Prediction of Landscape Pattern of Soft Sandstone Area (SSA) after Seabuckthorn Planting

As a pioneer plant in the gully slopes in the Soft Sandstone Area (SSA) for eco-economical consideration, ten years (1999-2008) planting of seabuckthorn has made 1642.83 km2, or 9.84%, of the total area of SSA change into seabuckthorn coverage. In SSA the landscape has been divided into 9 types, such as seabuckthorn, sand, water, settlement, bush, open vegetation, forest, grassland and unused land. Seabuckthorn type is separated from the bush type for estimating the role of seabuckthron planting. By means of the Markov model, the developing trends of every landscape types can be determined to support the seabuckthorn project which influences the landscape pattern deeply in SSA. The prediction shows that the optimism ratio of seabuckthorn in the future should be 10.21%, the open vegetation 32.25%, and the forest percentage under 10%, which is a very wise tactics to avoid the serious death of various vegetations in SSA to match the local arid eco-environment.

Mutation pattern in human adrenoleukodystrophy protein in terms of amino-acid pair predictability

The mutation pattern in protein is a very important feature and is studied through various approaches including the study on mutation pattern in domains where amino acids are converted into numbers from letters. In this study, we converted the amino acids in human adrenoleukodystrophy protein with its 128 missense mutations into random domain using the amino-acid pair predictability, and then we studied their mutation patterns. The results show 1) the mutations are more likely to target the amino-acid pairs whose actual frequency is larger than their predicted one, 2) the mutations are more likely to form the amino-acid pairs whose actual frequency is smaller than their predicted frequency, 3) mutations are more likely to occur at unpredictable amino-acid pairs, and 4) mutations have the trend to narrow the difference between predicted and actual frequencies of amino-acid pairs.

Case Study of Fog Predictability for an Event with Cold-Front Synoptic Pattern

Fog has recently become a frequent high-impact weather phenomenon along the coastal regions of North China. Accurate fog forecasting remains challenging due to limited understanding of the predictability and mechanism of fog formation associated with synoptic-scale circulation. One frequent synoptic pattern of fog formation in this area is associated with cold front passage(cold-front synoptic pattern, CFSP). This paper explored the predictability of a typical CFSP fog event from the perspective of analyzing key characteristics of synoptic-scale circulation determining fog forecasting performance and the possible mechanism. The event was ensemble forecasted with the Weather Research and Forecasting model. Two groups of ensemble members with good and bad forecasting performance were selected and composited. Results showed that the predictability of this case was largely determined by the simulated strengths of the cold-front circulation(i.e., trough and ridge and the associated surface high). The bad-performing members tended to have a weaker ridge behind a stronger trough, and associated higher pressure over land and a weaker surface high over the sea, leading to an adverse impact on strength and direction of steering flows that inhibit warm moist advection and enhance cold dry advection transported to the focus region. Associated with this cold dry advection, adverse synoptic conditions of stratification and moisture for fog formation were produced, consequently causing failure of fog forecasting in the focus region. This study highlights the importance of accurate synoptic-scale information for improved CFSP fog forecasting, and enhances understanding of fog predictability from perspective of synoptic-scale circulation.

Filling Pattern of Volcanostratigraphy of Cenozoic Volcanic Rocks in the Changbaishan Area and Possible Future Eruptions

The Cenozoic volcanostratigraphy in the Changbaishan area had complex building processes.Twenty-two eruption periods have been determined from the Wangtian＇e, Touxi, and Changbaishan volcanoes. The complex volcanostratigraphy of the Changbaishan area can be divided into four types of filling patterns from bottom to top. They are lava flows filling in valleys（LFFV）, lava flows filling in platform（LFFP）, lava flows formed the cone（LFFC）, and pyroclastic Flow filling in crater or valleys（PFFC/V）. LFFV has been divided into four layers and terminates as a lateral overlap. The topography of LFFV, which is controlled by the landform, is lens shaped with a wide flat top and narrow bottom.LFFP has been divided into three layers and terminates as a lateral downlap. The topography of LFFP is sheet and tabular shaped with a narrow top and wide bottom. It has large width to thickness ratio. It was built by multiple eruptive centers distributed along the fissure. The topography of LFFC, which is located above the LFFP, has a hummocky shape with a narrow sloping top and a wide flat bottom. It terminates as a later downlap or backstepping. It has large width to thickness ratio. It was built by a single eruptive center. The topography of PFFC/V, which located above the LFFC, LFFP, or valley, has the shape of fan and terminates as a lateral downlap or overlap. It has a small width to thickness ratio and was built by a single eruptive center. The filling pattern is controlled by temperature, SiO_2 content,volatile content, magma volume, and the paleolandform. In the short term, the eruptive production of the Changbaishan area is comenditic ash or pumice of a Plinian type eruption. The eruptive volume in future should be smaller than that of the Baguamiao period, and the filling pattern should be PFFC/V,which may cause huge damage to adjacent areas.

