共查询到20条相似文献，搜索用时 15 毫秒
1.
In this paper, we have utilized ANN (artificial neural network) modeling for the prediction of monthly rainfall in Mashhad synoptic station which is located in Iran. To achieve this black-box model, we have used monthly rainfall data from 1953 to 2003 for this synoptic station. First, the Hurst rescaled range statistical (R/S) analysis is used to evaluate the predictability of the collected data. Then, to extract the rainfall dynamic of this station using ANN modeling, a three-layer feed-forward perceptron network with back propagation algorithm is utilized. Using this ANN structure as a black-box model, we have realized the complex dynamics of rainfall through the past information of the system. The approach employs the gradient decent algorithm to train the network. Trying different parameters, two structures, M531 and M741, have been selected which give the best estimation performance. The performance statistical analysis of the obtained models shows with the best tuning of the developed monthly prediction model the correlation coefficient (R), root mean square error (RMSE), and mean absolute error (MAE) are 0.93, 0.99, and 6.02 mm, respectively, which confirms the effectiveness of the developed models. 相似文献
2.
Predictive modeling of hydrological time series is essential for groundwater resource development and management. Here, we examined the comparative merits and demerits of three modern soft computing techniques, namely, artificial neural networks (ANN) optimized by scaled conjugate gradient (SCG) (ANN.SCG), Bayesian neural networks (BNN) optimized by SCG (BNN.SCG) with evidence approximation and adaptive neuro-fuzzy inference system (ANFIS) in the predictive modeling of groundwater level fluctuations. As a first step of our analysis, a sensitivity analysis was carried out using automatic relevance determination scheme to examine the relative influence of each of the hydro-meteorological attributes on groundwater level fluctuations. Secondly, the result of stability analysis was studied by perturbing the underlying data sets with different levels of correlated red noise. Finally, guided by the ensuing theoretical experiments, the above techniques were applied to model the groundwater level fluctuation time series of six wells from a hard rock area of Dindigul in Southern India. We used four standard quantitative statistical measures to compare the robustness of the different models. These measures are (1) root mean square error, (2) reduction of error, (3) index of agreement (IA), and (4) Pearson’s correlation coefficient (R). Based on the above analyses, it is found that the ANFIS model performed better in modeling noise-free data than the BNN.SCG and ANN.SCG models. However, modeling of hydrological time series correlated with significant amount of red noise, the BNN.SCG models performed better than both the ANFIS and ANN.SCG models. Hence, appropriate care should be taken for selecting suitable methodology for modeling the complex and noisy hydrological time series. These results may be used to constrain the model of groundwater level fluctuations, which would in turn, facilitate the development and implementation of more effective sustainable groundwater management and planning strategies in semi-arid hard rock area of Dindigul, Southern India and alike. 相似文献
3.
K. Solaimani H. Mohammadi M. Z. Ahmadi M. Habibnejad 《International Journal of Environmental Science and Technology》2005,2(3):253-258
The application of Geographical Information system (GIS) in modeling flood and its prediction in catchments offers considerable potential. Several examples illustrate simple GIS techniques to produce flood hazard indices or its zonation using hydrologic-type models. Existing flood models can also be loosely coupled to a GIS, such as the HMS (Hydrological Modeling System) model. Forethermore, models can be fully integrated into a GIS by embedded coupling, such as the SCS (Soil Conservation Service) model. Installation of flood forecasting systems in watersheds with incomplete hydrometric data may reduce the flood-induced damages. In this study Geographical Information system used to up to date the watershed data and estimation of SCS model parameters which is sensible to considered the real time flood forecasting in Kasilian catchment of Mazandaran province. The main aim of this paper is to investigate the possibility of the linkage between GIS with a comprehensive hydrologic model, especially HMS. The use of GIS could produce a suitable agreement between observed results (extracted rainfall and runoff data of 1992, 1995 and 1996 from the related stations) with the calculated results of the hydrological model. The obtained results from rainfall-runoff process simulations of the model in this research showed that submergibility of the main watershed, Kasillian, does not depend on the outlet discharge rate of each one of its watershed independently. But it is related to how those two outlet hydrographs from main river watershed are combined. The model is capable of showing the flood characteristics temporally and spatially in each cross section of the channel network. 相似文献
4.
