检索结果-内蒙古大学图书馆

Novel simulation of aqueous total nitrogen and phosphorus concentrations in Taihu Lake with machine learning

ENVIRONMENTAL RESEARCH 2022年第PartB期204卷 111940-111940页

作者： Lu, Hao Yang, Liuyan Fan, Yifan Qian, Xin Liu, Tong Nanjing Univ Sch Environm State Key Lab Pollut Control & Resources Reuse Nanjing 210023 Peoples R China

This study demonstrates the utility of internal nutrient loads as an additional parameter to improve the performance of machine learning models in predicting the temporal variations of aqueous TN and TP concentrations in Taihu Lake, a large shallow lake. Internal loads, as a potential input parameter for machine learning models, were estimated using a mass balance calculation. The results showed that between 2011 and 2018 the maximum monthly internal loads of nitrogen and phosphorus in Taihu Lake were 4200 t and 178 t, respectively. Monthly changes in the aqueous TN and TP concentrations of Taihu Lake did not correlate significantly with inflow loads whereas the correlations with estimated internal loads were positive and significant. Long short-term memory (LSTM), random forest (RF), and gradient boosting regression tree (GBRT) models were built, and for all of them the inclusion of internal loads in the input parameters improved their performance. LSTM model III, whose input parameters included both inflow loads and internal loads, had the best performance, based on a testing root mean square error of 0.11 mg TN/L and 0.017 mg TP/L. A 28 % decrease in the annual aqueous TP concentration in Taihu Lake in 2018 simulated by LSTM model III was achieved by lowering the average water level from 3.29 m to 2.99 m, suggesting a possible strategy to control the TP concentration in the lake. In summary, our study showed that aqueous TN and TP concentrations in shallow lakes can be simulated using machine learning, with LSTM models outperforming RF and GBRT models;in these models, internal loads should be included as an input parameter. Additionally, our study identified the water level as an important factor affecting the aqueous TP concentration in Taihu Lake.

关键词： Internal load Long short-term memory Random forest gradient boosting regression tree Water level

来源：评论

学校读者我要写书评

暂无评论

Predicting pesticide dissipation half-life intervals in plants with machine learning models

引用

JOURNAL OF HAZARDOUS MATERIALS 2022年 436卷 129177页

作者： Shen, Yike Zhao, Ercheng Zhang, Wei Baccarelli, Andrea A. Gao, Feng Columbia Univ Mailman Sch Publ Hlth Dept Environm Hlth Sci New York NY 10032 USA Inst Plant Protect Beijing Acad Agr & Forestry Sci Beijing 100097 Peoples R China Michigan State Univ Dept Plant Soil & Microbial Sci E Lansing MI 48823 USA Michigan State Univ 1066 Bogue ST RM A516 E Lansing MI 48824 USA Columbia Univ Mailman Sch Publ Hlth Dept Environm Hlth Sci 630 W168th St Room 16-416 New York NY 10032 USA

Pesticide dissipation half-life in plants is an important factor to assessing environmental fate of pesticides and establishing pre-harvest intervals critical to good agriculture practices. However, empirically measured pesticide dissipation half-lives are highly variable and the accurate prediction with models is challenging. This study utilized a dataset of pesticide dissipation half-lives containing 1363 datapoints, 311 pesticides, 10 plant types, and 4 plant component classes. Novel dissipation half-life intervals were proposed and predicted to account for high variations in empirical data. Four machine learning models (i.e., gradient boosting regression tree [GBRT], random forest [RF], supporting vector classifier [SVC], and logistic regression [LR]) were developed to predict dissipation half-life intervals using extended connectivity fingerprints (ECFP), temperature, plant type, and plant component class as model inputs. GBRT-ECFP had the best model performance with F1-microbinary score of 0.698 +/- 0.010 for the binary classification compared with other machine learning models (e.g., LR-ECFP, F1-micro binary= 0.662 +/- 0.009). Feature importance analysis of molecular structures in the binary classification identified aromatic rings, carbonyl group, organophosphate, =C-H, and N-containing heterocyclic groups as important substructures related to pesticide dissipation half-lives. This study suggests the utility of machine learning models in assessing the environmental fate of pesticides in agricultural crops.