Quantitative multiparameter prediction of fault-related fractures： a case study of the second member of the Funing Formation in the Jinhu Sag, Subei Basin

In this paper, the analysis of faults with different scales and orientations reveals that the distribution of fractures always develops toward a higher degree of similarity with faults, and a method for calculating the multiscale areal fracture density is proposed using fault-fracture self-similarity theory. Based on the fracture parameters observed in cores and thin sections, the initial apertures of multiscale fractures are determined using the constraint method with a skewed distribution. Through calculations and statistical analyses of in situ stresses in combination with physical experiments on rocks, a numerical geomechanical model of the in situ stress field is established. The fracture opening ability under the in situ stress field is subsequently analyzed. Combining the fracture aperture data and areal fracture density at different scales, a calculation model is proposed for the prediction of multiscale and multiperiod fracture parameters, including the fracture porosity, the magnitude and direction of maximum permeability and the flow conductivity. Finally, based on the relationships among fracture aperture,density, and the relative values of fracture porosity and permeability, a fracture development pattern is determined.

Predicting the Geographic Traffic Distribution in Cellular Networks

Early detection and rapid resolution network congestion can considerably improve network capacity. Consequently, much research has been carried out on predicting traff ic patterns in 3G networks. This paper introduces an access point centric approach that is implemented by two prediction models, the traffic abstraction model and the order-k Markov model. Traffi c predictions are carried out to support the congestion control in the semi-smart antenna systems. The simulation result shows that the cumulative error rate is below 25% even carrying out multi-step-ahead predictions.

Bus Arrival Time Prediction Based on Mixed Model

How to predict the bus arrival time accurately is a crucial problem to be solved in Internet of Vehicle. Existed methods cannot solve the problem effectively for ignoring the traffic delay jitter. In this paper,a three-stage mixed model is proposed for bus arrival time prediction. The first stage is pattern training. In this stage,the traffic delay jitter patterns(TDJP)are mined by K nearest neighbor and K-means in the historical traffic time data. The second stage is the single-step prediction,which is based on real-time adjusted Kalman filter with a modification of historical TDJP. In the third stage,as the influence of historical law is increasing in long distance prediction,we combine the single-step prediction dynamically with Markov historical transfer model to conduct the multi-step prediction. The experimental results show that the proposed single-step prediction model performs better in accuracy and efficiency than short-term traffic flow prediction and dynamic Kalman filter. The multi-step prediction provides a higher level veracity and reliability in travel time forecasting than short-term traffic flow and historical traffic pattern prediction models.

Application of Data Mining Method to Improve the Accuracy of Springback Prediction in Sheet Metal Forming

A new method was worked out to improve the precision of springback prediction in sheet metal forming by combining the finite element method (FEM) with the data mining (DM) technique. First the genetic algorithm (GA) was adopted for recognizing the material parameters. Then according to the even design idea, the suitable calculation scheme was confirmed, and FEM was used for calculating the springback. The computation results were compared with experiment data, the difference between them was taken as source data, and a new pattern recognition method of DM called hierarchical optimal map recognition method (HOMR) is applied for summarizing the calculation regulation in FEM. At the end, the mathematics model of the springback simulation was established. Based on the model, the calculation errors of springback can be controlled within 10% compared with the experimental results.

Mutation Patterns in Lysostaphin

Lysostaphin is widely used in clinical settings against Staphylococcus aureus, but its mutants can abolish its killing activity. The difficulty in studies of mutations in lysostaphin is the shortage of data, which may need many decades to collect, although lysostaphin is so important for clinical therapeutics and drug development. In order not to passively wait for the accumulation of new data, in this study 1) the 23,442 mutations in 1408 proteins from databank were used to determine whether the mutations in lysostaphin follow the general mutation trend obtained from the databank, 2) the amino-acid pair predictability was used to explore the underlined mechanism for lysostaphin mutations, and 3) the amino-acid distribution probability was used to associate the mutation with dysfunction of lysostaphin. The results show that the mutations in lysostaphin follow the general trend of mutations in proteins;the underlined mechanism for mutations in lysostaphin is explainable from a viewpoint of randomness, and a mutation with increased distribution probability would have a larger chance to dysfunction lysostaphin. This study provides useful information for future design of anti-S. aureus drug and enzyme engineering.

