检索结果-内蒙古大学图书馆

Does increased model complexity improve description of phosphorus dynamics in a large treatment wetland?

ECOLOGICAL ENGINEERING 2012年 42卷 283-294页

作者： Paudel, Rajendra Jawitz, James W. Univ Florida Dept Soil & Water Sci Gainesville FL 32611 USA Univ Florida Ft Lauderdale Res & Educ Ctr Ft Lauderdale FL 33314 USA

As the structure of ecological models grows more complex, it becomes increasingly important to identify the appropriate level of complexity for reliable process description and prediction. Here, a suite of mechanistic biogeochemical models with different levels of complexity for representing phosphorus cycling processes was developed and tested against observations from a large treatment wetland. The study site was the 147-ha Cell 4 of Stormwater Treatment Area 1 West, which was designed to help protect the greater Everglades, FL, USA, from nutrient over-enrichment. Six biogeochemical models of differing complexity were coupled with a pre-calibrated two-dimensional hydrodynamic model of Cell 4 and tested against field data. We provide guidance for evaluating a set of models with varying level of complexity using key model attributes that influence the suitability of a model or a set of models. Considerations of model accuracy, complexity, and explanatory depth are combined into a single indicator of model effectiveness. Results revealed that the most complex model structure may not necessarily be the most effective in simulating the dynamics of total phosphorus (TP) concentrations in the wetland. The rate of improvement in the model performance decreased as model complexity increased. Although the most complex model reproduced the field observations best, the marginal improvement in model performance compared to simpler models was outweighed by the higher costs of increased complexity. Highly detailed representations of system structures may not be useful to simulate TP dynamics in treatment wetlands if comprehensive data sets are not available to constrain each pathway. It is crucial for model developers and users to evaluate model structures of differing complexity to identify the appropriate level of complexity for given data and questions of interest. (C) 2012 Elsevier B.V. All rights reserved.

关键词： model complexity Effectiveness Mechanistic Biogeochemical Wetland Everglades Phosphorus

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of the Accuracy of Machine Learning models for Predicting Tempered Martensite Hardness According to model complexity

KOREAN JOURNAL OF METALS AND MATERIALS

引用

KOREAN JOURNAL OF METALS AND MATERIALS 2022年第9期60卷 713-721页

作者： Jeon, Junhyub Kim, DongEung Hong, Jun-Ho Kim, Hwi-Jun Lee, Seok-Jae Jeonbuk Natl Univ Div Adv Mat Engn Jeonju 54896 South Korea Korea Inst Ind Technol Res Inst Adv Mfg & Mat Technol Incheon 21999 South Korea

We investigated various numerical methods including a physical-based empirical equation, linear regression, shallow neural network, and deep learning approaches, to compare their accuracy for predicting the hardness of tempered martensite in low alloy steels. The physical-based empirical equation, which had been previously proposed with experimental data, was labelled and used in the present study. While it had a smaller number of coefficients, the prediction accuracy of the physical-based empirical equation was almost similar to that of the regression model based on the response surface method. The prediction accuracy of the machine learning models clearly improved as the number of layers increased and became more complicated in structure before the model began to overfit. The key point we found was that a single layered neural network model with optimized hyperparameters resulted in similar or better hardness prediction performance compared to deep learning models with a more complex architecture. We also analyzed 18 research papers from the literature which used neural network models to predict the hardness of steels. Only two recent papers adopted a convolutional neural network, as a kind of deep learning model, in a new attempt to predict hardness. The other 16 papers from 1998 to 2021 commonly chose shallow neural network models because a more complicated model is less effective than a simple model for regression problems with well-labeled experimental data in materials science and engineering.

关键词： prediction accuracy model complexity machine learning model regression tempered martensite hardness

来源：评论

学校读者我要写书评

暂无评论

A Primer for model Selection: The Decisive Role of model complexity

引用

WATER RESOURCES RESEARCH 2018年第3期54卷 1688-1715页

作者： Hoege, Marvin Woehling, Thomas Nowak, Wolfgang Univ Stuttgart Inst Modelling Hydraul & Environm Syst LS3 SimTech Stuttgart Germany Univ Tubingen Ctr Appl Geosci Tubingen Germany Tech Univ Dresden Dept Hydrol Dresden Germany Lincoln Agritech Lincoln Environm Res Hamilton New Zealand

