A Physical Examination Method for Artificial Rainfall Effect Based on Radar Data

[Objective] This study aimed to establish a physical examination method for artificial rainfall effect based on radar data. [Method] The radar base data of Shenyang was processed with interpolation by using the nearest neighbor in radial and oriental direction to establish corresponding response variables, and the effect of a precipitation enhancement case was analyzed. [Result] The trends of response variables showed that there was certain positive effect of the precipitation enhancement operation. [Conclusion] The analysis on a case was not sufficient enough, and statistical test should be the future direction of the study on the physical effect.

Application of Artificial Neural Networks to Rainfall Forecasting in Queensland,Australia

In this study, the application of artificial intelligence to monthly and seasonal rainfall forecasting in Queensland, Australia, was assessed by inputting recognized climate indices, monthly historical rainfall data, and atmospheric temperatures into a prototype stand-alone, dynamic, recurrent, time-delay, artificial neural network. Outputs, as monthly rainfall forecasts 3 months in advance for the period 1993 to 2009, were compared with observed rainfall data using time-series plots, root mean squared error （RMSE）, and Pearson correlation coefficients. A comparison of RMSE values with forecasts generated by the Australian Bureau of Meteorology＇s Predictive Ocean Atmosphere Model for Australia （POAMA）-I.5 general circulation model （GCM） indicated that the prototype achieved a lower RMSE for 16 of the 17 sites compared. The application of artificial neural networks to rainfall forecasting was reviewed. The prototype design is considered preliminary, with potential for significant improvement such as inclusion of output from GCMs and experimentation with other input attributes.

Characteristics of flow production and sediment production of <i>Pinus tabulaeformis</i>through artificial rainfall simulation

In order to know well the relationship between vegetation and water in North China, especially Beijing, with exceptional water resources, we studied the characteristics of flow production and sediment production under different rainfall intensities by artificial rainfall simulation device. Results showed that increase of rainfall intensity would prolong the whole process of flow production, and vegetation on the slope would delay that process. Within the same duration, total runoff volume of each runoff plot and rainfall intensity had significant linear relationship. When vegetation kept unchanged, runoff velocity increased significantly with the increase of rainfall intensity, and owing to the formation of low permeable layer, the velocity increased fiercely during the early 3 minutes, reached stable at 10 - 15 minute. With the same rain intensity, total sediment yield decreased with rise of vegetation coverage, but increased obviously with rise of rain intensity and effectiveness of controlling sediment about 1 m x 1 m Pinus tabulaeformis stand decreased firstly and then increased, while that about 1.5 m x 1.5 m Pinus tabulaeformis stand kept decreasing. Since the tags with A, B and C for 0.42 mm/min, 0.83 mm/min, 1.29 mm/min, order of sediment concentration of wasteland plot was B > C > A, and 1 m x 1 m Pinus tabulaeformis plot B > A > C. Through this study, some suggestions were expected to be provided for water balance of Beijing area and certain basis for construction of shelter forest.

Artificial Neural Networks for Event Based Rainfall-Runoff Modeling

The Artificial Neural Network (ANN) approach has been successfully used in many hydrological studies especially the rainfall-runoff modeling using continuous data. The present study examines its applicability to model the event-based rainfall-runoff process. A case study has been done for Ajay river basin to develop event-based rainfall-runoff model for the basin to simulate the hourly runoff at Sarath gauging site. The results demonstrate that ANN models are able to provide a good representation of an event-based rainfall-runoff process. The two important parameters, when predicting a flood hydrograph, are the magnitude of the peak discharge and the time to peak discharge. The developed ANN models have been able to predict this information with great accuracy. This shows that ANNs can be very efficient in modeling an event-based rainfall-runoff process for determining the peak discharge and time to the peak discharge very accurately. This is important in water resources design and management applications, where peak discharge and time to peak discharge are important input

Assessment of Seasonal Rainfall Prediction in Ethiopia: Evaluating a Dynamic Recurrent Neural Network to Downscale ECMWF-SEAS5 Rainfall

