Estimation of monthly reference evapotranspiration using novel hybrid machine learning approaches

ABSTRACT

In this research, five hybrid novel machine learning approaches, artificial neural network (ANN)-embedded grey wolf optimizer (ANN-GWO), multi-verse optimizer (ANN-MVO), particle swarm optimizer (ANN-PSO), whale optimization algorithm (ANN-WOA) and ant lion optimizer (ANN-ALO), were applied for modelling monthly reference evapotranspiration (ET_o) at Ranichauri (India) and Dar El Beida (Algeria) stations. The estimates yielded by hybrid machine learning models were compared against three models, Valiantzas-1, 2 and 3 based on root mean square error (RMSE), Nash-Sutcliffe efficiency (NSE), Pearson correlation coefficient (PCC) and Willmott index (WI). The results of comparison show that the ANN-GWO-1 model with five input variables (T_min, T_max, RH, U_s, R_s) provides better estimates at both study stations (RMSE = 0.0592/0.0808, NSE = 0.9972/0.9956, PCC = 0.9986/0.9978, and WI = 0.9993/0.9989). Also, the adopted modelling strategy can build a truthful expert intelligent system for estimating the monthly ET_o at study stations.     

A conceptual evolutionary aseismic decision support framework for hospitals

In this paper, aconceptual evolutionary framework for aseismic decision support for hospitalsthat attempts to integrate a range of engineering and sociotechnical models is presented. Genetic algorithms are applied to find the optimal decision sets. A case study is completed to demonstrate how the frameworkmay applytoa specific hospital.The simulations show that the proposed evolutionary decision support framework is able to discover robust policy sets in either uncertain or fixed environments. The framework also qualitatively identifies some of the characteristicbehavior of the critical care organization. Thus, by utilizing the proposedframework, the decision makers are able to make more informed decisions, especially toenhance the seismic safety of the hospitals.     

GA-BP神经网络在罗源湾口波浪模拟研究中的应用

由于BP神经网络存在收敛速度慢和易于陷入极小值等缺点,引入遗传算法(GA)对网络的权值和阈值加以优化,并采用不同组合的输入因子和样本数,对福建省罗源湾口的波浪进行模拟研究.对输入因子的分析结果表明,研究区域的波浪主要受台湾海峡波浪传播影响,与局地气象因子(风速、风向、海气温差)的相关性较弱.训练样本试验表明,30 d以上的波浪历史数据可使GA-BP神经网络充分学习研究区域的波浪特征,从而实现对波浪要素的高精度模拟.模拟结果显示,对春、夏季实测波浪数据的模拟效果均很好,其中相关性分别为0.967和0.938,均方根误差分别为0.112 m和0.107 m,表明GA-BP神经网络在近岸波浪模拟预报中有较广阔的应用前景.     

基于移动网络的端到端密钥协商协议

虽然3G网络的安全机制扩展到核心网络,但是并没有实现端到端安全.基于自生成证书公钥密码体制,设计一种端到端密钥协商协议,只需要一个消息交换就可以建立安全的三方会话密钥.安全性分析结果表明:基于移动网络的端到端密钥协商协议能够解决密钥管理及第三方无举证窃听,与其他密钥协商协议相比,具有较好的安全性,为端到端加密在移动通信系统中的大规模应用提供基础.     

利用重测定的震源深度特征探讨2013年吉林前郭5.8级震群发震因素

利用Pn-Pg震相组合的局部搜索法,采用5种地壳速度模型对2013年吉林前郭5.8级地震震群进行震源深度测定。计算结果显示,5种结果的震源深度的主要分布特征相似。对选取的32个地震震源深度进行重新测定,结果最小为6 km,最大14 km,主要集中在10 km左右,系统深度偏差约1.74 km,震源深度分辨率约1.58km,重定位后地震震中优势分布呈北西向。与当地的沉积层厚度分布对比,这些地震最有可能发生在盆地基底的基岩顶层,而不在油气圈闭的沉积盖层内,并且地震震群分布走向与通榆—长春断裂走向相一致。结合该地区的历史地震活动与构造关系,最后推测这些地震与北西向的通榆—长春断裂构造运动密切相关,而不是油田作业的直接产物。     