Selecting a "best" model among several competing candidate models poses an often encountered problem in water resources modeling (and other disciplines which employ models). For a modeler, the best model fulfills a certain purpose best (e.g., flood prediction), which is typically assessed by comparing model simulations to data (e.g., stream flow). model selection methods find the "best" trade-off between good fit with data and model complexity. In this context, the interpretations of model complexity implied by different model selection methods are crucial, because they represent different underlying goals of modeling. Over the last decades, numerous model selection criteria have been proposed, but modelers who primarily want to apply a model selection criterion often face a lack of guidance for choosing the right criterion that matches their goal. We propose a classification scheme for model selection criteria that helps to find the right criterion for a specific goal, i.e., which employs the correct complexity interpretation. We identify four model selection classes which seek to achieve high predictive density, low predictive error, high model probability, or shortest compression of data. These goals can be achieved by following either nonconsistent or consistent model selection and by either incorporating a Bayesian parameter prior or not. We allocate commonly used criteria to these four classes, analyze how they represent model complexity and what this means for the model selection task. Finally, we provide guidance on choosing the right type of criteria for specific model selection tasks. (A quick guide through all key points is given at the end of the introduction.)

关键词： model selection model complexity information criteria (IC) primer

来源：评论

学校读者我要写书评

暂无评论

The influence of biogeochemical conditions and level of model complexity when simulating cometabolic biodegradation in sorbent-water systems

引用

ADVANCES IN WATER RESOURCES 2006年第4期29卷 571-589页

作者： Haws, NW Bouwer, EJ Ball, WP Johns Hopkins Univ Dept Geog & Environm Engn Baltimore MD 21218 USA

Eighteen models with different levels of complexity for representing sorption, mass transfer, and biodegradation are used to simulate the biodegradation of toluene (primary substrate) and TCE (cometabolic substrate). The simulations are conducted for hypothetical completely mixed systems of various scenarios with regard to sorbent, microbial composition, and solute concentrations. The purpose of the suite of simulations is to investigate the sensitivity of different modeling approaches in simulating the bio-attenuation of co-existing solutes in sorbent-water systems. The sensitivity of results to the modeling approach depends on the biogeochemical conditions of the system. For example, the results are insensitive to the type of sorption model in systems with low sorption strength and slow biodegradation rates, and insensitive to the biodegradation rate model if mass transfer controlled. Differences among model results are generally greater when evaluated in terms of total mass removal rather than aqueous phase concentration reduction. The fate of the cometabolite is more sensitive to the proper consideration of co-solute effects than is the fate of the primary substrate. For a given system, graphical comparison of a characteristic mass transfer rate coefficient (alpha(mt)) versus a characteristic biodegradation rate coefficient (alpha(bio)) Provides an indication of how sensitivity to the different processes may be expected to change with time and can guide the selection of an appropriate level of model complexity. (C) 2005 Elsevier Ltd. All rights reserved.

关键词： bioavailability cometabolism model complexity sorption mass transfer biodegradation

来源：评论

学校读者我要写书评

暂无评论

Systematic increase in model complexity helps to identify dominant streamflow mechanisms in two small forested basins

引用

HYDROLOGICAL SCIENCES JOURNAL-JOURNAL DES SCIENCES HYDROLOGIQUES 2019年第4期64卷 455-472页

作者： David, Paula C. Oliveira, Debora Y. Grison, Fernando Kobiyama, Masato Chaffe, Pedro L. B. Univ Fed Santa Catarina Grad Programme Environm Engn Florianopolis SC Brazil Fed Univ Fronteira Sul Acad Coordinat Chapeco Brazil Univ Fed Rio Grande do Sul Hydraul Res Inst Porto Alegre RS Brazil Univ Fed Santa Catarina Dept Sanit & Environm Engn Florianopolis SC Brazil

This study shows how the use of increasing model complexity allows us to hypothesize about dominant streamflow mechanisms in two small Brazilian forested basins. Nine different structures from SUPERFLEX, an objective framework to systematically increase hydrological model complexity, were tested and we extended the flexible modelling methodology to error models as well. We show that applying a rigorous methodology in a model evaluation framework, with residual analysis and control of model complexity, is essential for testing a model as a hypothesis for dominant hydrological controls. Our results indicate that the model architecture was more important than the increase in the number of model parameters. Better performing models were those with a parallel structure, which confirms our a priori belief about the dominant runoff mechanisms of the studied catchments, characterized by a rapid response to rainfall, but also a constant river discharge fed by water storage on the thick soil layer.

