Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2019-01-28 Cooperative journals: 《计算机应用研究》
Abstract： Aimed at the problems of over- fitting of mapping function and insufficient convergence of loss function in convolution neural network image super- resolution algorithm, combined existing vision recognition algorithm and depth learning theory, this paper proposed an improvement on it. Firstly, the original SRCNN network increased layer number from 3 to 13 layers, and proposed a form of self- gated activation function Swish to replace the usual network model Sigmoi, ReLU and other activation functions, and fully utilized the advantages of Swish function to effectively avoid Over-fitting problems, better to learn and use the mapping relationship between low-resolution and high-resolution images to guide image reconstruction. Then introduced the Newton-Raphson method into the traditional network loss function, which further accelerates the convergence speed. Finally, experiments show that the improved network model can effectively improve the image definition, and improve the visual effect and objective parameter evaluation index.
Subjects: Agriculture, Forestry,Livestock & Aquatic Products Science >> Basic Disciplines of Agriculture submitted time 2017-11-07 Cooperative journals: 《中国生态农业学报》
Abstract：为研究醋糟菌糠作为一种生物肥料对土壤肥力的影响, 为解决食用菌菌糠对环境污染及其有效利用提供科学依据, 本文通过田间试验, 对玉米、高粱、糯玉米3 种作物基施醋糟菌糠后不同生育期的土壤脲酶、 蔗糖酶和过氧化氢酶活性, 细菌、放线菌和真菌数量, 及微生物量碳、氮含量进行测试。研究结果表明: 1)醋糟菌糠显著提高了作物根际土壤细菌、放线菌和真菌的数量。在作物整个生育期, 加入醋糟菌糠的土壤细菌数量比对照提高32%~54%; 放线菌数量在成熟期提高明显, 玉米田土壤放线菌数量增幅最大, 为101%; 真菌数量变化总体趋势呈现先升高后下降的趋势。2)醋糟菌糠的施入增加了作物根际土壤脲酶、过氧化氢酶、蔗糖酶的活性。种植高粱、玉米和糯玉米土壤的脲酶活性增长率分别为239%、189%和185%; 3 种作物的土壤过氧化氢酶活性在抽穗期最高, 最大增长率为40%; 3 种作物的土壤蔗糖酶活性在不同生育期变化趋势不同,玉米各生育期土壤蔗糖酶活性变化较为稳定, 其增长率分别为38%、28%、48%。3)醋糟菌糠的施入增加了作物根际土壤微生物碳氮的含量, 不同生育期3 种作物的土壤微生物碳含量增幅为58.10~407.67 mg·kg1, 微生物氮含量增幅为11.98~27.55 mg·kg1。由此可见, 醋糟菌糠的施用可以增强土壤生产力的可持续性, 从而达到保护和改善土壤环境的效果。同时该研究也为醋糟菌糠的有效利用提供了一定的科学依据。
Subjects: Biology >> Botany >> Plant ecology, plant geography submitted time 2016-05-03
Abstract： Aims Carbon sequestration is the basic function and most primary service of forest ecosystems, and plays a vital role in mitigating the global climate change. However, carbon storage and allocation in forest ecosystems have been less studied at regional scales than for forest stands, and the results are subject to uncertainty due to inconsistent methodologies. Here, we aimed at relatively accurate estimates of forest carbon storage and sequestration rate at a provincial scale (regional) based on plot surveys of both stand biomass and soils over the province. Methods Based on the area and distribution of major forest types, 212 sampling plots, covering different age classes and originality (natural/planted), were surveyed in Gansu Province in northern China. Field investigations were conducted for vegetation layers (trees, shrubs, herbs and litter), soil profiles, and sampling of both plant materials and soils for laboratory analyses. Regional carbon storage was calculated by up-scaling the carbon densities of all forest types with their corresponding areas. Carbon sequestration rate was estimated by referring the reports of national forest inventory for different periods. Important findings Forest carbon storage at the provincial scale was 612.43 Tg C, including 179.04 Tg C in vegetation biomass and 433.39 Tg C in soil organic materials. Specifically, natural forests contributed largely and stored 501.42 Tg C, approximately 4.52 times that of the plantations. Vegetation carbon density in both natural forests and plantations showed increasing trend with the increase in age classes, and the natural forest showed a higher value than the plantation at the same age class. Soil carbon density also increased along the age classes in natural forests, whereas the highest value in plantations appeared at pre-mature stage. Weighted average of regional vegetation carbon density was 72.43 Mg C?hm–2, with 90.52 and 33.79 Mg C?hm–2 in natural forest and plantations, respectively. In 1996, vegetation biomass stored 132.47 and 12.81 Tg C in natural forests and plantations, respectively, and the values increased to 152.41 and 26.63 Tg C in 2011, with the mean carbon sequestration rates of 1.33 and 0.92 Tg C?a–1. Given that young and middle-aged forests account for a large proportion (62.28%) of the total forest area, they are expected to exert substantial potential of carbon sequestration in the province.
Peer Review Status:
Awaiting Review
Hits
Hits
Downloads
Comment