Predicting urbanization level by main element analysis and multiple linear regression---taking Xiantao district in Hubei Province as an example

In this paper we firstly select main factors relating to urbanization level of Xiantao District in Hubei Province by main element, then, make model of urbanization level by analysis of multiple liner regression, and lastly predict its urbanization level

Correlation Analysis of Fiscal Revenue and Housing Sales Price Based on Multiple Linear Regression Model

This paper selects seven indicators of financial revenue and housing sales price in recent 19 years in China,and uses SPSS and Excel to carry out descriptive statistics,independent sample t-test,correlation analysis and regression analysis to comprehensively study the correlation between financial revenue and housing sales price in China,and establishes the relationship between financial revenue and housing sales price When the average selling price of commercial housing increases by one unit,the fiscal revenue will increase by 27.855 points.

Predicting the Acute Toxicity of Aromatic Amines by Linear and Nonlinear Regression Methods

In current paper, a quantitative structure-activity relationship （QSAR） study was performed for the prediction of acute toxicity of aromatic amines. A set of 56 compounds was randomly divided into a training set of 46 compounds and a test set of 10 compounds. The electronic and topological descriptors computed by the Scigress package and Dragon software were used as predictor variables. Multiple linear regression （MLR） and support vector machine （SVM） were utilized to build the linear and nonlinear QSAR models, respectively. The obtained models with five descriptors show strong predictive ability. The linear model fits the training set with R2 = 0.71, with higher SVM values of R2 = 0.77. The validation results obtained from the test set indicate that the SVM model is comparable or superior to that obtained by MLR, both in terms of prediction ability and robustness.

基于RF和MLR的土壤重金属影响因素分析及生物有效性预测

为探究影响土壤中重金属累积和生物有效性的因素,以桂北地区某铅锌矿流域为研究对象,综合运用单因子指数法、风险评价编码法(RAC)、多元线性回归模型(MLR)和随机森林模型(RF)进行土壤重金属(Pb、Zn、Cu和Cr)累积影响因素分析及生物有效性预测。结果表明:研究区Cr含量无超标且空间分布相对均匀(变异系数为0.51);Cu、Pb和Zn的含量均值(分别为52.58、280.31 mg·kg^(-1)和654.71 mg·kg^(-1))均大于广西西江流域土壤重金属背景值,在思的河山前和地下河入口处全量和生物有效性均较大,对土壤生态环境具有一定风险;对于重金属全量分布和生物有效态的影响因素,阳离子交换量(CEC)、黏粒(Clay)、土壤有机质(SOM)和铁铝氧化物对Cr影响较大,SOM、Clay、pH和铁铝氧化物对Cu影响较大,pH、电导率(EC)和Clay对Pb影响较大,CEC、pH、土壤质地和铁铝氧化物对Zn影响较大;生物有效性预测结果显示RF和MLR均可较好地预测土壤重金属的全量与次生相,其中RF预测的R2区间为0.44~0.93,MLR预测的R2区间为0.30~0.72,RF预测结果表现更为准确。