关键词： Machine Learning Pesticide Dissipation half-life Extended connectivity fingerprints Molecular structure gradient boosting regression tree

来源：评论

学校读者我要写书评

暂无评论

Calculation of coating consumption quota for ship painting: a CS-GBRT approach

引用

JOURNAL OF COATINGS TECHNOLOGY AND RESEARCH 2020年第6期17卷 1597-1607页

作者： Bu, Henan Ji, Xingyu Yuan, Xin Han, Ziyan Li, Lei Yan, Zhuwen Jiangsu Univ Sci & Technol Sch Mech Engn Zhenjiang Jiangsu Peoples R China Nanjing Inst Technol Res Dept Intelligent Mfg Equipment Nanjing Peoples R China

This paper focuses on the prediction of the coating amount before the construction of ship painting, i.e., the calculation of coating consumption quota. At present, each shipyard uses a larger coating loss coefficient to calculate the coating consumption quota;after the construction, there is often a lot of inventory left, which is not conducive to the scientific management of the ship coating process and the cost control of shipbuilding. Therefore, this paper proposes a coating consumption prediction method based on ensemble learning, using cosine similarity and gradient boosting regression tree hybrid algorithm (CS-GBRT) to calculate the coating loss coefficient under different working conditions. Cosine similarity is used to select similar data with less difference from the target to be predicted as the training set, and the loss function in GBRT is improved based on similarity weight to improve the prediction performance and calculation accuracy of GBRT. The coating data recorded by a shipyard from 2014 to 2019 are randomly selected to evaluate the prediction ability of the model established in the paper. The results show that when the proposed CS-GBRT algorithm is used to calculate the coating loss coefficient, the mean absolute error of training set and test set are both < 1.4, and the mean absolute error percentages are both < 4%. Compared with other research methods, the prediction accuracy is obviously improved, and the output feature importance is also consistent with the trend calculated by Spearman method, which proves the validity of the model again.

关键词： Coating consumption Predictive analysis Ensemble learning gradient boosting regression tree Cosine similarity

来源：评论

学校读者我要写书评

暂无评论

Updated soil salinity with fine spatial resolution and high accuracy: The synergy of Sentinel-2 MSI, environmental covariates and hybrid machine learning approaches

引用

CATENA 2022年 212卷

作者： Ge, Xiangyu Ding, Jianli Teng, Dexiong Wang, Jingzhe Huo, Tianci Jin, Xiaoye Wang, Jinjie He, Baozhong Han, Lijing Xinjiang Univ Coll Geog Sci 666 Shengli Rd Urumqi 830046 Xinjiang Peoples R China Xinjiang Univ Xinjiang Key Lab Oasis Ecol Urumqi 830046 Peoples R China MNR Technol Innovat Ctr Cent Asia Geoinformat Expl Urumqi 830046 Peoples R China Chinese Acad Sci Inst Appl Ecol Shenyang 110164 Peoples R China Shenzhen Univ Shenzhen Key Lab Spatial Smart Sensing & Serv MNR Key Lab Geoenvironm Monitoring Great Bay Area Guangdong Key Lab Urban Informat Shenzhen 518060 Peoples R China China Agr Univ Coll Grassland Sci & Technol Beijing Peoples R China

Soil salinization is the main source of global soil degradation. It has impeded progress towards sustainable development goals (SDGs) by threatening 20% of irrigated areas. However, in many data-poor regions, accurate soil salinization information is unavailable. Thus, an updated soil salinity map with high accuracy and resolution is urgently needed to help local governments conduct precise management. In this study, a bootstrap hybrid machine learning framework was developed combine Sentinel-2 data and environmental covariates. The Boruta algorithm was applied to input the spectral information and environmental variables to identify the primary factors influencing soil salinity. By averaging 100 model iterations within a bootstrap framework, the soil salinity mapping outcomes were compared from four machine learning methods (bagging, classification and regression tree, random forest, and gradient boosting regression tree (GBRT)). The results showed that the models driven by spectral information and environmental covariates (strategy II) explained 68~88% of the variability in soil salinity. The model accuracy of strategy II was improved by 5%-8% over that of the models driven only by spectral information (strategy I). The GBRT yielded the most appropriate averaging performance of the four machine learning approaches within strategy II, with an R-2 of 0.88, a root mean square error (RMSE) of 6.33 dS m(-1) , a ratio of performance to interquartile distance (RPIQ) of 4.66 and model stability (ROB) of 0.44. The bootstrap averaging method was relatively stable and had high accuracy potential. The distribution of soil salinity in the Ebinur Lake region was the result of a combination of natural and human activity influences. The proposed approach provides a soil salinity mapping strategy with a fine resolution (10 m) and high accuracy in data-poor places. It may also aid in the restoration of biodiversity, the decrease in land degradation, and the avoidance of future food