三峡工程水库重点监视区不同蓄水阶段地震波Q值分析

利用2001～2015年三峡数字遥测地震台网记录到的数字地震观测资料,结合三峡工程水库蓄水情况,采用Atkinson方法分析该地区的地震波衰减特征,得到不同蓄水阶段、不同库段的非弹性衰减结果。结果显示,Q值与频率变化的线性关系较好,各频点在拟合线附近波动;3个库段在不同蓄水阶段均具有较小的Q0值和中等的η值,表明三峡工程水库重点监视区构造复杂,且介质的均匀程度较低;仙女山-九畹溪断裂附近地区Q值较大,表明该地区构造运动比较稳定;巴东高桥断裂附近地区Q值较小,表明该地区构造运动比较强烈;泄滩地区随着水位的升高,Q0值增大,表明该地区介质均匀程度有所提高。     

晋城矿区厚层脆韧性石灰岩顶板变形与控制特性研究

晋城矿区15#煤直接顶K2石灰岩厚8～12 m,结构致密坚硬,为坚硬难垮落顶板。针对厚层石灰岩顶板可能面临的大面积断裂和垮落,从而导致冲击地压等问题,通过岩石力学性质试验获得相关岩层力学参数,并运用关键层理论、数值模拟和相似材料模型试验,研究了厚层脆韧性石灰岩顶板的变形与垮落特性,得到了顶板初次来压步距20～25 m和周期来压步距10～15 m及垮落规律,并提出了顶板控制的技术途径,即初期中深孔爆破结合顶板关键层缓慢下沉综合控制技术。实践表明,厚层石灰岩顶板的垮落形态和垮落步距与理论和试验研究结果基本一致。该项成果为晋城矿区厚层脆韧性石灰岩顶板控制提供了有效途径。     

松辽盆地三肇地区扶杨油层油气成藏过程主控因素及成藏模式

从多元地质条件及其时空匹配关系的角度出发,对三肇地区扶杨油层油气成藏过程中的主控因素进行分析。结果表明:上覆青山口组一段源岩有效排烃范围、超压和T₂反射层油源断裂组合关系控制了油气垂向向下“倒灌”的运移范围、距离及层位;古构造背景、T₂断层与储层砂体配置关系控制着油气侧向运移的方向、通道和距离;基准面旋回、沉积微相类型与现今构造配置关系控制着油气的垂向聚集层位及平面分布规律。在此基础上,结合构造发育史、油源条件及沉积微相研究成果,对研究区扶杨油层油气成藏模式进行了总结,认为研究区扶杨油层主要存在4种成藏模式:源内--顶生下储式油气成藏模式、近源--短距离侧向运移--斜坡带断层遮挡油气成藏模式、源外--长距离侧向运移--继承性构造隆起带油气成藏模式、多源--多方式侧向运移油气成藏模式。     

Numerical correlation of speleothem stable isotope records using a genetic algorithm

The correlation of geological records is commonly based on subjective and arbitrary interpretation by a researcher. Geological data are usually collected as a series on a depth scale, and then chronologies of the profiles are constructed. The correlation of geological records based on matching quality indicators requires an efficient method of searching for the best position. GenCorr is a software based on a genetic algorithm, for correlation of records with or without accompanying chronological control. Where their age information is available, points on both records may be moved in the range limited by the age uncertainties. GenCorr has been developed by the authors in Borland RAD Studio 2007 environment. The authors tested the impact of matched record length, noise level, sampling resolution, or additional linear components and hiatuses on the correlation results using artificial test data. Finally, the genetic algorithm was applied to stable isotope records obtained from two stalagmites collected from the Demianova Cave System (Low Tatras, Slovakia). The results show that the genetic algorithm correlation method is similar to that used in pattern recognition by the human eye without prior knowledge of the ages. The genetic algorithm is able to correlate in multidimensional space and is free from human biases, but we accept that there are also occasions where additional expert opinion may be also important. GenCorr can be run on every PC with MS Windows operating system, the package was not tested in Mac environment. GenCorr is available as a freeware from the authors. For downloading, please contact: dzeq@twarda.pan.pl.     

Mining knowledge from result comparison between spatial clustering themes

This paper introduces some definitions and defines a set of calculating indexes to facilitate the research, and then presents an algorithm to complete the spatial clustering result comparison between different clustering themes. The research shows that some valuable spatial correlation patterns can be further found from the clustering result comparison with multi-themes, based on traditional spatial clustering as the first step. Those patterns can tell us what relations those themes have, and thus will help us have a deeper understanding of the studied spatial entities. An example is also given to demonstrate the principle and process of the method.