Seasonal rainfall plays a vital role in both environmental dynamics and decision-making for rainfed agriculture in Ethiopia, a country often impacted by extreme climate events such as drought and flooding. Predicting the onset of the rainy season and providing localized rainfall forecasts for Ethiopia is challenging due to the changing spatiotemporal patterns and the country's rugged topography. The Climate Hazards Group Infra Red Precipitation with Station Data(CHIRPS), ERA5-Land total precipitation and temperature data are used from 1981–2022 to predict spatial rainfall by applying an artificial neural network(ANN). The recurrent neural network(RNN) is a nonlinear autoregressive network with exogenous input(NARX), which includes feed-forward connections and multiple network layers, employing the Levenberg Marquart algorithm. This method is applied to downscale data from the European Centre for Medium-range Weather Forecasts fifth-generation seasonal forecast system(ECMWF-SEAS5) and the Euro-Mediterranean Centre for Climate Change(CMCC) to the specific locations of rainfall stations in Ethiopia for the period 1980–2020. Across the stations, the results of NARX exhibit strong associations and reduced errors. The statistical results indicate that, except for the southwestern Ethiopian highlands, the downscaled monthly precipitation data exhibits high skill scores compared to the station records, demonstrating the effectiveness of the NARX approach for predicting local seasonal rainfall in Ethiopia's complex terrain. In addition to this spatial ANN of the summer season precipitation, temperature, as well as the combination of these two variables, show promising results.

Flow-slide characteristics and failure mechanism of shallow landslides in granite residual soil under heavy rainfall

Affected by typhoons over years, Fujian Province in Southeast China has developed a large number of shallow landslides, causing a long-term concern for the local government. The study on shallow landslide is not only helpful to the local government in disaster prevention, but also the theoretical basis of regional early warning technology. To determine the whole-process characteristics and failure mechanisms of flow-slide failure of granite residual soil slopes, we conducted a detailed hazard investigation in Minqing County, Fujian Province, which was impacted by Typhoon Lupit-induced heavy rainfall in August 2021. Based on the investigation and preliminary analysis results, we conducted indoor artificial rainfall physical model tests and obtained the whole-process characteristics of flow-slide failure of granite residual soil landslides. Under the action of heavy rainfall, a granite residual soil slope experiences initial deformation at the slope toe and exhibits development characteristics of continuous traction deformation toward the middle and upper parts of the slope. The critical volumetric water content during slope failure is approximately 53%. Granite residual soil is in a state of high volumetric water content under heavy rainfall conditions, and the shear strength decreases, resulting in a decrease in stability and finally failure occurrence. The new free face generated after failure constitutes an adverse condition for continued traction deformation and failure. As the soil permeability(cm/h) is less than the rainfall intensity(mm/h), and it is difficult for rainwater to continuously infiltrate in short-term rainfall, the influence depth of heavy rainfall is limited. The load of loose deposits at the slope foot also limits the development of deep deformation and failure. With the continuous effect of heavy rainfall, the surface runoff increases gradually, and the influence mode changes from instability failure caused by rainfall infiltration to erosion and scouring of surface runoff on slope surface. Transportation of loose materials by surface runoff is an important reason for prominent siltation in disaster-prone areas.

A multiobjective evolutionary optimization method based critical rainfall thresholds for debris flows initiation

At present,most researches on the critical rainfall threshold of debris flow initiation use a linear model obtained through regression.With relatively weak fault tolerance,this method not only ignores nonlinear effects but also is susceptible to singular noise samples,which makes it difficult to characterize the true quantization relationship of the rainfall threshold.Besides,the early warning threshold determined by statistical parameters is susceptible to negative samples(samples where no debris flow has occurred),which leads to uncertainty in the reliability of the early warning results by the regression curve.To overcome the above limitations,this study develops a data-driven multiobjective evolutionary optimization method that combines an artificial neural network(ANN)and a multiobjective evolutionary optimization implemented by particle swarm optimization(PSO).Firstly,the Pareto optimality method is used to represent the nonlinear and conflicting critical thresholds for the rainfall intensity I and the rainfall duration D.An ANN is used to construct a dual-target(dual-task)predictive surrogate model,and then a PSO-based multiobjective evolutionary optimization algorithm is applied to train the ANN and stochastically search the trained ANN for obtaining the Pareto front of the I-D surrogate prediction model,which is intended to overcome the limitations of the existing linear regression-based threshold methods.Finally,a double early warning curve model that can effectively control the false alarm rate and negative alarm rate of hazard warnings are proposed based on the decision space and target space maps.This study provides theoretical guidance for the early warning and forecasting of debris flows and has strong applicability.

Analysis of Mean Monthly Rainfall Runoff Data of Indian Catchments Using Dimensionless Variables by Neural Network

This paper focuses on a concept of using dimensionless variables as input and output to Artificial Neural Network (ANN) and discusses the improvement in the results in terms of various performance criteria as well as simplification of ANN structure for modeling rainfall-runoff process in certain Indian catchments. In the present work, runoff is taken as the response (output) variable while rainfall, slope, area of catchment and forest cover are taken as input parameters. The data used in this study are taken from six drainage basins in the Indian provinces of Madhya Pradesh, Bihar, Rajasthan, West Bengal and Tamil Nadu, located in the different hydro-climatic zones. A standard statistical performance evaluation measures such as root mean square (RMSE), Nash–Sutcliffe efficiency and Correlation coefficient were employed to evaluate the performances of various models developed. The results obtained in this study indicate that ANN model using dimensionless variables were able to provide a better representation of rainfall–runoff process in comparison with the ANN models using process variables investigated in this study.

