Space-time video super-resolution using long-term temporal feature aggregation

Space-time video super-resolution(STVSR)serves the purpose to reconstruct high-resolution high-frame-rate videos from their low-resolution low-frame-rate counterparts.Recent approaches utilize end-to-end deep learning models to achieve STVSR.They first interpolate intermediate frame features between given frames,then perform local and global refinement among the feature sequence,and finally increase the spatial resolutions of these features.However,in the most important feature interpolation phase,they only capture spatial-temporal information from the most adjacent frame features,ignoring modelling long-term spatial-temporal correlations between multiple neighbouring frames to restore variable-speed object movements and maintain long-term motion continuity.In this paper,we propose a novel long-term temporal feature aggregation network(LTFA-Net)for STVSR.Specifically,we design a long-term mixture of experts(LTMoE)module for feature interpolation.LTMoE contains multiple experts to extract mutual and complementary spatial-temporal information from multiple consecutive adjacent frame features,which are then combined with different weights to obtain interpolation results using several gating nets.Next,we perform local and global feature refinement using the Locally-temporal Feature Comparison(LFC)module and bidirectional deformable ConvLSTM layer,respectively.Experimental results on two standard benchmarks,Adobe240 and GoPro,indicate the effectiveness and superiority of our approach over state of the art.

Distribution of soil aggregates and organic carbon in deep soil under long-term conservation tillage with residual retention in dryland

To ascertain the effects of long-term conservation tillage and residue retention on soil organic carbon(SOC) content and aggregate distribution in a deep soil(>20-cm depth) in a dryland environment,this paper analyzed the SOC and aggregate distribution in soil, and the aggregate-associated organic carbon(OC) and SOC physical fractions. Conservation tillage(reduced tillage with residue incorporated(RT) and no-tillage with residue mulch(NT)) significantly increased SOC sequestration and soil aggregation in deep soil compared with conventional tillage with residue removal(CT). Compared with CT, RT significantly increased the proportion of small macroaggregates by 23%–81% in the 10–80 cm layer, and the OC content in small macroaggregates by 1%–58% in the 0–80 cm layer. RT significantly increased(by 24%–90%) the OC content in mineral-SOC within small macroaggregates in the 0–60 cm layer, while there was a 23%–80% increase in the 0–40 cm layer with NT. These results indicated that:(1) conservation tillage treatments are beneficial for soil aggregation and SOC sequestration in a deep soil in a dryland environment; and(2)the SOC in mineral-associated OC plays important roles in soil aggregation and SOC sequestration. In conclusion, RT with NT is recommended as an agricultural management tool in dryland soils because of its role in improving soil aggregation and SOC sequestration.

A Lightweight Temporal Convolutional Network for Human Motion Prediction

A lightweight multi-layer residual temporal convolutional network model(RTCN)is proposed to target the highly complex kinematics and temporal correlation of human motion.RTCN uses 1-D convolution to efficiently obtain the spatial structure information of human motion and extract the correlation in the time series of human motion.The residual structure is applied to the proposed network model to alleviate the problem of gradient disappearance in the deep network.Experiments on the Human 3.6M dataset demonstrate that the proposed method effectively reduces the errors of motion prediction compared with previous methods,especially of long-term prediction.

Effect of Spatial and Temporal Scales on Habitat Suitability Modeling:A Case Study of Ommastrephes bartramii in the Northwest Pacific Ocean

Temporal and spatial scales play important roles in fishery ecology,and an inappropriate spatio-temporal scale may result in large errors in modeling fish distribution.The objective of this study is to evaluate the roles of spatio-temporal scales in habitat suitability modeling,with the western stock of winter-spring cohort of neon flying squid （Ornmastrephes bartramii） in the northwest Pacific Ocean as an example.In this study,the fishery-dependent data from the Chinese Mainland Squid Jigging Technical Group and sea surface temperature （SST） from remote sensing during August to October of 2003-2008 were used.We evaluated the differences in a habitat suitability index model resulting from aggregating data with 36 different spatial scales with a combination of three latitude scales （0.5°,1 ° and 2°）,four longitude scales （0.5°,1°,2° and 4°）,and three temporal scales （week,fortnight,and month）.The coefficients of variation （CV） of the weekly,biweekly and monthly suitability index （SI） were compared to determine which temporal and spatial scales of SI model are more precise.This study shows that the optimal temporal and spatial scales with the lowest CV are month,and 0.5° latitude and 0.5° longitude for O.bartramii in the northwest Pacific Ocean.This suitability index model developed with an optimal scale can be cost-effective in improving forecasting fishing ground and requires no excessive sampling efforts.We suggest that the uncertainty associated with spatial and temporal scales used in data aggregations needs to be considered in habitat suitability modeling.