Comparison of cokriging and adaptive neuro-fuzzy inference system models for suspended sediment load forecasting 总被引：1，自引：0，他引：1
Mehdi Vafakhah 《Arabian Journal of Geosciences》2013,6(8):3003-3018
The present research was carried out by using artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), cokriging (CK) and ordinary kriging (OK) using the rainfall and streamflow data for suspended sediment load forecasting. For this reason, the time series of daily rainfall (mm), streamflow (m3/s), and suspended sediment load (tons/day) data were used from the Kojor forest watershed near the Caspian Sea between 28 October 2007 and 21 September 2010 (776 days). Root mean square error, efficiency coefficient, mean absolute error, and mean relative error statistics are used for evaluating the accuracy of the ANN, ANFIS, CK, and OK models. In the first part of the study, various combinations of current daily rainfall, streamflow and past daily rainfall, streamflow data are used as inputs to the neural network and neuro-fuzzy computing technique so as to estimate current suspended sediment. Also, the accuracy of the ANN and ANFIS models are compared together in suspended sediment load forecasting. Comparison results reveal that the ANFIS model provided better estimation than the ANN model. In the second part of the study, the ANN and ANFIS models are compared with OK and CK. The comparison results reveal that CK was a better estimation than the OK. The ANFIS and ANN models also provided better estimation than the OK and CK models. 相似文献
5.
浙江省衢州庙源溪为典型的山区河流,庙源溪雨量丰富,河流比降大,源短流急,洪水陡涨陡落,汇流速度快,洪峰流量大。基于GIS的不规则三角网和空间分析功能,实现水文特征值等值线的内插。根据GIS获取的水文特征值,计算不同历时平均点雨量,考虑点面折算系数,得到平均面雨量。通过频率分析,获得不同频率下的设计雨量。采用瞬时单位线法,进行汇流计算,推求设计洪水过程线及洪峰流量,为制作山洪风险图,建立小流域防洪避洪保障体系提供依据。 相似文献
6.
Assessing flash flood hazard in an arid mountainous region 总被引：2，自引：1，他引：1
Although flash floods are one of the major natural disasters that may hamper human development in arid areas, aspects of the process leading to their initiation remain uncertain and poorly understood. In the present study, wadi El-Alam Basin, one of the major basins in the Eastern Desert of Egypt that is frequently subjected to severe flash flood damage, is selected for investigation. Here, a hydrological modeling approach was used to predict flash flood hazard within the basin. Earlier work conducted for the same basin showed that such approach is successful and was able to accurately highlight the locations of historical flood damage. However, such work was based on one set of arbitrary model parameters. The present study has taking into account the rainfall as the excitation factor in the adopted hydrological modeling. The study aims to build on the earlier study by investigating impacts of variation of rainfall depth, areal coverage, and location on flash flood generation. Results demonstrate that the basin under study requires a rainstorm intensity of at least 40 mm in order to initiate surface runoff with a noticeable flood peak at its main outlet. The location of rainstorm has a major effect on the shape of the basin final hydrograph. Furthermore, in the study basin, the upstream flood appears to be of a magnitude and a peak flow that is much higher than those for downstream ones, which believes to be strongly attributed to the surface steepness and impermeability of the former. The used approach shows to be useful in the rapid assessing of flash flood hazard in mountainous desert and could be adopted, with appropriate modifications, elsewhere in arid regions. 相似文献
7.
8.
9.
面向流域水资源管理,提出了一个基于GIS/RS的流域分布式水文模型,模型主要包括单元水文模型与河网汇流模型两大部分。单元水文模型涉及到冠层截留、融雪、蒸散发、坡面流、非饱和土壤水运动和地下水出流等水文物理过程。产流计算考虑到地形坡度的影响采用基于地形指数的计算方法。汇流演算基于河网结构采用分段马斯京根方法。模型的大部分参数与输入信息可以利用GIS和RS技术获取,能够对气候变化和人类活动对下垫面的改变,做出快速的模拟与响应。 相似文献
10.
