The applicability of using NARX neural network to forecast GRACE terrestrial water storage anomalies

Natural Hazards - The Gravity Recovery and Climate Experiment (GRACE) satellite has proven adept at monitoring, characterizing, and predicting hydrological variables. This paper attempted to...     

Social vulnerability to floods: a case study of Huaihe River Basin

Since ancient times, floods occurred frequently in Huaihe River with significant casualties and economic losses. In developing measures for disaster prevention or emergency response for disaster relief, the study of social vulnerability to floods in Huaihe River Basin should be strengthened. Based on the latest socioeconomic data, the index system of social vulnerability to floods was constructed from three dimensions: population, economy, and flood prevention. Sensitive indexes were identified from the original indexes by principal component analysis, and the social vulnerability index for floods was calculated for Huaihe River Basin. The results described the characteristics of the spatial distribution. It also demonstrated that vulnerability manifests itself as a regional phenomenon, with significant changes from city to city across the Huaihe River Basin. Understanding the impacts of changes in vulnerability was crucial in developing measures to prevent floods.     

Using statistical and artificial neural network models to forecast potentiometric levels at a deep well in South Texas

Reliable forecasts of monthly and quarterly fluctuations in groundwater levels are necessary for short- and medium-term planning and management of aquifers to ensure proper service of seasonal demands within a region. Development of physically based transient mathematical models at this time scale poses considerable challenges due to lack of suitable data and other uncertainties. Artificial neural networks (ANN) possess flexible mathematical structures and are capable of mapping highly nonlinear relationships. Feed-forward neural network models were constructed and trained using the back-percolation algorithm to forecast monthly and quarterly time-series water levels at a well that taps into the deeper Evangeline formation of the Gulf Coast aquifer in Victoria, TX. Unlike unconfined formations, no causal relationships exist between water levels and hydro-meteorological variables measured near the vicinity of the well. As such, an endogenous forecasting model using dummy variables to capture short-term seasonal fluctuations and longer-term (decadal) trends was constructed. The root mean square error, mean absolute deviation and correlation coefficient (R) were noted to be 1.40, 0.33 and 0.77 m, respectively, for an evaluation dataset of quarterly measurements and 1.17, 0.46, and 0.88 m for an evaluative monthly dataset not used to train or test the model. These statistics were better for the ANN model than those developed using statistical regression techniques.     

利用BP神经网络进行水库滑坡变形预测

滑坡变形监测与预测是滑坡预警预报中一种非常重要的途径。文章首先简单介绍了神经网络的基本原理和学习算法,然后利用某水库滑坡24期的GPS地表位移监测数据及其诱发因素即水库水位、降雨等资料,采用BP神经网络模型对该水库滑坡变形进行建模,最后将6期水库水位、降雨等资料输入模型进行滑坡变形预测,结果表明预测结果与实测数据符合性好,总体上能较好反映变形趋势。     

考虑不确定性的长江流域极值降水指标时空变异分析

降低不确定性影响是进行极值降水事件时空变异合理分析的前提。基于6种大气环流模式的输出结果,采用分位数映射校正方法和多模式集合平均方法降低不确定性影响,分析了长江流域极值降水指标的时空变异规律。结果表明:原始的气候模式输出结果具有较大的不确定性,必须对其进行定量分析和采取适当有效的措施进行缓解。5个极值降水指标总体上相对于基准期均增加,最大增幅10%左右。仅个别区域的极值降水指标显示出变异的时间一致性,而空间变异在相同情景和时段上差别明显。     