Surface Humidity Changes in Different Temporal Scales

As the key driven factor of hydrological cycles and global energy transfer processes, water vapour in the atmosphere is important for observing and understanding climatic system changes. In this study, we utilized the multi-dimensional Kolmogorov-Zurbenko filter (KZ filter) to assimilate a near-global high-resolution (monthly 1°?× 1°?grid) humidity climate observation database that provided consistent humidity estimates from 1973 onwards;then we examined the global humidity movements based on different temporal scales that separated out according to the average spectral features of specific humidity data. Humidity climate components were restored with KZ filters to represent the long-term trends and El Nino-like interannual movements. Movies of thermal maps based on these two climate components were used to visualize the water vapour fluctuation patterns over the Earth. Current results suggest that increases in water vapour are found over a large part of the oceans and the land of Eurasia, and the most confirmed increasing pattern is over the south part of North Atlantic and around the India subcontinent;meanwhile, the surface moisture levels over lands of south hemisphere are becoming less.

The Analysis of Spatial-Temporal Evolution of City Accessibility Based on Highway Network in Henan Province in China

Accessibility is an important tool to evaluate the maturity of a regional traffic network structure which describes the traffic convenience in the traffic network. The paper defines a new accessibility index by using the resident population weighted average value of the sum of inverse of the traveling time distance and time threshold coming from ordinary traffic network, and then uses this accessibility index to analyze the spatial-temporal characteristics of Henan highway network, as well as its evolution patterns from 2005 to 2020. The results show that with the expansion and improvement of Henan highway network, city accessibility level has been significantly improved, spatial convergence is obvious, the cities in the north central are always High-High aggregation area, the cities in the south are always Low-Low aggregation area, gradually forming the characteristics of Northwest high and Southeast low, relative balance between East and West. There is some non-conforming phenomenon in highway mileage growth and improvement of the city accessibility levels, but this situation is being weakened, the highway network layout is gradually rationalized, the spatial distribution of city accessibility and that of population are beginning to converge.

基于LUCC的生态系统服务价值时空演变——以祁连山区域为例

分析祁连山区域生态系统服务价值的时空变化特征,可为该区土地高效开发利用、生态恢复与保护机制的构建提供数据支撑。基于1980年、1990年、2000年、2010年和2020年的土地利用数据,运用改进的当量因子定量评估祁连山区域不同历史时期的生态系统服务价值,结合空间自相关及GIS空间统计方法,探究研究区不同乡镇的地均生态系统服务价值时空变化特征。结果表明:1)1980-2020年,研究区主要土地类型为未利用地、草地、林地、耕地,总覆盖率在93%以上。其中林地和未利用地面积减少,建设用地动态度变化最大。2)1980-2020年,祁连山区域生态系统服务总价值增加了170.8285×10^(8)元,其中草地、林地和水域的生态服务价值占78%,水文调节和气候调节的生态服务价值占60.14%。3)地均生态系统服务价值的空间正相关性较明显,空间集聚程度较高。高值聚集区有由增加向减少转变的趋势,低值聚集区逐年增加。4)1980-2010年,祁连山区域南部生态系统服务价值高于北部,北部生态系统服务价值在2010年后有增加趋势,但研究区南北间生态系统服务价值还未达到均衡和稳定。

中国20世纪建筑遗产时空分布特征及影响因素

以8批共计798项中国20世纪建筑遗产为研究对象,借助ArcGIS工具中的平均最近邻、核密度估计、标准差椭圆和平均中心方法对其时空分布特征进行探究,并从发生学角度出发对影响因素定性分析,结果表明:(1)省域层面总体呈现“一极多核、东密西疏”的高度集聚分布,市域层面遗产数量呈现“金字塔式”分布,且城市间遗产数量呈现“断崖式”差异,总体呈现“大分散、小集中”。(2)纪念建筑、教育建筑、工业建筑等遗产类别形成了4个主要聚集区和2条聚集带,此外,集聚、离散和随机的总体分布模式在不同类型中出现。(3)时间分布呈现跨度长、历史延续性强且阶段性显著,各时期分布较均衡,遗产总数上表现为增长→波动→减少,且分布中心呈现出西南→西北→东南方向的迁移。主要类型演变过程分为减少→增加、波动增加、持续减少等6种情况。(4)地形地势、人口密度、历史事件等因素与遗产空间分布密切相关,且历史事件对主要聚集区带的形成发挥了关键作用。依据研究结果,提出了相对具体的构建叙事性遗产区系和廊道的思路,并整合形成“20世纪中国发展史”主题文旅教育参观路线。

