人工神经网络在南海近海面气温反演中的应用研究

基于人工神经网络方法,利用海面水温、海面风速以及海面气压反演南海近海面气温,采用的基础数据集是国际综合海洋-大气数据集(International Comprehensive Ocean-Atmosphere Data Set,2.4 Release,ICOADS2.4)1981—2008年的观测资料,其中1981—2000年的观测资料用来建立模型,2001—2008年的观测资料用来进行模型检验。采用的人工神经网络方法是引入动量因子并采用批处理梯度下降法的BP(Back propagation)算法。试验结果表明,基于人工神经网络建立的近海面气温反演方法明显优于多元线性回归方法,尤其是在春季和冬季,海面水温、海面风速以及海面气压与近海面气温之间存在较强的非线性关系,人工神经网络的优势更加明显。总体而言,人工神经网络在各月的反演效果较均衡,均方根误差介于1.5—1.8℃之间,平均绝对误差为1.1—1.3℃。     

PaleoNet: new software for building,evaluating and applying neural network based transfer functions in paleoecology

Transfer functions that implement organism–environment relationships are now commonly used for inferring past environmental conditions in paleoecology. Specific software for developing and evaluating commonly used modelling techniques such as Weighted averaging (WA), Weighted averaging partial least square (WA-PLS), Maximum likelihood (ML), and Modern analog technique (MAT) are available. A new software programme, PaleoNet, is now available for modelling organism–environment relationships which is specifically designed for the development and the evaluation of artificial neural network (ANN) based transfer functions in paleoecology. Here we present the main characteristics of this new software PaleoNet (User guide version 1.01) and discuss in more detail one of its specific features: the pruning.     

An intelligent displacement back-analysis method for earth-rockfill dams

An intelligent method for the effective displacement back-analysis of earth-rockfill dams was proposed by combining artificial neural networks and evolutionary calculation. This method employs artificial neural networks, with optimal architecture trained by the evolutionary calculation and Vogl’s algorithm, instead of the time-consuming finite element analysis. In the back analysis, the soil parameters were optimized by performing evolutionary calculations on the tested neural network. The proposed method was verified by applying it to the displacement back-analysis of two projects in China, and the influence of generation number and set size on the simulation ability of neural networks was investigated.     

87Sr/86Sr ratio: a natural tracer to monitor groundwater flow paths during artificial recharge in the Bangkok area, Thailand

The aquifer system in the Thon Buri sedimentary basin below the deltaic flood plain of the Chao Phraya River, central Thailand, has been exploited for public water supply for the capital Bangkok since the early 1920s. Groundwater withdrawal, currently 1.4 million m³/d, has resulted in a maximum decline in hydraulic head of up to 40 m. This has induced land subsidence of as much as 1.7 m (1940–1992) in the eastern suburbs of the metropolis. Artificial injection of purified water within an area-wide network of recharge wells could constitute a remedy to slow the water level depression within the sedimentary basin, and thus the subsidence. This requires a prior shutdown of water withdrawal. The flow paths of the injected water can be traced by changes in the ⁸⁷Sr/⁸⁶Sr ratio of the groundwater and injected water mixture within the three main aquifers in the basin that are used for public supply. The ratios, monitored at five monitoring stations within the cone of depression, have been constant over 3 years. Injection of the calculated cone volume of 5.2?×?10⁹ m³ would take at least 10 years, depending on the injection pressure and the number and position of wells.     

Landslide susceptibility analysis and its verification using likelihood ratio, logistic regression, and artificial neural network models: case study of Youngin, Korea

The likelihood ratio, logistic regression, and artificial neural networks models are applied and verified for analysis of landslide susceptibility in Youngin, Korea, using the geographic information system. From a spatial database containing such data as landslide location, topography, soil, forest, geology, and land use, the 14 landslide-related factors were calculated or extracted. Using these factors, landslide susceptibility indexes were calculated by likelihood ratio, logistic regression, and artificial neural network models. Before the calculation, the study area was divided into two sides (west and east) of equal area, for verification of the models. Thus, the west side was used to assess the landslide susceptibility, and the east side was used to verify the derived susceptibility. The results of the landslide susceptibility analysis were verified using success and prediction rates. The verification results showed satisfactory agreement between the susceptibility map and the existing data on landslide locations.     

