes, a minor variation, representing 42.12% of the total, is noticeable; the mean coefficient of variation stands at 0.2786. The stability across varied ecological zones follows the order: R1 > R3 > R2 > R4 > R5. (3) Factors that have a facilitating effect on vegetation FVC included relative humidity, daylight hours, and precipitation, with relative humidity having a greater influence, while factors that have a hindering effect on vegetation FVC included air temperature and wind speed, with wind speed having a greater influence. (4) Vegetation alterations are primarily influenced by climate change, while human activities play a secondary role, contributing 56.93% and 43.07%, respectively. This research underscores the necessity for continued surveillance of vegetation dynamics and the enhancement of policies focused on habitat renewal and the safeguarding of vegetation in Xinjiang.

Semi-supervised learning has been widely used in big data analysis.Currently, one of the hot research topics in semisupervised deep learning is consistency-based methods.However, such methods do not take into account the manifold structure of the data, which may cause a portion of similar samples to get very different outputs, resulting in degraded classifier performance.To address this problem, a semi-supervised deep learning algorithm that combines consistency regularization with manifold regularization was proposed.The algorithm imposed a consistency constraint on the model while constructing a graph and adding a smoothing loss to achieve smoothing within the local neighborhood of each sample point and between adjacent (connected) sample points, thus improving the generalization performance of the semisupervised learning algorithm.The results on several image and text datasets show that the proposed algorithm is more effective compared with other semi-supervised deep learning algorithms.

Improving the carbon storage in terrestrial ecosystems can effectively reduce atmospheric CO2, which is one of the important ways of mitigating global climate change. The knowledge on terrestrial carbon stock research is relatively mature in the international community; however, the research pulse, hotspots, and trends in terrestrial ecosystems carbon stock research are not clear. To better understand the research focus and developmental directions of terrestrial ecosystems’ carbon storage, we conducted a bibliometric analysis of 6305 research articles between 2002 and 2022, which were gathered from the Web of Science Core Database. The temporal distribution, country/region distribution, co-citation network, keyword evolution and clustering, journals, and authors of the literature were analyzed, and the knowledge domain was mapped using the CiteSpace visualization software. This study established the following three observations: (1) The number of publications on carbon stock research in terrestrial ecosystems continues to expand, and the trend in the number of publications proves that carbon sinks in terrestrial systems remain an important research topic internationally. (2) Important issues concerning terrestrial ecosystem carbon stock research have evolved from monitoring the carbon stock changes in terrestrial ecosystems to the mechanism of carbon stock formation for the realization of monitoring and management under global climate change. Furthermore, the research methodology has evolved from small-scale, fixed-point instrumental observations to large-scale remote sensing and model simulations, with diversifications in research content and methodology. (3) In the future, academic research on carbon stocks in terrestrial ecosystems will focus more on international and interdisciplinary cooperations, increasing the intensity in surveying and monitoring carbon stocks in terrestrial ecosystems, and realizing the accurate monitoring, assessment, management, and enhancement of carbon stocks from the integrated carbon stock computation system for “sky, air, and land.” The results of this study comprehensively demonstrate the current status and development of the research on carbon stocks in terrestrial ecosystems worldwide, and provide a reference for future research on the sustainable management of terrestrial ecosystems within the context of global warming.

Fractional Vegetation Cover (FVC) is an important indicator to evaluate the quality of the regional ecological environment. Alar City is a typical desert oasis region. Investigating the spatial and temporal changes in its vegetation cover at different stages is a guide to the ecological balance and sustainable green development of the Tarim River basin. Based on the Google Earth Engine (GEE) cloud platform, this study analyzed the spatial and temporal characteristics and trends of vegetation cover changes in Alar City from 1990 to 2020 using the Hurst index and coefficient of variation. The results show that the spatial distribution of vegetation in the study area in the last 30 years shows a wave-like characteristic with an overall apparent upward trend. The vegetation cover in the study area is predominantly increasing and the spatial distribution shows a phased and regional character. Compared with 1990, there is a significant increase in the area of cultivated land in 2020. Among them, the areas of vegetation growth mainly occur in the basin around the Tarim River. Human activities have weakened the influence of natural factors on FVC. The results of the study suggest that the GEE platform can be an effective tool for permanently monitoring vegetation.

Plant nitrogen (N) uptake preference is a key factor affecting plant nutrient acquisition, vegetation composition and ecosystem function. However, few studies have investigated the contribution of different N sources to plant N strategies, especially during the process of primary succession of a glacial retreat area. By measuring the natural abundance of N isotopes (δ15N) of dominant plants and soil, we estimated the relative contribution of different N forms (ammonium-NH4+, nitrate-NO3− and soluble organic N-DON) and absorption preferences of nine dominant plants of three stages (12, 40 and 120 years old) of the Hailuogou glacier retreat area. Along with the chronosequence of primary succession, dominant plants preferred to absorb NO3− in the early (73.5%) and middle (46.5%) stages. At the late stage, soil NH4+ contributed more than 60.0%, In addition, the contribution of DON to the total N uptake of plants was nearly 19.4%. Thus, the dominant plants’ preference for NO3− in the first two stages changes to NH4+ in the late stages during primary succession. The contribution of DON to the N source of dominant plants should not be ignored. It suggests that the shift of N uptake preference of dominant plants may reflect the adjustment of their N acquisition strategy, in response to the changes in their physiological traits and soil nutrient conditions. Better knowledge of plant preferences for different N forms could significantly improve our understanding on the potential feedbacks of plant N acquisition strategies to environmental changes, and provide valuable suggestions for the sustainable management of plantations during different successional stages.