云南近5个半世纪雨季同旱涝空间模态的时间变化

旱涝灾害是云南的主要气象灾害,严重制约了云南社会经济的发展。文章根据云南21个地区来自历史文献资料的旱涝指数、树木年轮重建的帕默尔干旱指数及观测降水数据（1958~2012 A.D.）,采用五级旱涝指数分类系统将其归一化并应用反距离加权插值补充历史文献缺失的记录,最终获得21个地区近5个半世纪（1470~2012 A.D.）完整的雨季旱涝指数序列。应用主成分分析对该旱涝指数数据集作分析以揭示云南旱涝的主要空间模态,并应用系统突变检测、小波分析等方法对主要空间模态的得分作分析以探讨其时间变化特征和周期性。结果显示,主成分分析得出的第一主成分（解释总方差的50.9%）揭示了空间一致性模态,说明一致性旱涝（同旱同涝）是云南过去5个半世纪旱涝的主要空间模态。第一主成分得分显示了3个阶段（1470~1680 A.D.、1681~1910 A.D.和1911~2012 A.D.）的旱涝状况,活跃的1470~1680 A.D.出现较多极端、严重旱涝以及持续数年的云南大旱和大涝,平静的1681~1910 A.D.少见旱涝灾害,又复活跃的最近一个世纪（1911~2012 A.D.）见到较多的干旱,在2009~2012出现持续4年的云南大旱。小波分析结果表明,云南旱涝存在3~7 a、10~15 a和30~50 a周期变化,3~7 a周期贯穿近5个半世纪,显著的10~15 a和30~50 a涛动出现在1580~1750 A.D.和1470~1700 A.D.。将其与一系列气候代用指标和大型气候型的比较表明,云南雨季旱涝主要受控于南亚夏季风,而过去5个半世纪的南亚夏季风主要受ENSO和IOD的年际变化及PDO和AMO的年代际变化影响。

     

基于遗传神经网络的渗流实时预报方法研究

考虑渗流的主要影响因子,运用遗传神经网络建立了大坝渗流实时预报模型。该模型具有再学习能力,在应用过程中,可以用新的观测资料对模型不断地进行学习训练,且随着样本的积累,模型预报精度不断提高,预报速度很快,因而完全满足实时预报的需要。利用该模型对丰满大坝横向扬压力进行了建模预报,预报值与实测值基本吻合,预测精度高,证明该方法用于大坝渗流实时预报的有效性和实用性。     

Measuring individual vulnerability to floods in the lower and middle Grijalva River Basin,Tabasco, Mexico

Natural Hazards - We built an easy-to-interpret individual vulnerability index to floods that is amenable for empirical testing and may be adapted to any perceived hazard or ecological setting. An...     

Climatic water balance and droughts of Pageru River Basin, Cuddapah District, Andhra Pradesh

The study presented here was undertaken to determine the climatic water balance and droughts of Pageru River Basin by using the rainfall data of eight rain gauge stations in and around the Pageru River Basin. The data have been collected and analysed to compute the water balance parameters. The analysis of the data revealed that the annual distribution is mostly controlled by the physiography of the region. A comparison of water balance and cropping pattern adopted in the villages indicates that the area under the basin is only suitable for cultivation of drought-resistant crops, such as jowar, ragi, bajra, etc.     

NARX neural network approach for the monthly prediction of groundwater levels in Sylhet Sadar,Bangladesh

Groundwater is important for managing the water supply in agricultural countries like Bangladesh. Therefore, the ability to predict the changes of groundwater level is necessary for jointly planning the uses of groundwater resources. In this study, a new nonlinear autoregressive with exogenous inputs(NARX) network has been applied to simulate monthly groundwater levels in a well of Sylhet Sadar at a local scale. The Levenberg-Marquardt(LM) and Bayesian Regularization(BR) algorithms were used to train the NARX network, and the results were compared to determine the best architecture for predicting monthly groundwater levels over time. The comparison between LM and BR showed that NARX-BR has advantages over predicting monthly levels based on the Mean Squared Error(MSE), coefficient of determination(R~2), and Nash-Sutcliffe coefficient of efficiency(NSE). The results show that BR is the most accurate method for predicting groundwater levels with an error of ± 0.35 m. This method is applied to the management of irrigation water source, which provides important information for the prediction of local groundwater fluctuation at local level during a short period.     

长江水文发展及展望

长江水文监测的水文、水质、河道信息,水文气象预报、水文水资源分析评价成果是维护河流健康的基础支撑信息。加强水文水资源监测站网的规划,加快水文测报现代化建设,提升水文水资源预报能力,大力开展长江水文水资源变化规律研究,促进水文事业发展,是长江水文的发展方向。     

Fifty-year rainfall change and its effect on droughts and floods in Wenzhou,China