Formation Dynamics and Quantitative Prediction of Hydrocarbons of the Superpressure System in the Dongying Sag

Based on the theory of formation dynamics of oil/gas pools, the Dongying sag can be divided into three dynamic systems regarding the accumulation of oil and gas： the superpressure closed system, the semi-closed system and the normal pressure open system. Based on the analysis of genesis of superpressure in the superpressure closed system and the rule of hydrocarbon expulsion, it is found that hydrocarbon generation is related to superpressure, which is the main driving factor of hydrocarbon migration. Micro fractures formed by superpressure are the main channels for hydrocarbon migration. There are three dynamic patterns for hydrocarbon expulsion： free water drainage, hydrocarbon accumulation and drainage through micro fissures. In the superpressure closed system, the oil-driving-water process and oil/gas accumulation were completed in lithologic traps by way of such two dynamic patterns as episodic evolution of superpressure systems and episodic pressure release of faults. The oil-bearing capacity of lithologic traps is intimately related to reservoir-forming dynamic force. Quantitative evaluation of dynamic conditions for pool formation can effectively predict the oil-bearing capability of traps.

Prediction of powder characteristics of uniform NiO precursor prepared by homogeneous precipitation

Uniform NiO precursor particles were prepared by homogeneous precipitation in the presence of urea. Optimal discrimination plan, one of the chemical pattern recognition techniques, was applied to analyze the experimental data and the quantitative relationships among the process parameters and powder characteristics of the obtained particles were determined. It proves that the model fits well with the experimental results and it is quite effective to guide the process design. Based on the above results, an improved La Mer model and the reasonable formation mechanism of the particles are proposed.

水库消落带植物多样性空间格局预测模型及环境解释--基于XGBoost-SHAP模型框架

生物多样性的监测与预测对实现生物多样性保护及其可持续管理至关重要。传统方法通过实地调查来构建环境与生物多样性之间的多变量关系模型。空间大数据技术及机器和深度学习算法的发展为探索环境-生物多样性关系和预测生物多样性空间格局提供了新的视角和方法。构建了一种基于XGBoost算法的预测模型,融合实地调查的植物多样性数据和来自多源数据库的环境变量数据,分别构建了气候、地形、土壤、水文和人类活动5类共34个环境变量与植物群落物种丰富度、物种多样性和谱系多样性的关系模型,对丹江口水库消落带的植物多样性空间格局进行预测,同时结合SHAP框架确定关键环境因素;并进一步预测2050年水库消落带的植物多样性空间格局。研究表明,XGBoost算法在预测水库消落带植物多样性方面表现较好,3个多样性指标中谱系多样性的预测模型展现了最优的预测能力,而物种多样性预测模型的预测能力相对较低。结合SHAP分析发现年平均水淹时长、人类足迹与最冷季平均气温是影响消落带植物群落物种丰富度、物种多样性和谱系多样性的关键环境因素,其中年平均水淹时长的影响最为显著,随着年平均水淹时长增加,物种丰富度、物种多样性和谱系多样性降低。本研究构建的可解释预测模型可有效揭示消落带的植物多样性空间格局,为消落带生物多样性的保护和可持续管理提供科学依据,为生物多样性的监测和管理提供了新方法,对评估全球变化对生态系统的影响并促进生物多样性保护有重要意义。

