SRM模型在玛纳斯河流域春季洪水预警中的应用研究

在玛纳斯河流域应用SRM模型进行日径流量的预报,进一步完成对该流域春季融雪性洪水的监测和预警,为防洪、抗旱、提高水资源利用提供技术支撑。引入中国气象局T213数值产品来进行流域分带温度和降水的预报,为融雪径流预报开辟了新的数据方法。通过利用自主开发的融雪径流模拟预报软件1.0版对玛纳斯河流域肯斯瓦特水文站2004年春季融雪期进行径流量预报,从SRM模型的两个精度评价指标看来,预报结果比较满意。
     

基于Micaps3.1的暴雨洪涝预报预警模块的研发

文中利用C#.NET构建了基于MICAPS3.1系统应用的暴雨洪涝预报预警系统整体框架,重点介绍了该系统开发的基本情况、系统架构和系统中使用的关键技术和算法。并选取汉江丹江口为试验流域,初步完成了流域基础地理（边界、水系）、气象、水文监测站点的收集以及显示;流域QPE、QPF、实况监测等气象要素实时产品信息的提取以及气象要素产品与水文模型接口的设计;最后提供了流域实况降水监测场、流域实况降水雷达估算场、流域预报雨量场、流域水文预报信息数据、图形等产品文件。该模块的研发能为流域防洪决策提供支持,并为河流防汛精细化预报服务试点工作的推广提供经验和模式。     

基于 Micaps3.1的暴雨洪涝预报预警模块的研发

文中利用 C#. NET 构建了基于 MICAPS3.1系统应用的暴雨洪涝预报预警系统整体框架,重点介绍了该系统开发的基本情况、系统架构和系统中使用的关键技术和算法.并选取汉江丹江口为试验流域,初步完成了流域基础地理(边界、水系)、气象、水文监测站点的收集以及显示;流域 QPE、QPF、实况监测等气象要素实时产品信息的提取以及气象要素产品与水文模型接口的设计;最后提供了流域实况降水监测场、流域实况降水雷达估算场、流域预报雨量场、流域水文预报信息数据、图形等产品文件.该模块的研发能为流域防洪决策提供支持,并为河流防汛精细化预报服务试点工作的推广提供经验和模式     

数字孪生椒江防洪“四预”应用研究

针对椒江流域山区河流、平原河网、感潮河段、洪泛区均存在的水系及易受台风影响的洪涝格局,根据数字孪生流域的要求,开发了符合数字孪生标准的水利专业模型服务组件,建设了预报调度一体化系统;对模型计算所需的多源数据开发了多源数据融合平台;根据防洪“四预”业务需求开发了知识平台对调度规则、历史洪水的知识推送功能;建立了椒江流域273个子流域112条河流、2112个计算断面、84900个二维计算网格、17个控制单元的流域预报调度一体化模型,系统经过多场次台风暴雨检验,运行效率较高;对全国沿海地区防洪“四预”应用建设具有借鉴意义。     

GA-BP网络在凿岩防卡阀推进压力预测中的应用

分析了凿岩钻车防卡阀的结构和工作原理,利用某采石场原始卡钎数据,建立了防卡阀BP神经网络模型。基于遗传算法理论对BP神经网络模型进行了结构拓扑优化和训练,建立了GA-BP网络模型。分析结果表明,BP神经网络模型和GA-BP网络模型均可以较好地预测卡钎时防卡阀的推进压力,但GABP网络模型具有更高的预测精度、非线性映射和网络性能。     

基于图注意力网络与双阶注意力机制的径流预报模型

为了提高流域径流量预报的准确率,考虑数据驱动水文模型缺乏模型透明度与物理可解释性的问题,提出了一种使用图注意力网络与基于长短期记忆网络（LSTM）的双阶注意力机制（GAT-DALSTM）模型来进行径流预报。首先,以流域站点的水文资料为基础,引入图神经网络提取流域站点的拓扑结构并生成特征向量;其次,针对水文时间序列数据的特点,建立了基于双阶注意力机制的径流预报模型对流域径流量进行预测,并通过基于注意力系数热点图的模型评估方法验证所提模型的可靠性与透明度。在屯溪流域数据集上,将所提模型与图卷积神经网络（GCN）和长短期记忆网络（LSTM）在各个预测步长下进行比较,实验结果表明,所提模型的纳什效率系数分别平均提高了3.7%和4.9%,验证了GAT-DALSTM径流预报模型的准确性。从水文与应用角度对注意力系数热点图进行分析,验证了模型的可靠性与实用性。所提模型能为提高流域径流量的预测精度与模型透明度提供技术支撑。     