GIS and ANN-based spatial prediction of DOC in river networks: a case study in Dongjiang, Southern China 总被引：1，自引：0，他引：1
Yingchun Fu Yaolong Zhao Yongrui Zhang Taisheng Guo Ziwei He Jingyi Chen 《Environmental Earth Sciences》2013,68(5):1495-1505
This paper investigates the use of an artificial neural network (ANN) model to predict dissolved organic carbon (DOC) in a river network and evaluates the impacts of watershed characteristics on stream DOC. Samples and relevant environmental variables were obtained from field sampling at 28 hydrological response units (HRUs) and a MODIS/SRTM DEM satellite image. HRUs can provide reliable spatial interpolation for filling data gaps and incorporate potential spatial correlation among observations in each ANN neuron. The process and results of neural network modeling were assessed by deterministic and statistical methods and spatial regression kriging. The spatial prediction results show that ANN, using improved back propagation algorithms of 7-15-1 architecture, was the optimal network, by which predictions maintained most of the original spatial variation and eliminated smoothing effects of RK. The sum of the relative contributions of four sensitive variables, including soil organic carbon density, geographic longitude, surface runoff and Chl a in river water, was >75 %. A minor prediction error of ~6 % was found in HRUs of open shrublands, but HRUs of urban and croplands had an error of 24–30 %. This pattern exemplifies anthropogenic impacts in urban areas on stream DOC and agricultural activities in croplands. The usefulness of ANN modeling-based GIS in this study is demonstrated by depiction of spatial variation of stream DOC and indicates the benefits of understanding sensitive factors for watershed impact assessments. 相似文献
11.
12.
三峡区间的数字流域水系模型采用基于格网型的数字高程模型坡面流模拟方法和处理"洼地"的最短流程法构建,并以新安江模型为基础建立具有诸多特点的三峡区间流域水文模型;以水动力学理论为基础建立考虑水利工程影响的河川型水库洪水演进模型,并实现这两者的有机耦合。在GIS平台上,将三峡区间流域水文模型、库区洪水演进模型和流域水系生成模型在底层集成,研制了功能先进和完善的三峡水库实时洪水预报系统。该系统已安装在三峡总公司梯级水库调度中心,投入试运行。 相似文献
13.
M. Masoud 《Arabian Journal of Geosciences》2015,8(5):2587-2606
Flash flood forecasting of catchment systems is one of the challenges especially in the arid ungauged basins. This study is attempted to estimate the relationship between rainfall and runoff and also to provide flash flood hazard warnings for ungauged basins based on the hydrological characteristics using geographic information system (GIS). Morphometric characteristics of drainage basins provide a means for describing the hydrological behavior of a basin. The study examined the morphometric parameters of Wadi Rabigh with emphasis on its implication for hydrologic processes through the integration analysis between morphometric parameters and GIS techniques. Data for this study were obtained from ASTER data for digital elevation model (DEM) with 30-m resolution, topographic map (1:50,000), and geological maps (1,250,000) which were subject to field confirmation. About 36 morphometric parameters were measured and calculated, and interlinked to produce nine effective parameters for the evaluation of the flash flood hazard degree of the study area. Based on nine effective morphometric parameters that directly influence on the hydrologic behavior of the Wadi through time of concentration, the flash flood hazard of the Rabigh basin and its subbasins was identified and classified into three groups (High, medium, and low hazard degree). The present work proved that the physiographic features of drainage basin contribute to the possibility of a flash flood hazard evaluation for any particular drainage area. The study provides details on the flash flood prone subbasins and the mitigation measures. This study also helps to plan rainwater harvesting and watershed management in the flash flood alert zones. Based on two historical data events of rainfall and the corresponding maximum flow rate, morphometric parameters and Stormwater Management and Design Aid software (SMADA 6), it could be to generate the hydrograph of Wadi Rabigh basin. As a result of the model applied to Wadi Rabigh basin, a rainfall event of a total of 22 mm with a duration of 5 h at the station nearby the study area, which has an exceedance probability of 50 % and return period around 2 years, produces a discharge volume of 15.2?×?106 m3 at the delta, outlet of the basin, as 12.5 mm of the rainfall infiltrates (recharge). 相似文献
14.