关键词： Soil salinity Averaging model gradient boosting regression tree Environmental covariates

来源：评论

学校读者我要写书评

暂无评论

GBRT-Based Estimation of Terrestrial Latent Heat Flux in the Haihe River Basin from Satellite and Reanalysis Datasets

引用

REMOTE SENSING 2021年第6期13卷 1054-1054页

作者： Wang, Lu Zhang, Yuhu Yao, Yunjun Xiao, Zhiqiang Shang, Ke Guo, Xiaozheng Yang, Junming Xue, Shuhui Wang, Jie Capital Normal Univ Coll Resource Environm & Tourism Beijing 100048 Peoples R China Beijing Normal Univ Fac Geog Sci State Key Lab Remote Sensing Sci Beijing 100875 Peoples R China

An accurate and spatially continuous estimation of terrestrial latent heat flux (LE) is fundamental and crucial for the rational utilization of water resources in the Haihe River Basin (HRB). However, the sparsity of flux observation sites hinders the accurate characterization of spatiotemporal LE patterns over the HRB. In this study, we estimated the daily LE across the HRB using the gradient boosting regression tree (GBRT) from global land surface satellite NDVI data, reanalysis data and eddy covariance data. Compared with the random forests (RF) and extra tree regressor (ETR) methods, the GBRT obtains the best results, with R-2 = 0.86 and root mean square error (RMSE = 18.1 W/m(2). Then, we applied the GBRT algorithm to map the average annual terrestrial LE of the HRB from 2016 to 2018 with a spatial resolution of 0.05 degrees. When compared with the Global Land Surface Satellite (GLASS) and Moderate Resolution Imaging Spectroradiometer (MODIS) LE products, the difference between the terrestrial LE estimated by the GBRT algorithm and the GLASS and MODIS products was less than 20 W/m(2) in most areas;thus, the GBRT algorithm was reliable and reasonable for estimating the long-term LE estimation over the HRB.

关键词： latent heat flux gradient boosting regression tree machine learning method eddy covariance Haihe River Basin

来源：评论

学校读者我要写书评

暂无评论

Examining influential factors on the energy consumption of electric and diesel buses: A data-driven analysis of large-scale public transit network in Beijing

引用

ENERGY 2021年 216卷 119196-119196页

作者： Ma, Xiaolei Miao, Ran Wu, Xinkai Liu, Xianglong Beihang Univ Sch Transportat Sci & Engn Beijing Key Lab Cooperat Vehicle Infrastruct Syst Beijing 100191 Peoples R China Beihang Univ Beijing Adv Innovat Ctr Big Data & Brain Comp Beijing 100191 Peoples R China China Acad Transportat Sci China Urban Sustainable Transport Res Ctr Beijing 100013 Peoples R China

Switching from diesel-powered to battery-powered buses has been a global tendency. Traditional approaches rely on standard driving cycles or fuel economy data for energy consumption on a limited number of buses;thus, expanding to large bus fleets at the city level has become challenging. This study uses high-resolution GPS and smart card transaction data to generate each bus driving profile and weight dynamics in a large-scale transit network. Two vehicle activity-based energy consumption models are adopted and calibrated for diesel bus (DB) and electric bus by using the field data of 630 bus routes in Beijing. The average energy consumptions of DBs and electric buses are 43.5 and 14.1 L/100 km, respectively. A gradient boosting regression tree algorithm is presented to examine and rank distinct influential factors on the energy consumption of DBs and electric buses. Heterogenous behaviors are identified: the leading attributes affecting the energy consumption of electric buses and DBs are route characteristics and operational condition, respectively. After computing, the total energy conservation of electrifying all bus fleets is equivalent to 0.87% of daily electricity demand in Beijing. These findings set a good base for further studies on bus fleet replacement, charging infrastructure deployment, and electrified route prioritization. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Electric bus Diesel bus Energy consumption Public transit network gradient boosting regression tree

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Analysis Method for Human-Induced Vibration of Concrete Footbridges