Mapping Seabed Geology by Ground-Truthed Textural Image/Neural Network Classification of Acoustic Backscatter Mosaics

We present a novel, automated method for seabed classification based on shallow water backscatter mosaics from Sydney Harbour. Our approach compares the results between two different methods of image feature extraction when combined with artificial neural networks. The association of image textures with seabed geology is used to train the artificial neural networks to recognise the variability of textural attributes for three seabed classes comprising mud, sand and gravel. After network training, we classify unknown portions of the backscatter mosaic with a success rate ranging from 77% to 92%. Our results suggest that the computationally fast grey-level co-occurrence iteration algorithm holds promise for benthic habitat mapping in space and time, leading to real-time data analysis at sea.     

Feed forward Artificial Neural Network model to predict the average summer-monsoon rainfall in India

In the present research, possibility of predicting average summer-monsoon rainfall over India has been analyzed through Artificial Neural Network model. In formulating the ANN — based predictive model, three-layer network has been constructed with sigmoid non-linearity. The monthly summer monsoon rainfall totals, tropical rainfall indices and sea surface temperature anomalies have been considered as predictors while generating the input matrix for the ANN. The data pertaining to the years 1950–1995 have been explored to develop the predictive model. Finally, the prediction performance of neural net has been compared with persistence forecast and Multiple Linear Regression forecast and the supremacy of the ANN has been established over the other processes.     

南北方人工造雾的气象可行性研究

本文分析了造雾剂的成雾原理和影响成雾效果的温度、相对湿度和风速等环境因素,对典型南方城市(长沙)和北方城市(北京)的相关气象资料进行统计分析表明,南方的气候除14时外非常适合造雾,而北方02时和08时造雾完全可行,20时也存在很大的可能性。外场试验表明,由于开放空间的特点,造雾剂成雾所需的相对湿度降低,同时也由于大面积人造雾的集团效应和外场空间较高的凝水效率,使人工造雾的抗风能力加强,外场人工造雾的可行性很大。     

Using Artificial Neural Networks to Predict the Presence of Overpressured Zones in the Anadarko Basin,Oklahoma

Many sedimentary basins throughout the world exhibit areas with abnormal pore-fluid pressures (higher or lower than normal or hydrostatic pressure). Predicting pore pressure and other parameters (depth, extension, magnitude, etc.) in such areas are challenging tasks. The compressional acoustic (sonic) log (DT) is often used as a predictor because it responds to changes in porosity or compaction produced by abnormal pore-fluid pressures. Unfortunately, the sonic log is not commonly recorded in most oil and/or gas wells. We propose using an artificial neural network to synthesize sonic logs by identifying the mathematical dependency between DT and the commonly available logs, such as normalized gamma ray (GR) and deep resistivity logs (REID). The artificial neural network process can be divided into three steps: (1) Supervised training of the neural network; (2) confirmation and validation of the model by blind-testing the results in wells that contain both the predictor (GR, REID) and the target values (DT) used in the supervised training; and 3) applying the predictive model to all wells containing the required predictor data and verifying the accuracy of the synthetic DT data by comparing the back-predicted synthetic predictor curves (GRNN, REIDNN) to the recorded predictor curves used in training (GR, REID). Artificial neural networks offer significant advantages over traditional deterministic methods. They do not require a precise mathematical model equation that describes the dependency between the predictor values and the target values and, unlike linear regression techniques, neural network methods do not overpredict mean values and thereby preserve original data variability. One of their most important advantages is that their predictions can be validated and confirmed through back-prediction of the input data. This procedure was applied to predict the presence of overpressured zones in the Anadarko Basin, Oklahoma. The results are promising and encouraging.     

Remote sensing and GIS for artificial recharge study, runoff estimation and planning in Ayyar basin, Tamil Nadu, India

This paper focuses on artificial groundwater recharge study in Ayyar basin, Tamil Nadu, India. The basin is covered by hard crystalline rock and overall has poor groundwater conditions. Hence, an artificial recharge study was carried out in this region through a project sponsored by Tamil Nadu State Council for Science and Technology. The Indian Remote Sensing satellite 1A Linear Imaging Self Scanning Sensor II (IRS 1A LISS II) satellite imagery, aerial photographs and geophysical resistivity data were used to prioritize suitable sites for artificial recharge and to estimate the volume of aquifer dimension available to recharge. The runoff water available for artificial recharge in the basin is estimated through Soil Conservation Service curve number method. The land use/land cover, hydrological soil group and storm rainfall data in different watershed areas were used to calculate the runoff in the watersheds. The weighted curve number for each watershed is obtained through spatial intersection of land use/land cover and hydrological soil group through GeoMedia 3.0 Professional GIS software. Artificial recharge planning was derived on the basis of availability of runoff, aquifer dimension, priority areas and water table conditions in different watersheds in the basin.