基于PLUS模型的2030年滹沱河流域山区段生态承载力时空格局多情景预测

为探讨滹沱河流域山区段当前及未来不同发展情景下生态承载力的时空变化,应用植被净初级生产力改进的生态足迹模型测算分析了流域2015—2020年生态承载力的时空格局变化,并借助经过精度验证的PLUS模型对2030年区域自然发展、经济发展及生态保护三种发展情景下的生态承载力时空格局进行预测。结果表明:2015—2030年滹沱河流域山区段单位面积生态承载力整体格局变化不大,但内部空间分异明显,整体呈东南及西北区域单位面积生态承载力高,而东北、西南部区域单位面积生态承载力低的特点。2015—2020年区域生态承载力总量由1.0780×10^(6)bhm^(2)增加到1.0796×10^(6)bhm^(2),呈上升趋势;2030年自然发展和经济发展情景下区域生态承载力总量分别为1.0783×10^(6)、1.0782×10^(6)bhm^(2),与2020年相比呈下降趋势,草地向耕地的转移、林地向建设用地的转移是生态承载力下降的主要原因;2030年生态保护情景下生态承载力总量为1.0802×10^(6)bhm^(2),与2020年相比呈上升趋势,耕地向林地、草地转移是区域生态承载力增加的主要原因。各类用地的生态承载力总量由高到低依次为草地>耕地>林地>建设用地>水域,生态保护情景有益于林地、草地生态承载力总量的增加,经济发展情景有益于耕地和建设用地生态承载力总量的增加,水域生态承载力总量在各种发展情景下变化较小。生态保护情景更有利于未来生态承载力的增加,符合区域未来发展方向。严格控制草地向耕地的转变以及林地向建设用地的转变,继续实施退耕还林、还草生态工程,加强区域废弃矿山生态复垦的力度,将会提高区域未来生态承载力,实现区域生态安全及经济、社会、生态的可持续发展。

融合改进NBEATSx和时间注意力机制的空气污染预测

针对现有空气污染预测存在结构复杂、对多元变量与不同时间步间依赖关系提取不充分和多步预测精度低的问题,引入了β分布和非线性动态控制函数改进星鸦优化算法(INOA),优化NBEATSx模型参数,提高收敛精度;并融合时间模式注意力机制(TPA)为不同时间尺度的多外生变量自适应分配权重,再结合预测因子获取时间模式关系.利用所提模型对北京地区的PM2.5进行预测,与传统模型相比精度提高超过18.45%,为空气污染预测提供了一种新方法.

喜马拉雅成矿带锂-铍-铷-铯超常富集规律与稀有元素找矿潜力预测

稀有元素锂、铍、铷、铯地壳丰度低,需要数百至上千倍的超常富集才能成矿,导致其矿产资源分布极不均匀,发现稀有元素超常富集区是战略资源找矿预测的关键,特别是在青藏高原这种野外条件极困难的工作区。全国地球化学基准图揭示喜马拉雅成矿带锂、铍、铷、铯等稀有元素超常富集规律。这一超常富集的特点是:(1)锂、铍、铷、铯都发生超常富集,富集系数均大于2,其中喜马拉雅成矿带是铯和铍的全国最强富集区,是锂、铷的全国第二强富集区;(2)富集区异常规模达104156 km^(2),富集中心面积均超过1000 km^(2);(3)超常富集区沿喜马拉雅造山带呈近东西向展布,从西向东依次分布于札达县—日土县、吉隆县—聂拉木县、定日县—拉孜县、江孜县和洛扎县—错那县—隆子县一带;(4)异常核心区主要与含有电气石、石榴子石、锂辉石等淡色花岗岩密切相关,特别是铯的大规模超常富集,证明了喜马拉雅淡色花岗岩为高度结晶分异的花岗岩;(5)目前该成矿带内已发现定日县琼嘉岗和洛扎嘎波两处伟晶岩型锂矿,以及错那县境内错那洞钨-锡-铍矿床,喜马拉雅稀有元素超常富集区具有寻找锂-铍-铷-铯等稀有金属矿床的潜力。

成分数据视角下我国能源消费结构的定变权组合预测

能源是我国经济社会发展的重要物质基础,有效预测能源消费结构的变动趋势,对我国实现“双碳”目标有着重要的现实意义。然而能源消费结构属于一类具有特殊空间结构的复杂数据类型,其主要特征是各组成部分比例为非负且总和恒定为1。因此将成分数据理论引入到能源消费结构的研究中,旨在充分满足能源消费结构的特殊内部特征,并充分挖掘出其相对信息。分别构建了球坐标变换下各成分的BP神经网络、ARIMA模型和三次指数平滑等单一预测模型;基于成分数据中的Aitchison距离平方和最小化,分别构建了定权和变权的组合预测模型;以平均Aitchison距离值MSD最小的变权组合模型预测了2024-2030年我国能源消费结构的变化趋势。预测结果表明,我国能源消费结构中短期内将朝着多元化格局发展,清洁能源消费占比将呈现不断增加的趋势,但煤炭等化石资源仍将占据着能源消费的主体地位。

