Assessing Linkages in Stream Habitat,Geomorphic Condition,and Biological Integrity Using a Generalized Regression Neural Network

Watershed managers often use physical geomorphic and habitat assessments in making decisions about the biological integrity of a stream, and to reduce the cost and time for identifying stream stressors and developing mitigation strategies. Such analysis is difficult since the complex linkages between reach‐scale geomorphic and habitat conditions, and biological integrity are not fully understood. We evaluate the effectiveness of a generalized regression neural network (GRNN) to predict biological integrity using physical (i.e., geomorphic and habitat) stream‐reach assessment data. The method is first tested using geomorphic assessments to predict habitat condition for 1,292 stream reaches from the Vermont Agency of Natural Resources. The GRNN methodology outperforms linear regression (69% vs. 40% classified correctly) and improves slightly (70% correct) with additional data on channel evolution. Analysis of a subset of the reaches where physical assessments are used to predict biological integrity shows no significant linear correlation, however the GRNN predicted 48% of the fish health data and 23% of macroinvertebrate health. Although the GRNN is superior to linear regression, these results show linking physical and biological health remains challenging. Reasons for lack of agreement, including spatial and temporal scale differences, are discussed. We show the GRNN to be a data‐driven tool that can assist watershed managers with large quantities of complex, nonlinear data.     

基于随机搜索优化XGBoost的瓦斯涌出量预测模型*

为防治瓦斯灾害,解决井下瓦斯涌出量在预测过程中因影响因素繁多带来的精度较低问题,提出1种基于套索(Lasso)回归与随机搜索优化极限梯度提升(XGBoost)的模型进行瓦斯涌出量预测。以沈阳某煤矿综采面瓦斯涌出量历史数据为例,综合考虑影响瓦斯涌出量的影响因素。首先利用Lasso回归提取对瓦斯涌出量有重要影响的特征数据,作为预测输入;采用随机搜索算法对XGBoost模型4种主要参数进行寻优,选取最优参建立预测模型获得预测指标并分析比较其他模型。研究结果表明:Lasso回归筛选出的影响因素结合随机搜索获得的最优参数组合优化XGBoost比其他模型预测精度更高,平均相对误差为1.53%,均方根误差为0.140 3 m3/min,希尔不等系数为0.013 2,研究结果可为现场瓦斯管理提供参考依据。     

基于Logistic回归模型的大兴安岭地区林火发生概率预测研究*

为实现对大兴安岭地区林火发生概率的基本预测,根据该地区历史火灾资料、地形因子、气象因子和人为因子,基于Logistic回归模型建立该地区林火发生概率预测模型。研究结果表明:坡度、海拔、平均气压、平均气温、平均相对湿度、最小相对湿度是该地区林火发生的主要驱动因子;坡度、海拔、平均气压、平均气温与林火发生概率呈正相关,平均相对湿度和最小相对湿度与林火发生概率呈负相关;ROC曲线下面积值（AUC）为0.91,最佳临界值为0.425;建立的大兴安岭地区林火发生概率预测模型,建模样本总体准确率为82.4%,验证样本总体准确率为80.5%;该地区夏季林火发生概率明显高于春、秋季;林火发生概率较高的Ⅳ级和Ⅴ级火险区主要集中在夏季该地区东南部、西部以及春、秋季该地区东南部。研究结果可为该地区林火预测提供1种参考方法。     

基于PCA-PNN的采空区多源指标危险性辨识*

为了提高采空区多源指标危险性辨识的预测精度,基于主成分分析（PCA）和概率神经网络（PNN）,提出1种采空区多源指标危险性辨识方法。将影响华东某地区矿山采空区危险性辨识的9项因素作为主要影响因素,并以96个实测采空区为例进行分级。研究结果表明:与朴素贝叶斯、随机森林和AdaBoost 3种机器学习算法相比,PNN在测试集上表现更好,对实际工程具有良好的指导意义和应用价值。     