Treadmill exercise improves hippocampal neural plasticity and relieves cognitive deficits in a mouse model of epilepsy

Epilepsy frequently leads to cognitive dysfunction and approaches to treatment remain limited.Although regular exercise effectively improves learning and memory functions across multiple neurological diseases,its application in patients with epilepsy remains controversial.Here,we adopted a 14-day treadmill-exercise paradigm in a pilocarpine injection-induced mouse model of epilepsy.Cognitive assays confirmed the improvement of object and spatial memory after endurance training,and electrophysiological studies revealed the maintenance of hippocampal plasticity as a result of physical exercise.Investigations of the mechanisms underlying this effect revealed that exercise protected parvalbumin interneurons,probably via the suppression of neuroinflammation and improved integrity of blood-brain barrier.In summary,this work identified a previously unknown mechanism through which exercise improves cognitive rehabilitation in epilepsy.

利用地理流时空相关性分析揭示人群移动规律

人群移动流具有时空依赖特征,识别和定量刻画其时空相关性是揭示人群移动规律和对其进行模拟预测的基础。本文通过对比和讨论流的空间自相关和时空自相关分析方法,探索在城市内部和省际两个不同空间尺度下的人群移动流时空依赖特征及其集聚模式。结果表明:(1)城市内部和省际的人群移动流均表现出强时空依赖性;(2)城市内部和省际人群移动流的高-高模式均以短距离流为主,低-低模式则是跨组团的远距离流;(3)相比于仅考虑空间依赖,同时考虑时间和空间依赖可以有效捕捉跨区域移动流,这在省际移动流的集聚模式分析中尤为重要;(4)时空相关性中的高-低和低-高模式可以识别流量随时间变化剧烈的流,有助于进一步揭示局部区域的异常流模式。本文结论进一步强调了时空相关性的优势及特点,可丰富地理流的探索性分析方法,服务于人群动态观测的移动规律和模式特征挖掘。

呼和浩特市城中心人口时空聚集特征及其影响因素

城市人口时空聚集展现人群时空动态行为规律,基于大数据——百度热力图创建时空立方体,运用新兴时空热点分析方法,研究呼和浩特市中心城区某工作日和休息日人口时空聚集动态变化,并从POI数据、路网数据、建筑物高度等数据中筛选出影响因子,通过地理探测器的方法进行人口时空聚集的影响因素进行分析,结果表明:(1)主城区城市人口聚集特征为由内向外延伸圈状规律特征;二环线为人口密度界限,高度集中于二环以内区域,以外地区人口密度低;(2)主要影响人口聚集度因素为土地利用混合度;交互因子中85%呈增强效果,建筑物高度与其余因子交互作用最为显著,而功能混合度交互作用中影响力减弱。

2005—2022年上海市青浦区肺结核时空特征分析

目的:通过分析上海市青浦区2005—2022年的肺结核疫情,旨在发现区域内肺结核发病的空间聚集性及时空特征,为相关部门制定防控策略提供参考依据。方法:从中国疾病预防控制信息系统中筛选2005年1月1日—2022年12月31日上海市青浦区肺结核登记报告资料,进行空间全局自相关分析、空间局部自相关分析和时空扫描分析。结果:2005—2022年上海市青浦区男性肺结核患者数量多于女性患者,20~39岁年龄段肺结核患者数量最多。从时间上看,2013—2015年青浦区各街(镇)的发病率普遍上升,大部分街(镇)在此期间达到历年发病峰值,2015年之后各街(镇)的发病率呈逐步下降趋势。从空间上看,青浦区东部和西部地区整体发病率高于中心地区。2011年、2013年、2016年、2017年、2020年青浦区肺结核发病在空间上存在显著正相关性,呈现明显的空间集聚趋势,2010年青浦区肺结核发病的空间分布呈现负相关性。2005—2022年青浦区各街(镇)肺结核患者年均登记率的空间分布不均衡。2015—2022年青浦区肺结核患者呈现出明显的时空聚集特征。结论:2005—2022年青浦区肺结核病例男性显著多于女性,肺结核患者主要集中在20~39岁年龄段人群,且呈现时空聚集性,高发病率区域主要集中在青浦区西南部地区。相关部门应针对高发病区域和高风险人群加强筛查,制定分类分时的防控措施,从而有效防控肺结核疫情。