关键词： SUPERFLEX model complexity DREAM Bayesian inference

来源：评论

学校读者我要写书评

暂无评论

Time complexity and model complexity of fast identification of continuous-time LTI systems

引用

IEEE TRANSACTIONS ON AUTOMATIC CONTROL 1999年第10期44卷 1814-1828页

作者： Lin, L Wang, LY Zames, G MPD Technol Inc Hauppauge NY 11788 USA Wayne State Univ Dept Elect & Comp Engn Detroit MI 48202 USA

The problem of fast identification of continuous-time systems is formulated in the metric complexity theory setting. It is shown that the two key steps to achieving fast identification, i.e., optimal input design and optimal model selection, can be carried out independently when the true system belongs to a general a priori set. These two optimization problems can be reduced to standard Gel'fand and Kolmogorov n-width problems in metric complexity theory. It is shown that although arbitrarily accurate identification can be achieved on a small time interval by reducing the noise-signal ratio and designing the input carefully, identification speed is limited by the metric complexity of the a priori uncertainty set when the noise/signal ratio is fixed.

关键词： adaptive control H-infinity identification model complexity time complexity

来源：评论

学校读者我要写书评

暂无评论

Two Recurrent Neural Networks With Reduced model complexity for Constrained l1-Norm Optimization

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第9期34卷 6173-6185页

作者： Xia, Youshen Wang, Jun Lu, Zhenyu Huang, Liqing Nanjing Univ Informat Sci & Technol Coll Artificial Intelligence Nanjing 211544 Peoples R China City Univ Hong Kong Dept Comp Sci Kowloon Hong Kong Peoples R China Nanjing Univ Informat Sci & Technol Jiangsu Key Lab Meteorol Observat & Informat Proc Nanjing 210044 Peoples R China Fujian Normal Univ Coll Math & Informat Fuzhou 350117 Peoples R China

Because of the robustness and sparsity performance of least absolute deviation (LAD or l(1)) optimization, developing effective solution methods becomes an important topic. Recurrent neural networks (RNNs) are reported to be capable of effectively solving constrained l(1)-norm optimization problems, but their convergence speed is limited. To accelerate the convergence, this article introduces two RNNs, in form of continuous- and discrete-time systems, for solving l(1)-norm optimization problems with linear equality and inequality constraints. The RNNs are theoretically proven to be globally convergent to optimal solutions without any condition. With reduced model complexity, the two RNNs can significantly expedite constrained l(1)-norm optimization. Numerical simulation results show that the two RNNs spend much less computational time than related RNNs and numerical optimization algorithms for linearly constrained l(1)-norm optimization.

关键词： Fast computation linearly constrained l(1)-norm optimization model complexity recurrent neural network (RNN)

来源：评论

学校读者我要写书评

暂无评论

Forecasting future global food demand: A systematic review and meta-analysis of model complexity

引用

ENVIRONMENT INTERNATIONAL 2018年 120卷 93-103页

作者： Flies, Emily J. Brook, Barry W. Blomqvist, Linus Buettel, Jessie C. Univ Tasmania Sch Biol Sci Private Bag 55 Hobart Tas 7001 Australia Breakthrough Inst Oakland CA USA ARC Ctr Excellence Australian Biodivers & Heritag Wollongong NSW Australia

Predicting future food demand is a critical step for formulating the agricultural, economic and conservation policies required to feed over 9 billion people by 2050 while doing minimal harm to the environment. However, published future food demand estimates range substantially, making it difficult to determine optimal policies. Here we present a systematic review of the food demand literature-including a meta-analysis of papers reporting average global food demand predictions-and test the effect of model complexity on predictions. We show that while estimates of future global kilocalorie demand have a broad range, they are not consistently dependent on model complexity or form. Indeed, time-series and simple income-based models often make similar predictions to integrated assessments (e.g., with expert opinions, future prices or climate influencing forecasts), despite having different underlying assumptions and mechanisms. However, reporting of model accuracy and uncertainty was uncommon, leading to difficulties in making evidence-based decisions about which forecasts to trust. We argue for improved model reporting and transparency to reduce this problem and improve the pace of development in this field.

