检索结果-内蒙古大学图书馆

A new synergistic approach for Sentinel-1 and PALSAR-2 in a machine learning framework to predict aboveground biomass of a dense mangrove forest

引用

ECOLOGICAL INFORMATICS 2022年 72卷

作者： Prakash, A. Jaya Behera, M. D. Ghosh, S. M. Das, A. Mishra, D. R. Indian Inst Technol Kharagpur Ctr Ocean River Atmosphere & Land Sci Kharagpur 721302 West Bengal India ISRO Space Applicat Ctr Ahmadabad India Univ Georgia Dept Geog Athens GA USA

Mangroves are well-recognized for their very high carbon sequestration potential. However, studies on their role in global carbon cycling and climate change are hindered due to lack of operational methodologies to model and map their biophysical properties. This study establishes a robust methodological protocol for aboveground biomass (AGB) estimation using i) field measurements, ii) a generic (in the absence of species-specific) allometric equation, iii) multi-sensor/polarization SAR data and derived variables thereof, and iv) machine learning models;that demonstrated high prediction accuracy (R-2 = 0.93) and low uncertainty (mean <= 3% and median <= 1.5%) for a mangrove forest. Following stratified random sampling and on-field accessibility criteria, we laid out 314 elementary sampling points of 0.04 ha each at Bhitarkanika wildlife sanctuary (BWS), India and measured circumference at breast height (CBH) and canopy tree height for 18 species. The estimated AGB range of a generic allometric equation was 9-474 Mg/ha for BWS, with a major representation of 9-347 Mg/ha. We utilized Sentinel-1 and ALOS-2/PALSAR-2 and derived their variables for AGB prediction. Compared to single sensor-based model, we observed higher prediction accuracy for combined sensor data (R-2 = 0.63, 0.87, 0.93;RMSE = 66.75, 39.95, 28.35 Mg/ha;MAE = 52.63, 24.21, 19.55 Mg/ha;and Bias = 3.42, 0.22, 2.15 Mg/ha for C, L and C & L bands respectively using a generalized additive model (GAM) over Random Forest (RF), Gradient Boosting Machines (GBM) and Support Vector Regression (SVR). The higher uncertainty pixels represented seasonal grassland and scrubs in the swampy areas and along the fringes of the creeks that experience diurnal tidal fluctuations. This robust methodology can be replicated for AGB estimates in other mangrove ecosystems to meet the operational carbon accounting requirements of various entities.

关键词： generalized additive model Bhitarkanika wildlife sanctuary Aboveground biomass Non-parametric models Sentinel-1 ALOS-2 PALSAR-2

来源：评论

学校读者我要写书评

暂无评论

A comparison of presence-only analytical techniques and their application in forest pest modeling

引用

ECOLOGICAL INFORMATICS 2022年 68卷 101525-101525页

作者： Munro, Holly L. Montes, Cristian R. Gandhi, Kamal J. K. Poisson, Miguel A. Univ Georgia DB Warnell Sch Forestry & Nat Resources 180 E Green St Athens GA 30602 USA Univ Georgia Warnell Sch Forestry & Nat Resources Plantat Management Res Cooperat Athens GA 30602 USA Bioforest SA Silviculture & Phytosanit Protect Div Concepcion Chile

Insect pests are natural disturbance agents that can significantly alter the structure and composition of forested landscapes, and thus impact their ability to provide critical ecosystem services. Predicting population levels of pest species has become crucial for the management of healthy forests, and species distribution modeling techniques may assist with predictions. Due to the nature of sampling in pest assessments there is often a lack of absence data which requires practitioners to rely on presence-only information. modeling approaches have been developed for presence-only data but have not been tested for pest species that have major impacts on forest ecosystems. Our research objectives were to compare species distribution models for traditional techniques (i.e., generalized linear and additive models) and contemporary machine learning algorithms (i.e., maximum entropy, random forest, gradient boosted decision trees, and extreme gradient boosting), as well as assess how varying background points influence model performance. True presence-absence data and presences combined with background point data at one, two, three, and ten times the number of presences were compared. Comparisons were done using a comprehensive dataset from 2405 survey plots that assessed the presence and absence of nonnative Sirex woodwasp (Sirex noctilio Fabricius) collected in pine plantations in Chile. Contemporary machine learning techniques (> 84% average accuracy) outperformed traditional modeling techniques (< 82% average accuracy) when utilizing true presence-absence data. For presence-background point models, accuracy tended to increase as the number of background points increased, except for generalized additive models and MaxEnt which had relatively similar performances. generalized linear models, MaxEnt, and random forest substantially underperformed as compared to other modeling frameworks when using background point data. Gradient boosting and extreme gradient boosting had

