Erosion pattern of artificial gravel deposits

Sediment replenishment with artificial gravel deposits is an option to compensate for sediment deficits in rivers and to improve their ecological conditions. Predicting and quantifying the erosion rate of an artificial gravel deposit is important to successfully perform river restoration projects. Laboratory experiments have been done to investigate the influence of various parameters on the erosion pattern of artificial gravel deposits. In the present paper the effects of deposit geometry, bulk density, grain size distribution, and hydraulic load on the erosion process are described. The temporal evolution of the deposit geometry and the corresponding mean erosion rates were studied. The mean erosion rate increases with deposit height, deposit width, and decreasing grain size. Furthermore, no significant impact of the bulk density was observed. Equations to predict the mean erosion rate are proposed. This investigation helps to determine the design frequency of gravel dumping and deposit volumes for restoration projects.     

基岩输入时程随机数对场地峰值加速度的影响研究

研究基岩输入时程随机数对场地峰值加速度的影响,对核电厂设计地震动参数的合理确定具有重要意义。本文选取了某重要核电站场地具有代表性的3个钻孔,建立了场地计算模型。根据确定性方法、概率性方法得到的基岩反应谱及其包络谱,基于不同随机数,分别合成了400条基岩输入时程。采用LSSRLI-1程序进行了场地地震反应,根据4800个计算结果,研究了不同随机数对地表峰值加速度的影响,给出了自然对数下峰值加速度标准差的估计,揭示了峰值加速度的分布规律,提出了对核电厂设计地震动参数合理确定的建议。     

Artificial intelligence in seismology:Advent,performance and future trends

Realistically predicting earthquake is critical for seismic risk assessment,prevention and safe design of major structures.Due to the complex nature of seismic events,it is challengeable to efficiently identify the earthquake response and extract indicative features from the continuously detected seismic data.These challenges severely impact the performance of traditional seismic prediction models and obstacle the development of seismology in general.Taking their advantages in data analysis,artificial intelligence(AI) techniques have been utilized as powerful statistical tools to tackle these issues.This typically involves processing massive detected data with severe noise to enhance the seismic performance of structures.From extracting meaningful sensing data to unveiling seismic events that are below the detection level,AI assists in identifying unknown features to more accurately predicting the earthquake activities.In this focus paper,we provide an overview of the recent AI studies in seismology and evaluate the performance of the major AI techniques including machine learning and deep learning in seismic data analysis.Furthermore,we envision the future direction of the AI methods in earthquake engineering which will involve deep learning-enhanced seismology in an internet-of-things(IoT) platform.     

支持向量机、随机森林和人工神经网络机器学习算法在地球化学异常信息提取中的对比研究

地球化学勘查是通过发现异常、解释评价异常进行找矿的。因此,地球化学异常识别对矿产资源的定位、定量预测具有重要的的指示作用。在大数据时代的背景下,机器学习方法不要求数据满足正态分布的分布形式,且具有非线性以及泛化能力强等特点,因而逐渐地被应用于矿产资源的定量预测评价,如神经网络、支持向量机、贝叶斯网络、随机森林、受限玻尔兹曼机、极限学习机等。本文通过设计理论实验,可视化了不同算法,提出了不同机器学习方法在不同地区的地球化学异常信息提取中的效果存在不一致性的假设。在此基础上,以湖南香花岭锡多金属矿整装勘查区及甘肃合作金矿整装勘查区的地球化学异常提取为研究内容,将人工神经网络、随机森林以及支持向量机应用于研究区地球化学异常信息的提取与识别工作。在香花岭研究区,人工神经网络的结果较好,在合作研究区,随机森林的结果较好,从而验证了上述假设。通过生成两研究区的地球化学异常图,讨论了该方法在两研究区地球化学异常的地质意义和该方法的可靠性与实用性。此外,还完善了基于多种监督机器学习方法的地球化学异常信息提取流程,为软件开发提供了一定的理论依据。     

湿地植物固体碳源养分释放动态及其对人工湿地水体脱氮效率的影响

污水低碳氮比(C/N)是影响人工湿地氮去除效果限制因素,传统的碳源添加及利用存在成本较高、补充困难的局限性.本研究契合“就地取材,原位处理”的废物利用原则,选择人工湿地常见的水生植物和农业废弃物(玉米芯、稻草)作为对照,对比了挺水植物(香蒲、美人蕉)、浮叶植物(莲)、沉水植物(菹草)、湿生植物(南荻、短尖苔草)的释碳能力,初步确定了以香蒲、美人蕉、南荻为代表的植物具有较好的释放碳能力,在中国湿地中分布广泛,且均对水体二次污染较小.以南荻、美人蕉、玉米芯作为碳源添加的模拟人工湿地实验验证表明,在低碳氮比的模拟表流人工湿地投入植物碳源,能有效提高系统的脱氮效率,对照组、南荻组、美人蕉组和玉米芯组的出水总氮浓度分别为(5.24±0.07)、(4.50±0.10)、(3.75±0.17)和(2.97±0.18) mg/L,对应的去除率分别为58%、64%、70%和76%,确定南荻和美人蕉植物残体以及改性材料均残体和改性材料适合作为人工湿地中原位利用的外加碳源.本研究探索了通过湿地植物配置解决人工湿地水体低C/N比的问题,为提高湿地脱氮效果提供了有意义的新途径.     

