基于自组织映射与随机森林耦合模型的流域水质空间差异性评估

流域水环境质量空间分布特征分析是推进流域精细化管理的基础.本研究基于流域特征指标与水质的关联性,以子流域为分析单元,利用自组织映射人工神经网络模型（SOM）对苕溪流域水质数据聚类分析为3类后与随机森林模型（RF）进行耦合,对全流域水质进行了空间差异性评估.研究结果显示,上游山地区域水质较好,而平原河网人口集聚区的COD_Mn、NH₃-N及TP浓度较高,山地与平原过渡地带水质则主要受到COD_Mn和TN的影响.采用自然环境、社会经济及土地利用/覆盖指标作为流域特征进行水质分级模式识别,SOM与RF模型耦合模型的准确率稳定在80%左右;在对强相关性特征进行筛选识别后,将蒸发蒸腾量、坡度、人口密度、大于10℃积温、旱地占比、城镇用地占比及景观多样性指数为作为输入特征,准确率可达83%,可以有效地开展全流域水质分级评估.     

有机磷酸酯在重庆不同城市功能区土壤的分布特征及来源

本研究利用超高效液相色谱飞行时间质谱(UPLC-Q-TOF~-MS)检测分析了重庆市4个不同功能区城市表层土壤中12种有机磷酸酯(organophosphate esters,OPEs)含量水平,探讨了其组成特征,通过相关性分析讨论了土壤有机质(soil organic matter,SOM)与ΣOPEs及各单体含量之间的关系,利用主成分分析阐述了OPEs可能的来源.结果表明,ΣOPEs含量(以干重计,下同)范围为10. 7～108 ng·g~(-1),平均值为46. 4 ng·g~(-1),处于国内外较低水平;不同功能区土壤中ΣOPEs平均含量大小依次为:工业区(55. 6 ng·g~(-1)),住宅区(55. 5 ng·g~(-1)),商业区(41. 8 ng·g~(-1)),城市公园(34. 1 ng·g~(-1)).磷酸三(2-氯异丙基)酯(TCPP)和2-乙基己基二苯基磷酸酯(EHDPP)是主要OPEs污染物单体,TCPP在工业区土壤贡献率最高达到了31. 5%,而EHDPP在商业区和城市公园贡献率最高分别为23. 4%和24. 7%.相关性分析表明SOM含量和ΣOPEs含量呈显著相关(P 0. 05),和单体磷酸三甲苯酯(TCP)含量呈极显著相关(P 0. 01),表明SOM是影响OPEs分布的因素之一.主成分分析表明城市土壤OPEs来源并不单一,污水灌溉、路面径流、室内源污染及污泥再利用等都可能成为土壤OPEs潜在来源途径.     

Modeling soil and plant phosphorus within DSSAT

The crop models in the Decision Support System for Agrotechnology Transfer (DSSAT) have served worldwide as a research tool for improving predictions of relationships between soil and plant nitrogen (N) and crop yield. However, without a phosphorus (P) simulation option, the applicability of the DSSAT crop models in P-deficient environments is limited. In this study, a soil-plant P model integrated to DSSAT was described, and results showing the ability of the model to mimic wide differences in maize responses to P in Ghana are presented as preliminary attempts to testing the model on highly weathered soils. The model simulates P transformations between soil inorganic labile, active and stable pools and soil organic microbial and stable pools. Plant growth is limited by P between two concentration thresholds that are species-specific optimum and minimum concentrations of P defined at different stages of plant growth. Phosphorus stress factors are computed to reduce photosynthesis, dry matter accumulation and dry matter partitioning. Testing on two highly weathered soils from Ghana over a wide range of N and P fertilizer application rates indicated that the P model achieved good predictability skill at one site (Kpeve) with a final grain yield root mean squared error (RMSE) of 535 kg ha⁻¹and a final biomass RMSE of 507 kg ha⁻¹. At the other site (Wa), the RMSE was 474 kg ha⁻¹ for final grain yield and 1675 kg ha⁻¹ for final biomass. A local sensitivity analysis indicated that under P-limiting conditions and no P fertilizer application, crop biomass, grain yield, and P uptake could be increased by over 0.10% due to organic P mineralization resulting from a 1% increase in organic carbon. It was also shown that the modeling philosophy that makes P in a root-free zone unavailable to plants resulted in a better agreement of simulated crop biomass and grain yield with field measurements. Because the complex soil P chemistry makes the availability of P to plants extremely variable, testing under a wider range of agro-ecological conditions is needed to complement the initial evaluation presented here, and extend the use of the DSSAT-P model to other P-deficient environments.     

应用过硫酸盐氧化法预测焦化厂土壤中PAHs的生物有效性

采用过硫酸盐氧化法测定了北京市某焦化厂表层土壤中16种PAHs的生物有效性,并分析了过硫酸盐氧化前、后SOM(土壤有机质)的质量分数及其结构组成,以研究过硫酸盐氧化法预测焦化厂土壤中PAHs生物有效性方面的可行性. 结果表明:①7个供试土壤样品中w(∑PAHs)(16种PAHs质量分数之和)为10.80~249.00 mg/kg,并以HPAHs(高分子量PAHs)为主,不同环数PAHs的质量分数与w(SOM)均呈正相关,二者关系符合对数方程(R2为0.653~0.798). ②依据过硫酸盐氧化前、后土壤中w(PAHs)的变化得到PAHs的生物有效性,其中,2~3环PAHs的生物有效性平均值为0.46,略高于4环PAHs(0.22)和5~6环PAHs(0.28),较高w(SOM)及HPAHs均易引起焦化厂土壤中PAHs生物有效性的下降. ③过硫酸盐氧化前不同环数PAHs的质量分数与氧化后PAHs的残留量呈显著正相关(R2为0.991~0.994),故可利用过硫酸盐氧化前的w(PAHs)预测土壤中PAHs的生物有效性. ④与过硫酸盐氧化前相比,氧化后土壤中w(SOM)平均下降23.0%,FTIR(傅里叶变换红外光谱)分析结果显示,1 448 cm-1处吸收峰表征的脂肪碳可能是被氧化去除的软质碳的主要组分,氧化后SOM中的芳香碳相对吸光度增幅为0.88%~11.62%,可引起SOM的缩合程度加剧、憎水性增强. 因此,过硫酸盐氧化法能够作为测定焦化厂土壤中PAHs生物有效性的快速方法,可利用过硫酸盐氧化前的w(PAHs)预测土壤中PAHs的生物有效性.      