关键词： generalized additive model Gradient boosting Insects Machine learning MaxEnt Nonnative species Random forest Sirex noctilio

来源：评论

学校读者我要写书评

暂无评论

Interaction between sea surface chlorophyll a and seawater indicators in the sea ranching area: A case study in Haizhou Bay

引用

REGIONAL STUDIES IN MARINE SCIENCE 2022年 56卷

作者： Gao, Shike Ren, Shuangning Xie, Bin Zhang, Shuo Lu, Jikun Fu, Guanghui Shanghai Ocean Univ Coll Marine Sci Shanghai Peoples R China

Chlorophyll A (Chla) is a key parameter that reflects phytoplankton biomass and estimates red tide intensity. Studying the distribution characteristics of Chla concentrations and their correlation with various environmental indicators is of great significance. In this study, we analysed environmental monitoring data of Haizhou Bay, Lianyungang, Jiangsu Province, from 2004 to 2021 using a generalized additive model (GAM) to investigate the spatiotemporal variation in sea surface chlorophyll a (Chla) and its correlation with other sea water indicators. The results showed that the concentration of Chla increased gradually over the years but varied within the year, with the highest concentration in summer (July to September). With the passage of years, the fitting results of the model may be more consistent with the actual situation of Chla concentration distribution in this region. Compared with univariate GAM, multivariate GAM could effectively explain the variation in Chla concentration in the region over 20 years. Generally, the variation in Chla concentration is influenced by nutrients, BOD5 and salinity, depth, temperature and DO. BOD5 and depth are significant variables that can explain the variation in Chla concentration, but their interactions should be avoided in the analysis. We believe that the Chla concentration not only is affected by the rapid change in the estuarine environment but also has a potentially positive effect on the time lag effect of sea ranching construction, indicating that the interannual change in sea ranching construction plays a positive role in the potential change in the offshore environment. This study can provide a theoretical basis and an important reference for the further construction and management of sea ranching in the coastal waters of the world. (C) 2022 Elsevier B.V. All rights reserved.

关键词： Haizhou Bay Sea ranching Chlorophyll a Sea water indicator generalized additive model

来源：评论

学校读者我要写书评

暂无评论

Evidence of a Climate-Change-Induced Shift in European Beech Distribution: An Unequal Response in the Elevation, Temperature and Precipitation Gradients

引用

FORESTS 2022年第8期13卷 1311页

作者： Klopcic, Matija Rozman, Andrej Boncina, Andrej Univ Ljubljana Biotechn Fac Dept Forestry & Renewable Forest Resources Jamnikarjeva 101 Ljubljana 1000 Slovenia

Climate is a strong predictor of the geographic distribution of tree species, and thus climate change may trigger shifts in the distribution of a tree species and/or its demographic structure. In the study, we aim to comprehensively compare the distributions of four life stages of European beech (Fagus sylvatica) (i.e., regeneration, recruitment, young trees and mature trees) in forests in Slovenia, Central Europe, which are characterized by strong gradients of elevation (ELV), temperature (TEMP) and precipitation (PREC) to detect possible shifts in distribution and demography. Beech life stages were surveyed on 3366 plots. To depict disparities between ELV, TEMP and PREC distributions of beech life stages, we applied several non-parametric methods: basic statistical tests to study differences in medians, means, and 1st and 9th deciles;generalized additive models to study shifts in the optimum;and extreme value analysis to study shifts at the trailing and leading edges. A substantial shift in juvenile beech stages upward and toward colder sites was detected. However, the shift was not uniform along the distributions;the most significant shift was detected at the leading edge of ELV (+73 m) and TEMP (-2.6 degrees C), but surprisingly there was no beech movement identified at the trailing edge. The observed shift may be a result of the interplay between climate change, high spatial variability in microclimate, unexceptional droughts in the recent past, changes in forest use and possible limitations in the migration ability of beech and its adaptation capacity.

