Identification of physical processes inherent in artificial neural network rainfall runoff models

The emergence of artificial neural network (ANN) technology has provided many promising results in the field of hydrology and water resources simulation. However, one of the major criticisms of ANN hydrologic models is that they do not consider/explain the underlying physical processes in a watershed, resulting in them being labelled as black‐box models. This paper discusses a research study conducted in order to examine whether or not the physical processes in a watershed are inherent in a trained ANN rainfall‐runoff model. The investigation is based on analysing definite statistical measures of strength of relationship between the disintegrated hidden neuron responses of an ANN model and its input variables, as well as various deterministic components of a conceptual rainfall‐runoff model. The approach is illustrated by presenting a case study for the Kentucky River watershed. The results suggest that the distributed structure of the ANN is able to capture certain physical behaviour of the rainfall‐runoff process. The results demonstrate that the hidden neurons in the ANN rainfall‐runoff model approximate various components of the hydrologic system, such as infiltration, base flow, and delayed and quick surface flow, etc., and represent the rising limb and different portions of the falling limb of a flow hydrograph. Copyright © 2004 John Wiley & Sons, Ltd.     

Contribution of storms to groundwater recharge in the semi‐arid region of Karnataka,India

This paper describes the application of environmental isotopes and injected tracer techniques in estimating the contribution of storms as well as annual precipitation to groundwater recharge and its circulation, in the semi‐arid region of Bagepalli, Kolar district, Karnataka. Environmental isotopes ²H, ¹⁸O and ³H were used to study the effect of storms on the hydrological system, and an isotope balance was used to compute the contribution of a storm component to the groundwater. Some of the groundwater samples collected during the post‐storm periods were highly depleted in stable isotope content with higher deuterium excess relative to groundwater from the pre‐storm periods. Significant variation in deuterium excess in groundwater from the same area, collected in two different periods, indicates the different origin of air masses. The estimated recharge component of a storm event of 600 mm to the groundwater was found to be in the range of 117–165 mm. There was no significant variation in environmental tritium content of post‐storm and pre‐storm groundwater, indicating the fast circulation of groundwater in the system. After completion of the environmental isotope work, an injected radiotracer ³H technique was applied to estimate the direct recharge of total precipitation to the groundwater. The estimated recharge to the groundwater is 33 mm of the 550 mm annual precipitation during 1992. Copyright © 2003 John Wiley & Sons, Ltd.     

基于EMD与神经网络的机械故障诊断技术

经验模式分解 (EMD)是分析非线性、非平稳信号的有力工具 ,它将信号分解为突出了原信号的不同时间尺度的局部特征信息的内在模函数 (IMF)分量。本文通过将各 IMF分量输入到 BP网络中进行训练学习和故障诊断 ,比直接输入原信号可以提高 BP网络对故障诊断的准确率 ,而且减少了训练时间。     

人工神经网络在岩体质量分级中的应用

结合四川省金沙江某水电站工程实例，应用BP人工神经网络方法建立3层BP网络模型，选取岩石单轴抗压强度等6个影响因素为输入变量，对坝基复杂岩体进行质量分级。通过机算机Visual C 语言编程实现神经网络模型，进行网络的学习和运算。以神经网络合理结构分析方法选取合理结构，确定合理隐层单元的数量，提高网络测试的精度。对测试结果的分析发现，经过优化的BP网络模型经多次学习后，测试精度提高，结果可靠，取得较好的实际应用效果。     

机载粉剂催化剂播撒设备的研制及其在奥运和残奥消云中的应用

人为引发的下沉气流可以抑制对流云的发展,这一现象已在试验中得到验证。用“人工下沉气流法”实施人工消云试验时,需在云顶大剂量的播撒粉剂催化剂。北京市人工影响天气办公室研制了能完成此类大剂量播撤任务的设备,并通过外场飞行试验对设备进行检验和改进。这是国内人工影响天气领域首个采用空投播撒法的粉剂催化剂播撤设备;可减少催化剂对飞机和播撤设备的污染。分析发现,新设备能够满足人工消云作业中播撒大剂量粉剂催化剂的需要。该设备在北京奥运会、残奥会开闭幕式当日的消云试验作业中投入使用,共实施消云飞行作业9架次,累计利用新设备播撒吸湿性粉剂催化剂34吨。     

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.     

