Application of support vector machine and relevance vector machine to determine evaporative losses in reservoirs

This article employs Support Vector Machine (SVM) and Relevance Vector Machine (RVM) for prediction of Evaporation Losses (E) in reservoirs. SVM that is firmly based on the theory of statistical learning theory, uses regression technique by introducing ε‐insensitive loss function has been adopted. RVM is based on a Bayesian formulation of a linear model with an appropriate prior that results in a sparse representation. The input of SVM and RVM models are mean air temperature (T) ( °C), average wind speed (WS) (m/sec), sunshine hours (SH)(hrs/day), and mean relative humidity (RH) (%). Equations have been also developed for prediction of E. The developed RVM model gives variance of the predicted E. A comparative study has also been presented between SVM, RVM and ANN models. The results indicate that the developed SVM and RVM can be used as a practical tool for prediction of E. Copyright © 2011 John Wiley & Sons, Ltd.     

Estimating near-shore wave statistics from regional hindcasts using downscaling techniques

Several downscaling techniques, comprising fully dynamical and statistical–dynamical methods applied to near-shore local wave climate, are tested and assessed in terms of wave statistics with respect to the added value that can be achieved compared to larger scale data. The techniques are applied for the example of Helgoland, a small island in the German Bight. It was found that an improved representation could generally be obtained from all downscaling techniques by comparing the near-shore wave climate. Based on a balance between the required computer resources and the improvements achieved, it is suggested, to this end, that a dynamical–statistical approach based on high-resolution coastal wave modeling and linear regression provides the optimal choice.     

基于支持向量机的非线性AVO反演

本文提出了一种新的AVO非线性反演方法,即利用支持向量机来求解AVO非线性反演问题.文中先对支持向量机的原理进行了阐述,然后建立了适合AVO反演的支持向量机模型.最后利用该方法对模型数据和实际资料进行了反演计算,反演结果表明,该方法在没有牺牲反演效果的情况下较好的解决了传统反演方法所具有的局限性,可以直接从合成记录中提取地层的弹性参数,反演速度快、稳定性好.     

中国大陆强震时间序列预测的支持向量机方法

统计学习理论（Statistical Learning Theory或SLT）是研究有限样本情况下机器学习规律的理论。支持向量机（Support Vector Machines或SVM）是基于统计学习理论框架下的一种新的通用机器学习方法。它不但较好地解决了以往困扰很多学习方法的小样本、过学习、高维数、局部最小等实际难题，而且具有很强的泛化（预测）能力。文中使用支持向量机对中国大陆最大地震时间序列进行预测，预测次年的我国大陆最大地震震级，结果表明该方法具有较好的预报效果。研究结果还表明我国大陆强震活动除了与强震时间序列本身有关外，还与全球的强震活动、太阳黑子活动等有密切的关系。尽管这种关系还不清楚，但是通过支持向量机可以很好地反应出这种非线性关系。     

Potential of support vector regression for prediction of monthly streamflow using endogenous property

In the recent past, a variety of statistical and other modelling approaches have been developed to capture the properties of hydrological time series for their reliable prediction. However, the extent of complexity hinders the applicability of such traditional models in many cases. Kernel‐based machine learning approaches have been found to be more popular due to their inherent advantages over traditional modelling techniques including artificial neural networks(ANNs ). In this paper, a kernel‐based learning approach is investigated for its suitability to capture the monthly variation of streamflow time series. Its performance is compared with that of the traditional approaches. Support vector machines (SVMs) are one such kernel‐based algorithm that has given promising results in hydrology and associated areas. In this paper, the application of SVMs to regression problems, known as support vector regression (SVR), is presented to predict the monthly streamflow of the Mahanadi River in the state of Orissa, India. The results obtained are compared against the results derived from the traditional Box–Jenkins approach. While the correlation coefficient between the observed and predicted streamflows was found to be 0·77 in case of SVR, the same for different auto‐regressive integrated moving average (ARIMA) models ranges between 0·67 and 0·69. The superiority of SVR as compared to traditional Box‐Jenkins approach is also explained through the feature space representation. Copyright © 2009 John Wiley & Sons, Ltd.     

