BP及RBF人工神经元网络对臭氧生物活性炭水处理系统建模的比较

运用BP和RBF人工神经元网络建立臭氧生物活性炭系统模型,考察了两个网络对水处理系统建模的适应性。研究表明,BP和RBF人工神经元网络的臭氧生物活性炭系统模型准确地描述了系统影响因素的关系,可以求出系统中臭氧的经济投量;用BP人工神经元网络建立水处理系统模型,泛化能力好,但逼近速度较慢;运用RBF人工神经元网络建模,泛化能力较差,但逼近速度快。该项研究克服了运用传统方法建模的不足,为实现水处理系统的优化设计提供了可行的途径。     

重庆酸雨对陆地生态系统的影响和控制对策——中日酸雨合作研究总结

中日合作研究项目：酸沉降对陆地生态系统的影响及其控制对策的研究,于１９９０至１９９５年期间在中国重庆地区进行。本文是该项目最终研究结果主要方面的报导,包括大气污染和酸雨的状况,酸沉降对池塘、森林和土壤生态系统的影响以及大气污染和酸雨控制对策。该项研究为今后酸沉降生态监测的研究,打下了有力的基础。     

酸化模型及其发展趋势评述

本文将酸化模型分为指标评价模型、经验酸化模型和以湖泊－流域为基础的机理模型三大类。概述了几个典型的酸化模型的结构、对参数和过程的处理方法、存在的问题和应用范围并介绍了它们的一些具体应用。还以ＭＡＧＩＣ模型为例说明了酸化模型的发展及其趋势。作为模型的一个有机组成部分,本文还阐述了酸化模型的不确定性分析。     

酸化模型及其在确定酸沉降临界负荷中的应用

简述了国外近１０年来在酸沉降影响研究中,为预测酸沉降对土壤、地表水、地下水和湖泊的长期影响而开发的各种酸化模型,经比较分析,归纳出建立这此匠基本方法及应用于确定酸沉降临界负葆的基本原理。     

厦门地区酸沉降现状研究

在1992～1994年,厦门地区进行了降水的连续监测?结果表明:厦门地区降水已呈酸性,其年均pH值范围为4.48～5.09,酸雨的频率为46%～92%;降水酸化的季节性变化明显,四季的降水酸化程度顺序为春季>冬季>夏季>秋季;降水中的主要阴离子为SO2-₄,表明厦门地区的酸雨为硫酸型,其降水酸性呈逐年增加的趋势。      

湖北省连阴雨的分析

从农业气候角度，重点讨论湖北春秋雨季连阴雨的时空分布，形成原因和对农业生产的影响，首次较为系统地利用模糊聚类方法对湖北省连阴雨进行分区，对各区连阴雨的时空变化规律作了较深入的探讨。最后找出影响湖北省连阴雨的天气系统主要是北方冷空气的频繁活动。用回归分析方法找出连阴雨与我省西部北部上空５００ｈｐａ高空环流指数有明显的相关关系。     

Approximating SWAT Model Using Artificial Neural Network and Support Vector Machine1

Abstract: With the popularity of complex, physically based hydrologic models, the time consumed for running these models is increasing substantially. Using surrogate models to approximate the computationally intensive models is a promising method to save huge amounts of time for parameter estimation. In this study, two learning machines [Artificial Neural Network (ANN) and support vector machine (SVM)] were evaluated and compared for approximating the Soil and Water Assessment Tool (SWAT) model. These two learning machines were tested in two watersheds (Little River Experimental Watershed in Georgia and Mahatango Creek Experimental Watershed in Pennsylvania). The results show that SVM in general exhibited better generalization ability than ANN. In order to effectively and efficiently apply SVM to approximate SWAT, the effect of cross‐validation schemes, parameter dimensions, and training sample sizes on the performance of SVM was evaluated and discussed. It is suggested that 3‐fold cross‐validation is adequate for training the SVM model, and reducing the parameter dimension through determining the parameter values from field data and the sensitivity analysis is an effective means of improving the performance of SVM. As far as the training sample size, it is difficult to determine the appropriate number of samples for training SVM based on the test results obtained in this study. Simple examples were used to illustrate the potential applicability of combining the SVM model with uncertainty analysis algorithm to save efforts for parameter uncertainty of SWAT. In the future, evaluating the applicability of SVM for approximating SWAT in other watersheds and combining SVM with different parameter uncertainty analysis algorithms and evolutionary optimization algorithms deserve further research.     