Hyperparameter optimization of neural network-driven spatial models accelerated using cyber-enabled high-performance computing

Artificial neural networks (ANNs) have been extensively used for the spatially explicit modeling of complex geographic phenomena. However, because of the complexity of the computational process, there has been an inadequate investigation on the parameter configuration of neural networks. Most studies in the literature from GIScience rely on a trial-and-error approach to select the parameter setting for ANN-driven spatial models. Hyperparameter optimization provides support for selecting the optimal architectures of ANNs. Thus, in this study, we develop an automated hyperparameter selection approach to identify optimal neural networks for spatial modeling. Further, the use of hyperparameter optimization is challenging because hyperparameter space is often large and the associated computational demand is heavy. Therefore, we utilize high-performance computing to accelerate the model selection process. Furthermore, we involve spatial statistics approaches to improve the efficiency of hyperparameter optimization. The spatial model used in our case study is a land price evaluation model in Mecklenburg County, North Carolina, USA. Our results demonstrate that the automated selection approach improves the model-level performance compared with linear regression, and the high-performance computing and spatial statistics approaches are of great help for accelerating and enhancing the selection of optimal neural networks for spatial modeling.     

Layered berthing method and experiment of unmanned surface vehicle based on multiple constraints analysis

Considering the dynamic changes of unmanned surface vehicle (USV) in berthing tasks, the planning and control modes are divided into two phases: the remote phase and the terminal phase. According to the main influencing factors of the two phases, an improved artificial potential field method is proposed to complete autonomous berthing trajectory planning based on the analysis of environment constraint, berth point constraint and USV’s dynamics constraint. Combining with the dynamic characteristics and control objectives at different phases of berthing and analyzing the fuzzy rule regulation strategy of USV’s heading and speed control, an improved adaptive fuzzy PID control method is proposed to solve the control problem of USV, which is influenced by weak maneuver, large disturbance, limited water area and strong shore effect. Finally, the comparative test of berthing simulation verifies the superiority of the proposed control method. The autonomous berthing field experiment is completed based on the "Dolphin-I" small USV. It verifies the validity and feasibility of the proposed autonomous berthing method.     

基于CMIP6多模式集合的未来中国风功率预估

实现我国2060年“碳中和”目标,需要大力发展包括风能在内的清洁能源,然而气候变化给未来风资源利用带来较大的不确定性。本文利用人工神经网络(Artificial Neural Network,ANN)算法对16个CMIP6气候模式风速数据进行逐一订正,在此基础上预估21世纪30、60年代以及21世纪末这3个不同年代在低(SSP1-2.6)和高(SSP5-8.5)排放情景下中国风功率较当代的变化。结果表明,ANN算法使CMIP6气候模式均方根误差平均降低(39.93％±9.57％),并使多模式集合平均与观测的相关系数从0.56增加到0.83,更好地再现了中国当代风速的空间分布和季节变化。在此基础上,预估的21世纪60年代(2050—2064年)风功率密度在两种情景下分别减少了(1.01±0.94) W·m^-2(2.62％±2.27％)和(1.11±1.45) W·m^-2(1.90％±2.51％)。时间上,春季作为风能密度最大的季节,两种排放情景下风功率分别减少了(1.16±1.14) W·m^-2和(1.43±1.58) W·m^-2。空间上,中国东南部风功率密度在SSP1-2.6情景下降(0.56±0.53) W·m^-2,而SSP5-8.5情景下上升(0.40±0.29) W·m^-2。近期(2025—2039年)全国平均风功率密度在两种情景下分别减少了(0.52±0.83) W·m^-2和(0.54±1.02) W·m^-2,而长期(2085—2099年)风功率密度分别减小了(0.98±1.17) W·m^-2和(1.83±1.17) W·m^-2。利用极度梯度提升(XGB)算法订正CMIP6数据的预估变化量级偏小但趋势一致,表明随着全球变暖幅度的增加,我国风功率降低的趋势将更加显著。     

A practical device for evaluating periphyton colonization dynamics in tropical shallow wetlands

Here, we have presented a field device for sampling periphyton in lentic systems, with a tropical lowland wetland in Colombia as the model system. The periphyton sampler (PS) is composed of a central soft iron pole to which rectangular woody boxes and glass slides are attached to lateral iron axes, which can be distributed at different depths. Our PS can be used to evaluate changes in the richness and density of algal communities at different scales as well as in water quality studies.     

自动观测与人工观测数据差异的初步分析

利用2004—2007年内蒙古地区50个地面自动气象站与人工平行观测期间的数据,对自动与人工观测的气温、相对湿度、地表温度进行了差异分析,统计了两种观测之间的对比差值。对各要素观测差异在全区的分布特点进行了分析。结果表明:自动观测与人工观测各气象要素均存在一定的差异,但大部分地区各要素的差异都在自动站误差允许范围之内;造成差异的原因是多方面的,包括仪器本身存在缺陷及观测方法不一致等。