A spatial temporal downscaling approach to development of IDF relations for Perth airport region in the context of climate change

ABSTRACT

Downscaling of climate projections is the most adapted method to assess the impacts of climate change at regional and local scales. This study utilized both spatial and temporal downscaling approaches to develop intensity–duration–frequency (IDF) relations for sub-daily rainfall extremes in the Perth airport area. A multiple regression-based statistical downscaling model tool was used for spatial downscaling of daily rainfall using general circulation models (GCMs) (Hadley Centre’s GCM and Canadian Global Climate Model) climate variables. A simple scaling regime was identified for 30 minutes to 24 hours duration of observed annual maximum (AM) rainfall. Then, statistical properties of sub-daily AM rainfall were estimated by scaling an invariant model based on the generalized extreme value distribution. RMSE, Nash-Sutcliffe efficiency coefficient and percentage bias values were estimated to check the accuracy of downscaled sub-daily rainfall. This proved the capability of the proposed approach in developing a linkage between large-scale GCM daily variables and extreme sub-daily rainfall events at a given location. Finally IDF curves were developed for future periods, which show similar extreme rainfall decreasing trends for the 2020s, 2050s and 2080s for both GCMs.

Editor M.C. Acreman; Associate editor S. Kanae     

Spatio-temporal downscaling of projected precipitation in the 21st century: indication of a wetter monsoon over the Upper Mahanadi Basin,India

An attempt is made to assess the future trend of spatio-temporal variation of precipitation over a medium-sized river basin. The Statistical Downscaling Model (SDSM, version 4.2) is used to downscale the outputs from two general circulation models (GCMs) for three future epochs: epoch-1 (2011–2040), epoch-2 (2041–2070) and epoch-3 (2071–2100). Considering the Upper Mahanadi Basin as a test bed, the study results indicate a “wetter” monsoon (June–September) and the annual increase in precipitation is 12% during epoch-3, which is consistent for both GCMs. Monthly analyses indicate that the precipitation totals are likely to increase and the magnitude of increase is greater during monsoon months than non-monsoon months. The number of month-wise daily extremes increases in most months in the year. However, the maximum percentage increase (with respect to baseline period, 1971–2000) in the number of extreme events is found in the non-monsoon months (specifically before and after the monsoon).     

Downscaling of precipitation for climate change scenarios: A support vector machine approach

The Climate impact studies in hydrology often rely on climate change information at fine spatial resolution. However, general circulation models (GCMs), which are among the most advanced tools for estimating future climate change scenarios, operate on a coarse scale. Therefore the output from a GCM has to be downscaled to obtain the information relevant to hydrologic studies. In this paper, a support vector machine (SVM) approach is proposed for statistical downscaling of precipitation at monthly time scale. The effectiveness of this approach is illustrated through its application to meteorological sub-divisions (MSDs) in India. First, climate variables affecting spatio-temporal variation of precipitation at each MSD in India are identified. Following this, the data pertaining to the identified climate variables (predictors) at each MSD are classified using cluster analysis to form two groups, representing wet and dry seasons. For each MSD, SVM- based downscaling model (DM) is developed for season(s) with significant rainfall using principal components extracted from the predictors as input and the contemporaneous precipitation observed at the MSD as an output. The proposed DM is shown to be superior to conventional downscaling using multi-layer back-propagation artificial neural networks. Subsequently, the SVM-based DM is applied to future climate predictions from the second generation Coupled Global Climate Model (CGCM2) to obtain future projections of precipitation for the MSDs. The results are then analyzed to assess the impact of climate change on precipitation over India. It is shown that SVMs provide a promising alternative to conventional artificial neural networks for statistical downscaling, and are suitable for conducting climate impact studies.     

Application of support vector machine to synthetic earthquake prediction

This paper introduces the method of support vector machine (SVM) into the field of synthetic earthquake pre-diction, which is a non-linear and complex seismogenic system. As an example, we apply this method to predict the largest annual magnitude for the North China area (30°E-42°E, 108°N-125°N) and the capital region (38°E-41.5°E, 114°N-120°N) on the basis of seismicity parameters and observed precursory data. The corresponding prediction rates for the North China area and the capital region are 64.1% and ...     