关键词： Food demand Prediction model complexity Global Aggregation Gross domestic product (GDP)

来源：评论

学校读者我要写书评

暂无评论

Evaluation of admittance domain behavioural model complexity requirements for Power Amplifier design

引用

IET MICROWAVES ANTENNAS & PROPAGATION 2022年第12期16卷 780-788页

作者： Rocio Moure, Maria Casbon, Michael Ladero, Nicolas Fernandez-Barciela, Monica Tasker, Paul J. Univ Vigo AtlanTTic Res Ctr C Maxwell S-N Vigo 36310 Spain Cardiff Univ Cardiff Sch Engn Cardiff Wales

In the framework of Power Amplifier (PA) design for communications, frequency domain non-linear behavioural models have shown their potential as efficient complementary modelling tools when Field Effect Transistor compact models are not available or sufficiently accurate. The Admittance behavioural model, formulated in the V-I domain, is especially suitable for device size and fundamental frequency scaling. It is important to note that the direct extraction of this model, from the Nonlinear Vector Network Analyser (NVNA) load-pull (LP) measurements, requires some extra processing since it necessitates a Look-up-Table indexed to |V-11| rather than |A(11)|. When using such models in PA design, there is the need for the user to select the necessary model complexity. To address this requirement, in this paper, a systematic analysis methodology, to guide the user, is presented and validated in different PA design scenarios. The methodology was tested using NVNA LP measurements of GaN Heterostructure FETs. A fifth order Admittance model formulation showed good accuracy in the studied PA design scenarios.

关键词： model complexity direct extraction network synthesis gallium compounds wide band gap semiconductors frequency domain nonlinear behavioural models frequency-domain analysis systematic analysis methodology table lookup nonlinear vector network analyser load-pull measurements III-V semiconductors power amplifiers circuit complexity V-I domain network analysers admittance domain behavioural model complexity requirement evaluation power amplifier design NVNA LP measurements look-up-table semiconductor heterojunctions field effect transistor compact models field effect transistor circuits fifth order admittance model formulation heterostructure FETs PA design scenarios fundamental frequency scaling Admittance behavioural model efficient complementary modelling tools

来源：评论

学校读者我要写书评

暂无评论

Combined uncertainty of hydrological model complexity and satellite-based forcing data evaluated in two data-scarce semi-arid catchments in Ethiopia

引用

JOURNAL OF HYDROLOGY 2014年第PartB期519卷 2049-2066页

作者： Knoche, Malte Fischer, Christian Pohl, Eric Krause, Peter Merz, Ralf UFZ Helmholtz Ctr Environm Res Dept Catchment Hydrol D-06120 Halle Germany Univ Jena Dept Geoinformat Hydrol & Modelling D-07743 Jena Germany Bergakad Freiberg Univ Min & Technol Inst Geol Remote Sensing Grp D-09599 Freiberg Germany Thuringen State Inst Environm & Geol D-07745 Jena Germany

In water resources modeling, meteorological data scarcity can be compensated by various global data sets, but those data sets can differ tremendously. In the literature, hydrological models of differing complexity are proposed for estimating the water resources of semi-arid catchments, and also to evaluate rainfall data sets. The goal of this paper is to provide a joint analysis of modeling uncertainty due to different input data and increasing model complexity. Impacts of mutually concealed uncertainties on model performance and model outputs are exemplified in two data sparse semi-arid catchments in Ethiopia. We applied a semi-distributed and a fully distributed hydrological model, having different levels of complexity. Three different satellite-based rainfall data sets and two temperature products were used as model inputs. The semi-distributed model demonstrated good validation performances, while the fully distributed model was more sensitive to data uncertainties. The application of TRMM version 6 completely failed and the high-resolution CMORPH precipitation estimate outperformed TRMM version 7. In contrast, the use of high-resolution temperature data did not improve the model results. The large differences in remotely sensed input data were buffered inside the hydrological models. Therefore, data set evaluations regarding only the simulated hydrographs were less meaningful. In contrast, the investigation of parameter evolution and distributed outputs' variability appeared to be a valuable tool to uncover the interdependencies of data and model uncertainties. We suggest this procedure to be applied by default in water resources estimations that are affected by data scarcity, but especially when data sets are evaluated using hydrological models. Our case study demonstrates that estimations of groundwater recharge and actual evapotranspiration vary largely, depending on the applied data sets and models. The joint analysis reveals large interdependencies between

关键词： Hydrological modeling Data scarcity Uncertainty Remote sensing precipitation model complexity East Africa

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：