The order Commelinales comprises many species with important economic and ecological values and represents a striking case of morphologically convergent evolution in monocots. However, so far the genomic resources of species within Commelinales are limited and the deep level phylogeny of Commelinales has not been well resolved. Here we reported and characterized the first complete chloroplast (cp) genome of Pontederia cordata and analysed the phylogenomic relationship of Commelinids based on complete cp sequences. The complete cp genome of P. cordata is 162,234 bp in length with a typical quadripartite structure. The overall GC content is 36.2%. A total of 124 genes were annotated, including 85 encoding genes, 38 transfer RNA genes, and 8 ribosomal RNA genes. The inverted repeat regions contain six CDSs, eight tRNA genes and all the four rRNA genes. Phylogenetic study validated the phylogenetic position of P cordata and showed that the three species from Commelinales form a monophyletic group sister to Zingiberales with high support rate. Meanwhile, species from Zingiberales and Commelinale form a molophyletic group sister to the Poales clade.

Alismatales play an important role in the systematics of angiosperm, yet different phylogenetic topologies of Alismatales based on different species have been generated from several studies. Here we reported and characterized the first complete chloroplast (cp) genomes of two Alismataceae species, Alisma plantago-aquatica and Sagittaria trifolia, and analyzed the phylogenomic relationship of Alismatales based on the complete chloroplast sequences of 21 Alismatales species. The two chloroplast genomes have the typical quadripartite structure with 113 genes in total, including 79 protein-encoding genes, 30 transfer RNA genes and four ribosomal RNA genes. Both IR regeions of plastid genomes contain 8 protein-encoding genes, 7 tRNA genes and all the four rRNA genes. The genome of A. plantago-aquatica is 177,417 bp in length, with an overall G + C content of 35.7%, and the genome of Sagittaria trifolia is 167,642 bp in length, with an overall G + C content of 37.0%. Phylogenetic study showed that the three Alismataceae species comprise a monophyletic group with a high support rate, which was a sister to the Hydrocharitaceae clade. The core Alismatids, consisting of Potamogetonaceae, Zosteraceae, Hydrocharitaceae and Alismataceae, is sister to Tofieldiaceae. Alocasia macrorrhizos of Araceae is the basal taxon of Alismatales, and the other twelve Araceae species formed a sister group to the clade Tofieldaceae and core Alismatids.

A large-scale and high-quality training dataset is an important guarantee to learn an ideal classifier for text sentiment classification. However, manually constructing such a training dataset with sentiment labels is a labor-intensive and time-consuming task. Therefore, based on the idea of effectively utilizing unlabeled samples, a synthetical framework that covers the whole process of semi-supervised learning from seed selection, iterative modification of the training text set, to the co-training strategy of the classifier is proposed in this paper for text sentiment classification. To provide an important basis for selecting the seed texts and modifying the training text set, three kinds of measures—the cluster similarity degree of an unlabeled text, the cluster uncertainty degree of a pseudo-label text to a learner, and the reliability degree of a pseudo-label text to a learner—are defined. With these measures, a seed selection method based on Random Swap clustering, a hybrid modification method of the training text set based on active learning and self-learning, and an alternately co-training strategy of the ensemble classifier of the Maximum Entropy and Support Vector Machine are proposed and combined into our framework. The experimental results on three Chinese datasets (COAE2014, COAE2015, and a Hotel review, respectively) and five English datasets (Books, DVD, Electronics, Kitchen, and MR, respectively) in the real world verify the effectiveness of the proposed framework.

Most proteins perform their biological functions while interacting as complexes. The detection of protein complexes is an important task not only for understanding the relationship between functions and structures of biological network, but also for predicting the function of unknown proteins. We present a new nodal metric by integrating its local topological information. The metric reflects its representability in a larger local neighborhood to a cluster of a protein interaction (PPI) network. Based on the metric, we propose a seed-expansion graph clustering algorithm (SEGC) for protein complexes detection in PPI networks. A roulette wheel strategy is used in the selection of the seed to enhance the diversity of clustering. For a candidate node u, we define its closeness to a cluster C, denoted as NC(u, C), by combing the density of a cluster C and the connection between a node u and C. In SEGC, a cluster which initially consists of only a seed node, is extended by adding nodes recursively from its neighbors according to the closeness, until all neighbors fail the process of expansion. We compare the F-measure and accuracy of the proposed SEGC algorithm with other algorithms on Saccharomyces cerevisiae protein interaction networks. The experimental results show that SEGC outperforms other algorithms under full coverage.

Aiming at several data mining tasks,research developments on data granulation,multi-granularity pattern discovery and fusion,multi-granularity reasoning were carded and analyzed,and the preliminary study on two typical applications astronomical data mining and microblog data mining was summarized,which would be helpful for making a beneficial exploration in big data mining area.