Using SWAT to Model Streamflow in Two River Basins With Ground and Satellite Precipitation Data1

Abstract: Both ground rain gauge and remotely sensed precipitation (Next Generation Weather Radar – NEXRAD Stage III) data have been used to support spatially distributed hydrological modeling. This study is unique in that it utilizes and compares the performance of National Weather Service (NWS) rain gauge, NEXRAD Stage III, and Tropical Rainfall Measurement Mission (TRMM) 3B42 (Version 6) data for the hydrological modeling of the Middle Nueces River Watershed in South Texas and Middle Rio Grande Watershed in South Texas and northern Mexico. The hydrologic model chosen for this study is the Soil and Water Assessment Tool (SWAT), which is a comprehensive, physical‐based tool that models watershed hydrology and water quality within stream reaches. Minor adjustments to selected model parameters were applied to make parameter values more realistic based on results from previous studies. In both watersheds, NEXRAD Stage III data yields results with low mass balance error between simulated and actual streamflow (±13%) and high monthly Nash‐Sutcliffe efficiency coefficients (NS > 0.60) for both calibration (July 1, 2003 to December 31, 2006) and validation (2007) periods. In the Middle Rio Grande Watershed NEXRAD Stage III data also yield robust daily results (time averaged over a three‐day period) with NS values of (0.60‐0.88). TRMM 3B42 data generate simulations for the Middle Rio Grande Watershed of variable qualtiy (MBE = +13 to ?16%; NS = 0.38‐0.94; RMSE = 0.07‐0.65), but greatly overestimates streamflow during the calibration period in the Middle Nueces Watershed. During the calibration period use of NWS rain gauge data does not generate acceptable simulations in both watersheds. Significantly, our study is the first to successfully demonstrate the utility of satellite‐estimated precipitation (TRMM 3B42) in supporting hydrologic modeling with SWAT; thereby, potentially extending the realm (between 50°N and 50°S) where remotely sensed precipitation data can support hydrologic modeling outside of regions that have modern, ground‐based radar networks (i.e., much of the third world).     

应用电性拓扑状态指数预测烷烃自燃点

建立了一个基于人工神经网络的定量结构-性质相关性模型,用于52种烷烃化合物自燃点的预测研究。应用原子类型电性拓扑状态指数作为表征分子结构特征的描述符。该指数既能表征分子的电子特性,又反映其拓扑特征,同时易于计算,并有较强的同分异构体区分能力。采用误差反向传播（BP）神经网络方法对烷烃自燃点与电性拓扑状态指数间可能存在的非线性关系进行拟合。将52种烷烃样本随机划分为训练集（30种）、验证集（8种）和测试集（14种）,并通过“试差法”确定网络的最优参数。运用最佳网络结构[64—1]对实验样本进行模拟,结果表明,多数样本的自燃点预测值与实验值符合良好,对于测试集,平均预测绝对误差为8．4℃,均方根误差为11．8,优于多元线性回归方法和传统基团贡献法所得结果。该方法的提出为工程上提供了一种根据分子结构预测有机物白燃点的有效方法。     

不同恢复年限刺槐林土壤碳、氮、磷含量及其生态化学计量特征

地处西秦岭山地的甘肃天水吕二沟小流域土壤侵蚀问题严重,上世纪五六十年代开始,当地政府在研究区实施了多年的生态恢复措施以保持水土,但目前尚未有植被恢复对土壤生态计量特征的系统调查.分析不同林龄人工林土壤碳、氮、磷含量及其生态化学计量特征可在一定程度上揭示土壤养分的限制情况.选取黄土丘陵沟壑区不同生长年限(5、20、40、...