共查询到20条相似文献，搜索用时 313 毫秒
1.
Bagher Shirmohammadi Hamidreza Moradi Vahid Moosavi Majid Taie Semiromi Ali Zeinali 《Natural Hazards》2013,69(1):389-402
Drought is accounted as one of the most natural hazards. Studying on drought is important for designing and managing of water resources systems. This research is carried out to evaluate the ability of Wavelet-ANN and adaptive neuro-fuzzy inference system (ANFIS) techniques for meteorological drought forecasting in southeastern part of East Azerbaijan province, Iran. The Wavelet-ANN and ANFIS models were first trained using the observed data recorded from 1952 to 1992 and then used to predict meteorological drought over the test period extending from 1992 to 2011. The performances of the different models were evaluated by comparing the corresponding values of root mean squared error coefficient of determination (R 2) and Nash–Sutcliffe model efficiency coefficient. In this study, more than 1,000 model structures including artificial neural network (ANN), adaptive neural-fuzzy inference system (ANFIS) and Wavelet-ANN models were tested in order to assess their ability to forecast the meteorological drought for one, two, and three time steps (6 months) ahead. It was demonstrated that wavelet transform can improve meteorological drought modeling. It was also shown that ANFIS models provided more accurate predictions than ANN models. This study confirmed that the optimum number of neurons in the hidden layer could not be always determined using specific formulas; hence, it should be determined using a trial-and-error method. Also, decomposition level in wavelet transform should be delineated according to the periodicity and seasonality of data series. The order of models with regard to their accuracy is as following: Wavelet-ANFIS, Wavelet-ANN, ANFIS, and ANN, respectively. To the best of our knowledge, no research has been published that explores coupling wavelet analysis with ANFIS for meteorological drought and no research has tested the efficiency of these models to forecast the meteorological drought in different time scales as of yet. 相似文献
2.
Quality and reliable drought prediction is essential for mitigation strategies and planning in disaster-stricken regions globally. Prediction models such as empirical or data-driven models play a fundamental role in forecasting drought. However, selecting a suitable prediction model remains a challenge because of the lack of succinct information available on model performance. Therefore, this review evaluated the best model for drought forecasting and determined which differences if any were present in model performance using standardised precipitation index (SPI). In addition, the most effective combination of the SPI with its respective timescale and lead time was investigated. The effectiveness of data-driven models was analysed using meta-regression analysis by applying a linear mixed model to the coefficient of determination and the root mean square error of the validated model results. Wavelet-transformed neural networks had superior performance with the highest correlation and minimum error. Preprocessing data to eliminate non-stationarity performed substantially better than did the regular artificial neural network (ANN) model. Additionally, the best timescale to calculate the SPI was 24 and 12 months and a lead time of 1–3 months provided the most accurate forecasts. Studies from China and Sicily had the most variation based on geographical location as a random effect; while studies from India rendered consistent results overall. Variation in the result can be attributed to geographical differences, seasonal influence, incorporation of climate indices and author bias. Conclusively, this review recommends use of the wavelet-based ANN (WANN) model to forecast drought indices.
相似文献3.
Hossein Bari Abarghouei Mohammad Reza Kousari Mohammad Amin Asadi Zarch 《Arabian Journal of Geosciences》2013,6(5):1417-1433
Drought is one of the most important natural hazards in Iran. It is especially more prevalent in arid and hyper arid regions where there are serious limitations in regard to providing sufficient water resources. On the other hand, drought modeling and particularly its prediction can play important role in water resources management under conditions of lack of sufficient water resources. Therefore, in this study, drought prediction in a hyper arid location of Iran (Ardakan region) has been surveyed based on the abilities of artificial neural. Standardized Precipitation Index (SPI) in different time scales (3, 6, 9, 12, and 24 monthly time series) computed based on the data gathered from four rain gauge stations. After evaluation and testing of different artificial neural networks (ANN) structures, gradient descent back propagation (traingd) network showed higher abilities than others. Then, the predictions of SPI time series with different monthly lag times (1:12 months) were tested. Generally, drought prediction by ANNs in the Ardakan region has shown considerable results with the correlation coefficient (R) more than 0.79 and in the most cases and it rises more than 0.90, which indicates the ANN’s ability of drought prediction. 相似文献
4.