Flash flood disaster is a prominent issue threatening public safety and social development throughout the world, especially in mountainous regions. Rainfall threshold is a widely accepted alternative to hydrological forecasting for flash flood warning due to the short response time and limited observations of flash flood events. However, determination of rainfall threshold is still very complicated due to multiple impact factors, particular for antecedent soil moisture and rainfall patterns. In this study, hydrological simulation approach (i.e., China Flash Flood-Hydrological Modeling System: CNFF-HMS) was adopted to capture the flash flood processes. Multiple scenarios were further designed with consideration of antecedent soil moisture and rainfall temporal patterns to determine the possible assemble of rainfall thresholds by driving the CNFF-HMS. Moreover, their effects on rainfall thresholds were investigated. Three mountainous catchments (Zhong, Balisi and Yu villages) in southern China were selected for case study. Results showed that the model performance of CNFF-HMS was very satisfactory for flash flood simulations in all these catchments, especially for multimodal flood events. Specifically, the relative errors of runoff and peak flow were within?±?20%, the error of time to peak flow was within?±?2 h and the Nash–Sutcliffe efficiency was greater than 0.90 for over 90% of the flash flood events. The rainfall thresholds varied between 93 and 334 mm at Zhong village, between 77 and 246 mm at Balisi village and between 111 and 420 mm at Yu village. Both antecedent soil moistures and rainfall temporal pattern significantly affected the variations of rainfall threshold. Rainfall threshold decreased by 8–38 and 0–42% as soil saturation increased from 0.20 to 0.50 and from 0.20 to 0.80, respectively. The effect of rainfall threshold was the minimum for the decreasing hyetograph (advanced pattern) and the maximum for the increasing hyetograph (delayed pattern), while it was similar for the design hyetograph and triangular hyetograph (intermediate patterns). Moreover, rainfall thresholds with short time spans were more suitable for early flood warning, especially in small rural catchments with humid climatic characteristics. This study was expected to provide insights into flash flood disaster forecasting and early warning in mountainous regions, and scientific references for the implementation of flash flood disaster prevention in China. 相似文献
15.
为实现中小流域降雨径流过程精细化模拟, 合理估算水文模型参数的空间分布具有重要意义。基于新版全球数字土壤制图系统(SoilGrids)构建栅格新安江模型(GXM)参数化方案, 对陕西省陈河流域2003—2012年16场洪水进行模拟, 与新安江模型计算结果进行对比, 开展基于洪水过程划分的自由水蓄水容量敏感性及空间分布特征量化分析。结果表明: GXM模拟的峰现时间误差水平降低约0.31 h, 洪峰和洪量模拟精度较高, 模型能够对土壤水饱和度等水文要素的动态空间分布进行较合理的模拟; 自由水蓄水容量参数对洪峰和涨洪过程的确定性系数以及涨洪段的洪量相对误差影响较大, 对退水过程影响小; 自由水蓄水容量在陈河流域河谷和山脊附近较大, 坡段中部较小。 相似文献
16.
This study proposes an application of two techniques of artificial intelligence (AI) for rainfall-runoff modeling: the artificial
neural networks (ANN) and the evolutionary computation (EC). Two different ANN techniques, the feed forward back propagation
(FFBP) and generalized regression neural network (GRNN) methods are compared with one EC method, Gene Expression Programming
(GEP) which is a new evolutionary algorithm that evolves computer programs. The daily hydrometeorological data of three rainfall
stations and one streamflow station for Juniata River Basin in Pennsylvania state of USA are taken into consideration in the
model development. Statistical parameters such as average, standard deviation, coefficient of variation, skewness, minimum
and maximum values, as well as criteria such as mean square error (MSE) and determination coefficient (R
2) are used to measure the performance of the models. The results indicate that the proposed genetic programming (GP) formulation
performs quite well compared to results obtained by ANNs and is quite practical for use. It is concluded from the results
that GEP can be proposed as an alternative to ANN models. 相似文献
17.