Indian summer monsoon rainfall (ISMR) forecasting using time series data: A fuzzy-entropy-neuro based expert system

This study presents a model to forecast the Indian summer monsoon rainfall（ISMR）（June-September）based on monthly and seasonal time scales. The ISMR time series data sets are classified into two parts for modeling purposes, viz.,（1） training data set（1871-1960）, and（2） testing data set（1961-2014）.Statistical analyzes reflect the dynamic nature of the ISMR, which couldn＇t be predicted efficiently by statistical and mathematical based models. Therefore, this study suggests the usage of three techniques,viz., fuzzy set, entropy and artificial neural network（ANN）. Based on these techniques, a novel ISMR time series forecasting model is designed to deal with the dynamic nature of the ISMR. This model is verified and validated with training and testing data sets. Various statistical analyzes and comparison studies demonstrate the effectiveness of the proposed model.

Performance Comparison of Artificial Neural Network Models for Daily Rainfall Prediction

With an aim to predict rainfall one-day in advance, this paper adopted different neural network models such as feed forward back propagation neural network （BPN）, cascade-forward back propagation neural network （CBPN）, distributed time delay neural network （DTDNN） and nonlinear autoregressive exogenous network （NARX）, and compared their forecasting capabilities. The study deals with two data sets, one containing daily rainfall, temperature and humidity data of Nilgiris and the other containing only daily rainfall data from 14 rain gauge stations located in and around Coonoor （a taluk of Nilgiris）. Based on the performance analysis, NARX network outperformed all the other networks. Though there is no major difference in the performances of BPN, CBPN and DTDNN, yet BPN performed considerably well confirming its prediction capabilities. Levenberg Marquardt proved to be the most effective weight updating technique when compared to different gradient descent approaches. Sensitivity analysis was instrumental in identifying the key predictors.

Vulnerability Assessment Method for Immovable Cultural Relics Based on Artificial Neural Networks—An Example of a Heavy Rainfall Event in Henan Province

Cultural relic conservation capability is an important issue in cultural relic conservation research,and it is critical to decrease the vulnerability of immovable cultural relics to rainfall hazards.Commonly used vulnerability assessment methods are subjective,are mostly applied to regional conditions,and cannot accurately assess the vulnerability of cultural relics.In addition,it is impossible to predict the future vulnerability of cultural relics.Therefore,this study proposed a machine learning-based vulnerability assessment method that not only can assess cultural relics individually but also predict the vulnerability of cultural relics under different rainfall hazard intensities.An extreme rainfall event in Henan Province in 2021 was selected as an example,with a survey report on the damage to cultural relics as a database.The results imply that the back propagation(BP)neural network-based method of assessing the vulnerability of immovable cultural relics is reliable,with an accuracy rate higher than 92%.Based on this model to predict the vulnerability of Zhengzhou City’s cultural relics,the vulnerability levels of cultural relics under different recurrence periods of heavy rainfall were obtained.Among them,the vulnerability of ancient sites is higher than those of other cultural relic types.The assessment model used in this study is suitable for predicting the vulnerability of immovable cultural relics to heavy rainfall hazards and can provide a technical means for cultural relic conservation studies.

Variations in the disintegration rate of physical crusts induced by artificial rainfall in different alcohol concentrations

Disintegration is closely correlated with geological disasters and soil erosion.However,quantitative studies on the disintegration processes of physical crust controlling the soil surface erosion are limited.Therefore,we disintegration process in structural and sedimentary crusts induced by artificial rainfall on a typical cropland soil from the Loess Plateau,China.The physical crusts were immersed for 200 s at different alcohol concentrations applied for delaying disintegration process to obtain disintegration rate(DR).The content of organic matter and the sand percentage in the structural and sedimentary crusts decreased with increasing rainfall duration,while the bulk density,silt and clay percentages increased.The initial DR values ranged from0.01 to 1.82 in structural crusts and from0.01 to 1.47 in sedimentary crusts under different alcohol concentrations.DR decreased by[86.5%,91.3%]in structural crusts and by[86.3%,88.2%]in sedimentary crusts during the whole disintegration period.For both structural and sedimentary crust,the DR was the lowest when the rainfall lasted for 30 min,and finally stabilized at 0.19 and 0.18,respectively,at the disintegration time of 80 s.Notably,the 50%alcohol concentration slowed the disintegration process most efficiently.The structural crust had a lower erosion resistance than the sedimentary crust due to the lower DR.These results provide a theoretical method for evaluating disintegration process and timely information revealing the erosion resistance mechanism of physical crusts.