The shortage of surface water in arid and semiarid regions has led to the more use of the groundwater resources. In these areas, the groundwater is essential for activities such as water supply and irrigation. One of the most important stages in sustainable yield of groundwater resources is awareness of groundwater level. In this study, we have applied artificial neural networks (ANN) and autoregressive integrated moving average (ARIMA) models for groundwater level forecasting to 4 months ahead in Shiraz basin, southwestern Iran. Time series analysis was conducted according to the Box–Jenkins method. Meanwhile, gamma and M-test were considered for determining the optimal input combination and length of training and testing data in the ANN model. The results indicated that performance of multilayer perceptron neural network (4, 14, 1) and ARIMA (2, 1, 2) is satisfactory in the groundwater level forecasting for one month ahead. The performance comparison shows that the ARIMA model performs appreciably better than the ANN. 相似文献
5.
不同时间尺度的中长期水文预报研究 总被引：1，自引：0，他引：1
为研究中长期水文预报时间尺度对预报精度的影响,选取最近邻抽样回归模型与基于小波分析的组合模型对长江干流典型断面不同时间尺度的径流序列进行中长期径流预报。将1980~2012年的逐日径流资料经过时间聚集方法转换成三天、周、旬、半月、月、双月、季、半年、九月、年等10个不同时间尺度,对高场、寸滩、宜昌、螺山、汉口、大通6个典型断面的径流进行拟合和预报。结果表明:随着预报时间尺度增加,预报精度呈现先降低后提高的趋势,其中,在月时间尺度上预报效果最差,三天和年尺度上预报效果相对较好。 相似文献
6.
In this study, the preprocessing of the gamma test was used to select the appropriate input combination into two models including the support vector regression (SVR) model and artificial neural networks (ANNs) to predict the stream flow drought index (SDI) of different timescales (i.e., 3, 6, 9, 12, and 24 months) in Latian watershed, Iran, which is one of the most important sources of water for the large metropolitan Tehran. The variables used included SDI t , SDI t ? 1, SDI t ? 2, SDI t ? 3, and SDI t ? 4 monthly delays. Two variables including SDI t and SDI t ? 1 with lower gamma values were identified as the most optimal combination of variables in all drought timescales. The results showed that the gamma test was able to correctly identify the right combination for the forecasting of 6, 9, and 12 months SDI using the ANN model. Also, the gamma test was considered in selecting the appropriate inputs for identifying the values of 9, 12, and 24 months SDI in SVR. The support vector machine approach showed a better efficiency in the forecast of long-term droughts compared to the artificial neural network. In total, among forecasts made for 30 scenarios, the support vector machine model only in scenario 3 of SDI3, scenario 1 of SDI6, and scenarios 2 and 3 of SDI24 represented poorer efficiency compared to the artificial neural network (MLP layer), but in other scenarios, the results of SVR had better efficiency. 相似文献
7.
A quantitative approach for hydrological drought characterization, based on non-seasonal water storage deficit data from NASA’s Gravity Recovery and Climate Experiment (GRACE) satellite mission, is assessed. Non-seasonal storage deficit is the negative terrestrial water storage after deducting trend, acceleration and seasonal signals, and it is designated as a drought event when it persists for three or more continuous months. The non-seasonal water storage deficit is used for measuring the hydrological drought in southwestern China. It is found that this storage-deficit method clearly identifies hydrological drought onset, end and duration, and quantifies instantaneous severity, peak drought magnitude, and time to recovery. Moreover, it is found that severe droughts have frequently struck southwestern China in the past several decades, among which, the drought of 2011–2012 was the most severe; the duration was 10 months, the severity was ?208.92 km3/month, and the time to recovery was 17 months. These results compare well with the National Climate Center of China drought databases, which signifies that the GRACE-based non-seasonal water storage deficit has a quantitative effect on hydrological drought characterization and provides an effective tool for researching droughts. 相似文献
8.
In recent decades, population growth associated with unplanned urban occupation has increased the vulnerability of the Brazilian population to natural disasters. In susceptible regions, early flood forecasting is essential for risk management. Still, in Brazil, most flood forecast and warning systems are based either on simplified models of flood wave propagation through the drainage network or on stochastic models. This paper presents a methodology for flood forecasting aiming to an operational warning system that proposes to increase the lead time of a warning through the use of an ensemble of meteorological forecasts. The chosen configuration was chosen so it would be feasible for an operational flood forecast and risk management. The methodology was applied to the flood forecast for the Itajaí-Açu River basin, a region which comprises a drainage area of approximately 15,500 km2 in the state of Santa Catarina, Brazil, historically affected by floods. Ensemble weather forecasts were used as input to the MHD-INPE hydrological model, and the performance of the methodology was assessed through statistical indicators. Results suggest that flood warnings can be issued up to 48 h in advance, with a low rate of false warnings. Streamflow forecasting through the use of hydrological ensemble prediction systems is still scarce in Brazil. To the best of our knowledge, this is the first time this methodology aiming to an operational flood risk management system has been tested in Brazil. 相似文献
9.