用于时态聚合范围查询的分布式时态索引

在大数据与云计算时代,时态大数据的查询分析面临许多重要挑战。针对其中时态聚合范围查询性能不佳和不能有效利用索引等问题,提出一种用于时态聚合范围查询的分布式时态索引(DTI)。首先,采用随机或轮询策略对时态数据分区;其次,采用基于时间位数组前缀的分区内索引构造算法建立索引,同时记录包括时间跨度在内的分区统计信息;再次,利用谓词下推筛选时间跨度与查询时间区间重叠的数据分区,扫描索引进行预聚合;最后,将各分区得到的预聚合值按时间归并并聚合。实验结果表明,索引的分区内构造算法处理时间密度2400条每单位时间和0.001条每单位时间的数据的执行时间相近。索引的聚合查询算法相较于ParTime算法:在查询时间线前75%的数据时,每一步用时都至少减少22%;执行选择型聚合函数时,每一步用时都至少减少11%。因此,索引在多数时态聚合范围查询任务中具有更高的速度,它的分区内构造算法能解决数据稀疏问题且执行效率高。

基于聚合时空图卷积网络的多风场超短期风速预测

在一定环境内区域风电场呈不规则分布的条件下,传统卷积神经网络预测方法无法体现出各区域风场的分布状态和影响关系,难以实现对风速的准确预测。针对此问题,采用图卷积网络进行特征建模,并根据多风场的拓扑结构和各区域风场风速的互相关系数建立连通图和权重矩阵。其次,依赖风场风速的时间动态特征,采用改进并列式卷积结构获取同一风场下多时间段的风速序列相关性。再次,利用风场风速的空间相关性和延时效应,采用二阶聚合方法将不同区域内风速的时空特征聚合。最后,经某区域风场数据验证表明,在0~4 h预测尺度下该方法在多风场超短期风速预测中具有提取时空特征并提升预测性能的效果。

计及负荷时空转移需求响应的数据中心聚合商最优运行策略

利用聚合技术构建数据中心聚合商以参与系统需求响应,提出一种计及负荷时空转移需求响应的数据中心聚合商最优运行策略。首先,根据数据中心的物理特性,建立负荷时空转移需求响应模型;然后,以数据中心运行成本最小化和数据中心聚合商利益最大化为目标,建立计及负荷时空转移需求响应的数据中心聚合商最优运行模型;最后,通过Karush-Kuhn-Tucker(KKT)条件以及大M法将双层模型转换成单层混合整数线性规划模型进行求解。仿真结果表明:所提最优运行策略可有效提高数据中心内工作负荷的灵活性,并促进数据中心运行经济性的提高。

考虑时序相关性的需求侧资源可调节功率域聚合方法

在新能源高比例接入电网的背景下,需充分利用需求侧资源的灵活可调特性以保证电网的安全稳定与经济性。针对需求侧资源多样、数量多、容量小且分布广的特点,提出一种考虑时序相关性的需求侧资源可调节功率域聚合方法。首先,考虑需求侧资源功率调节的时序相关性,以相邻时段可调节功率域来量化其功率调节能力。其次,基于闵可夫斯基之和及上下边界近似法提出可调节功率域聚合方法,采用自适应分布鲁棒优化算法求解近似可行域边界辨识模型,确保其聚合最优性和解的可行性。然后,通过时段聚类方法得到适用于日前调度的多时段可调节功率域,降低计算复杂度。最后,通过算例对比分析可知,所提方法具有更高的计算效率和近似精度。

我国香菇和黑木耳生产时空演化及影响因素分析

强化产业集聚和提升产业质量是推动我国由食用菌产业大国转为强国的重要途径,研究我国食用菌产业地理集聚特征及空间演变趋势,对于科学优化食用菌产业布局具有重要的基础性和支撑性作用。探究产量居我国食用菌前2的香菇和黑木耳产业地理集聚特征、空间演变趋势、影响因素,为我国香菇和黑木耳产业科学布局及健康发展提供理论支持。运用区位基尼系数、产业集中度、空间自相关模型和空间计量模型,基于2010—2020年我国香菇和黑木耳的相关产量及面板数据,对我国香菇和黑木耳的地理集聚及其影响因素进行综合分析。结果表明:香菇和黑木耳“南菇北移,北耳南扩”现象明显;香菇产业集聚程度升高,而黑木耳产业集聚程度下降;香菇和黑木耳地理集聚的高-高(H-H)象限所对应的省份变化不大,香菇低-低(L-L)象限所对应的省份增加,黑木耳低-低(L-L)象限所对应的省份减少,黑木耳高-低(H-L)象限所对应的省份增加;城镇化率和小麦产量对香菇生产布局集聚具有显著的正向促进作用,城镇化率和农机台数对黑木耳生产布局集聚有显著的正向促进作用,而蔬菜价格指数对香菇和黑木耳生产布局集聚呈现负向抑制作用。加强省际间沟通交流,提升小麦等主粮产量,推动农村城镇化建设,推进食用菌生产机械化和智能化,完善蔬菜、食用菌等农产品的价格调控机制,可以促进我国香菇和黑木耳产业科学布局和高质量发展。本研究可为其他类似食用菌生产时空演化及影响因素分析提供参考和借鉴。

