SOIL SALINITY PREDICTION USING ARTIFICIAL NEURAL NETWORKS1

ABSTRACT: This study explores the applicability of Artificial Neural Networks (ANNs) for predicting salt build‐up in the crop root zone. ANN models were developed with salinity data from field lysimeters subirrigated with brackish water. Different ANN architectures were explored by varying the number of processing elements (PEs) (from 1 to 30) for replicate data from a 0.4 m water table, 0.8 m water table, and both 0.4 and 0.8 m water table lysimeters. Different ANN models were developed by using individual replicate treatment values as well as the mean value for each treatment. For replicate data, the models with twenty, seven, and six PEs were found to be the best for the water tables at 0.4 m, 0.8 m and both water tables combined, respectively. The correlation coefficients between observed salinity and ANN predicted salinity of the test data with these models were 0.89, 0.91, and 0.89, respectively. The performance of the ANNs developed using mean salinity values of the replicates was found to be similar to those with replicate data. Not only was there agreement between observed and ANN predicted salinity values, the results clearly indicated the potential use of ANN models for predicting salt build‐up in soil profile at a specific site.     

FLOOD STAGE FORECASTING WITH SUPPORT VECTOR MACHINES1

ABSTRACT: Machine learning techniques are finding more and more applications in the field of forecasting. A novel regression technique, called Support Vector Machine (SVM), based on the statistical learning theory is explored in this study. SVM is based on the principle of Structural Risk Minimization as opposed to the principle of Empirical Risk Minimization espoused by conventional regression techniques. The flood data at Dhaka, Bangladesh, are used in this study to demonstrate the forecasting capabilities of SVM. The result is compared with that of Artificial Neural Network (ANN) based model for one‐lead day to seven‐lead day forecasting. The improvements in maximum predicted water level errors by SVM over ANN for four‐lead day to seven‐lead day are 9.6 cm, 22.6 cm, 4.9 cm and 15.7 cm, respectively. The result shows that the prediction accuracy of SVM is at least as good as and in some cases (particularly at higher lead days) actually better than that of ANN, yet it offers advantages over many of the limitations of ANN, for example in arriving at ANN's optimal network architecture and choosing useful training set. Thus, SVM appears to be a very promising prediction tool.     

智能型地理信息系统（AIGIS）在城市抗震防灾规划中的应用

本文简要介绍地理信息系统GIS的发展概况、主要功能以及在国内外的应用现状.对现有的GIS软件技术加以改进,引进人工神经元网络和模糊综合评判技术,发展了一种智能型的GIS,在我国若干城市的抗震设防区划工作中应用,取得良好的效果。     

WATER QUALITY PREDICTION WITHIN AN INTERBASIN TRANSFER SYSTEM1

ABSTRACT A methodology for predicting the spatial and temporal levels of conservative water quality constituents within a multibasin water resource system is presented. Dissolved solids, sulfates, and chlorides are the constituents used during this investigation; however, any other conservative ion or mineral can be incorporated into the simulation model. The methodology is tested on the proposed Texas Water System. The water quality model, QNET-I, utilizes monthly canal and river flows and reservoir storage levels calculated by the Texas Water Development Board's systems simulation model. Discharge-concentration relationships are developed for each source of water in the system, including significant waste-water discharges. Reservoirs in the system are assumed to be completely mixed with respect to conservative constituents. A mass balance analysis is performed for each node and each month during the simulation period. The output from the water quality simulation is a table of the concentrations of the conservative water quality constituents at each demand point in the system and in each reservoir and canal for every month the system is in operation. The desired quality of the water at the demand locations is used to determine the economic utility of transporting and mixing water from various sources.     

两种定性天气预报模型的对比分析

以南京１９６５～１９９４ 年４ 月平均气温作为预报量, 选取前期５００ ｈ Ｐａ 月平均高度场相关因子, 分别建立了事件概率回归预报模型和神经网络预报模型。通过对比分析发现, 在同等条件下,由于神经网络方法能更好地反映预报量与预报因子间的非线性关系, 并能有效避免采用事件概率回归方法预报建模时, 对预报因子分级造成信息损失的缺点。因此, 其拟合和预报效果明显优于传统的概率回归预报方法     

