检索结果-内蒙古大学图书馆

Investigation on the Relationship between Satellite Air Quality Measurements and Industrial Production by generalized additive modeling

引用

REMOTE SENSING 2021年第16期13卷 3137-3137页

作者： Tong, Chao Zhang, Chengxin Liu, Cheng Hefei Univ Technol Sch Management Hefei 230009 Peoples R China Univ Sci & Technol China Dept Precis Machinery & Precis Instrumentat Hefei 230026 Peoples R China

The development of the green economy is universally recognized as a solution to natural resource shortages and environmental pollution. When exploring and developing a green economy, it is important to study the relationships between the environment and economic development. As opposed to descriptive and qualitative research without modeling or based on environmental Kuznets curves, quantitative relationships between environmental protection and economic development must be identified for exploration and practice. In this paper, we used the generalized additive model (GAM) regression method to identify relationships between atmospheric pollutants (e.g., NO2, SO2 and CO) from remote sensing and in situ measurements and their driving effectors, including meteorology and economic indicators. Three representative cities in the Anhui province, such as Hefei (technology-based industry), Tongling (resource-based industry) and Huangshan (tourism-based industry), were studied from 2016 to 2020. After eliminating the influence of meteorological factors, the relationship between air quality indexes and industrial production in the target cities was clearly observed. Taking Hefei, for example, when the normalized output of chemical products increases by one unit, the effect on atmospheric NO2 content increases by about 20%. When the normalized output of chemical product increases by one unit, the effect on atmospheric SO2 content increases by about 10%. When chemical and steel product outputs increase by one unit, the effect on atmospheric CO content increases by 25% and 20%, respectively. These results can help different cities predict local economic development trends varying by the changes in air quality and adjust local industrial structure.

关键词： green economy satellite air quality measurements industrial production remote sensing generalized additive model

来源：评论

学校读者我要写书评

暂无评论

Interpretable diurnal impacts on extreme urban PM2.5 concentrations of soil temperature, soil water content, humidity and temperature inversion

引用

ATMOSPHERIC RESEARCH 2024年 307卷

作者： de Foy, Benjamin Schauer, James J. St Louis Univ Dept Earth & Atmospher Sci 1 N Grand Ave St Louis MO 63108 USA Univ Wisconsin Madison Environm Chem & Technol Program 1415 Engn Dr Madison WI 53706 USA Wisconsin State Lab Hyg 465 Henry Mall Madison WI 53706 USA

Inhabitants of megacities around the world are suffering from severely unhealthy concentrations of PM2.5 as a result of intense emissions from numerous sectors, often combined with adverse meteorological conditions. Machine learning algorithms can be applied to multiyear datasets of hourly measurements in order to identify the main drivers causing intense pollution. In particular, generalized additive models (GAM) provide interpretable associations of the interplay between emissions and meteorology. GAM simulations were developed for five dry seasons in Kolkata and Dhaka. In the model, soil temperature was associated with 21% of PM2.5 variability. Instead of 2-m humidity, model performance was improved by including air humidity at 1000 hPa and soil water content individually, with each accounting for around 6% of PM2.5 variability. Boundary layer heights have a significant impact on daytime concentrations, but the GAM output showed that temperature inversion intensity better characterized the stability of the nocturnal boundary layer and had a larger contribution to the PM2.5 variability. The GAM model could also identify interactions between parameters and showed that boundary layer height, temperature inversion intensity and air humidity had impacts that varied by time of day. By using GAM factors for winds at 100 m above the surface in combination with the Trajectory Cluster Contribution Function, the model estimated that local winds were associated with around 6% of variability whereas long range transport was associated with around 9% of variability. The analysis shows that there are no silver bullets for improving air quality and that adverse meteorology is making the problem harder to solve. Nevertheless, the results show that sustained efforts at controlling both local and regional sources will yield cleaner air that is greatly needed to improve the health of people living in large metropolitan areas.