基于APCS-MLR模型的煤矿开采对地下水的影响定量识别

中国煤炭与水资源储量呈逆向分布,煤炭基地水资源相对短缺,生态环境脆弱。随着煤炭资源的大规模和高强度开发,区域地下水环境问题越发凸显。为定量识别煤矿开采对地下水的影响程度,以蒙东能源基地某矿区为例,通过采集矿区周边地下水化学样品进行测试,系统分析了研究区地下水水化学特征,采用相关性分析、PCA等多元统计方法确定了地下水的影响因子,据此建立了基于绝对因子得分-多元线性回归法(APCS-MLR)的定量识别模型,对研究区地下水受煤矿开采的影响贡献进行了计算分析。结果显示:研究区浅层地下水pH值为6.52~7.86,平均7.27,TDS为126.14~2240.34mg/L,平均为638.18 mg/L。主要阳离子平均含量Na^(+)>Ca^(2+)>Mg^(2+)>K^(+),主要阴离子平均含量HCO_(3)^(-)>Cl^(-)>SO_(4)^(2-)>NO_(3)^(-)。其中Cl^(-)和SO_(4)^(2-)的含量分别为4.25~779.77 mg/L和0~483.20 mg/L,其变异系数均大于100%。SO_(4)^(2-)与Na^(+)、Ca^(+)、Mg^(2+)、Cl^(-)存在显著正相关关系(r>0.72,P<0.01),TDS与SO_(4)^(2-)、Na^(+)、Ca^(+)、Mg^(2+)、Cl^(-)存在显著正相关关系。多项指标显示研究区地下水水质已经受到了煤矿开采的影响。主成分分析(PCA)解析了4个地下水影响因子,分别为煤炭开采影响因子、自然因素的硅酸盐溶解因子、自然因素的反硝化作用和农业活动的化肥使用,其占总荷载的37.061%、16.067%、14.807%和8.775%。以SO_(4)^(2-)作为煤矿开采对地下水影响的表征因子,构建了SO_(4)^(2-)来源计算分析的APCS-MLR定量识别模型。通过最小二乘法计算得到模型的各项参数,确定SO_(4)^(2-)的实际浓度和预测浓度拟合曲线为y=0.9716x+2.9702(R^(2)=0.9759),说明构建的回归方程符合实际,效果良好。据此计算了4个地下水影响因子的贡献比分别为79.3%、6.06%、2.00%和9.96%,其他未识别的因子占比2.67%。分析了煤矿开采影响地下水水质的主要方式为形成降落漏斗影响周边水化学场以及外排含有特殊组分的矿井水进而影响地下水水质。因此需要采取合理措施控制煤矿开采产生的降落漏斗范围继续扩大,必要时对已经产生的漏斗进行恢复治理,同时加强对高盐、高SO_(4)^(2-)矿井水的处理和排放管理,研究成果可为煤炭绿色开发和环境高质量发展提供技术支持。

基坑开挖诱发侧方隧道变形的PCA-MLR预测方法

研究基坑开挖对侧方隧道变形的影响是岩土工程领域的热点与难点问题。为预测基坑开挖诱发临近侧方隧道变形,首先通过主成分分析方法(PCA)对侧方隧道变形指标影响因素进行降维处理并获取其主成分指标,然后采用多元线性回归方法(MLR)建立隧道变形指标与主成分指标间的关系模型,最后基于工程实例验证提出的PCA-MLR预测模型的正确性。研究结果表明:PCA-MLR模型考虑了基坑开挖诱发侧方隧道变形的高维度影响因素耦合作用,且实现了低维度主成分指标与变形指标间的关系模型建立。采用PCA-MLR模型预测的隧道最大水平及竖向位移与实测值的相对误差均小于10%,验证了提出模型的正确性与适用性。

Regression analysis and its application to oil and gas exploration:A case study of hydrocarbon loss recovery and porosity prediction,China

In oil and gas exploration,elucidating the complex interdependencies among geological variables is paramount.Our study introduces the application of sophisticated regression analysis method at the forefront,aiming not just at predicting geophysical logging curve values but also innovatively mitigate hydrocarbon depletion observed in geochemical logging.Through a rigorous assessment,we explore the efficacy of eight regression models,bifurcated into linear and nonlinear groups,to accommodate the multifaceted nature of geological datasets.Our linear model suite encompasses the Standard Equation,Ridge Regression,Least Absolute Shrinkage and Selection Operator,and Elastic Net,each presenting distinct advantages.The Standard Equation serves as a foundational benchmark,whereas Ridge Regression implements penalty terms to counteract overfitting,thus bolstering model robustness in the presence of multicollinearity.The Least Absolute Shrinkage and Selection Operator for variable selection functions to streamline models,enhancing their interpretability,while Elastic Net amalgamates the merits of Ridge Regression and Least Absolute Shrinkage and Selection Operator,offering a harmonized solution to model complexity and comprehensibility.On the nonlinear front,Gradient Descent,Kernel Ridge Regression,Support Vector Regression,and Piecewise Function-Fitting methods introduce innovative approaches.Gradient Descent assures computational efficiency in optimizing solutions,Kernel Ridge Regression leverages the kernel trick to navigate nonlinear patterns,and Support Vector Regression is proficient in forecasting extremities,pivotal for exploration risk assessment.The Piecewise Function-Fitting approach,tailored for geological data,facilitates adaptable modeling of variable interrelations,accommodating abrupt data trend shifts.Our analysis identifies Ridge Regression,particularly when augmented by Piecewise Function-Fitting,as superior in recouping hydrocarbon losses,and underscoring its utility in resource quantification refinement.Meanwhile,Kernel Ridge Regression emerges as a noteworthy strategy in ameliorating porosity-logging curve prediction for well A,evidencing its aptness for intricate geological structures.This research attests to the scientific ascendancy and broad-spectrum relevance of these regression techniques over conventional methods while heralding new horizons for their deployment in the oil and gas sector.The insights garnered from these advanced modeling strategies are set to transform geological and engineering practices in hydrocarbon prediction,evaluation,and recovery.