深圳市水库水质SOM网络分析与评价

运用SOM网络对深圳市12个主要饮用水源水库水质进行了分析评价.结果表明水源水库按水质状况可划分为4种类型,从第1类到第4类,水污染程度依次加重;SOM网络能兼顾对单个水质指标监测数据和整体数据的分析,正确反映水质污染格局状况.提出了保护水库水质对策与建议.     

海面溢油油种激光遥感ANN探测方法的研究

目前激光荧光遥感是探测海面溢油最有效的工具。作者将神经网络(ANN)的自组织特征映射SOM模型引入激光遥感的荧光光谱鉴别领域。本文主要进行的是理论建模和分析工作，而且用计算机软件方法实现了神经网络的模式识别和分类功能，对推广能力进行了实验分析。经过改进神经网络已具有比较理想的推广能力，并认为SOM应作为溢油识别的较理想方法。     

基于SOM模型的中国耕地压力分类研究

根据耕地利用在经济、社会和生态方面面临的压力状况,以指标构建原则为基础,设计一套压力大小量化的指标体系,引入具有较强的聚类和容错能力的自组织特征映射(SOM)神经网络模型,在说明SOM 网络模型和算法的基础上,应用自组织特征映射网络的聚类功能,以MATLAB语言构建SOM网络模型,对我国的31省（市、自治区）耕地利用压力大小进行了分类。结果显示我国耕地压力的区域差显著且与经济地域差异有高度的一致性,表明经济发展是耕地压力的主要来源。选取大样本的神经网络训练得到的结果和现实的一致也表明,自组织特征映射模型是一种适用的耕地压力区域分类新方法。     

Modelling dynamics of soil organic matter under different historical land-use management techniques in European Russia

We have analyzed an influence of the traditional agricultural system techniques on the soil organic matter dynamics using the model of carbon and nitrogen cycling in forest ecosystems EFIMOD linked with the model of SOM dynamics ROMUL. Forest stands on the loamy soddy-podzolic soils (Alfisoils) located in the Central European Russia have been taken for the case study. The following land-use management scenarios were simulated: (a) slash-and-burn system with 3 years for crops and 120, 60 and 25 years for forest; (b) three-field crop rotation system with organic fertilization (dung) every 3 and 9 years and the same rotation without fertilization; and (c) short-term field-forest shifting system with 10 years for crops and 10 and 25 years for forest. Analysis of the results showed that the frequency of agricultural use in mixed field-forest land-use systems was crucial for soil organic matter dynamics. Under the short interval between agriculture, the stocks of all soil organic matter pools decreased. Under all scenarios except the three-field crop rotation with fertilization and the slash-and-burn system with 120 years for forest, a strong reduction of soil organic matter occurred after 30-130 years of the agricultural impacts. The highest reduction rates were modelled under the short-term field-forest shifting system and three-field rotation without fertilization. Fertilization led to stabilization of soil organic matter pools and gave a possibility for a long time stable agricultural use.     

象山港海域水质时空格局的自组织特征映射神经网络识别

于2007—2008年对象山港23个站点(包括10个电厂站点)的水质样品进行连续2年的季节性采集,采用SOM(Self-Organizing Map)工具箱,结合k-nn(knearest neighbors)神经元聚类对15个水质参数进行分析,以探明象山港海域水质时空变化并识别敏感的影响区域.结果显示,象山港海域N/P(物质的量比)平均值为27.0.水体污染指数(AI)和海水营养指数(NI)分别指示整个象山港水质处于严重污染和富营养化状态,但水质加权指数(WDX)显示,加权水质标准未超过3类水质,说明传统的AI和NI指数不能反映象山港的实际水质状况.经SOM分析发现,象山港海域各取样站点按季节和空间格局可分为8个聚类组.从季节上看,pH和油类含量在春季最低;夏季水温、COD、NO2--N最高,而DO最低.NO3--N、DIN、DIP在秋冬季节高于春夏季节,但透明度相反.Chl-a含量以夏季最高,冬季最低.GLM(General Linear Model)方差分析显示,不同季节的安全性指数(SFT)和N/P无显著差异(p>0.05),而NI、AI和WDX差异极显著(p<0.01).空间分析显示,象山港水体可分为港底区和口中部区,其中,港底区盐度、pH显著低于口中部区(p<0.01),而NO2--N、NH4+-N、DIN、DIP、Chl-a则显著高于口中部区(p<0.05).除WDX无显著差异外,港底区的N/P显著低于口中部区(p<0.01),而NI、AI、SFT相反(p<0.05).建议港区底部宜采用养殖大型海藻方式以减轻富营养化,此外,冬季黄墩港的水体中粪大肠菌群严重超标,生食该季节贝类产品时需要检测.