关键词： PM2.5 Air pollution generalized additive model Interpretable machine learning eXplainable artificial intelligence Mixing height Temperature Inversion

来源：评论

学校读者我要写书评

暂无评论

Forecasting of Heat Production in Combined Heat and Power Plants Using generalized additive models

引用

ENERGIES 2021年第8期14卷 2331-2331页

作者： Bujalski, Maciej Madejski, Pawel PGE Energia Ciepla SA Ul Zlota 59 PL-00120 Warsaw Poland AGH Univ Sci & Technol Fac Mech Engn & Robot Dept Power Syst & Environm Protect Facil Mickiewicz 30 Ave PL-30059 Krakow Poland

The paper presents a developed methodology of short-term forecasting for heat production in combined heat and power (CHP) plants using a big data-driven model. An accurate prediction of an hourly heat load in the day-ahead horizon allows a better planning and optimization of energy and heat production by cogeneration units. The method of training and testing the predictive model with the use of generalized additive model (GAM) was developed and presented. The weather data as an input variables of the model were discussed to show the impact of weather conditions on the quality of predicted heat load. The new approach focuses on an application of the moving window with the learning data set from the last several days in order to adaptively train the model. The influence of the training window size on the accuracy of forecasts was evaluated. Different versions of the model, depending on the set of input variables and GAM parameters were compared. The results presented in the paper were obtained using a data coming from the real district heating system of a European city. The accuracy of the methods during the different periods of heating season was performed by comparing heat demand forecasts with actual values, coming from a measuring system located in the case study CHP plant. As a result, a model with an averaged percentage error for the analyzed period (November-March) of less than 7% was obtained.

关键词： heat demand prediction generalized additive model combined heat and power plant district heating network heat production

来源：评论

学校读者我要写书评

暂无评论

FXAM: A unified and fast interpretable model for predictive analytics

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartB期252卷

作者： Jiang, Yuanyuan Ding, Rui Qiao, Tianchi Zhu, Yunan Han, Shi Zhang, Dongmei Renmin Univ China Sch Stat 59 Zhongguancun St Beijing Peoples R China Microsoft Res Asia Beijing Peoples R China Southeast Univ Sch Comp Sci & Engn Nanjing 211189 Jiangsu Peoples R China Univ Sci & Technol China Sch Informat Sci & Technol Hefei 230031 Anhui Peoples R China

Predictive analytics aims to build machine learning models to predict behavior patterns and use predictions to guide decision -making. Predictive analytics is human involved, thus the machine learning model is preferred to be interpretable. In literature, generalized additive model (GAM) is a standard for interpretability. However, due to the one -to -many and many -to -one phenomena which appear commonly in real -world scenarios, existing GAMs have limitations to serve predictive analytics in terms of both accuracy and training efficiency. In this paper, we propose FXAM (Fast and eXplainable additive model), a unified and fast interpretable model for predictive analytics. FXAM extends GAM's modeling capability with a unified additive model for numerical, categorical, and temporal features. FXAM conducts a novel training procedure called Three -Stage Iteration (TSI). TSI corresponds to learning over numerical, categorical, and temporal features respectively. Each stage learns a local optimum by fixing the parameters of other stages. We design joint learning over categorical features and partial learning over temporal features to achieve high accuracy and training efficiency. We prove that TSI is guaranteed to converge to the global optimum. We further propose a set of optimization techniques to speed up FXAM's training algorithm to meet the needs of interactive analysis. Thorough evaluations conducted on diverse data sets verify that FXAM significantly outperforms existing GAMs in terms of training speed, and modeling categorical and temporal features. In terms of interpretability, we compare FXAM with the typical post -hoc approach XGBoost+SHAP on two real -world scenarios, which shows the superiority of FXAM's inherent interpretability for predictive analytics.