Comparison of direct statistical and indirect statistical-deterministic frameworks in downscaling river low-flow indices

ABSTRACT

This work explores the ability of two methodologies in downscaling hydrological indices characterizing the low flow regime of three salmon rivers in Eastern Canada: Moisie, Romaine and Ouelle. The selected indices describe four aspects of the low flow regime of these rivers: amplitude, frequency, variability and timing. The first methodology (direct downscaling) ascertains a direct link between large-scale atmospheric variables (the predictors) and low flow indices (the predictands). The second (indirect downscaling) involves downscaling precipitation and air temperature (local climate variables) that are introduced into a hydrological model to simulate flows. Synthetic flow time series are subsequently used to calculate the low flow indices. The statistical models used for downscaling low flow hydrological indices and local climate variables are: Sparse Bayesian Learning and Multiple Linear Regression. The results showed that direct downscaling using Sparse Bayesian Learning surpassed the other approaches with respect to goodness of fit and generalization ability.

Editor D. Koutsoyiannis; Associate editor K. Hamed     

Impact of climate change on water resources in Yongdam Dam Basin,Korea

The main purpose of this study is to investigate and evaluate the impact of climate change on the runoff and water resources of Yongdam basin, Korea. First, we construct global climate change scenarios using the YONU GCM control run and transient experiments, then transform the YONU GCM grid-box predictions with coarse resolution of climate change into the site-specific values by statistical downscaling techniques. The downscaled values are used to modify the parameters of a stochastic weather generator model for the simulation of the site-specific daily weather time series. The weather series is fed into a semi-distributed hydrological model called SLURP to simulate the streamflows associated with other water resources for the condition of 2CO₂. This approach is applied to the Yongdam dam basin in the southern part of Korea. The results show that under the condition of 2CO₂, about 7.6% of annual mean streamflow is reduced when it is compared with the current condition. Seasonal streamflows in the winter and autumn are increased, while streamflow in the summer is decreased. However, the seasonality of the simulated series is similar to the observed pattern An erratum to this article can be found at     

Assessment of GCM simulations of annual and seasonal rainfall and daily rainfall distribution across south‐east Australia

Global warming can potentially lead to changes in future rainfall and runoff and can significantly impact the regional hydrology and future availability of water resources. All the large‐scale climate impact studies use the future climate projections from global climate models (GCMs) to estimate the impact on future water availability. This paper presents results from a detailed assessment to investigate the capability of 15 GCMs to reproduce the observed historical annual and seasonal mean rainfalls, the observed annual rainfall series and the observed daily rainfall distribution across south‐east Australia. The assessment shows that the GCMs can generally reproduce the spatial patterns of mean seasonal and annual rainfalls. However, there can be considerable differences between the mean rainfalls simulated by the GCMs and the observed rainfall. The results clearly show that none of the GCMs can simulate the actual annual rainfall time series or the trend in the annual rainfall. The GCMs can also generally reproduce the observed daily (ranked) rainfall distribution at the GCM scale. The GCMs are ranked against their abilities to reproduce the observed historical mean annual rainfall and daily rainfall distribution, and, based on the combined score, the better GCMs include MPI‐ECHAM5, MIUB, CCCMA_T47, INMCM, CSIRO‐MK3·0, CNRM, CCCMA_T63 and GFDL 2·0 and those with poorer performances are MRI, IPSL, GISS‐AOM, MIROC‐M, NCAR‐PCM1, IAP and NCAR‐CCSM. However, the reduction in the combined score as we move from the best‐ to the worst‐performing GCMs is gradual, and there is no evident cut‐off point or threshold to remove GCMs from climate impact studies. There is some agreement between the results here and many similar studies comparing the performance of GCMs in Australia, but the results are not always consistent and do significantly disagree with several of the studies. Copyright © 2010 John Wiley & Sons, Ltd.     

