基于ANN模型重塑岩溶地下河系统流量数据可行性研究

西南岩溶地区地下河系统的多层次和多级性特征,决定了其输入因子与响应因子之间为非线性关系,传统的统计方法在揭示此类关系时效果欠佳,而人工神经网络模型( Artificial Neural Ne two rk—— ANN)正好弥补了此项不足,其在原理和构模上均表现出与岩溶地下河系统十分相似的特点。通过对广西地苏地下河系统水量数据的重塑发现, ANN模型重塑的效果明显优于传统的回归分析法,证明了运用ANN模型重塑岩溶地下河系统流量数据是完全可行的。      

Chemical and isotopic methods for management of artificial recharge in Mazraha Station (Damascus Basin,Syria)

Artificially enhancing recharge rate into groundwater aquifer at specially designed facilities is an attractive option for increasing the storage capacity of potable water in arid and semi‐arid region such as Damascus basin (Syria). Two dug wells (I and II) for water injection and 24 wells for water extraction are available in Mazraha station for artificial recharge experiment. Chemical and stable isotopes (δ²H and δ¹⁸O) were used to evaluate artificial recharge efficiency. 400 to 500*10³ m³ of spring water were injected annually into the ambient shallow groundwater in Mazraha station, which is used later for drinking purpose. Ambient groundwater and injected spring water are calcium bicarbonate type with EC about 880 ± 60 μS/cm and 300 ± 50 μS/cm, respectively. The injected water is under saturated versus calcite and the ambient groundwater is over saturated, while the recovered water is near equilibrium. It was observed that the injection process formed a chemical dilution plume that improves the groundwater quality. Results demonstrate that the hydraulic conductivity of the aquifer is estimated around 6.8*10^?4 m/s. The effective diameter of artificial recharge is limited to about 250 m from the injection wells. Mixing rate of 30% is required in order to reduce nitrate concentration below 50 mg/l which is considered the maximum concentration limit for potable water. Deuterium and oxygen‐18 relationship demonstrates that mixing line between injected water and ambient groundwater has a slope of 6.1. Oxygen‐18 and Cl^? plot indicates that groundwater salinity origin is from mixing process, and no dissolution and evaporation were observed. These results demonstrate the efficiency of the artificial recharge experiments to restore groundwater storage capacity and to improve the water quality. Copyright © 2011 John Wiley & Sons, Ltd.     

http://www.sciencedirect.com/science/article/pii/S1674987112000254

The applications of intelligent techniques have increased exponentially in recent days to study most of the non-linear parameters.In particular,the behavior of earth resembles the non-linearity applications.An efficient tool is needed for the interpretation of geophysical parameters to study the subsurface of the earth.Artificial Neural Networks(ANN) perform certain tasks if the structure of the network is modified accordingly for the purpose it has been used.The three most robust networks were taken and comparatively analyzed for their performance to choose the appropriate network.The single-layer feed-forward neural network with the back propagation algorithm is chosen as one of the well-suited networks after comparing the results.Initially,certain synthetic data sets of all three-layer curves have been taken for training the network,and the network is validated by the Held datasets collected from Tuticorin Coastal Region(78°7′30″E and 8°48′45″N),Tamil Nadu.India.The interpretation has been done successfully using the corresponding learning algorithm in the present study.With proper training of back propagation networks,it tends to give the resistivity and thickness of the subsurface layer model of the field resistivity data concerning the synthetic data trained earlier in the appropriate network.The network is trained with more Vertical Electrical Sounding(VES) data,and this trained network is demonstrated by the field data.Groundwater table depth also has been modeled.     

基于初始二维水权的流域水资源调控框架初析

为推动中国水权制度建设进程与落实最严格水资源管理制度提供技术支撑,基于二维水权概念与内涵等现有研究成果,结合对国内外初始水权分配相关研究进展与需求实践的系统梳理,从供水管理视角提出了包括"初始分配"、"优化调控"和"实时调控"3项内容在内的基于初始二维水权的流域水资源调控理论框架,详细阐述了各组成部分的实现途径、支撑技术、建模步骤及其之间的工作关系。     

基于遗传神经网络的克钦湖叶绿素反演研究

叶绿素a浓度能够在一定程度上反映内陆湖泊水质情况。为实现对克钦湖水体叶绿素a浓度的监测,于2010年8月15日对克钦湖进行了现场光谱测量和同步采样。通过分析叶绿素a浓度和光谱数据之间的关系,建立基于反射比、人工神经网络和遗传神经网络的叶绿素a浓度估测模型。结果表明:利用R700nm/R670nm反射比建立的模型估测精度为R2=0.67;人工神经网络模型的估测精度较高,R2=0.882;将遗传算法引入神经网络之后,模型的估测精度进一步提高,R2达到0.956,将模型预测的结果与克里格内插法相结合对研究区的叶绿素a空间分布情况进行定量估测,发现北湖的叶绿素a浓度明显高于南湖,有由北向南逐渐递减的趋势,这为今后利用高光谱数据对克钦湖叶绿素a浓度大面积遥感反演提供了研究基础。     