关键词： generalized additive model Interpretable machine learning Predictive analytics Training efficiency

来源：评论

学校读者我要写书评

暂无评论

Time Series Analysis of the Impact of Meteorological Conditions and Air Quality on the Number of Medical Visits for Hypertension in Haikou City, China

引用

ATMOSPHERE 2024年第3期15卷 370页

作者： Zhang, Mingjie Zhang, Yajie Zhang, Jinghong Lin, Shaowu Climate Ctr Hainan Prov Haikou 570203 Peoples R China South China Sea Meteorol & Disaster Mitigat Res Ke Haikou 570203 Peoples R China

Meteorological conditions and air quality are important environmental factors in the occurrence and development of cardiovascular diseases (CVDs) such as hypertension. The aim of this study was to take Haikou City, located on the tropical edge, as the research area and to analyze the exposure-response relationship and lag effect between its meteorological conditions, air quality, and the number of hypertensive patients. Using the data from the hypertension outpatient department of Hainan Provincial People's Hospital from 2016 to 2018, together with meteorological data and air quality data, a distributed lag nonlinear model based on the nested generalized addition model of meteorological element base variables was established. The results showed that the impact of temperature on the risk of hypertension was mainly due to the cold effect, which was associated with high risk, with a lag of 1-10 days. When the temperature dropped to 10 degrees C, the cumulative effect on the risk of hypertension of relative risk (RR) reached its highest value on the day the low temperature occurred (RR was 2.30 and the 95% confidence interval was 1.723 similar to 3.061), passing the test with a significance level of 0.05. This result indicated that efforts should be made to strengthen the prevention of hypertension under low-temperature conditions and the prediction and early warning of disease risks. The impact of the air-quality effect (the environmental Air Quality Index was selected as an indicator) on the risk of hypertension was mainly characterized by a low air-quality effect, with a lag effect of 0-8 days. When the risk reached approximately 124, the RR was highest (RR was 1.63 and the 95% confidence interval was 1.104 similar to 2.408), passing the test with a significance level of 0.05. The research results can provide technical support for conducting medical meteorological forecasting, early warning, and services for hypertension. A joint work and research mechanism among mul

关键词： hypertension generalized additive model distributed hysteresis nonlinear model Haikou

来源：评论

学校读者我要写书评

暂无评论

Study on the Health Effect of Temperature on Cardiovascular and Cerebrovascular Diseases in Haikou City

引用

ATMOSPHERE 2024年第6期15卷 725-725页

作者： Zhang, Mingjie Lin, Shaowu Zhang, Yajie Zhang, Jinghong Climate Ctr Hainan Prov Haikou 570203 Peoples R China South China Sea Meteorol & Disaster Mitigat Res Ke Haikou 570203 Peoples R China

Research on the impact of temperature in tropical regions on the risk of cardiovascular and cerebrovascular diseases was limited. The aim of the study was to investigate this topic using Haikou, a tropical city, as the research area. Outpatient data on cardiovascular and cerebrovascular diseases (CVD and CeVD) from Hainan Provincial People's Hospital during 2016-2018 (total of 77,820) and meteorological and air-quality data were used to establish a distributed-lag nonlinear model (DLNM) based on the nested generalized addition model (GAM) of meteorological elements. The results revealed the impact on the risk of CVD and CeVD was mainly due to the cold effect, which significantly lagged behind. The thermal effect had a strong impact on the onset of CVD and CeVD on the day of high temperature. Males were easily affected by low temperatures, while females were the opposite. The lag period of the working-age group affected by low temperatures was longer and greater than that of the elderly group. The high-temperature effect only had an impact on the working-age group. The lag effect of low temperatures on the risk of hypertension was the greatest. These results can provide technical support for carrying out meteorological forecasting, warning, and services for individuals with CVD and CeVD, suggesting attaching importance to health protection for special populations.

关键词： cardiovascular and cerebrovascular diseases generalized additive model distributed-lag nonlinear model subclass analysis Haikou

来源：评论

学校读者我要写书评

暂无评论

Estuarine environmental flow assessment based on the flow-ecological health index relation model: a case study in Yangtze River Estuary, China

引用

ENVIRONMENTAL MONITORING AND ASSESSMENT 2024年第4期196卷 348-348页

作者： Huang, Weizheng Wei, Lai Yang, Ya Sun, Jinnuo Ding, Ling Wu, Xinghua Zheng, Leifu Huang, Qinghui Tongji Univ Coll Environm Sci & Engn Key Lab Yangtze River Water Environm Minist Educ Shanghai 200092 Peoples R China Shanghai Invest Design & Res Inst Co Ltd SIDRI Shanghai Peoples R China China Three Gorges Corp Ecoenvironm Engn Res Ctr Beijing 100038 Peoples R China Shanghai Inst Pollut Control & Ecol Secur Shanghai 200092 Peoples R China