M. Rezaeianzadeh A. Stein H. Tabari H. Abghari N. Jalalkamali E. Z. Hosseinipour V. P. Singh 《International Journal of Environmental Science and Technology》2013,10(6):1181-1192
Artificial neural networks (ANNs) are used by hydrologists and engineers to forecast flows at the outlet of a watershed. They are employed in particular where hydrological data are limited. Despite these developments, practitioners still prefer conventional hydrological models. This study applied the standard conceptual HEC-HMS’s soil moisture accounting (SMA) algorithm and the multi layer perceptron (MLP) for forecasting daily outflows at the outlet of Khosrow Shirin watershed in Iran. The MLP [optimized with the scaled conjugate gradient] used the logistic and tangent sigmoid activation functions resulting into 12 ANNs. The R 2 and RMSE values for the best trained MPLs using the tangent and logistic sigmoid transfer function were 0.87, 1.875 m3 s?1 and 0.81, 2.297 m3 s?1, respectively. The results showed that MLPs optimized with the tangent sigmoid predicted peak flows and annual flood volumes more accurately than the HEC-HMS model with the SMA algorithm, with R 2 and RMSE values equal to 0.87, 0.84 and 1.875 and 2.1 m3 s?1, respectively. Also, an MLP is easier to develop due to using a simple trial and error procedure. Practitioners of hydrologic modeling and flood flow forecasting may consider this study as an example of the capability of the ANN for real world flow forecasting. 相似文献
10.
11.
Evaluation of CHIRPS and its application for drought monitoring over the Haihe River Basin,China 总被引：2，自引：0，他引：2
Feng Gao Yuhu Zhang Xiulin Ren Yunjun Yao Zengchao Hao Wanyuan Cai 《Natural Hazards》2018,91(1):155-178
To establish the drought index objectively and reasonably and evaluate the hydrological drought accurately, firstly, the optimal distribution was selected from nine distributions (normal, lognormal, exponential, gamma, general extreme value, inverse Gaussian, logistic, log-logistic and Weibull), then the Optimal Standardized Streamflow Index (OSSI) was calculated based on the optimal distribution, and last, the spatiotemporal evolution of hydrological drought based on the OSSI series was investigated through the monthly streamflow data of seven hydrological stations during the period 1961–2011 in Luanhe River basin, China. Results suggest: (1) the general extreme value and log-logistic distributions performed prominently in fitting the monthly streamflow of Luanhe River basin. (2) The main periods of hydrological drought in Luanhe River basin were 148–169, 75–80, 42–45, 14–19 and 8–9 months. (3) The hydrological drought had an aggravating trend over the past 51 year and with the increase in timescale, the aggravating trend was more serious. (4) The lower the drought grade was, the broader the coverage area. As for the Luanhe River basin, the whole basin suffered the mild and more serious drought, while the severe and more serious drought only cover some areas. (5) With the increase in time step, the frequency distribution of mild droughts across the basin tended to be concentrated, the frequency of extreme droughts in middle and upper reaches tended to increase and the frequency in downstream tends to decrease. This research can provide powerful references for water resources planning and management and drought mitigation. 相似文献
12.
13.
气象干旱发展到一定程度可以传递为水文干旱。以潘家口水库流域1961—2010年逐月平均降水数据和潘家口水库的入库径流序列为基础数据,分别计算了1、3、6、12个月时间尺度的标准化降水指数（SPI）和标准化径流指数（SRI）,以表征研究区域的气象干旱和水文干旱。基于条件分布模型,分析了不同时间尺度的气象干旱传递到未来的不同等级和不同的预测期（或滞后期）的水文干旱的概率。结果表明,当SPI时间尺度较短或预测期（滞后期）较短时,其对应的SRI水文干旱等级越倾向于维持与SPI相同的干旱等级;随着SPI时间尺度的增长或预测期（滞后期）延长,其对应的SRI水文干旱等级略低于气象干旱或恢复到正常状态。 相似文献
14.
Soil temperature has an important role in agricultural, hydrological, meteorological and climatological studies. In the present research, monthly mean soil temperature at four different depths (5, 10, 50 and 100 cm) was estimated using artificial neural networks (ANN), adaptive neuro-fuzzy inference system (ANFIS) and gene expression programming (GEP). The monthly mean soil temperature data of 31 stations over Iran were employed. In this process, the data of 21 and 10 stations were used for training and testing stages of used models, respectively. Furthermore, the geographical information including latitude, longitude and altitude as well as periodicity component (the number of months) was considered as inputs in the mentioned intelligent models. The results demonstrated that the ANN and ANFIS models had good performance in comparison with the GEP model. Nevertheless, the ANFIS generally performed better than ANN model. 相似文献
15.