基于图注意力网络与双阶注意力机制的径流预报模型

为了提高流域径流量预报的准确率,考虑数据驱动水文模型缺乏模型透明度与物理可解释性的问题,提出了一种使用图注意力网络与基于长短期记忆网络（LSTM）的双阶注意力机制（GAT-DALSTM）模型来进行径流预报。首先,以流域站点的水文资料为基础,引入图神经网络提取流域站点的拓扑结构并生成特征向量;其次,针对水文时间序列数据的特点,建立了基于双阶注意力机制的径流预报模型对流域径流量进行预测,并通过基于注意力系数热点图的模型评估方法验证所提模型的可靠性与透明度。在屯溪流域数据集上,将所提模型与图卷积神经网络（GCN）和长短期记忆网络（LSTM）在各个预测步长下进行比较,实验结果表明,所提模型的纳什效率系数分别平均提高了3.7%和4.9%,验证了GAT-DALSTM径流预报模型的准确性。从水文与应用角度对注意力系数热点图进行分析,验证了模型的可靠性与实用性。所提模型能为提高流域径流量的预测精度与模型透明度提供技术支撑。     

基于GA-BP神经网络的配电网工程造价预测

为了解决前馈(BP)神经网络在配电网工程建设工程造价预测时,容易陷入局部极小而导致预测精度降低的问题,提出了一种GA-BP神经网络的配电网工程造价预测模型。模型试算与分析结果表明:除了个别样本数据外,GA-BP模型预测数据的相对误差小于BP模型预测数据的相对误差。其中,GA-BP模型的预测数据的相对误差整体最小,BP模型的相对误差整体最大,BP整体的相对误差要稍小于GA-BP。GA-BP和BP的模型平均相对误差数值更小,GA-BP模型的平均相对误差最小,说明该模型的预测稳定性最强。此外,GA-BP和BP的模型稳定性和预测的精度上都要优于GA-BP和BP。其中,GA-BP的预测模型最好,BP预测模型最差。该基于GA-BP神经网络的配电网工程造价预测模型为提高配电网工程造价预测精度提供了一定的理论基础。     

一种基于深度网络的多环境因素降水量预报模型

为了更好地反映区域降水的变化趋势,开展区域降水量预报显得尤为重要。在流域信息时代存在丰富大数据的情况下,提出一种基于DBN(Deep Belief Nets)深度网络降水量预报模型的新方案。该方案通过模拟大脑神经元的多层结构,并使用反向传播网络对整个网络进行微调。模型使用了与每日降水量息息相关的七种环境因素作为输入向量,未来24小时降水作为输出向量,通过在贵州遵义地区的实验证明了模型的有效性,并与现有方法进行了对比实验,结果表明模型具有更好的预测效果。     

基于KPCA粒子群算法的预报模型优化研究

空气质量关系着人们的身体健康,因此研究实时、高效的空气质量预报系统,不仅能为公众出行提供指导,还能指导职能部门防控重污染天气并提供相应技术支持.近几年,国内外对预报理论及方法的研究主要集中在BP神经网络预报[1].Deden Supriyatman[2]应用传统BP神经网络预报输气管道腐蚀速率,N.Haghdadi等人[3]应用改进BP网络预报半固态A356铝合金的热变形行为,对学习步长加入动量项,改善了收敛慢的问题,但预报精度较低.蒋吉丽基于BP神经网络的强对流天气预报模型,将观测实况资料作为专家样本对BP神经网络模型进行训练和测试,对训练好了的模型进行了对比测试,为强对流天气的预报提供了依据.分析学者们的预报方法,均考虑了问题的非线性特征,利用BP网络处理非线性问题的优势,建立预报模型,但忽略了数据的相关性和神经网络参数初始化的随意性带来的影响,因此,在实际应用中预报精度较低,速度较慢.     