《地学前缘(英文版)》2021,12(3)
Flash floods are responsible for loss of life and considerable property damage in many countries.Flood susceptibility maps contribute to flood risk reduction in areas that are prone to this hazard if appropriately used by landuse planners and emergency managers.The main objective of this study is to prepare an accurate flood susceptibility map for the Haraz watershed in Iran using a novel modeling approach(DBPGA) based on Deep Belief Network(DBN) with Back Propagation(BP) algorithm optimized by the Genetic Algorithm(GA).For this task, a database comprising ten conditioning factors and 194 flood locations was created using the One-R Attribute Evaluation(ORAE) technique.Various well-known machine learning and optimization algorithms were used as benchmarks to compare the prediction accuracy of the proposed model.Statistical metrics include sensitivity,specificity accuracy, root mean square error(RMSE), and area under the receiver operatic characteristic curve(AUC) were used to assess the validity of the proposed model.The result shows that the proposed model has the highest goodness-of-fit(AUC = 0.989) and prediction accuracy(AUC = 0.985), and based on the validation dataset it outperforms benchmark models including LR(0.885), LMT(0.934), BLR(0.936), ADT(0.976), NBT(0.974), REPTree(0.811), ANFIS-BAT(0.944), ANFIS-CA(0.921), ANFIS-IWO(0.939), ANFIS-ICA(0.947), and ANFIS-FA(0.917).We conclude that the DBPGA model is an excellent alternative tool for predicting flash flood susceptibility for other regions prone to flash floods. 相似文献
18.
流域暴雨山洪过程时空异质性强,准确评估雨洪变化特性和洪水危险性对山洪灾害防治具有重要意义。以7个降雨特征指标和6个洪水特征指标刻画流域场次雨洪特性,采用中国山洪水文模型和洪水频率指标相结合,模拟和评估口前流域洪水过程及其危险性。结果表明：场次洪水洪峰模数、洪峰时间偏度、高脉冲历时占比、涨落洪速率与降雨总量、平均雨量、最大雨强、雨峰位置系数、基尼系数等降雨特征指标显著相关,三场致灾洪水过程的降雨均呈现量级大、强度大、历时短、暴雨中心偏中下游的特点;率定期和验证期的平均径流深相对误差均在9%以内,平均洪峰流量相对误差均在11%以内,平均峰现时间误差均在1.7 h以内,平均Nash-Sutcliffe系数为0.80和0.76;各场次洪水有0.0%～93.3%的河段流量达到一般危险及以上等级,三场致灾洪水过程的危险性等级最高,分别有80.0%、35.0%和1.7%的小流域河段流量达到高危险及以上等级。研究可为山区小流域暴雨洪水危险性评估、灾害响应和复盘等提供技术支撑。 相似文献
19.
ArcTOP:TOPKAPI与GIS紧密连接的分布式水文模型系统 总被引：4，自引：0，他引：4
基于遥感（RS）和地理信息系统（GIS）的分布式水文模型已成为当前水文科学发展的前沿，地理信息建模系统是目前地理信息系统研究的热点问题之一。目前实现通用GIS空间分析功能与水文模型的集成主要有四种途径：水文模型嵌入CIS平台．GIS功能嵌入水文模型．水文模型和GIS的松散连接以及水文模型和CIS的紧密连接。本文提出的ArcTOP分布式水文模型系统，运用ArcViewGIS提供的宏语言，将以物理概念为基础的分布式水文模型TOPKAPI和CIS紧密连接，实现分布式水文模型和GIS的完全集成。 相似文献
20.
Shattri Mansor Nader Saadatkhah Zailani Khuzaimah Arnis Asmat Nor Aizam Adnan Siti Noradzah Adam 《Natural Hazards》2018,93(2):739-764
The objective of this paper is to develop a spatial temporal runoff modelling of local rainfall patterns effect on the plant cover hilly lands in Kelantan River Basin. Rainfall interception loss based on leaf area index, loss/infiltration on the ground surface, and runoff calculation were considered as the main plant cover effects on the runoff volume. In this regard, a hydrological and geotechnical grid-based regional model (integrated model) was performed using Microsoft Excel® and GIS framework system for deterministic modelling of rainfall-induced runoff by incorporating plant cover effects. The infiltration process of the current model was integrated with the precipitation distribution method and rainfall interception approach while the runoff analysis of integrated model was employed based on loss/infiltration water on the ground surface with consideration of water interception loss by canopy and the remaining surface water. In the following, the spatial temporal analysis of rainfall-induced runoff was performed using 10 days of hourly rainfall events at the end of December 2014 in Kelantan River Basin. The corresponding changes in pressure head and consequent rate of infiltration were calculated during rainfall events. Subsequently, flood volume is computed using local rainfall patterns, along with water interception loss and the remaining surface water in the study area. The results showed the land cover changes caused significant differences in hydrological response to surface water. The increase in runoff volume of the Kelantan River Basin is as a function of deforestation and urbanization, especially converting the forest area to agricultural land (i.e. rubber and mixed agriculture). 相似文献