引用

INTERNATIONAL JOURNAL OF STRUCTURAL STABILITY AND DYNAMICS 2021年第1期21卷

作者： Fu, Bo Wei, Xinxin Changan Univ Sch Civil Engn Xian 710061 Peoples R China Xian Univ Architecture & Technol State Key Lab Green Bldg Western China Xian 710055 Peoples R China Ruhr Univ Bochum Univ Str 150 D-44780 Bochum Germany

It is essential to reliably predict the human-induced vibrations in serviceability design of footbridges to ensure the vibration levels to be within the acceptable comfort limits. The human-induced structural responses are dependent on the dynamic properties of structures and human-induced excitations. For concrete footbridges, the elastic modulus of concrete is a vital parameter for determining the dynamic structural properties. To this end, a two-stage machine learning (ML)-based method is first proposed for modeling the elastic modulus of concrete. At the first stage, the ensemble algorithm, i.e. the gradient boosting regression tree (GBRT), is used to predict the compressive strength by selecting eight parameters, including concrete ingredients and curing time, as the inputs. At the second stage, the elastic modulus of concrete is modeled by using the GBRT method with the compressive strength as the input. Pedestrian crowd-induced load is the most common and crucial design load for footbridges. To consider the inter- and intra-subject variability in walking parameters and induced forces among persons in a crowd, a load model is developed by associating a modified social force model with a walking force model. By integrating the two submodels of structure and excitation, an intelligent analysis method for human-induced vibration is finally developed. A concrete footbridge with typical box cross-section subjected to human-induced excitation is analysed to illustrate the application of the proposed method.

关键词： Machine learning serviceability footbridge social force model human-induced vibration gradient boosting regression tree

来源：评论

学校读者我要写书评

暂无评论

Estimation of Long-Term Surface Downward Longwave Radiation over the Global Land from 2000 to 2018

引用

REMOTE SENSING 2021年第9期13卷 1848-1848页

作者： Feng, Chunjie Zhang, Xiaotong Wei, Yu Zhang, Weiyu Hou, Ning Xu, Jiawen Yang, Shuyue Xie, Xianhong Jiang, Bo Beijing Normal Univ State Key Lab Remote Sensing Sci Beijing 100875 Peoples R China Beijing Normal Univ Chinese Acad Sci Aerosp Informat Res Inst Fac Geog SciState Key Lab Remote Sensing Sci Beijing 100875 Peoples R China

It is of great importance for climate change studies to construct a worldwide, long-term surface downward longwave radiation (L-d, 4-100 mu m) dataset. Although a number of global L-d datasets are available, their low accuracies and coarse spatial resolutions limit their applications. This study generated a daily L-d dataset with a 5-km spatial resolution over the global land surface from 2000 to 2018 using atmospheric parameters, which include 2-m air temperature (Ta), relative humidity (RH) at 1000 hPa, total column water vapor (TCWV), surface downward shortwave radiation (S-d), and elevation, based on the gradient boosting regression tree (GBRT) method. The generated L-d dataset was evaluated using ground measurements collected from AmeriFlux, AsiaFlux, baseline surface radiation network (BSRN), surface radiation budget network (SURFRAD), and FLUXNET networks. The validation results showed that the root mean square error (RMSE), mean bias error (MBE), and correlation coefficient (R) values of the generated daily L-d dataset were 17.78 W m(-2), 0.99 W m(-2), and 0.96 (p < 0.01). Comparisons with other global land surface radiation products indicated that the generated L-d dataset performed better than the clouds and earth's radiant energy system synoptic (CERES-SYN) edition 4.1 dataset and ERA5 reanalysis product at the selected sites. In addition, the analysis of the spatiotemporal characteristics for the generated L-d dataset showed an increasing trend of 1.8 W m(-2) per decade (p < 0.01) from 2003 to 2018, which was closely related to Ta and water vapor pressure. In general, the generated L-d dataset has a higher spatial resolution and accuracy, which can contribute to perfect the existing radiation products.