基于流水线模式的河系径流预报并发计算研究

在河系径流预报计算中,一方面受单站水文过程计算复杂性影响,另一方面下游站点依赖上游关联节点,现有洪水预报系统在河系预报计算时多采用串联模式进行计算。这在河流系预报节点较多、模型方法略为复杂时,计算效率较低。为突破河系径流预报计算效率瓶颈,本研究引入流水线并行模式,对河系径流预报站点初始化、单元产汇流计算、河道洪水演算、校正分析等模块进行拆解,构建流水线式工作站,将径流预报站点按水力联系连续入站,实现河系节点集径流过程的平行并发计算。选取淮河正阳关以上流域50余断面进行了模拟试验,结果表明：研究构建的并发计算方法计算结果可靠,较串行结构效率提升超3倍,可满足洪水预报实时性要求、尤其适用于B/S模式对系统响应效率的需求。     

Modelling rainfall intensity from NOAA AVHRR data for operational flood forecasting in Malaysia

Many empirical studies in numerical weather prediction have been carried out that establish the relationship between top‐of‐the‐cloud brightness temperature and rainfall particularly in tropical and equatorial regions of the world. Malaysia is a tropical country that lies along the path of the north‐east and south‐west monsoon rainfall, which sometimes causes extensive flood disasters. Observations have generally shown that heavy cumulonimbus cloud formation and thunderstorms precede the usual heavy monsoon rains that cause flood disasters in the region. In this study, a model has been developed to process National Oceanic & Atmospheric Administration Advanced Very High Resolution Radiometer (AVHRR) satellite data for rainfall intensity in an attempt to improve quantitative precipitation forecasting (QPF) as input to operational hydro‐meteorological flood early warning. The thermal bands in the multispectral AVHRR data were processed for brightness temperature. Data were further processed to determine cloud height and classification performed to delineate clouds in three broad classes of low, middle, and high. A rainfall intensity of 3–12 mm h^?1 was assigned to the 1‐D cloud model to determine the maximum rain rate as a function of maximum cloud height and minimum cloud model temperature at a threshold level of 235 K. The result of establishing the rainfall intensity based on top of the cloud brightness temperature was very promising. It also showed a good areal coverage that delineated areas likely to receive intense rainfall on a regional scale. With a spatial resolution of 1.1 km, data are course but provide a good coverage for an average river catchment/basin. This raises the opportunity of simulating rainfall runoff for the river catchment through the coupling of a suitable hydro‐dynamic model and GIS to provide early warning prior to the actual rainfall event.     

Mesoscale grid rainfall estimation from AVHRR and GMS data

Areal rainfall averages derived from rain-gauge observations suffer from limitations not only due to sampling but also because gauges are usually distributed with a spatial bias towards populated areas and against areas with high elevation and slope. For a large river basin, however, heavy rainfall in the mountain upstream can result in severe flooding downstream. In this study, cloud-indexing and cloud model-based techniques were applied to Advanced Very High Resolution Radiometer (AVHRR) and Geostationary Meteorological Satellite (GMS) imager data based on the cloud-top brightness temperature (T _B) and processed for estimating mesoscale grid rainfall. This study aims to improve and refine rainfall estimation in Malaysian monsoons based on cloud model techniques for operational pre-flood forecasting using readily available near-real-time satellite data such as the National Oceanic and Atmospheric Administration (NOAA)-AVHRR and GMS imager. Rain rates between 3 and 12 mm h^?1 were assigned to cloud pixels of hourly coverage AVHRR or GMS data over the Langat Basin area for the duration of the monsoon rainfall event of 27 September to 8 October 2000 in Malaysia. The observed rainfall and quantitative precipitation forecast (QPF) showed an R ² value of 0.9028, while the observed rainfall run-off (RR; recorded) and its simulated data had an R ² value of 0.9263 and the QPF run-off and its simulated data had an R ² value of 0.815. The rainfall estimate was used to simulate the flood event of the catchment. The estimated rainfall over the catchment showed similar flood area coverage to the observed flood event.     

Assessment and weighting of meteorological ensemble forecast members based on supervised machine learning with application to runoff simulations and flood warning