Statistical Analysis of Leaf Water Use Efficiency and Physiology Traits of Winter Wheat Under Drought Condition

Five statistical methods including simple correlation, multiple linear regression, stepwise regression, principal components, and path analysis were used to explore the relationship between leaf water use efficiency （WUE） and physiological traits （photosynthesis rate, stomatal conductance, transpiration rate, intercellular CO2 concentration, etc.） of 29 wheat cultivars. The results showed that photosynthesis rate, stomatal conductance, and transpiration rate were the most important leaf WUE parameters under drought condition. Based on the results of statistical analyses, principal component analysis could be the most suitable method to ascertain the relationship between leaf WUE and relative physiological traits. It is reasonable to assume that high leaf WUE wheat could be obtained by selecting breeding materials with high photosynthesis rate, low transpiration rate, and stomatal conductance under dry area.

基于BPT-MLR模型的建筑能耗分析和预测

通过对福建省厦门市某高校8栋公寓楼的房间日平均用电量的分析,提出一种建筑能耗的平衡点温度-多元线性回归(BPT-MLR)模型.使用统计方法识别平衡点温度,并根据该平衡点温度分段对房间日平均用电量进行多元线性回归预测分析;对8个参数进行筛选,最终选4个参数作为模型变量,包括1个数值型变量(室外空气平均温度)和3个定类型变量(性别、节假日指数和晴雨天指数).结果表明:对比3种数据驱动模型,BPT-MLR模型的预测性能最优,其R 2值达到了95.29%,比BP神经网络模型和多元线性回归模型的R 2值分别高出0.04%和24.64%.

APCS-MLR结合PMF模型的塔里木河上游沉积物重金属源解析与风险评估

为探究塔里木河上游沉积物中重金属的污染来源及潜在生态风险,选取上游阿拉尔—沙雅段表层沉积物为研究对象,测定Cu、Fe、Zn、Pb、As、Cr、Cd、Mn和Ni等9种重金属的含量,分析其污染及空间分布特征.结合相关性分析、聚类分析、绝对主成分-多元线性回归(APCS-MLR)和正定矩阵因子分析(PMF)等解析污染来源及其贡献,运用富集系数法、地质累积指数法、沉积物污染指数法和沉积物质量基准法(SQG)对重金属进行了风险评估.结果表明,除As外,Cu、Fe、Zn、Pb、Cr、Cd、Mn和Ni的平均含量均超过背景值;空间上重金属含量较高的采样点基本都出现在河流汇合处及人类活动的密集区.相关性分析、聚类分析和PCA/APCS分析表明,塔里木河上游沉积物的重金属来源主要有3类,第Ⅰ类中Cu、Fe、Zn、Pb、Mn和Ni可能代表禽类粪便和自然来源;第Ⅱ类中As、Cd和Ni可能代表农业活动源;第Ⅲ类中Pb和Cr可能代表交通活动源.APCS-MLR和PMF模型表明,源贡献率最高的是农业活动源,贡献率分别为63.20%和52.36%;养殖和自然来源、交通活动源是解析出的其他2个源,APCS-MLR和PMF解析得到的贡献率分别为10.80%、26.00%和36.09%、11.55%.风险评估方法均表明Cd和Ni处于轻度污染,偶尔会产生生物毒性效应;Zn无污染,生物毒性效应很少发生;塔里木河上游沉积物整体为自然-低风险水平,但样点TH1、TH4和TH7可能存在潜在生态风险.