Environmental flow (e-flow) is the water demand of one given ecosystem, which can become the flow regulation target for protection and restoration of river or estuarine ecosystems. In this study, an e-flow assessment based on the flow-ecological health index (EHI) relation model was conducted to improve ecosystem health of the Yangtze River Estuary (YRE). Monitoring data of hydrology, biology, and water environment in the last decades were used for the model establishment. For the description of the YRE ecosystem, an EHI system was developed by cumulative frequency distribution curves and adaption of national standards. After preprocessing original flow values into proportional flow values, the generalized additive model and Monte Carlo random sampling were used for the establishment of the flow-EHI relation model. From the model calculation, the e-flow assessment results were that, in proportional flow values, the suitable flow range was 1.05-1.35, and the optimum flow range was 1.15-1.25 (flows in Yangtze River Datong Station). For flow regulation in two crucial periods, flows of 42,630-65,545 m3/s or over 14,675 m3/s are needed for the suitable flow of YRE in summer (June-August) or January, respectively. An adaptive management framework of ecological health-based estuarine e-flow assessment for YRE was contrived due to the limitation of current established model when facing the extreme drought in summer, 2022. The methodology and framework in this study are expected to provide valuable management and data support for the sustainable development of estuarine ecosystems and to bring inspiration for further studies at even continental or global levels.

关键词： Environmental flow Yangtze River Estuary generalized additive model Monte Carlo random sampling Ecological health index

来源：评论

学校读者我要写书评

暂无评论

Quantifying bark thickness and bark volume with alternative modeling procedures for eight species in the southeastern US

引用

FOREST ECOLOGY AND MANAGEMENT 2024年 553卷

作者： Yang, Sheng-, I Qiao, Yudan Univ Tennessee Sch Nat Resources 427 Plant Biotechnol Bldg Knoxville TN 37996 USA Northeast Forestry Univ Sch Forestry Key Lab Sustainable Forest Ecosyst Management Minist Educ Harbin 150040 Peoples R China

Bark thickness is one of the important tree characteristics to assess plant survival following silvicultural treatments or natural disturbances. With an increased number of catastrophic wildfires under changing climate, a reliable approach for modeling bark thickness and bark volume is critical to monitor forest health and quantify carbon stocking in sustainable forest management. The objective of the study was to compare the efficacy of three alternative quantifying approaches and statistical models for both bark thickness and volume. In approach I, bark thickness is quantified from the differences of inside-and outside-bark diameters, which are predicted with two separate stem taper functions. The second approach combines a stem taper function and a bark thickness model, while in the third approach, bark thickness is quantified via a single predictive model with bark thickness at breast height included. The statistical models examined include segmented polynomial regression models (SEG), variable-exponent models (VEM) and generalized additive models (GAM). A total number of 71,187 observations of 2,932 trees were queried from the LegacyTree database, including eight ecologically and economically important species in the southeastern *** show that all combinations of approaches and models can quantify bark thickness and bark volume without bias for all eight species examined. Approach III yields higher accuracy and precision levels than approaches I and II. The performance of the models varies among quantifying approaches and species. GAM and VEM generally produce a more reliable quantification than SEG. Although GAM may not be the optimal model for a given species, such a model can provide preliminary quantitative information about bark thickness and bark volume when there is no existing model for the target species. The results of this work provide additional insights for forest ecologists and practitioners to select appropriate modeling approaches for qua

关键词： Stem taper function Segmented polynomial regression Variable-exponent model generalized additive model Mixed-hardwood forests Bark thickness at breast height

来源：评论

学校读者我要写书评

暂无评论

Interpretable machine learning tools to analyze PM2.5 sensor network data so as to quantify local source impacts and long-range transport

引用

ATMOSPHERIC RESEARCH 2024年 311卷

作者： de Foy, Benjamin Edwards, Ross Joy, Khaled Shaifullah Zaman, Shahid Uz Salam, Abdus Schauer, James J. St Louis Univ Dept Earth & Atmospher Sci St Louis MO 63103 USA Wisconsin State Lab Hyg Madison WI USA Univ Dhaka Dept Chem Dhaka Bangladesh Bangladesh Univ Engn & Technol Dept Chem Dhaka Bangladesh Drexel Univ Dept Chem Philadelphia PA 19104 USA Univ Wisconsin Madison Environm Chem & Technol Program Madison WI USA