Differences in the quality of steamed hull-less barley and wheat cakes北大核心CSCD

In this study, three different hull-less barley varieties were used to prepare steamed cakes, and their nutritional value, sensory qualities, textural properties, and in vitro starch hydrolysis were evaluated. The results showed that the contents of total dietary fiber (4.50%-5.12%), β-glucan (2.96%-3.96%), total flavonoids (12.56-38.73 mg/100 g), and γ-aminobutyric acid (5.08-9.53 mg/100 g) in the steamed hull-less barley cakes were significantly higher than that in the steamed wheat cake, which were 0.65%, 0.23%, 3.93 mg/(100 g), and 2.63 mg/(100 g), respectively. The sensory properties of steamed ordinary hull-less barley and wheat cakes were not significantly different, but the steamed 08-1127 (waxy hull-less barley) cake was softer and out of shape. The springiness, resilience, cohesiveness, gumminess, and adhesiveness of steamed ordinary hull-less barley cakes were similar to those of steamed wheat cake, while those of steamed 08-1127 cakes were significantly lower than those of steamed ordinary hull-less barley cakes. Steamed hull-less barley cake also showed a maximum starch hydrolysis rate (38.76%-42.74%) that was lower than that of steamed wheat cake (49.92%), and the contents of rapidly (11.58%-13.16%) and slowly digested starch (5.34%-7.56%) were lower than that of steamed wheat cake (17.21% and 15.97%, respectively). In addition, the glycemic (59.37-61.67) and hydrolysis indexes (35.82-40.00) were lower than those of steamed wheat cake (76.66 and 67.30, respectively), and the contents of resistant starch (2.74%-3.55%) were higher than those of wheat steamed cake (1.68%). Therefore, the steamed cakes of ordinary hull-less barley had a higher content of nutritional components than the steamed cake of wheat, and the in vitro starch hydrolysis parameters were better than those of steamed wheat cake. When it is necessary to consider both nutritional and sensory qualities, ordinary hull-less barley can be selected as the raw material for steamed cakes, but waxy hull-less barley is not suitable for making steamed cakes. © 2022 Science Press. All rights reserved.     

便携式气相色谱-氢火焰离子化检测器法测定低浓度总烃的氧气干扰特征研究

研究了采用便携式气相色谱-氢火焰离子化检测器法测定气体中的总烃浓度时,氧气浓度对测定结果的影响,并采用多元线性回归模型对总烃的测定结果进行了校准。当总烃的实际浓度不低于9 mg/m³时,氧气的干扰较小(相对标准偏差≤2%)。在试验的所有总烃实际浓度下(1~200 mg/m³),当氧气浓度为1%~7%时,也无需考虑氧气干扰的影响(相对标准偏差≤2%)。当总烃的实际浓度低于9 mg/m³且氧气浓度为9%~21%时,需依据多元线性回归分析原理并采用模型对测得的总烃浓度进行校准。线性回归方程分析结果显示,模型拟合情况良好(R²=0.999),可以用来修正测试结果,从而得到更加准确的总烃实际浓度。     

重点生态功能区生态资产保护成效及驱动力研究

重点生态功能区是保障国家生态安全、扩大绿色生态空间的重要区域,在实现全国生态资产保值增值方面发挥着重要作用。然而,现阶段围绕重点生态功能区生态资产保护成效及驱动力开展的研究较少。为明确重点生态功能区生态资产保护的驱动力以及存在的问题,本文利用遥感影像并结合图像解译、GIS空间分析和数理统计等方法对重点生态功能区内生态资产展开分析,并将其与非重点生态功能区进行比较。研究结果显示:重点生态功能区内森林、灌丛、草地和湿地生态资产总面积为349.30万km~2,优级和良级生态资产占生态资产总面积的42.42%,生态资产综合指数为21.19。15年间,重点功能区内生态资产总面积增加0.05%,优级和良级生态资产面积占比分别增加0.59%和0.85%,生态资产综合指数增加2.94。重点生态功能区生态资产面积和质量增幅均小于非重点生态功能区,然而重点生态功能区生态资产指数增量高于非重点生态功能区。生态恢复是驱动重点生态功能区生态资产面积变化的主因,对原有生态资产的保护是促进生态资产指数增加的最主要驱动力(贡献率达81%),城镇化和农业开发对生态资产的不利影响不容忽视(贡献率达-6.81%)。研究表明,对重点生态功能区生态资产保护成效显著,同时还有较大提升空间。本研究也为优化重点生态功能区的城镇化和农业开发的管理提供了证据和参考。     

广州市交通环境承载力变化的相关性分析

根据广州市的统计资料,分析了广州市交通环境承载力的变化态势,应用主成分分析方法定量分析了交通环境承载力变化的宏观驱动因子。结果表明:经济发展动态和社会系统压力是影响广州市交通环境承载力变化的主要驱动因素。结合主成分分析结果构建了多元线性回归模型,预测了2010和2015年广州市交通环境承载力的变化趋势,为政府部门规划城市交通规模及实现城市交通可持续发展提供决策依据。     

基于GIS的太湖蓝藻预警系统研究

蓝藻爆发恶化了太湖水质,严重降低了太湖的使用功能。文章分析太湖蓝藻爆发的影响因素,结合预警模型和GIS技术,描述了太湖蓝藻预警系统的设计与实现流程,为太湖蓝藻预警提供科学、合理的辅助决策支持。     

SPSS 10.0在实验数据分析中的应用

主要介绍如何把SPSS10.0这个软件应用于实验数据分析之中。该软件包括了几种实验数据分析中常用的统计方法如:样本检验、均数比较分析、方差分析、回归分析、偏相关分析、曲线拟合、时间序列分析、聚类分析、主成分分析法、因子分析等。