Pritpal Singh 《地学前缘(英文版)》2018,9(4):1243-1257
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. 相似文献
16.
三种基于神经网络的洪水实时预报方案的比较研究 总被引：8，自引：1，他引：7
在总结神经网络应用的基础上,归纳了3种基于神经网络的洪水实时预报方案。第一种是神经网络水文模型的模拟模式加模拟误差的自回归校正模型,第二种是权重系数固定的神经网络实时预报方案,第三种是权重系数自动更新的神经网络实时预报方案。采用10个不同流域的日流量资料对这3种方案进行率定和校核。比较这3种方案的实时预报精度。结果发现,第三种方案不仅预报精度要高于其他两种方案,而且比第一种方案少了一个自回归校正模型,结构简洁。本文建议采用第三种洪水实时预报方案。 相似文献
17.
Because of scarcity and high variability of rainfall in arid areas, from one hand, reliable prediction of precipitation in such regions is considerably difficult. Furthermore, in some cases, shortage of observation data and several other limitations may intensify complexity of the forecasting. On the other hand, these regions highly suffer from low availability of water which necessitates development of an appropriate modeling approach to provide as precise as possible predictions of precipitation. Artificial neural networks (ANNs) are expected to be a powerful tool in capturing and analyzing high interannual variability of precipitation in arid climates and, subsequently, in proper prediction of precipitation fluctuations in the future. The end of this paper is to improve ANN predictions of precipitation in arid climates using better training of the network. To this end, two approaches were applied. In the first one, just the rainfall monthly data were considered as input. In the second approach, in addition to precipitation, several exogenous variables of precipitation are considered as input to predict precipitation. The chosen exogenous parameters are either effective on or relevant to the precipitation patterns. Then, several lag times, hidden layer sizes, and training algorithms for different running sums are used in order to produce best forecasts. It was shown that the performance of networks increases significantly by importing more external factors as inputs. The bigger time scales also exhibited better performances. In all the five time scales, smaller lag times (especially one month), bigger hidden layer sizes (especially between 31 and 40), and GDX training algorithm presented the best performance. The highest obtained performance was presented by the network with 10 inputs, 1 month lag, 36 hidden layers, and CGF training method in 18 months running sum with R 2 of 0.93. 相似文献
18.
Our aim was to develop a remote sensing-based forest fire danger forecasting system (FFDFS) and its implementation in forecasting 2011 fire season in the Canadian province of Alberta. The FFDFS used Moderate Resolution Imaging Spectroradiometer (MODIS)-derived 8-day composites of surface temperature, normalized multiband drought index, and normalized difference vegetation index as input variables. In order to eliminate the data gaps in the input variables, we propose a gap-filling technique by considering both of the spatial and temporal dimensions. These input variables were calculated during the i period and then integrated to forecast the fire danger conditions into four categories (i.e., very high, high, moderate, and low) during the i + 1 period. It was observed that 98.19 % of the fire fell under “very high” to “moderate” danger classes. The performance of this system was also demonstrated its ability to forecast the worst fires occurred in Slave Lake and Fort McMurray region during mid-May 2011. For example, 100 and 94.0 % of the fire spots fell under “very high” to “high” danger categories for Slave Lake and Fort McMurray regions, respectively. 相似文献
19.
随着全球气候变化、自然变迁及陆表生境改变,极端天气频发且呈现出多尺度时空变异特征,对其进行预报和预警一直是气象水文领域关注的焦点。临近预报可较准确地预报未来短时间天气显著变化,是当前预报强降水等极端事件的主要手段。从基于天气雷达0~3 h外推临近预报、融合数值模式0~6 h临近预报的发展历程梳理了临近预报的研究进展,阐述了雷达外推算法的发展进程、雷达外推预报与数值模式预报融合技术进展,指出"取长补短"的0~6 h融合预报在提高降水预报精度、延长降水预见期等多方面有较大的发展潜力,进一步探寻及提升融合技术是未来融合预报发展的核心。将临近预报以气象水文耦合的方式引入水文预报是从源头提高水文预报精度、保障水文预报效果的主要途径,总结了现阶段主流耦合方式、空间尺度匹配技术、水文模型不确定等陆气耦合中的关键问题,阐述了外推临近预报、融合临近预报作为水文预报输入的研究进展,明确了融合临近预报在延长洪水预见期、提高洪水预报精度中存在优势,并讨论了未来的研究重点及发展方向。 相似文献