Based on daily, monthly, seasonal and annual precipitation, monthly duration and flood-affected area data from 1954 to 2007, we examined the absolute and relative change trends of rainfall and their effects on hazard intensity in Wenzhou city, China. The long-term trend of precipitation was studied by linear regression, moving average, cumulative anomaly and Z index methods, respectively. Our results show that there was no significant downward trend of annual precipitation. In contrast, there was significant decrease in autumn, July, mid-January and early June and significant increase in early January and late May, especially in late June. During 1954 and 2007, although significant fluctuation existed in the absolute value of precipitation, the relative changes of wet and dry were not significant compared with the average. The 10-year decrease in precipitation was 23.37 mm in autumn, 14.85 mm in July, 0.33 mm in mid-January and 6.87 mm in early June; while the 10-year increase was 0.35 mm in early January, 3.05 mm in late May and 8.57 mm in late June, respectively. Moreover, we found that 1964, 1966, 1977 and 1995 were the transition periods when the rainfall Z index was at peaks, the flood intensity was high, and the drought intensity was relatively low. On the other hand, 1958, 1968, 1971, 1980, 1989 and 1992 were the periods when the rainfall Z index was at valleys, the flood intensity was low, and the drought intensity was relatively high. Taken together, we demonstrated the obvious effects of precipitation changes on flood and drought intensities.     

BP神经网络在基坑变形预测分析中的应用

本文提出了基坑变形预测与分析的BP神经网络方法,建立了基坑变形预测分析的模型,应用MATLAB语言编制计算程序进行计算并与实际工程监测值进行比较,从而验证了神经网络在基坑变形预测分析中的可行性、有效性。     

人工神经网络在煤与瓦斯突出强度预测中的应用

介绍了人工神经网络的原理及算法,并从地质角度出发,建立了突出强度预测的BP网络模型,通过实例应用结果表明,人工神经网络用于煤与瓦斯突出强度预测是可行的,操作较为简便、准确性高。     

论长江流域河湖体系演化与洪灾防治

长江上游剥蚀沉积物通量是影响长江流域河湖体系平衡的最重要因素。近几十年来,不适人为的地质作用已严重影响并打破了原有的长江流域河湖体系的沉积一搬运平衡系统,主要表现在:①上游自然环境的破坏,使河湖沉积体系沉积物通量大量增加;②中下游围湖造田和不适当的人为河湖治理工程(如裁弯取直、送沙出湖等),改变了长江流域洪沙的自然分配平衡。研究表明,洞庭湖及鄱阳湖为现代构造沉降型补偿平衡盆地,沉降速率等于或略大于目前盆地范围内的沉积物平均淤积速率,具备为长江分洪滞淤的潜在沉积可容空间。长江流域河湖体系沉积平衡的恢复治理,应包括以下几个方面的措施:①整治上游,减少水土流失,减少或抑制整个河湖体系沉积物通量,减缓河湖淤积压力;②顺应长江流域河湖自然分洪分沙规律,开辟荆江南北二岸分洪分沙河道,同时开垸扩湖或湖垸置换;③疏通河道与加固垸堤并举;④上游(主、支流)建坝分洪分沙。     

煤矿立井井筒非采动破裂的人工神经网络预测

应用人工神经网络的基本原理,建立了一个基于神经网络的煤矿立井井筒非采动破裂的预测系统,实现了立井井筒破裂预测的智能化。最后将神经网络预测结果与数值计算结果对比,认为应用人工神经网络对立井井筒破裂时间的预测比较准确、实用。     

An artificial neural network model for flood simulation using GIS: Johor River Basin, Malaysia

Flooding is one of the most destructive natural hazards that cause damage to both life and property every year, and therefore the development of flood model to determine inundation area in watersheds is important for decision makers. In recent years, data mining approaches such as artificial neural network (ANN) techniques are being increasingly used for flood modeling. Previously, this ANN method was frequently used for hydrological and flood modeling by taking rainfall as input and runoff data as output, usually without taking into consideration of other flood causative factors. The specific objective of this study is to develop a flood model using various flood causative factors using ANN techniques and geographic information system (GIS) to modeling and simulate flood-prone areas in the southern part of Peninsular Malaysia. The ANN model for this study was developed in MATLAB using seven flood causative factors. Relevant thematic layers (including rainfall, slope, elevation, flow accumulation, soil, land use, and geology) are generated using GIS, remote sensing data, and field surveys. In the context of objective weight assignments, the ANN is used to directly produce water levels and then the flood map is constructed in GIS. To measure the performance of the model, four criteria performances, including a coefficient of determination (R ²), the sum squared error, the mean square error, and the root mean square error are used. The verification results showed satisfactory agreement between the predicted and the real hydrological records. The results of this study could be used to help local and national government plan for the future and develop appropriate (to the local environmental conditions) new infrastructure to protect the lives and property of the people of Johor.     

长江河源地区及通天河流域水文特征

介绍了长江河源地区及通天河流域的地理概况,从降水、蒸发、径流、输沙量、地下水和水质等方面论述了该地区的水文特征,分析了各水文要素的变化趋势。