基于BP神经网络的低渗透底水油藏油井见水模式预测模型

注水开发使得低渗透底水油藏油井见水模式更加复杂,需要进一步明确及预测油井见水模式来针对性地指导水淹治理措施。神经网络模型具备处理多元回归问题和计算速度快等优势,可被用于分析地质工程多因素参数与油井见水模式的内在关系,构建见水模式预测模型。在油井见水模式划分的基础上,通过灰色关联理论和神经网络算法对BCL低渗透底水油藏油井见水模式的主控因素和预测模型进行了研究。发现水层厚度、隔夹层数、隔夹层长度和避水高度是该类油藏注水开发下影响油井见水模式的主控因素。基于主控因素结合神经网络算法建立了油井见水模式预测模型。通过对18组测试数据进行验证,平均预测误差1.4%,获得了较好的预测精度。通过易于获取的主控因素快速预测注水开发低渗透底水油藏油井的见水模式,为该类油藏的高含水针对性治理提供基础依据。

整合类内差异与类间关联的隐喻感情预测

隐喻感情预测有助于改进社交媒体内容的用户体验,同时在心理健康监测和虚拟心理治疗方面也具有潜在价值。此外,它还可以更精确地识别目标受众的感情需求,优化广告策略,提升商业效益。为了进一步提升情绪识别与情感检测的有效性,提出了一种整合类内差异与类间关联的多模式隐喻感情识别架构。首先引出三种单模式模型,包括视觉语义模型,文本语义模型和音频语义模型,从文本、视觉和音频三种不同的数据源中分别提取每个模式的个性化差异特征;随后引出一种深度层次多模式模型,通过中间层融合的方式对多模式之间的关联性进行学习,更好地利用双模式与三模式之间提供的互补信息;最后,基于决策层融合的方式将上述四种模型进行融合,在一种端到端的框架中,实现多模式隐喻感情的预测。在开源的数据集中进行的大量消融实验与对比实验证明了方法的有效性。

朴素贝叶斯下新型建筑室内空调瞬态能耗预测

新型建筑通常具有较为复杂的结构,使得室内空调系统的能耗受到如建筑朝向、室内人员活动以及设备使用情况等因素影响,导致无法精准预测空调能耗。为此,提出新型建筑室内空调瞬态能耗朴素贝叶斯预测方法。采用K均值聚类(K-means clustering,K-Means)算法将新型建筑室内空调划分为除湿模式、制冷模式、通风模式、制热模式和自动模式,并分析影响空调瞬态能耗的因素,建立朴素贝叶斯预测模型,剔除空调瞬态能耗异常数据,输入至朴素贝叶斯预测模型中,实现新型建筑室内空调的瞬态能耗预测。仿真结果表明,所提方法可有效完成不同模式和运行时间下的瞬态能耗预测,与实际能耗之间的偏离程度较低,期望误差仅为2.31%,变异系数为4.76%,预测误差小。

基于支持向量机与模型预测控制的混合动力船舶能量管理策略

为了提高混合动力船舶能量利用效能,提升混合动力船舶燃油经济性,将在线工况识别与实时优化策略相结合,提出了基于支持向量机(support vector machine,SVM)与模型预测控制(model predictive control,MPC)的混合动力船舶能量管理策略。引入SVM理论,使用“美维凯越”号新能源游轮的实船数据,优化核函数类型及关键参数,构建船舶运行4个典型工况的在线识别模型;再通过对船舶当前时刻工况特征参数的分析与判断,确定船舶实时运行工况。以最小燃油消耗和保持储能单元荷电状态(state of charge,SOC)稳定为目标,以主机和复合储能单元之间的实时输出功率为优化变量,以功率需求预测模型为约束条件,构建模型预测控制MPC模型;为提高不同工况下功率需求预测的精度,提出基于多步马尔科夫模型的功率预测模型,并根据实时工况识别结果,更新MPC模型中的功率需求预测模型约束,实现船舶能量实时动态优化。最后,采用小波变换方法,将最优功率解分解成高频信号和低频信号;再根据复合储能单元中不同动力源工作特性的差异,将高频信号和低频信号分别分配给具有高功率密度的超级电容和具有高能量密度的蓄电池。为验证方法的有效性,开展了基于MATLAB的仿真实验,结果表明:在相同工况下,所提策略累计燃油消耗量为4 404.556 1 g,平均燃油消耗率为202.973 7 g/kWh;与基于单一模型预测控制的能量管理策略相比,所提方法可节省燃油消耗4.55%,验证了所提能量管理策略的有效性。