Numerical weather forecasts, such as meteorological forecasts of precipitation, are inherently uncertain. These uncertainties depend on model physics as well as initial and boundary conditions. Since precipitation forecasts form the input into hydrological models, the uncertainties of the precipitation forecasts result in uncertainties of flood forecasts. In order to consider these uncertainties, ensemble prediction systems are applied. These systems consist of several members simulated by different models or using a single model under varying initial and boundary conditions. However, a too wide uncertainty range obtained as a result of taking into account members with poor prediction skills may lead to underestimation or exaggeration of the risk of hazardous events. Therefore, the uncertainty range of model-based flood forecasts derived from the meteorological ensembles has to be restricted.In this paper, a methodology towards improving flood forecasts by weighting ensemble members according to their skills is presented. The skill of each ensemble member is evaluated by comparing the results of forecasts corresponding to this member with observed values in the past. Since numerous forecasts are required in order to reliably evaluate the skill, the evaluation procedure is time-consuming and tedious. Moreover, the evaluation is highly subjective, because an expert who performs it makes his decision based on his implicit knowledge.Therefore, approaches for the automated evaluation of such forecasts are required. Here, we present a semi-automated approach for the assessment of precipitation forecast ensemble members. The approach is based on supervised machine learning and was tested on ensemble precipitation forecasts for the area of the Mulde river basin in Germany. Based on the evaluation results of the specific ensemble members, weights corresponding to their forecast skill were calculated. These weights were then successfully used to reduce the uncertainties within rainfall-runoff simulations and flood risk predictions.     

秦淮河流域东山站洪水位预报模型研究

为了提高秦淮河流域洪水预报的水平,对东山站洪水位过程预报模型进行深入研究。采用线性动态系统模型与BP人工神经网络模型建立东山站洪水位逐时段预报模型,采用2010—2015年及2016—2017年汛期秦淮河流域实测雨量和东山站水位资料对模型进行率定和验证。结果表明:东山站洪水位逐时段预报的BP人工神经网络模型相对于线性动态系统模型具有较高的精度;相对于一维河网水动力模型,简单实用。     

数字孪生永宁江洪水预报模型构建及系统应用

以永宁江流域作为试点,构建数字孪生流域,建设具有“四预”功能的“2+N”业务应用体系,综合保障区域防洪安全。考虑到流域内地势起伏大、用地类型复杂、横跨多个行政区块等客观原因,为提高预报精度,基于Mike系列模型,建立永宁江洪水预报模型。采用2013年“菲特”、2015年“苏迪罗”和2019年“利奇马”等台风洪水作为计算场次,根据2013—2019年水文资料选取5场洪水进行率定,结果表明各站模拟与实测过程趋势线基本一致,其中峰值水位误差：下路站为1.31%,西江闸下站为2.23%,永宁江闸上站为-0.98%,南洋站为0.04%。4站的洪峰水位平均误差为0.58%,洪峰滞时平均误差为0.8 h,主要预报站点的确定性系数在0.7以上,计算时间在30 s以内。将预报模型、工程调度信息与数字孪生流域系统相耦合,总体展示永宁江流域的工情和防汛情况,实现永宁江流域防汛的智慧决策,为调度指挥提供有力的数值分析保障。     

Prediction of extreme precipitation using a neural network: application to summer flood occurrence in Moravia

Dramatic floods occurred in Central Europe in summer 1997, and Czech Republic has been seriously affected in its eastern part—Moravia. A predictive approach based on modelling flood recurrence may be helpful in flood management. Summer floods are typically characterized by saturated catchment due to long-lasting heavy precipitation followed by a sudden extreme rainfall. In present work an artificial neural network (ANN) model was evaluated for precipitation forecasting. Back propagation neural networks were trained with actual monthly precipitation data from two Moravian meteorological stations for a time period of 38 years. Predicted amounts are of next-month-precipitation and summer precipitation in the next year. The ANN models provided a good fit with the actual data, and have shown a high feasibility in prediction of extreme precipitation.     

A Web-based flood forecasting system for Shuangpai region

Traditional flood forecasting and operation of reservoirs in China are based on manual calculations by hydrologists or through standalone computer programs. The main drawbacks of these methods are long forecasting time due to time-consuming nature, individual knowledge, lack of communication, absence of experts, etc. A Web-based flood forecasting system (WFFS), which includes five main modules: real-time rainfall data conversion, model-driven hydrologic forecasting, model calibration, precipitation forecasting, and flood analysis, is presented in this paper. The WFFS brings significant convenience to personnel engaged in flood forecasting and control and allows real-time contribution of a wide range of experts at other spatial locations in times of emergency. The conceptual framework and detailed components of the proposed WFFS, which employs a multi-tiered architecture, are illustrated. Multi-tiered architecture offers great flexibility, portability, reusability and reliability. The prototype WFFS has been developed in Java programming language and applied in Shuangpai region with a satisfactory result.