Sensor networks provide spatially resolved information about the time variation of PM2.5 concentrations in urban areas around the world. With relatively simple improvements to the control of the temperature and humidity of incoming air, and with proper quality assurance and calibration protocols, a low cost monitor was developed that provides measurements that were highly correlated with a reference PM2.5 monitor. These have sufficient resolution and reliability to quantify small differences within an urban area. Nevertheless, many sites report similar concentrations and it can be difficult to interpret the results or distinguish local from regional effects. generalized additive models are an effective Machine Learning method to distinguish the impact of factors across very different scales. As a type of Interpretable Machine Learning / eXplainable Artificial Intelligence, they provide direct information on the link between specific factors and PM2.5 concentrations. GAM simulations were developed for sensors located around Dhaka, Bangladesh, for both the dry and the wet seasons. The simulations show that the largest contributor to high PM2.5 concentration variations across both urban and peri-urban sites is the boundary layer height which represent the vertical mixing of the urban plume. Using Trajectory Cluster Concentration Impacts, the simulations showed that robust estimates of long-range transport could be obtained from measurements located within a polluted environment, and the model further showed that enhancements of more than 40 mu g/m3 were associated with air transport from the Indo-Gangetic Plain in the dry season. Finally, interaction maps of the effect of horizontal wind speed and direction showed that these could be associated with up to +/-20 % variation in PM2.5 from site to site. Most of the enhancements are related to very calm winds and appear to be more strongly associated with road emissions than with point sources. Overall, the sensor network

关键词： PM 2.5 Low cost sensor Sensor network generalized additive model Interpretable machine learning eXplainable artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

The association between gaseous pollutants and non-accidental mortality: a time series study

引用

ENVIRONMENTAL GEOCHEMISTRY AND HEALTH 2021年第8期43卷 2887-2897页

作者： Deng, Jixiang Hu, Xingxing Xiao, Changchun Pan, Faming Anhui Med Univ Sch Publ Hlth Dept Epidemiol & Biostat 81 Meishan Rd Hefei 230032 Anhui Peoples R China Hefei Ctr Dis Control & Prevent 86 Luan Rd Hefei 230032 Anhui Peoples R China

To evaluate the effects of gaseous pollutants (SO2, NO2) on non-accidental mortality of residents in Hefei city, we collected non-accidental deaths, air pollutants and meteorological data of Hefei city from 2014 to 2017. After controlling confounding factors with Poisson generalized additive model, we analyzed the relationship between air pollutants and non-accidental mortality and used subgroup analysis to identify susceptible groups. The number of non-accidental deaths during the study period was 42,116, with an average of 28.83 per day. The average concentrations of SO2 and NO2 were 16.08 mu g/m(3) and 39.10 mu g/m(3), respectively. In the single-pollutant model, every 10 mu g/m(3) increase in SO2 and NO2 concentrations was significantly associated with non-accidental mortality, and there was a significant lag effect. SO2 increased the risk of non-accidental death by 4.93% (95% CI: 1.94% similar to 8.00%) at lag0-3. In addition, male, the elderly, non-elderly and low-education people were more susceptible (P < 0.05). NO2 increased the risk of non-accidental death by 2.11% (95% CI: 1.18% similar to 3.05%) at lag0-1 and had an effect on all subgroups (P < 0.05). For every 10 mu g/m(3) increase in SO2 and NO2, the two-pollutant model showed that the risk of non-accidental death, respectively, increased by 3.34% (95% CI: 0.29% similar to 6.50%) and 1.82% (95% CI: 0.85% similar to 2.79%), suggesting that the effect was weakened. Our study suggested that SO2 and NO2 were associated with non-accidental mortality, and there were lag effects. Therefore, environmental management should be strengthened and health protection education should be carried out for different groups.

关键词： Gaseous pollutant Mortality generalized additive model Risk assessment

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：