关键词： Fagus sylvatica successional life stages regeneration recruitment mature trees generalized additive model extreme value analysis

来源：评论

学校读者我要写书评

暂无评论

Negative binomial additive model for RNA-Seq data analysis

引用

BMC BIOINFORMATICS 2020年第1期21卷 171-171页

作者： Ren Xu Kuan Pei-Fen SUNY Stony Brook Dept Appl Math & Stat Stony Brook NY 11794 USA

Background: High-throughput sequencing experiments followed by differential expression analysis is a widely used approach for detecting genomic biomarkers. A fundamental step in differential expression analysis is to model the association between gene counts and covariates of interest. Existing models assume linear effect of covariates, which is restrictive and may not be sufficient for certain phenotypes. Results: We introduce NBAMSeq, a flexible statistical model based on the generalized additive model and allows for information sharing across genes in variance estimation. Specifically, we model the logarithm of mean gene counts as sums of smooth functions with the smoothing parameters and coefficients estimated simultaneously within a nested iterative method. The variance is estimated by the Bayesian shrinkage approach to fully exploit the information across all genes. Conclusions: Based on extensive simulations and case studies of RNA-Seq data, we show that NBAMSeq offers improved performance in detecting nonlinear effect and maintains equivalent performance in detecting linear effect compared to existing methods. The vignette and source code of NBAMSeq are available at http:// ***/packages/release/bioc/html/***.

关键词： Bayesian shrinkage Differential expression analysis generalized additive model RNA-Seq Spline model

来源：评论

学校读者我要写书评

暂无评论

A Comparative Classification Analysis of Abdominal Aortic Aneurysms by Machine Learning Algorithms

引用

ANNALS OF BIOMEDICAL ENGINEERING 2020年第4期48卷 1419-1429页

作者： Rengarajan, Balaji Wu, Wei Wiedner, Crystal Ko, Daijin Muluk, Satish C. Eskandari, Mark K. Menon, Prahlad G. Finol, Ender A. Univ Texas San Antonio Dept Mech Engn One UTSA Circle San Antonio TX 78249 USA Univ Texas San Antonio Dept Management Sci & Stat San Antonio TX 78249 USA Allegheny Gen Hosp Dept Thorac & Cardiovasc Surg Pittsburgh PA 15212 USA Northwestern Univ Feinberg Sch Med Chicago IL 60611 USA Carlow Univ Dept Math & Data Analyt Pittsburgh PA USA Univ Texas San Antonio UTSA UTHSA Joint Grad Program Biomed Engn San Antonio TX 78249 USA

The objective of this work was to perform image-based classification of abdominal aortic aneurysms (AAA) based on their demographic, geometric, and biomechanical attributes. We retrospectively reviewed existing demographics and abdominal computed tomography angiography images of 100 asymptomatic and 50 symptomatic AAA patients who received an elective or emergent repair, respectively, within 1-6 months of their last follow up. An in-house script developed within the MATLAB computational platform was used to segment the clinical images, calculate 53 descriptors of AAA geometry, and generate volume meshes suitable for finite element analysis (FEA). Using a third party FEA solver, four biomechanical markers were calculated from the wall stress distributions. Eight machine learning algorithms (MLA) were used to develop classification models based on the discriminatory potential of the demographic, geometric, and biomechanical variables. The overall classification performance of the algorithms was assessed by the accuracy, area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and precision of their predictions. The generalized additive model (GAM) was found to have the highest accuracy (87%), AUC (89%), and sensitivity (78%), and the third highest specificity (92%), in classifying the individual AAA as either asymptomatic or symptomatic. The k-nearest neighbor classifier yielded the highest specificity (96%). GAM used seven markers (six geometric and one biomechanical) to develop the classifier. The maximum transverse dimension, the average wall thickness at the maximum diameter, and the spatially averaged wall stress were found to be the most influential markers in the classification analysis. A second classification analysis revealed that using maximum diameter alone results in a lower accuracy (79%) than using GAM with seven geometric and biomechanical markers. We infer from these results that biomechanical and geometric measures by t

关键词： Abdominal aortic aneurysm Rupture risk evaluation Image segmentation Machine learning generalized additive model

来源：评论

学校读者我要写书评

暂无评论

Deadwood stocks in south-western European forests: Ecological patterns and large scale assessments

引用

SCIENCE OF THE TOTAL ENVIRONMENT 2020年 747卷 141237-141237页

作者： Alberdi, Iciar Moreno-Fernandez, Daniel Canellas, Isabel Adame, Patricia Hernandez, Laura Inst Nacl Invest & Tecnol Agr & Alimentaria INIA Dept Selvicultura & Gest Sistemas Forestales Ctr Invest Forestal CIFOR Ctra La Coruna Km 7-5 Madrid 28040 Spain Univ Alcala Henares Dept Ciencias Vida Forest Ecol & Restorat Grp Madrid Spain