Automatic signal detection based on support vector machine

Introduction The automatic processing of continuous seismic data is important for monitoring earthquake, in which real data recorded by field stations located in different regions is transmitted to data cen- tre through internet or satellite communication systems. Automatic processing will run firstly on data, afterwards these automatic processing results will be reviewed and modified. The load of interactive analysis would be increase if there were more false events or missed events after run…     

Probabilistic reservoir operation using Bayesian stochastic model and support vector machine

Available water resources are often not sufficient or too polluted to satisfy the needs of all water users. Therefore, allocating water to meet water demands with better quality is a major challenge in reservoir operation. In this paper, a methodology to develop operating strategies for water release from a reservoir with acceptable quality and quantity is presented. The proposed model includes a genetic algorithm (GA)-based optimization model linked with a reservoir water quality simulation model. The objective function of the optimization model is based on the Nash bargaining theory to maximize the reliability of supplying the downstream demands with acceptable quality, maintaining a high reservoir storage level, and preventing quality degradation of the reservoir. In order to reduce the run time of the GA-based optimization model, the main optimization model is divided into a stochastic and a deterministic optimization model for reservoir operation considering water quality issues.The operating policies resulted from the reservoir operation model with the water quantity objective are used to determine the released water ranges (permissible lower and upper bounds of release policies) during the planning horizon. Then, certain values of release and the optimal releases from each reservoir outlet are determined utilizing the optimization model with water quality objectives. The support vector machine (SVM) model is used to generate the operating rules for the selective withdrawal from the reservoir for real-time operation. The results show that the SVM model can be effectively used in determining water release from the reservoir. Finally, the copula function was used to estimate the joint probability of supplying the water demand with desirable quality as an evaluation index of the system reliability. The proposed method was applied to the Satarkhan reservoir in the north-western part of Iran. The results of the proposed models are compared with the alternative models. The results show that the proposed models could be used as effective tools in reservoir operation.     

Streamflow forecasting using least-squares support vector machines

Abstract

This paper investigates the ability of a least-squares support vector machine (LSSVM) model to improve the accuracy of streamflow forecasting. Cross-validation and grid-search methods are used to automatically determine the LSSVM parameters in the forecasting process. To assess the effectiveness of this model, monthly streamflow records from two stations, Tg Tulang and Tg Rambutan of the Kinta River in Perak, Peninsular Malaysia, were used as case studies. The performance of the LSSVM model is compared with the conventional statistical autoregressive integrated moving average (ARIMA), the artificial neural network (ANN) and support vector machine (SVM) models using various statistical measures. The results of the comparison indicate that the LSSVM model is a useful tool and a promising new method for streamflow forecasting.

Editor D. Koutsoyiannis; Associate editor L. See

Citation Shabri, A. and Suhartono, 2012. Streamflow forecasting using least-squares support vector machines. Hydrological Sciences Journal, 57 (7), 1275–1293.     

Statistical downscaling of reference evapotranspiration in Haihe River Basin: applicability assessment and application to future projection

Future changes in reference evapotranspiration (ET₀) are of increasing importance in assessing the potential impacts on hydrology and water resources systems of more pronounced climate change. This study assesses the applicability of the Statistical Downscaling Model (SDSM) in projecting ET₀, and investigates the seasonal and spatial patterns of future ET₀ based on general circulation models (GCMs) across the Haihe River Basin. The results indicate that SDSM can downscale ET₀ well in term of different basin-averaged measures for the HadCM3 and CGCM3 GCMs. HadCM3 has a much superior capability in capturing inter-annual variability compared to CGCM3 and thus is chosen as the sole model to assess the changes in future ET₀. There are three homogeneous sub-regions of the Haihe River Basin: Northwest, Northeast and Southeast. Change points are detected at around 2050 and 2080 under the A2 and B2 scenarios, respectively. The Northwest is revealed to have a slight to strong increase in ET₀, while the Northeast and the Southeast tend to experience a pattern change from decrease to increase in ET₀.

