Spatiotemporal Classification Analysis of Long-Term Environmental Monitoring Data in the Northern Part of Lake Taihu, China by Using a Self-Organizing Map

Li, Wei; Zhang, H. T.; Zhu, Yuanrong; Liu, Zheng; He, Bin; Hashmi, Muhammad Zaffar; Chen, Z. L.; Wang, Y. S.

doi:10.3808/jei.201500297

Cited by 4 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, a simpler model structure means that the propagation of uncertainty from different sources is easier to assess. The use of data-driven models, such as neural networks, statistical methods or regression-based techniques (e.g., Li et al, 2015b, Li et al, 2015cYang et al, 2015), has been widespread in hydrology, particularly for short term daily flow rate forecasts, using a variety of input variables (Garen, 1992;Zealand et al, 1999;Campolo et al, 1999;Schilling and Walter, 2005;Adamowski and Sun, 2010;Duncan et al, 2011;Li et al, 2015a;Nourani et al, 2015). A recent regression based study predicted flow in the Bow River in Calgary, using a base difference regression model (Veiga et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

Short-Term Peak Flow Rate Prediction and Flood Risk Assessment Using Fuzzy Linear Regression

Khan¹,

Valeo²

2016

J ENVIRON INFORM

View full text Add to dashboard Cite

ABSTRACT.A fuzzy linear regression (FLR) method is proposed that uses real-time data to accurately predict daily peak flow rate for the Bow and Elbow Rivers in southern Alberta. FLR model performance was compared to a non-fuzzy, error-in-variables model (EIV). Mean daily flow rate, with a delay of one, two, three or seven days was used as the independent variable. In implementing the FLR, a unique hybrid modelling approach was devised that treated peak flow rate as probabilistic and mean daily flow rate as possibilistic. Three gauge errors, 5%, 10% and 20%, were tested and compared to quantify uncertainty in observed flow rate. The research proposed a new method of computing the exceedance probability of peak flow rate using fuzzy numbers. NSE, PBIAS and RSR and a proposed rating system were used to evaluate and compare the methods. Two different calibration schemes were used, including a quasi-real time system. The tests demonstrated that FLR with a one day lag was a very good predictor of peak flow rate and outperformed EIV for two stations on the Bow River. A test dataset from the floods of June 2013 in Calgary was used for risk assessment. The FLR results demonstrated higher flexibility and sensitivity to the flood as it approached Calgary. The fuzzy method was able to capture the peak flow rate for the majority of the high flow rate days, while the EIV model was unable to predict this data within the 95% confidence interval.

show abstract

Section: Introductionmentioning

confidence: 99%

Short-Term Peak Flow Rate Prediction and Flood Risk Assessment Using Fuzzy Linear Regression

Khan¹,

Valeo²

2016

J ENVIRON INFORM

View full text Add to dashboard Cite

show abstract

“…In this context, the analysis of the relationship among physical, chemical, and biological character-istics of the environment is becoming crucial (Huang and Chang, 2003). Many methods for environmental monitoring have been proposed in recent studies, demonstrating that the debate among scholars on this issue is very lively (Li et al, 2015;Yang et al, 2015;Rege et al, 2015). Since changes in environmental factors involve qualitative modifications in species composition, the most direct and effective measure of water body condition is the status of its living systems (Pompeu et al, 2005).…”

Section: Introductionmentioning

confidence: 99%

Parametric Functional Analysis of Variance for Fish Biodiversity Assessment

Battista¹,

Fortuna²,

Maturo³

2016

J ENV INFORM

View full text Add to dashboard Cite

ABSTRACT. Due to the increasing impact of human activities, water conservation has become a primary aim of environmental management policies. In this context, fish biodiversity represents a good measure of water quality because changes in ecological factors involve qualitative modifications in species composition. For this reason, the analysis of the interaction between biodiversity and environmental characteristics becomes crucial. This paper aims to analyse the effects of habitat and seasonality on fish biodiversity in freshwater environments. In particular, we applied functional data analysis to the beta diversity profile. The proposed approach allows us to overcome the limitations of the classical biodiversity indices, highlighting its multidimensional aspect. More in detail, our research focuses on the functional data analysis of variance in order to quantify the effects exerted on a functional observation by some factors. This model is applied to a real data set concerning ichthyic biodiversity of 104 streams in the province of Arezzo (Central Italy). We consider first the fish zonation and then the seasonality as factors; the results show that species diversity fluctuates seasonally whereas the zonation has no significant effect in influencing the biodiversity. Our proposal is a powerful tool for the analysis of the relationship between qualitative variables and a functional response. Since the diversity profile is a function of the relative abundance vector in a fixed domain, this method is particularly suited to the beta profile and it could be very helpful to monitor or to identify areas of high environmental risk.

show abstract

“…While there are many different approaches to explore the relationship of variables, multivariate statistical tech-niques including cluster analysis, principle component analysis, factor analysis, discriminant analysis, and self-organizing map are most frequently adopted to qualitatively identify critical influential factors on water quality and spatial and temporal variations from complex data sets Panda et al, 2006;Shrestha and Kazama, 2007;Li et al, 2015). In particular, these methods have the merit of computational simplicity and provide a geometrically intuitive interpretation due to the data matrix structure, for instance, in the principal component analysis.…”

Section: Introductionmentioning

confidence: 99%

Probabilistic Evaluation of Causal Relationship between Variables for Water Quality Management

He¹

2016

J ENVIRON INFORM

View full text Add to dashboard Cite

ABSTRACT. In aquatic environments, a complex interplay exists among physical, chemical, and biological water quality characteristics, which are constantly influenced by exogenous factors such as hydrological, meteorological and geological conditions. Due to the spatial and temporal variations of exogenous factors, the relationship between the water quality parameters and these factors hence becomes complicated and challenging. Given the large data matrix, one type of methods frequently seen in the literature belongs to the multivariate analysis which generates a qualitative measure of the relationships among variables in a geometrically intuitive way. However, a quantitative evaluation from a probabilistic perspective is favorable since it defines a measurable causality among variables so that more efficient water management strategies can be formulated. This paper illustrates a new way to discover the relationship between two variables by estimating their joint distribution which fully interprets the statistical dependence. A multivariate Gaussian mixture model was employed to describe the data. The model parameters were determined using the previously developed estimation approach, which is capable of dealing with both multivariate variables and censored data. The joint distribution and the conditional distribution were computed and used to describe the statistical distribution of water quality parameters, which are subject to the effects of hydrometeorological conditions. The method was demonstrated by a case study on the Bow River in Alberta, Canada. The results shed light on how one variable affects the distribution of the other variable under complex environments in a probabilistic context.

show abstract

Spatiotemporal Classification Analysis of Long-Term Environmental Monitoring Data in the Northern Part of Lake Taihu, China by Using a Self-Organizing Map

Cited by 4 publications

References 32 publications

Short-Term Peak Flow Rate Prediction and Flood Risk Assessment Using Fuzzy Linear Regression

Short-Term Peak Flow Rate Prediction and Flood Risk Assessment Using Fuzzy Linear Regression

Parametric Functional Analysis of Variance for Fish Biodiversity Assessment

Probabilistic Evaluation of Causal Relationship between Variables for Water Quality Management

Contact Info

Product

Resources

About