关于山东省地热尾水回灌试验的应用研究

为解决地热水开采利用过程中造成诸如水位下降、热流体排放引起的热污染和化学污染等问题,通过开展地热尾水回灌试验研究,认为在开采深层的地下热水资源的同时,必须进行人工的回灌补源,山东省通过在德州、东营、济南等地开展地热尾水回灌试验工作,效果显著。     

向心扩张指数构建及其在郑州都市圈城镇空间扩张中的应用

探究城镇空间扩张的方向性及其时间变化特征,能够反映都市圈发展过程中核心城市与边缘地区空间关联的动态过程,为制定都市圈发展的相关政策提供科学依据。本文从都市圈的核心城市与边缘地区相互关联的视角,借鉴物理学中力的分解原理,构建了同时兼顾扩张强度和方向性的向心扩张指数CEI,并以郑州都市圈为对象,采用2000—2018年30 m分辨率的全球人造不透水面数据产品GAIA,分析了建设用地扩张的总体数量和占比变化、动态度及强度变化、以及空间方向性变化等特征,进一步应用多元逻辑回归模型,揭示了影响城镇空间扩张向心性的关键因素。结果表明：(1)向心扩张指数CEI为揭示都市圈核心城市对边缘地区的辐射带动作用提供方法支撑,能够定量刻画边缘地区朝向核心城市的发展趋势;(2)在郑州都市圈近20年的快速扩张过程中,尽管各区县市的DEI指数和CEI指数随时间而增减波动,但郑州都市圈总体呈现“核心—边缘”发展模式,除个别地级市中心城区及其下辖县以外,多数区县市的向心性显著且随时间增强,郑州市中心城区对于边缘地区具有显著的辐射带动作用;(3)核心城市与边缘地区的人均GDP差异及城镇化率差异是影响边缘地区向心扩张的重要...     

沙坡头人工植被固沙区天然降水的入渗和分配研究

土壤、植被冠层与大气界面间(SVAT)物质传输过程日益成为水文学研究最感兴趣的领域,降水量的迁移与转换是非灌溉区SVAT主要的物质传输过程.干旱半干旱区稀疏灌丛蒸散量占降水量的90%以上,因此对降水入渗与水分在土壤内植物根际区再分配的研究显得十分重要.试验于2001年8月17日至9月30日在中国科学院沙坡头试验站进行,主要观测人工植被荒漠灌木柠条(Caragana korshinskii) 灌丛固定沙丘降水入渗与再分配过程.结果表明:在7次不连续降水过程中,土壤入渗深度与降水强度呈简单线性相关关系,土壤入渗速率约为降水强度的10倍.当次降水过程中降水强度小于0.46 mmh-1时,土壤入渗速率约为0 cm*h-1,此时的降水对沙区土壤基本上没有水分补给作用.受荒漠灌木柠条根系吸水作用的影响,其根系密集剖面深度40～140 cm内降水水分入渗积累不明显.降水入渗速率及入渗深度受土壤剖面初始含水率多寡而变化,干燥土壤剖面有助于提高瞬时入渗速率.降水以后随着时间的推移,人工固沙区微环境内空气温度、湿度等气象条件适宜,柠条生长进入相对旺盛阶段,其根系密集层140 cm深度处土壤含水率在总体上下降的过程中,表现出昼消夜长的趋势,试验期间翌日 8:00时土壤含水率值略高于前一日20:00时水分值 0.1%～0.3%.     

毛蚶人工育苗技术

根据对毛蚶性腺发育、产卵孵化、浮游幼虫及稚贝习性等的研究，初步探索了其人工育苗中主要技术环节。2龄毛蚶全为雄性或雌雄同体，3龄以上群体雌性占70％以上。26．6～27．4℃，受精卵22h发育到D形幼虫；26．5～23．0℃，D形幼虫经过15天发育到眼点幼虫；25．O～20．0℃，投附着基、13天左右稚贝壳长达到600μm时，可以出池到室外进行中间育成。