基于多时间粒度时空图网络的蜂窝网络流量预测

蜂窝网络流量预测对于运营商提高网络服务质量、降低能耗、优化资源配置具有重要意义。针对当前蜂窝网络流量预测方法无法同时提取多时间粒度序列特征和空间特征的问题,提出一种基于多时间粒度时空图神经网络的蜂窝网络流量预测方法。该方法首先将基站历史数据建模为多个时间粒度的时序数据,并使用一维卷积网络提取每个序列的特征,然后使用图注意力网络对多时间粒度的特征进行聚合得到单一基站的数据特征,最后将多个基站的特征进行空间聚合,并使用全连接层将每个基站聚合后的特征映射为预测结果。实验选择公开数据集Telecom Italia验证该方法的有效性,使用RMSE和R 2作为预测结果的评价指标,与当前已有方法相比该方法可取得最好的预测结果。论文最后分析了不同时间粒度序列对最终预测结果的影响,结果表明时间粒度位于40分钟至1.5小时之间的序列对提高模型预测效果的贡献最大。

Comparison of carbon sequestration efficiency in soil aggregates between upland and paddy soils in a red soil region of China

There is limited information on carbon sequestration efficiency(CSE)of soil aggregates in upland and paddy soils under long-term fertilization regimes.In a red soil region of southern China,an upland soil experiment started in 1986 and a paddy soil experiment commenced in 1981.These experiments were conducted using different fertilization treatments.After 30 years,soil organic carbon(SOC)content and stock of different aggregate components were analyzed.The results showed that the SOC contents and stocks in upland soil were lower than in paddy soil.In both upland and paddy soils,the SOC contents and stocks of all aggregate components in NPKM(combined treatment with chemical nitrogen(N),phosphorus(P),potassium(K)fertilizers and manure)were the highest among all treatments.Compared with CK(no fertilizer),SOC content of all aggregate components in NPKM was increased by 13.21–63.11%and 19.13–73.33%in upland and paddy soils,respectively.Meanwhile,the change rates in SOC stock of all aggregate components in upland soil were lower than in paddy soil,although the change rate of SOC stock of all aggregate components in NPKM was higher than in other treatments.Furthermore,a linear equation could fit the relationships between carbon(C)input and change rate of SOC stock(P<0.05).Results indicated that the sum of CSE from all aggregate components in upland soil(16.02%)was higher than that of paddy soil(15.12%)in the same climatic condition and from the same parent material.However,the CSEs from all aggregates were higher than that of bulk soil,although the result from bulk soil also showed that the CSE of upland soil was higher than that of paddy soil.

Response of Soil Organic Carbon and Its Aggregate Fractions to LongTerm Fertilization in Irrigated Desert Soil of China

Irrigated desert soil samples in the Hexi Corridor of China were collected over a period of 23 years from a site where different fertilization methods had been used. Changes of soil organic carbon （SOC） and its water stable aggregate （WSA） size fractions were studied. The effects of various fertilization methods on the distribution of added organic carbon （OC） in different WSA size fractions were also analyzed. The results showed that the applied fertilizations for 23 years improved SOC concentrations and OC concentrations in all WSA size fractions compared to the non-fertilized treatment （CK）. In addition, fertilization obviously increased the OC stocks of2 mm, 0.25-2 mm and 0.053-0.25 mm WSA fractions, respectively. A signiifcant positive correlation was found between soil C gains and OC inputs （r=0.92, P〈0.05）, indicating that SOC may have not reached the saturation point yet at the site. The C sequestration rate was estimated by 14.02%at the site. The OC stocks in all of the〈2 mm WSA fractions increased with the increase of OC input amounts;and the conversion rate of the input fresh OC to the OC stock of〈0.053 mm WSA fraction was 1.2 and 2.6 times higher than those of the 0.25-2 mm and 0.053-0.25 mm WSA fractions, respectively. Therefore, the〈0.053 mm WSA fraction was the most important component for soil C sequestration in the irrigated desert soil.