Biomass estimation of Shorea robusta with principal component analysis of satellite data

Spatio-temporal assessment of the above ground biomass （AGB） is a cumbersome task due to the difficulties associated with the measurement of different tree parameters such as girth at breast height and height of trees. The present research was conducted in the campus of Birla Institute of Technology, Mesra, Ranchi, India, which is predomi- nantly covered by Sal （Shorea robusta C. F. Gaertn）. Two methods of regression analysis was employed to determine the potential of remote sensing parameters with the AGB measured in the field such as linear regression analysis between the AGB and the individual bands, principal components （PCs） of the bands, vegetation indices （VI）, and the PCs of the VIs respectively and multiple linear regression （MLR） analysis be- tween the AGB and all the variables in each category of data. From the linear regression analysis, it was found that only the NDVI exhibited regression coefficient value above 0.80 with the remaining parameters showing very low values. On the other hand, the MLR based analysis revealed significantly improved results as evidenced by the occurrence of very high correlation coefficient values of greater than 0.90 determined between the computed AGB from the MLR equations and field-estimated AGB thereby ascertaining their superiority in providing reliable estimates of AGB. The highest correlation coefficient of 0.99 is found with the MLR involving PCs of VIs.

基于机器学习MLR模型的地下水循环井优化设计

针对污染场地地下水循环井(groundwater circulating well, GCW)的优化设计问题,提出一种基于机器学习多元线性回归(multiple linear regression, MLR)模型的优化设计方法。该方法首先利用有限差分法建立不同条件下单个GCW运行的数值模型,通过运行数值模型,得到不同条件下GCW的运行效果,从而构建数据集;然后利用MLR算法对模型进行训练,构建计算多种GCW运行效果刻画指标的数学模型,并比较各个数学模型的拟合精度,结果显示纵向影响半径(RL)、横向影响半径(RT)模型的拟合程度较好,具有一定的泛化能力;最后根据机器学习所得的数学模型,对某试验场地GCW进行优化设计,得到最终优化设计方案,通过优化前的设计方案相比,RL、RT指标有了一定的提升,验证了方法的有效性。该研究结果可为GCW前期结构的快速设计提供参考,具有一定的实际意义。

Study on mechanism and genetic analysis of lipid metabolism disorder in pregnant rats

Objective: To analyze the characteristics and possible mechanism of lipid metabolism in pregnant rats with intestinal flora imbalance. Methods: A total of 129 sexually mature female SD rats were divided into three groups: non-pregnant group (untreated healthy rats), healthy pregnant group (natural insemination pregnant rats), and pregnant microflora disorder group (pregnant rats were given mixed antibiotics by gavage to build the modeling), with 43 rats in each group. The contents of TG, LDL, HDL and TC were detected by automatic biochemical analyzer, and the contents of SCD1, PGC-1 alpha, PEPCK, ApoE and MTTP genes were detected by fluorescence quantitative PCR technology. Regression analysis was used to explore the comprehensive influence of each gene on total cholesterol expression in rats. Principal component analysis was used to explore the internal mechanism of lipid metabolism in pregnant rats with intestinal flora disorder. Results: The contents of TG, TC, LDL and HDL were compared among the three groups of rats and the differences were statistically significant (P<0.05) . The expression levels of related genes (SCD1, PGC-1, PEPCK, ApoE, MTTP) in the three groups were statistically significant (P<0.05) . SCD1 content in the non-pregnant group, healthy pregnancy group, and disordered pregnancy group was (0.92±0.12) μg/mL, (1.20±0.15)μg/mL, and (1.53±0.20) μg/mL, respectively. PGC-1 alpha content in the non-pregnant group, healthy pregnancy group, and disordered pregnancy group was (1.34±0.21) μg/mL, (0.93±0.12) micron /mL, and (0.41±0.08) μg/mL, respectively. PEPCK content in the non-pregnant group, healthy pregnancy group, and disordered pregnancy group was (0.48±0.06) μg/mL, (0.35±0.09)μg/mL, and (0.22±0.05) μg/mL, and the differences were statistically significant (P<0.05) . Multivariate linear regression analysis showed that the influence of gene content on The effect of each gene content on TC content was in order from large to small: SCD1 (OR=4.572) , PGC-1 (OR=3.387) , PEPCK (OR=3.935) , ApoE (OR=3.597) , MTTP (OR=3.096) . The principal component analysis showed that three principal components could be extracted from five related genes of lipid metabolism in pregnant rats with intestinal dysbiosis: SCD1/PEPCK pathway (contribution rate: 36.28%) , PGC-1 /ApoE pathway (contribution rate: 30.42%) , and MTTP pathway (contribution rate: 15.37%) . Conclusion: After pregnancy, blood lipids in rats are significantly increased while the imbalance of intestinal flora will lead to decreased blood lipids. The disorder of lipid metabolism in pregnant rats with intestinal flora imbalance is mainly related to the disorder of gene expression, which further affects the functions of SCD1/PEPCK, PGC-1 /ApoE and MTTP pathways.