Using meshes to change the characteristics of simulated rainfall produced by spray nozzles

Rainfall simulators have been used for many years contributing to the understanding of soil and water conservation processes.Nevertheless,rainfall simulators’design and operation might be rather demanding for achieving specific rainfall intensity distributions and drop characteristics and are still open for improvement.This study explores the potential of combining spray nozzle simulators with meshes to change rainfall characteristics,namely drop properties(drop diameters and fall speeds).A rainfall simulator laboratory set-up was prepared that enabled the incorporation of different wire meshes beneath the spray nozzles.The tests conducted in this exploratory work included different types of spray nozzles,mesh materials(plastic and steel),square apertures and wire thicknesses,and positions of the meshes in relation to the nozzles.Rainfall intensity and drop size distribution and fall speed were analysed.Results showed that the meshes combined with nozzles increased the mean rainfall intensity on the 1 m^(2) control plot below the nozzle and altered the rain drops’properties,by increasing the mass-weighted mean drop diameter,for example.

安徽省燃气炮人工增雨作业效果综合评估

选取2021—2023年安徽省81次燃气炮作业的双偏振天气雷达、雨量计等多源观测数据,综合评估燃气炮作业增雨效果并分析可能机理。结果显示:在降水开始前作业个例增雨效果较好,并伴有水平反射率因子Z_(H)、差分反射率Z_(DR)的增加和共极化相关系数ρ_(hv)的减少;降水开始后作业增雨效果欠佳。使用携带暖云催化剂的燃气炮作业后云体变化主要在零度层以下,且维持时间较短;使用携带冷云催化剂的燃气炮作业后暖云区和冷云区均有明显变化,且作业影响持续时间更长。燃气炮作业过程中雷达速度谱宽增大,可能是作业引起气流涡旋的增加所导致。统计结果显示:增雨的显著性与作业时长呈负相关,作业时长与Z_(DR)增量呈负相关,过量播撒会导致减雨;增雨的显著性与作业前影响区雨量呈负相关;增雨量与Z_(H)、中低层风速、风切变呈正相关,与高层风速呈负相关。

机器学习在人工增雨效果统计检验中的应用

利用福建省古田人工增雨试验基地2014年1月—2023年1月小时自然降水数据,结合线性拟合、多项式回归和样条回归等多种数学统计方法,开展决策树、支持向量机(SVM)和卷积神经网络(CNN)3种机器学习方法在估测目标区自然降水中的应用研究。目标区和对比区自然雨量关系模型对比结果表明:以区域平均面雨量为统计变量时,CNN和四项式回归效果相对较好,其中CNN的确定系数为0.516,均方根误差为1.097 mm;对平均面雨量进行六次方根变换后,各模型的精准度大幅提升,CNN表现最优,确定系数为0.658,其次为SVM;为克服目标区和对比区雨量时间序列效应及空间分布不均等问题,以面雨量空间格点数据作为研究对象,采用CNN 3种优化器(自适应矩估计、均方根传递和梯度随机下降)算法进行对比,发现基于自适应矩估计优化器建立目标区和对比区雨量关系模型最优,其降水估测值与实测值更接近,均方根误差最小,为0.61 mm。因此,利用CNN方法能够进一步优化目标区和对比区雨量关系模型,可为定量评估人工增雨效果提供参考。

2020年雾灵山人工低频强声波增雨和消雾试验

为了研究人工低频强声波增雨和消雾作业手段的效果,使用最大声压级为155 dB的电声低频强声波装置原型机,于2020年8—9月在河北省雾灵山开展增雨和消雾外场作业观测试验。具有明显消雾效果的两个典型个例显示:作业开始后2~3 min内尺度小于10μm的雾滴减少,尺度大于10μm的雾滴增多;随后大部分尺度的雾滴明显减少,10 min内能见度可从小于100 m回升至最高1000 m。在风速、风向与消雾效果的关系方面,消雾效果明显的个例均发生在平均风速小于1.5 m·s^(-1)且风向可使雾能够途经声波装置影响范围近侧的条件下,而平均风速大于2m·s^(-1)的个例能见度几乎未出现趋势性变化。在一次地面平均风速为1.4 m·s^(-1)的对流云增雨作业中观测到符合试验预期的结果,开始作业后的3 min内地面雨强从0.3 mm·h^(-1)迅速增至7 mm·h^(-1)以上,并观测到出现迅速但维持时间较短的大雨滴。其他增雨个例在作业时段的平均风速均超过3 m·s^(-1),可能受风速偏大和观测点单一的影响,未能观测到明确且一致的增雨证据。