EDITOR M.C. Acreman

ASSOCIATE EDITOR J. Thompson     

On selection of kernel parametes in relevance vector machines for hydrologic applications

Recent advances in statistical learning theory have yielded tools that are improving our capabilities for analyzing large and complex datasets. Among such tools, relevance vector machines (RVMs) are finding increasing applications in hydrology because of (1) their excellent generalization properties, and (2) the probabilistic interpretation associated with this technique that yields prediction uncertainty. RVMs combine the strengths of kernel-based methods and Bayesian theory to establish relationships between a set of input vectors and a desired output. However, a bias–variance analysis of RVM estimates revealed that a careful selection of kernel parameters is of paramount importance for achieving good performance from RVMs. In this study, several analytic methods are presented for selection of kernel parameters. These methods rely on structural properties of the data rather than expensive re-sampling approaches commonly used in RVM applications. An analytical expression for prediction risk in leave-one-out cross validation is derived. For brevity, the effectiveness of the proposed methods is assessed first by data generated from the benchmark sinc function, followed by an example involving estimation of hydraulic conductivity values over a field based on observations. It is shown that a straightforward maximization of likelihood function can lead to misleading results. The proposed methods are found to yield robust estimates of parameters for kernel functions.     

Statistical downscaling of extreme daily precipitation,evaporation, and temperature and construction of future scenarios

Generally, the statistical downscaling approaches work less perfectly in reproducing precipitation than temperatures, particularly for the extreme precipitation. This article aimed to testify the capability in downscaling the extreme temperature, evaporation, and precipitation in South China using the statistical downscaling method. Meanwhile, the linkages between the underlying driving forces and the incompetent skills in downscaling precipitation extremes over South China need to be extensively addressed. Toward this end, a statistical downscaling model (SDSM) was built up to construct future scenarios of extreme daily temperature, pan evaporation, and precipitation. The model was thereafter applied to project climate extremes in the Dongjiang River basin in the 21st century from the HadCM3 (Hadley Centre Coupled Model version 3) model under A2 and B2 emission scenarios. The results showed that: (1) The SDSM generally performed fairly well in reproducing the extreme temperature. For the extreme precipitation, the performance of the model was less satisfactory than temperature and evaporation. (2) Both A2 and B2 scenarios projected increases in temperature extremes in all seasons; however, the projections of change in precipitation and evaporation extremes were not consistent with temperature extremes. (3) Skills of SDSM to reproduce the extreme precipitation were very limited. This was partly due to the high randomicity and nonlinearity dominated in extreme precipitation process over the Dongjiang River basin. In pre‐flood seasons (April to June), the mixing of the dry and cold air originated from northern China and the moist warm air releases excessive rainstorms to this basin, while in post‐flood seasons (July to October), the intensive rainstorms are triggered by the tropical system dominated in South China. These unique characteristics collectively account for the incompetent skills of SDSM in reproducing precipitation extremes in South China. Copyright © 2011 John Wiley & Sons, Ltd.     

Temporal analysis of the frequency and duration of low and high streamflow: years of record needed to characterize streamflow variability

A temporal analysis of the number and duration of exceedences of high- and low-flow thresholds was conducted to determine the number of years required to detect a level shift using data from Virginia, North Carolina, and South Carolina. Two methods were used—ordinary least squares assuming a known error variance and generalized least squares without a known error variance. Using ordinary least squares, the mean number of years required to detect a one standard deviation level shift in measures of low-flow variability was 57.2 (28.6 on either side of the break), compared to 40.0 years for measures of high-flow variability. These means become 57.6 and 41.6 when generalized least squares is used. No significant relations between years and elevation or drainage area were detected (P>0.05). Cluster analysis did not suggest geographic patterns in years related to physiography or major hydrologic regions. Referring to the number of observations required to detect a one standard deviation shift as ‘characterizing’ the variability, it appears that at least 20 years of record on either side of a shift may be necessary to adequately characterize high-flow variability. A longer streamflow record (about 30 years on either side) may be required to characterize low-flow variability.     

基于近似支持向量机的流体识别因子融合

通过叠前反演获得的单参数或组合参数都有一定的流体识别能力,但如何将多种流体识别因子有效融合是目前进行流体识别的一个难题.利用人工参与进行流体性质的综合解释是目前流体识别因子融合的主要途径,但这种方法人为干扰较大,不确定性强.鉴于此,本文提出了一种基于近似支持向量机的流体识别方法.该方法首先以实际工区测井资料为依据,优选出对工区内储层所含流体特征敏感的流体识别因子作为输入参数,然后通过近似支持向量机进行流体性质的判别,实例证明该方法的识别结果客观准确,是一种可靠的流体识别方法.