DEVELOPMENT OF A BASIN GEOMORPHIC INFORMATION SYSTEM USING A TIN-DEM DATA STRUCTURE1

ABSTRACT: To make a distributed rainfall-runoff model, it is very important to build a model of topographic surface of a basin which takes account of the direction of water flow. In this paper, a geographic information system in hydrologic modeling, the BGIS (Basin Geomorphic Information Systems) are presented for modeling a river basin using a TIN-DEM (Triangulated Irregular Network - Digital Elevation Model) data structure. The BGIS have two core systems, which are the TIN-DEM generating system and the topographic analysis system. In the TIN-DEM generating system, landscapes are modeled as a set of contiguous non-overlapping terangular facets whose vertices are made up of points on a regular grid DEM and on river segments. These triangular facets are subdivided, if needed, so that each of them has only one side through which water flows out. The TIN-DEM generating system is made up of four modules, (1) a module for generating triangles from a grid DEM, (2) a module for getting rid of pits, (3) a module for joining discontinuous valley segments to a channel network, (4) a module for subdividing triangular facets. In the topographic analysis system, using datasets processed with the TIN-DEM generating system, a watershed source area for any segments in a stream network are delineated automatically, and topographic attributes of slopes, aspects, flow path lengths and upslope contributing areas are computed.     

改进BP算法在煤与瓦斯突出预测中的应用

为了正确预测煤与瓦斯突出的趋势与危险性 ,基于反向BP神经网络 ,笔者提出了一种改进的BP网络模型 :为了加快BP网络的收敛速度 ,增强其跳出局部极小点的能力 ,采用了自适应变步长法和改进模拟退火法 (SA法 )相结合的方法。实际应用表明 ,该模型收敛速度快 ,准确性高 ,具有较高的可靠性和实用性 ,是一种十分有效的煤与瓦斯突出危险性预测方法。     

煤层底板采动导水破坏深度计算的神经网络方法

在综合分析影响煤层底板采动导水破坏深度因素的基础上 ,应用人工神经网络方法 ,建立了底板破坏深度的计算模型。该模型利用现场观测资料作为学习训练样本和测试样本 ,对模型的测算结果、理论计算值和实测值进行了对比分析。结果表明 :用神经网络方法计算底板破坏深度考虑的因素更加全面 ,结果更接近于实际。笔者研究的计算模型和测算方法 ,为承压水上安全采煤决策提供了科学依据。     

人工神经网络方法在资源与环境预测方面的应用

用人工神经网络方法对不同水域、不同环境因子之间非线性和不确定性的复杂关系进行学习训练并预测检验。结果表明：人工神经网络方法在模拟和预测方面 优于传统的统计回归模型,在资源与环境方面的应用是可行的。具有较强的模拟预测能力。与传统的回归模型相比,人工神经网络方法不要求监测数据具有很强的规律性,就可用后的网络模型对其进行预报,燕且预测相对误差均比回归模型预测相对误差要小,具有一定的实用性。两个实例的应用     

Stochastic Transfer Function Model and Neural Networks to Estimate Soil Moisture1

Abstract: A practical methodology is proposed to estimate the three‐dimensional variability of soil moisture based on a stochastic transfer function model, which is an approximation of the Richard’s equation. Satellite, radar and in situ observations are the major sources of information to develop a model that represents the dynamic water content in the soil. The soil‐moisture observations were collected from 17 stations located in Puerto Rico (PR), and a sequential quadratic programming algorithm was used to estimate the parameters of the transfer function (TF) at each station. Soil texture information, terrain elevation, vegetation index, surface temperature, and accumulated rainfall for every grid cell were input into a self‐organized artificial neural network to identify similarities on terrain spatial variability and to determine the TF that best resembles the properties of a particular grid point. Soil moisture observed at 20 cm depth, soil texture, and cumulative rainfall were also used to train a feedforward artificial neural network to estimate soil moisture at 5, 10, 50, and 100 cm depth. A validation procedure was implemented to measure the horizontal and vertical estimation accuracy of soil moisture. Validation results from spatial and temporal variation of volumetric water content (vwc) showed that the proposed algorithm estimated soil moisture with a root mean squared error (RMSE) of 2.31% vwc, and the vertical profile shows a RMSE of 2.50% vwc. The algorithm estimates soil moisture in an hourly basis at 1 km spatial resolution, and up to 1 m depth, and was successfully applied under PR climate conditions.