基于机器学习降雨动态时空特征识别山丘区小流域洪水预报方法研究

山丘区洪水产汇流速度快,破坏力强,预报难度大。如何进一步提高山丘区洪水预报的准确性和预见期,是当前亟待解决的主要问题。针对该问题,本文基于机器学习技术,创新性地提出了一种洪水预报的新方法。该方法通过识别与当前降雨动态时空特征最相似的历史降雨洪水过程,“借古喻今”进行洪水预报。结果表明,在人为影响小、流域面积在600 km^(2)左右的山丘区小流域,该方法预报洪峰流量平均误差为8.33%,洪量平均误差为14.27%,峰现时间平均误差1 h,均达到了洪水预报精度要求。区别于传统的洪水预报方法,该方法从整场降雨发展趋势的角度上预报山洪,更有针对性,为山丘区小流域洪水预报提供了新思路,为“三道防线”数据深度挖掘,防洪“四预”智能化水平提升提供有力技术支撑。

基于人工智能技术的雨量校准故障诊断与预警辅助系统研究

基于人工智能技术的雨量校准故障诊断与预警辅助系统,通过气象观测数据“云”获取设备计量数据进行预处理,采用多种数据驱动和人工智能算法,利用深度学习及神经网络,对采集的数据进行分析,对数据样本进行训练学习,诊断设备是否存在故障并对设备存在的风险进行预警判断。采用神经网络分析设备故障,根据分析出的设备故障情况,系统以大数据为核心、智能算法为底层逻辑模式分析并推送解决方案,有效地提升了户外计量工作效能,对气象自动站其他高精度传感器检定、校准的多源数据分析和诊断具有较好的开拓意义。

聚氨酯用作煤矸石固化材料综合性能研究

针对青海木里矿区露天煤矿风化煤矸石堆场边坡发生优先流现象导致土壤破坏、水土流失以及边坡不稳定等生态环境问题,选用高分子材料聚氨酯作为固化剂,通过固结表层风化煤矸石,达到固化坡面,降低坡面入渗率目的。针对聚氨酯固化煤矸石实际效果及关键影响因素研究尚不充分问题,本研究开展45组不同配比煤矸石—聚氨酯固化试件的单轴压缩试验,60组不同工况煤矸石—聚氨酯固化坡面的人工降雨试验,研究煤矸石—聚氨酯复合材料的主要力学性能、渗透性和技术经济,运用层次分析法对不同配合比进行综合评价,揭示其关键影响因素,筛选最优配比方案。结果表明:1)聚氨酯浓度对提高固化试件的抗压强度贡献最大,而弹性模量主要受煤矸石粒径大小的影响;2)固化煤矸石坡面的平均产流率与聚氨酯浓度成正比,与煤矸石密度成正比,与粒径成反比;平均产沙率与粒径、密度和聚氨酯浓度均成反比;稳定入渗率与粒径成正比,密度与聚氨酯浓度成反比,与密度成反比;3)综合评价45组煤矸石—聚氨酯固化方案,其中最优方案为煤矸石粒径0~0.5 mm、密度1.55 g/cm^(3),聚氨酯浓度3.5%,该煤矸石—聚氨酯固化方案能够大幅提升坡面的抗压强度,并有效降低入渗性能,同时保持较好的经济性(约17元/m^(2))。研究结果可为木里煤矿生态修复工程提供重要技术参考。

基于物理实验的典型透水铺装水文效应研究

为了研究典型透水铺装水文效应,设计研制了一套人工模拟降雨实验系统,经过降雨特性检验,对透水混凝土铺装和植草砖铺装进行了定雨强下渗实验和设计暴雨情景下降雨径流实验。结果表明,本实验系统可实现雨强自动连续变化,人工降雨与设计暴雨在降雨峰值、降雨总量和降雨过程上接近,模拟降雨效果较好。透水混凝土铺装初始下渗率较大,相比于植草砖铺装更早进入稳定下渗阶段,稳定下渗率也更小;植草砖铺装在充分供水条件下也可一定程度控制径流;Horton模型对于透水铺装下渗特性有较好的描述能力。透水混凝土铺装产流过程与降雨过程呈现较高相关性,相同重现期下透水混凝土铺装产流时间均早于植草砖铺装,且产流量大;在削减径流总量和径流峰值、延后径流峰值方面,植草砖铺装都表现更好。