Education Investment Fixed Asset Investment and Regional Economic Development Differences--Empirical analysis based on Chinese

In this article,it discusses the di£ferences in economic development between urban and rural areas and regions in our country from the perspective of education investment and fixed asset investment.Based on the provincial data of 31 provinces from 1999 to 2017 released by National Bureau of Statistics,it expends the Cobb-Douglas model and Lucas model,and analyses the data with multiple linear regression models.From the study,it finds that compared with investment in fixed assets,investment in education has a larger role in promoting economic development,which is more obvious in the underdeveloped central and western regions and rural areas.However,at the same time it needs to note that the positive effects of education investment will be restricted by the economic structure and policy environment,and education expenditure policies should also be implemented in accordance with time and local conditions.

疫情后深圳市生活垃圾产生量的预测及变化分析

疫情后针对生活垃圾产生量的变化,开展预测并对结果进行分析,是地方政府科学制定相关规划、合理布局环卫设施建设的重要依据。因此,立足深圳市疫情前后数据,结合灰色关联度模型、多元线性回归等方法,分析2022—2035年生活垃圾产生量预测值的变化。结果表明,生活垃圾产生量保持逐年增长趋势,规划期末水平年(2035年)的具体数值有一定程度调整。预测到2035年的生活垃圾产生量为45 547 t/d,其中再生资源回收量为14 576 t/d,生活垃圾处理处置量为30 971 t/d。建议各项环卫设施建设可灵活调整设施规模及建设周期,提升城市垃圾处理效能。

基于正交试验的煤岩相似材料最优配比研究

目的为了探寻煤岩相似材料最优配比,方法以赵固一矿煤样的自然视密度、单轴抗压强度、弹性模量为模拟指标,采用正交设计法开展相似材料配比试验。选用碳酸钙、水泥、细河砂、煤粉、蒸馏水为原料,以骨料与胶结剂质量比、胶结剂成分间质量比、骨料成分间质量比和掺水率为控制因素,按照4因素3水平正交配比方案制备了9组相似材料。结果试验结果表明:不同配比下相似材料物理力学参数变化较大,各因素对模拟指标影响规律性强,且骨胶比对相似材料各模拟指标起控制作用,自然视密度、单轴抗压强度、弹性模量均随骨胶比增加而显著下降。通过多元线性回归分析得到相似材料最优配比为碳酸钙∶水泥∶河砂∶煤粉∶水=1∶4∶0.9∶5.8∶3.3,经验证,使用该配比制作的试样在物理力学参数、单轴压缩曲线和破坏形态上能够很好地模拟原煤。结论该研究采用理论与试验相结合的方法寻找最优配比有效可行,可为煤岩相似材料领域研究提供一定借鉴。

Multiple linear regression, artificial neural network, and fuzzy logic prediction of 28 days compressive strength of concrete

Evaluating the in situ concrete compressive strength by means of cores cut from hardened concrete is acknowledged as the most ordinary method, however, it is very difficult to predict the compressive strength of concrete since it is affected by many factors such as different mix designs, methods of mixing, curing conditions, compaction, etc. In this paper, considering the experimental results, three different models of multiple linear regression model （MLR）, artificial neural network （ANN）, and adaptive neuro-fuzzy inference system （ANFIS） are established, trained, and tested within the Matlab programming environment for predicting the 28 days compressive strength of concrete with 173 different mix designs. Finally, these three models are compared with each other and resulted in the fact that ANN and ANFIS models enables us to reliably evaluate the compressive strength of concrete with different mix designs, however, multiple linear regression model is not feasible enough in this area because of nonlinear relationship between the concrete mix parameters. Finally, the sensitivity analysis （SA） for two different sets of parameters on the concrete compressive strength prediction are carried out.