Forest deadwood is a relevant factor in the provision of ecosystem services (forest biodiversity, carbon sequestration, recreational and aesthetic values), but it also influences the risk and impact of forest perturbations. Hence, reliable estimations are urgently need in the lack of detailed information in Mediterranean forests at large scales. In this study we provide, for the first time, national-level estimations for Spain based on the information from the Spanish National Forest Inventory (38,945 plots). In addition, we compare and validate two approaches for estimating deadwood stocks where data is lacking;the first of these being a modelling approach based on stand, climatic and physiographical variables, and the other considers the ratio between deadwood and living biomass. We also examine the different patterns stock across forest types in four biogeographical regions according to a broad-spectrum of species groups and forests with different degrees of anthropogenic influence. The degrees are based on levels of protection and naturalness categories. The modelling approach provides more robust deadwood estimates and better predictive capacity than the ratio approach. Alpine (6.09 ***-1) and Atlantic (3.53 ***(-1)) bioregion forests store significantly higher mean deadwood biomass stocks than Macaronesian and Mediterranean forests. However, the share of deadwood in relation to the total biomass stock is greater in Mediterranean biogeographical region. As regards species groups, the mean deadwood stock of mixed forests doubled the stocks found in conifer and broadleaved dominated forests. We also found significant differences in deadwood biomass stocks between forests with different levels of anthropogenic protection. However, forest types with intensive forest management had contrasting figures for deadwood stock. The mean values obtained at national level according to forest type, bioregion and degree of anthropogenic influence, provide baseline informat

关键词： Forest biodiversity indicator Carbon accounting Sustainability National statistics generalized additive model

来源：评论

学校读者我要写书评

暂无评论

Temperature significantly changes COVID-19 transmission in (sub) tropical cities of Brazil

引用

SCIENCE OF THE TOTAL ENVIRONMENT 2020年 729卷 138862-138862页

作者： Prata, David N. Rodrigues, Waldecy Bermejo, Paulo H. Fed Univ Tocantins Inst Reg Dev Grad Program Computat Modelling Quadra 109 Norte BR-77001090 Palmas TO Brazil Univ Brasilia Adm Dept Brasilia DF Brazil

The coronavirus disease 2019 (COVID-19) outbreak has become a severe public health issue. The novelty of the virus prompts a search for understanding of how ecological factors affect the transmission and survival of the virus. Several studies have robustly identified a relationship between temperature and the number of cases. However, there is no specific study for a tropical climate such as Brazil. This work aims to determine the relationship of temperature to COVID-19 infection for the state capital cities of Brazil. Cumulative data with the daily number of confirmed cases was collected from February 27 to April 1, 2020, for all 27 state capital cities of Brazil affected by COVID-19. A generalized additive model (GAM) was applied to explore the linear and nonlinear relationship between annual average temperature compensation and confirmed cases. Also, a polynomial linear regression model was proposed to represent the behavior of the growth curve of COVID-19 in the capital cities of Brazil. The GAM dose-response curve suggested a negative linear relationship between temperatures and daily cumulative confirmed cases of COVID-19 in the range from 16.8 degrees C to 27.4 degrees C. Each 1 degrees C rise of temperature was associated with a -4.8951% (t = -2.29, p = 0.0226) decrease in the number of daily cumulative confirmed cases of COVID-19. A sensitivity analysis assessed the robustness of the results of the model. The predicted R-squared of the polynomial linear regression model was 0.81053. In this study, which features the tropical temperatures of Brazil, the variation in annual average temperatures ranged from 16.8 degrees C to 27.4 degrees C. Results indicated that temperatures had a negative linear relationship with the number of confirmed cases. The curve flattened at a threshold of 25.8 degrees C. There is no evidence supporting that the curve declined for temperatures above 25.8 degrees C. The study had the goal of supporting governance for healthcare policy

关键词： Tropical temperature COVID-19 Brazil generalized additive model Transmission

来源：评论

学校读者我要写书评

暂无评论

Effects of temperature variation and humidity on the death of COVID-19 in Wuhan, China