关键词： surface downward longwave radiation air temperature relative humidity surface downward shortwave radiation total column water vapor gradient boosting regression tree

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of forecasting for air cargo volume: Statistical techniques vs. machine learning

引用

Journal of Data, Information and Management 2020年第4期2卷 243-255页

作者： Liu, Jiaming Ding, Lina Guan, Xiaoyu Gui, Jiao Xu, Jianbin School of Economics and Management Beijing University of Chemical Technology Beijing 100029 China InfoSky Technology Limited Beijing 100070 China

Air transportation is an important part of modern air logistics business, thereby providing safe, efficient, convenient and high-quality services. An accurate forecasting of daily air cargo volume can help to relieve the time delays and congestion for air transportation system. Therefore, this study is devoted to investigate the forecasting models which are suitable for air cargo volume prediction. To this end, this study presents an empirical evaluation of two statistical techniques and three machine learning models for air cargo volume prediction. Specifically, multiple linear regression(MLR), auto-regression integrated moving average(ARIMA), support vector regression(SVR), neural network(NN) and gradient boosting regression tree(GBRT) are deployed for this aim. The air cargo volume data from the real world over one year are collected to test the five forecasting models. For thoroughly comparison, the experiments with different forecasting horizons and strategies are conducted. The results show that two categories of forecasting models have complementary advantages in different scenarios. ARIMA is good at modeling short-term air cargo volume forecasting task while SVR obtains the best performances in long-term air cargo volume forecasting task. This study provides an useful tool for air cargo volume prediction of air transportation system. © Springer Nature Switzerland AG 2020.

关键词： Air cargo volume forecasting ARIMA gradient boosting regression tree Multiple linear regression Neural network Support vector regression

来源：评论

学校读者我要写书评

暂无评论

Prediction of splitting tensile strength of fiber-reinforced recycled aggregate concrete utilizing machine learning models with SHAP analysis

Hybrid Advances

引用

Hybrid Advances 2025年 11卷

作者： Md Al Adnan Muhammad Babur Faisal Farooq Mursaleen Shahid Zamiul Ahmed Pobithra Das Institute of Information Technology Noakhali Science and Technology University Noakhali Bangladesh Department of Civil Engineering Faculty of Engineering University of Central Punjab Pakistan Department of Engineering Aarhus University Denmark Department of Industrial Engineering University of Trento Trento Italy Department of Civil Engineering East West University Bangladesh Department of Civil Engineering Leading University Sylhet 3112 Bangladesh

The infrastructure industry utilizes a significant number of natural resources and produces a lot of construction waste, both of which have negative environmental effects. As a solution, recycled aggregate concrete has emerged as a practical substitute. Predicting strength accurately is essential for cutting design time and expenses while limiting material waste from numerous mixing tests. Machine learning methods tackle structural engineering issues, including the prediction of Splitting Tensile Strength (STS). In this study, used four novel machine learning models such as Random Forest regression (RFR), Extreme gradient boosting (XGBoost), gradient Boosted regression trees (GBRT), and Bagging Regressor (BR) with grid search for hyperparameter tuning to forecast the splitting tensile strength of fiber-reinforced recycled aggregate concrete (FRRAC). The machine learning models demonstrated high reliability in predicting splitting tensile strength, including robust values for R-squared (R 2 ), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Absolute Error (MAE). The prediction performance of the GBRT models showed the greatest R 2 value of 0.95 during the training stage and R 2 value of 0.83 during the testing phase. The XGBoost, RFR and BR models found R-square values were 0.822, 0.781 and 0.824 at the testing phase, respectively. Moreover, the RFR, BR, GBRT, and XGBoost model RMSE values were found to be 0.333, 0.298, 0.276, and 0.3004 at the testing phase, respectively, where the GBRT model RMSE value was found to be good. The GBRT model showed the lowest uncertainty value of both phases, with values of 0.619 and 0.597 for the training and testing phases, respectively. Furthermore, SHapley Additive exPlanations (SHAP) analysis found that CR, and additional of Fiber were the most influential input features and replacement percentage of CR (%) and RCA Absorption capacity (%) inputs had the lowest impact of Fiber-Reinforced Recycled Aggr

关键词： Splitting tensile strength Machine learning Recycled aggregate concrete Fiber-reinforced And SHapley additive exPlanations FRRAC Fiber-Reinforced Recycled Aggregate Concrete STS Splitting Tensile strength ML Machine Learning GBRT gradient boosting regression tree XGB Extreme gradient boosting RF Random forest BR Bagging algorithm SHAP Shapely Additive Explanatory Analysis RMSE Root Mean Squared Error R2 Coefficient of Determination MAE Mean Absolute Error MAPE Mean Absolute Percentage Error SD Standard Deviation CR Cement Ratio

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：