秦岭北麓乡村植物景观与物种丰富度的关系

选取陕西省秦岭北麓5个村落作为试验区,采用多元线性回归分析和熵值法等相结合,探讨了秦岭北麓乡村地区植物丰富度对乡村景观的影响。结果表明:远离城镇的乡村植物多样性单一,物质丰富度偏低,其乡村景观评价指标体系得分偏低。多元线性逐步回归分析结果表明,Pielou均匀度指数与社会效应、美感效果、生态质量之间存在显著正相关,Menhinick丰富度指数与美感效果、生态质量、文化价值之间存在显著正相关。综上,提出了在乡村景观建设过程中,应立足资源优势,选择适合乡村景观发展的优势特色植物,有效增加评价较低乡村近水生境、居民点周边、农田边缘、林地比例和物种丰富度等建议,以期在促进乡村可持续发展的同时维护农村的环境治理,为乡村景观建设中植物多样性研究提供参考。

渤海海域井壁取心裂解烃S_(2)烃类损失恢复回归分析

地化录井受工程、地质条件及人为因素的影响,往往造成岩石样品从井底到地表的烃类损失,不能很好地反映地下储层的真实含油气信息,因此需要一种合理准确的方法进行烃类损失恢复。针对渤海海域不同地区不同层位的岩屑值(自变量)与壁心值(因变量)之间的关系,基于最小二乘法、梯度下降法及其衍生算法,以多元线性回归和非线性回归两种方式来拟合研究区井壁取心数据。多元线性回归模型可使用标准方程法、岭回归、LASSO(Least Absolute Shrinkage and Selection Operator)及弹性网进行回归拟合,非线性回归模型可使用梯度下降法和分段函数的拟合方法。对不同回归分析方法进行分析对比可知,岭回归在计算线性关系的烃类损失方面具有较好的效果,决定系数r^(2)均超过0.7;基于岭回归分段函数拟合和非线性回归模型y=x/(b+kx)适合非线性烃类损失恢复。与传统的烃类损失恢复方法相比,使用量化的方式对研究区烃类进行恢复,更加科学全面,具有广泛的应用前景。

QSRR Study of GC Retention Indices of Volatile Compounds Emitted from Mosla chinensis Maxim by Multiple Linear Regression

The volatile compounds emitted from Mosla chinensis Maxim were analyzed by headspace solid-phase micro- extraction （HS-SPME） and headspace liquid-phase microextraction （HS-LPME） combined with gas chromatography-mass spectrometry （GC-MS）. The main volatiles from Mosla chinensis Maxim were studied in this paper. It can be seen that 61 compounds were separated and identified. Forty-nine volatile compounds were identified by SPME method, mainly including myrcene, a-terpinene, p-cymene, （E）-ocimene, thymol, thymol acetate and （E）-fl-farnesene. Forty-five major volatile compounds were identified by LPME method, including a-thujene, a-pinene, camphene, butanoic acid, 2-methylpropyl ester, myrcene, butanoic acid, butyl ester, a-terpinene, p-cymene, （E）-ocimene, butane, 1,1-dibutoxy-, thymol, thymol acetate and （E）-fl-farnesene. After analyzing the volatile compounds, multiple linear regression （MLR） method was used for building the regression model. Then the quantitative structure-retention relationship （QSRR） model was validated by predictive-ability test. The prediction results were in good agreement with the experimental values. The results demonstrated that headspace SPME-GC-MS and LPME-GC-MS are the simple, rapid and easy sample enrichment technique suitable for analysis of volatile compounds. This investigation provided an effective method for predicting the retention indices of new compounds even in the absence of the standard candidates.