基于核混合效应回归模型的地震数据预测

针对地震观测数据难以准确预测的难题,提出基于核混合效应回归模型。为验证该算法模型的可行性,结合湖北地震台站地球物理仪器产出数据开展仿真实验,并与传统的神经网络算法作对比。结果表明,该模型能准确预测地震地球物理观测数据且性能优于其他神经网络算法,对水温、水位数据的预测相对误差低于0.05%及0.48%。该研究为地震监测预报人员积累、分析地震基础数据提供了全新思路,同时也为较复杂的深度学习类算法框架模型的构建提供了实践基础。     

土壤水分微波反演方法进展和发展趋势

土壤水分是连接地表水循环和能量循环的关键参量,精确获取该参量对于理解气候变化、地表水文过程、地气间能量交换机理等具有重要意义。微波遥感由于其较为合适的探测深度和坚实的理论基础在观测地表浅层土壤水分上具有很大优势,结合反演方法可以获取空间连续的土壤水分含量,有助于更加客观认知土壤水分的时空演变机理。随着微波遥感数据的不断丰富,多种微波遥感土壤水分反演方法相继涌现,为了更好地了解其发展和趋势,本文总结了当前土壤水分微波反演常用的卫星遥感数据并分析其发展趋势,后从主动微波反演、被动微波反演和多源协同反演3个方面梳理了各类土壤水分微波反演方法的原理、发展和优缺点,最终总结出目前微波遥感土壤水分反演方法的发展趋势：即土壤水分微波反演方法的时空普适性逐渐增强、面向高时空分辨率的土壤水分微波协同反演方法快速发展以及土壤水分微波反演方法的智能化水平不断提高。     

Groundwater use and policy in community water supply in Finland

Selection between ground and surface water in community water supply has been one of the key strategic questions in Finland since the early 1900s. After some cities failed to find reliable groundwater sources, many turned to surface waters. Since the 1950s the use of groundwater and artificial recharged groundwater have continuously increased. Presently their use is promoted by the government and European water policy through technical advice and financial support. It is obvious that the share of groundwater and artificial recharged groundwater will increase in the future. This requires active public response and transparency in decision-making.

---

Resumen Desde el principio de 1900 una de las preguntas estratégicas clave en Finlandia es la selección entre agua subterranea y de superficie para el suministro de agua de la comunidad. Muchas ciudades renunciaron al agua de superficie luego de haber fracesado en encontrar fuentes de agua subterránea confiables. Desde 1950 el uso de agua subterránea y de agua subterránea recargada artificialmente ha aumentado continuamente. Actualmente los políticas de agua del gobierno y de Europa promueven su uso por medio de asesoría técnica y apoyo financiero. Es obvio que la participación del agua subterránea y del agua subterránea recargada artificialmente va a aumentar en el futuro. Esto requiere una respuesta activa pública y transparencia en el proceso de toma de decisiones.

---

Resumé Le choix parmi lutilisation de leau de surface ou de leau souterraine comme source dapprovisionnement en eau potable est, depuis le début des années 1900, une question stratégique en Finlande. Suite à léchec de certaines villes à sapprovisionner en eau souterraine, plusieurs se sont tournées vers leau de surface. Depuis les années 1950, lutilisation de leau souterraine et la recharge artificielle des aquifères est en constante croissance. Actuellement, leur utilisation est encouragée par le Gouvernement ainsi que par la politique européenne de leau qui fournit une expertise technique et un soutient financier. Il est évident que les proportions occupées par lapprovisionnement en eau souterraine et la recharge artificielle vont augmenter avec le temps. Ceci requiert une participation active du public ainsi que de la transparence lors du processus décisionnel.

     

Removing cosmic-ray hits from CCD images in real-time mode by means of an artificial neural network

A feed-forward artificial neural network has been implemented to the problem of removing cosmic-ray hits (CRH) from CCD images. The results of a number of tests demonstrate the effectiveness of this method especially for undersampled stellar profiles. The problem of optimal and low price preparing of training data, which could enable real-time or at least fast post-processing filtering out of CRH is discussed. The training and test ensembles were composed of a number of synthetic stellar profiles involving different S/N ratios and CRH images taken from real data. Certain aspects of the network’s architecture and its training efficiency for different modes of the back-propagation procedure as well as for the pre-process normalization of data have been examined. It is shown that for training set composed of stellar images and CRH at a ratio of 1:2 recognition can reach 99% in the case of stars and 96% for CRH. To determine the extent to which the cognition power of a network trained using an ensemble of circular symmetric stellar profiles of a given radius can be generalised the test data included stellar profiles of different radii, as well as elongated profiles. The goal was to mimic temporal changes in seeing as well as such problems as image defocusing, the lack of isoplanatism and improper sideral tracking of a telescope. The experiments provided us with the conclusion that for S/N > 10 excellent classification property is maintained in cases where the change in the radius of a circular profile is up to 30%, as well as for elongated profiles where the longest dimension is almost double that of the shortest one. Moreover, the generalization capability has been investigated for test images of synthetic pairs of overlapping stars with different distances between components. Almost 99% recognition efficiency was achieved even if the separation was nearly three times the radius of the stellar profile, a case when two stars could be analyzed by appropriate software as separate objects. The example of removal of CRH from real CCD images is presented to give an idea of how an algorithm based on a neural network can work in practice. The result of such an experiment appears fully consistent with the conclusions drawn from the tests made on synthetic data.