引用

SCIENCE OF THE TOTAL ENVIRONMENT 2020年 724卷 138226-138226页

作者： Ma, Yueling Zhao, Yadong Liu, Jiangtao He, Xiaotao Wang, Bo Fu, Shihua Yan, Jun Niu, Jingping Zhou, Ji Luo, Bin Lanzhou Univ Sch Publ Hlth Inst Occupat Hlth & Environm Hlth Lanzhou 730000 Gansu Peoples R China Gansu Prov Ctr Dis Control & Prevent Sexually Transmitted Dis & Acquired Immune Defici Lanzhou 730000 Gansu Peoples R China Lanzhou Univ Dept Gen Surg Affiliated Hosp 1 Lanzhou 730000 Gansu Peoples R China Fudan Univ Dept Atmospher & Ocean Sci Shanghai Peoples R China Fudan Univ Inst Atmospher Sci Shanghai Peoples R China Shanghai Meteorol Bur Shanghai Key Lab Meteorol & Hlth Shanghai 200030 Peoples R China China Meteorol Adm Shanghai Typhoon Inst Shanghai 200030 Peoples R China

Meteorological parameters are the important factors influencing the infectious diseases such as severe acute respiratory syndrome (SARS) and influenza. This study aims to explore the association between Corona Virus Disease 2019 (COVID-19) deaths and weather parameters. In this study, we collected the daily death numbers of COVID-19, meteorological parameters and air pollutant data from 20 January 2020 to 29 February 2020 in Wuhan, China. generalized additive model was applied to explore the effect of temperature, humidity and diurnal temperature range on the daily death counts of COVID-19. There were 2299 COVID-19 death counts in Wuhan during the study period. A positive association with COVID-19 daily death counts was observed for diurnal temperature range (r = 0.44), but negative association for relative humidity (r = -0.32). In addition, one unit increase in diurnal temperature range was only associated with a 2.92% (95% CI: 0.61%, 5.28%) increase in COVID-19 deaths in lag 3. However, both 1 unit increase of temperature and absolute humidity were related to the decreased COVID-19 death in lag 3 and lag 5, with the greatest decrease both in lag 3 [-7.50% (95% CI: -10.99%,-3.88%) and -11.41% (95% CI: -19.68%,-2.29%)]. In summary, this study suggests the temperature variation and humidity may also be important factors affecting the COVID-19 mortality. (C) 2020 Elsevier B.V. All rights reserved.

关键词： COVID-19 Diurnal temperature range Temperature Humidity generalized additive model

来源：评论

学校读者我要写书评

暂无评论

The effects of air pollution and meteorological factors on measles cases in Lanzhou, China

引用

ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH 2020年第12期27卷 13524-13533页

作者： Peng, Lu Zhao, Xiuge Tao, Yan Mi, Shengquan Huang, Ju Zhang, Qinkai Lanzhou Univ Coll Earth & Environm Sci Key Lab Western Chinas Environm Syst Minist Educ Lanzhou 730000 Peoples R China Lanzhou Univ Coll Earth & Environm Sci Key Lab Environm Pollut Predict & Control 222 Tianshui South Rd Lanzhou 730000 Gansu Peoples R China Chinese Res Inst Environm Sci State Key Lab Environm Criteria & Risk Assessment Beijing 100012 Peoples R China Beijing Union Univ Coll Biochem Engn 97 North Fourth Ring East Rd Beijing 100023 Peoples R China South China Inst Environm Sci Minist Ecol & Environm PRC Guangzhou 510655 Peoples R China

By collecting daily data on measles cases, air pollutants, and meteorological data from 2005 to 2009 in Chengguan District of Lanzhou City, semi-parametric generalized additive model (GAM) was used to quantitatively study the impact of air pollutants and meteorological factors on daily measles cases. The results showed that air pollutants and meteorological factors had effect on the number of daily measles cases, and there was a certain lag effect. Except for SO2 and relative humidity, other factors showed statistically significant associations with daily measles cases: NO2 lag 6 days, PM10 and maximum temperature lag 5 days, minimum temperature and average temperature and average air pressure lag 4 days, visibility, and wind speed lag 3 days had the greatest impact on the number of daily measles cases. Under the optimum lag conditions, the number of daily measles cases increased by 15.1%, 17.6%, 7.0%, 116.6%, 98.6%, 85.7%, and 14.4% with the increase of 1 IQR in SO2, NO2, PM10, maximum temperature, minimum temperature, average temperature, and wind speed;with the increase of 1 IQR in average pressure, relative humidity, visibility, and daily measles cases decreased by 12.8%, 9.7%, and 13.1%, respectively. And different factors showed different seasonal effects. The effects of SO2 and temperature factors on daily measles cases were greater in spring and winter, but PM10 in summer.

关键词： Measles Air pollution Meteorological factors generalized additive model Lanzhou

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：