Performance Enhancement of Rainfall Pattern – Water Level Prediction Model Utilizing Self-Organizing-Map Clustering Method

Fahimi, Farzad; El-Shafie, Ahmed

doi:10.1007/s11269-016-1556-7

Cited by 23 publications

(13 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The map usually has a 2D structure with a map unit associated with a weight vector. where N ij is a 2D map grid (also called a neuron); W ij is the weight vector assigned to (i, j), the unit of SOM architecture; and L and M are number of rows and columns, respectively 43 – 45 . The steps of the SOM algorithm are displayed as follows: Step 1: Data normalization and SOM network initialize, the weight vector w ij ( i = 1 , 2 , …… , S; j = 1, 2, 3, ……, R ) is randomly set in the interval [0, 1], R is the sample dimension, and S is the number of output neurons.…”

Section: Methodsmentioning

confidence: 99%

Effects of land use/cover on surface water pollution based on remote sensing and 3D-EEM fluorescence data in the Jinghe Oasis

Wang

Fei

2018

Sci Rep

View full text Add to dashboard Cite

The key problem in the reasonable management of water is identifying the effective radius of surface water pollution. Remote sensing and three-dimensional fluorescence technologies were used to evaluate the effects of land use/cover on surface water pollution. The PARAFAC model and self-organizing map (SOM) neural network model were selected for this study. The results showed that four fluorescence components, microbial humic-like (C1), terrestrial humic-like organic (C2, C4), and protein-like organic (C3) substances, were successfully extracted by the PARAFAC factor analysis. Thirty water sampling points were selected to build 5 buffer zones. We found that the most significant relationships between land use and fluorescence components were within a 200 m buffer, and the maximum contributions to pollution were mainly from urban and salinized land sources. The clustering of land-use types and three-dimensional fluorescence peaks by the SOM neural network method demonstrated that the three-dimensional fluorescence peaks and land-use types could be grouped into 4 clusters. Principal factor analysis was selected to extract the two main fluorescence peaks from the four clustered fluorescence peaks; this study found that the relationships between salinized land, cropland and the fluorescence peaks of C1, W2, and W7 were significant by the stepwise multiple regression method.

show abstract

Section: Methodsmentioning

confidence: 99%

Effects of land use/cover on surface water pollution based on remote sensing and 3D-EEM fluorescence data in the Jinghe Oasis

Wang

Fei

2018

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Inside the black-box, a network is formed within the neurons which is similar to that of the nervous system in human brain [23,24,28]. The advantages of the ANN models include: (i) generalization of the unseen situations [29,30], (ii) ability to perform model-free function estimations, (iii) ability to learn from data relationships that are not otherwise known and, (iv) ability of handling non-linear functions [31,32]. The ANN model consists of input layer, hidden layer and output layer [33].…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Optimised neural network model for river-nitrogen prediction utilizing a new training approach

et al. 2020

View full text Add to dashboard Cite

In the past few decades, there has been a rapid growth in the concentration of nitrogenous compounds such as nitrate-nitrogen and ammonia-nitrogen in rivers, primarily due to increasing agricultural and industrial activities. These nitrogenous compounds are mainly responsible for eutrophication when present in river water, and for 'blue baby syndrome' when present in drinking water. High concentrations of these compounds in rivers may eventually lead to the closure of treatment plants. This study presents a training and a selection approach to develop an optimum artificial neural network model for predicting monthly average nitrate-N and monthly average ammonia-N. Several studies have predicted these compounds, but most of the proposed procedures do not involve testing various model architectures in order to achieve the optimum predicting model. Additionally, none of the models have been trained for hydrological conditions such as the case of Malaysia. This study presents models trained on the hydrological data from 1981 to 2017 for the Langat River in Selangor, Malaysia. The model architectures used for training are General Regression Neural Network (GRNN), Multilayer Neural Network and Radial Basis Function Neural Network (RBFNN). These models were trained for various combinations of internal parameters, input variables and model architectures. Post-training, the optimum performing model was selected based on the regression and error values and plot of predicted versus observed values. Optimum models provide promising results with a minimum overall regression value of 0.92.

show abstract

“…Candelieri [16] used clustering algorithms to detect water consumption patterns before applying short-term forecasting models. Similarly, Farzad and El-Shafie [17] enhanced the typical ANNs rainfall-water level data prediction model with the SOM clustering method in an unsupervised manner. Kardan Moghaddam et al [18] instead used spatial clustering approaches in a combination with machine learning models to predict aquifer groundwater level.…”

Section: Introductionmentioning

confidence: 99%

Hydrological Time Series Clustering: A Case Study of Telemetry Stations in Thailand

Prakaisak

Wongchaisuwat

2022

Water

View full text Add to dashboard Cite

Water level data from telemetry stations typically demonstrate diverse behaviors over time. Specific characteristics can be observed among distinct station groups that are different from others. Clustering time series data into a specified number of groups based on their similarity is an initial step for further analysis in water management analytics. Our main goal in this work is to develop a clustering framework based on a combination of feature representations, feature reduction techniques, as well as clustering algorithms. Thorough experiments on multiple combinations of these methods were conducted and compared. Based on collected water level data in Thailand, UMAP reduced representations of engineered features using HAC clustering with euclidean distance outperformed other methods. Its performance reached 0.8 Fowlkes-Mallows score. Out of 81 stations, only nine unclear cases were incorrectly clustered. Distinct behaviors with abrupt and frequent fluctuations could be perfectly identified.

show abstract

Performance Enhancement of Rainfall Pattern – Water Level Prediction Model Utilizing Self-Organizing-Map Clustering Method

Cited by 23 publications

References 27 publications

Effects of land use/cover on surface water pollution based on remote sensing and 3D-EEM fluorescence data in the Jinghe Oasis

Effects of land use/cover on surface water pollution based on remote sensing and 3D-EEM fluorescence data in the Jinghe Oasis

Optimised neural network model for river-nitrogen prediction utilizing a new training approach

Hydrological Time Series Clustering: A Case Study of Telemetry Stations in Thailand

Contact Info

Product

Resources

About