Evaluation of different types of artificial intelligence methods to model the suspended sediment load in Tigris River

Al-Mukhtar, Mustafa

doi:10.1051/matecconf/201816203003

Cited by 3 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the history of the ANFIS soft computing technique, [24][25] were pioneers. Because of its ability to deal with nonlinear phenomena, it is preferred for simulating and modelling complex hydrological systems [29][30][31][32]. Applications of ANFIS in diverse fields are quite numerous in the literature.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of ANFIS Predictive Ability Using Computed Sediment from Gullies and Dam

Oladosu¹,

Alademomi²,

Olaleye³

et al. 2023

J. Nig. Soc. Phys. Sci.

View full text Add to dashboard Cite

The study proposed an Adaptive Neuro-Fuzzy Inference Systems (ANFIS) model capable of predicting sediment deposited in a dam and sediment loss-in-transit (SLIT) using the potential of a formulated mathematical relation. The input parameters consist of five members viz: the rainfall, the slope, the particle size, the velocity, and the computed total volume of sediment exited from two prominent gullies for 2017, 2018, and 2019. The outputs are the total volume of sediment deposited at the adjoining Ikpoba dam for 2017, 2018, and 2019, respectively. The Ordinary Least Square (OLS) regression model on sediment volume retained all covariates with p<0.05, explaining 93.8% of the variability in the dataset. The multicollinearity effect on the dataset was assessed using the Variance Inflation Factor (VIF) which was found not to pose a problem for (VIF<5). The model was validated using the (MSE), the (MAE), and the correlation coefficient (r). The best prediction was obtained as: (RMSE = 0.0423; R2 = 0.947). The predicted volume of sediment was 842,895.8547m3 with an error of -0.3295344% and the predicted volume of SLIT was 57,787.98m3 which is an indication that ANFIS performs satisfactorily in predicting sediment volume for the gullies and the dam respectively

show abstract

Section: Introductionmentioning

confidence: 99%

Evaluation of ANFIS Predictive Ability Using Computed Sediment from Gullies and Dam

Oladosu¹,

Alademomi²,

Olaleye³

et al. 2023

J. Nig. Soc. Phys. Sci.

View full text Add to dashboard Cite

show abstract

Suspended sediment prediction using integrative soft computing models: on the analogy between the butterfly optimization and genetic algorithms

Fadaee

Mahdavi‐Meymand

Zounemat‐Kermani

2020

Geocarto International

View full text Add to dashboard Cite

A Critical Review of Capacitance-Resistance Models

Al‐Ghamdi

Hiba

Aly

et al. 2021

Day 1 Tue, October 12, 2021

View full text Add to dashboard Cite

A Capacitance Resistance Model (CRM) is an analytical model that only requires production and injection rates to predict reservoir performance. The CRM input is the injection rates and the output is the production rate. The input and output are related by the CRM parameters. The first parameter is the time delay (also called time constant) and is a function of pore volume, total compressibility, and productivity indices. The second parameter is the connectivity (also called gain, or weight), which quantifies the connectivity between producers and injectors (i.e. how much of the input is supporting the output). The CRM was developed for fields with minimum reservoir data, or for small fields not requiring a full reservoir simulation model, which can be time-consuming and expensive. The CRM is a quick, powerful analytical tool that is simple to use and requires readily available data. Most of the time, the injection and production rates are measured accurately and frequently, either weekly or bi-weekly. By solving the continuity equation for a homogenous reservoir (i.e. constant reservoir and fluid properties throughout the reservoir) the solution of the continuity equation can be indicative of the injection and production relation and therefore can be used to optimize injection schemes for higher ultimate hydrocarbon recovery. It is important to recognize that the CRM is not supposed to replace numerical reservoir simulators, which, in essence, are the most accurate means of reservoir performance prediction. Instead, the CRM aims to be a quick and easy way to infer reservoir performance in the absence of full-fledged simulation. The CRM has been used for several purposes as seen in the literature. First, as a tool to optimize waterflooding in oil reservoirs. The CRM can infer inter-well connectivity which will allow the engineer to adjust water injection rates to ensure uniform sweep in the reservoir and reduce the chance of early water breakthrough. The CRM was also used to optimize CO2 sequestration, whereby CO¬2 is captured from the atmosphere and stored in subsurface formations. The main hypothesis in CRM is that the characteristics of the reservoir can be inferred from analyzing production and injection data only. CRM does not require core data, logs, seismic, or any rock or fluids properties. This hypothesis can be challenged easily since most reservoirs have gradients of fluid properties, multi-porosity systems, and heterogeneous formations with different wettability presences. Albeit, several publications have shown that CRM can result in high certainty output. The objective of this report is to explain the concept of the CRM, conduct a critical review of the main CRM publications, compare CRM to other reservoir characterization tools and finally demonstrate some applications of the CRM.

show abstract

Evaluation of different types of artificial intelligence methods to model the suspended sediment load in Tigris River

Cited by 3 publications

References 24 publications

Evaluation of ANFIS Predictive Ability Using Computed Sediment from Gullies and Dam

Evaluation of ANFIS Predictive Ability Using Computed Sediment from Gullies and Dam

Suspended sediment prediction using integrative soft computing models: on the analogy between the butterfly optimization and genetic algorithms

A Critical Review of Capacitance-Resistance Models

Contact Info

Product

Resources

About