A technique for improving petroleum products forecasts using grey convolution models and genetic algorithms

Sapnken, Flavian Emmanuel; Ahmat, Khazali Acyl; Boukar, Michel; Nyobe, Serge Luc Biobiongono; Tamba, Jean Gaston

doi:10.1016/j.mex.2023.102097

Cited by 4 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, using GM to predict the main type of Fuel Combustion Emissions by Fuel Category and Statewide Greenhouse Gas Emissions. GM(1;1) [26,34,35] is mainly divided into the following step: Obtaining original sequence…”

Section: Hybrid Gm (11) Optimized By Svm -Elm Algorithmmentioning

confidence: 99%

Analysis of decarbonization path in New York state and forecasting carbon emissions using different machine learning algorithms

Ekaterina,

2024

Carb Neutrality

View full text Add to dashboard Cite

The state of New York admitted 143 million metric tons of carbon emissions from fossil fuels in 2020, prompting the ambitious goal set by the CLCPA to achieve carbon neutrality. The paper focused on analyzing and predicting carbon emissions using four different machine-learning algorithms. It examined emissions from fossil fuel combustion from 1990 to 2020 and validated four different algorithms to choose the most effective one for predicting emissions from 2020 to 2050. The analysis covered various economic sectors including transportation, residential, commercial, industrial, and electric power. By analyzing policies, the paper forecasted emissions for 2030 and 2050, leading to the identification of different pathways to reach carbon neutrality. The research concluded that in order to achieve neutrality, radical measures must be taken by the state of New York. Additionally, the paper compared the most recent data for 2021 with the forecasts, showing that significant measures need to be implemented to achieve the goal of carbon neutrality. Despite some studies assuming a trend of decreased emissions, the research revealed different results. The paper presents three pathways, two of which follow the ambitious plan to reach carbon neutrality. As a result, the emission amount by 2050 for the different pathways was projected to be 31.1, 22.4, and 111.95 of MMt CO2 e, showcasing the need for urgent action to combat climate change.

show abstract

Section: Hybrid Gm (11) Optimized By Svm -Elm Algorithmmentioning

confidence: 99%

Analysis of decarbonization path in New York state and forecasting carbon emissions using different machine learning algorithms

Ekaterina,

2024

Carb Neutrality

View full text Add to dashboard Cite

show abstract

“…In some cases, GM models fail to produce forecasts with the desired accuracy. When this is the case, we can either use optimisation algorithms, such as machine learning (Sapnken et al, 2023c) optimise predictions using heuristic algorithms (Sapnken et al, 2023a(Sapnken et al, , 2022a or restructure the functional prediction model (Sapnken and Tamba, 2022). As an example, Sonmez et al (2017) predicted Turkey's transport energy needs over the period 2014-2034, using the ABC algorithm across different variables such as total annual vehicle-km, population and gross domestic product.…”

Section: Related Studiesmentioning

confidence: 99%

“…This article uses the Sequential-GM (1,N)-GA (Sapnken et al, 2022b) and NeuralODE-GM(1,1) (Sapnken et al, 2023b) to estimate the future consumption of road transport gasoline and diesel needs in Chad for the period 2020-2030. The two models are compared based on their respective accuracies in order to of the selected models are assessed in the context of the projected demand for PP in the road transport sector in Chad up to 2030, the year of emergence.…”

Section: Objectives Contribution and Work Organisationmentioning

confidence: 99%

See 1 more Smart Citation

Forecasting Petroleum Products Consumption in the Chadian Road Transport Sector using Optimised Grey Models

Acyl,

Sapnken,

Jeutsa

et al. 2024

IJEEP

View full text Add to dashboard Cite

This study aims to estimate the demand for petroleum products (PP) in the Chadian road sector by 2030 and to determine which of the two models used is the most efficient. The methodology is based on two optimised Grey models, namely: the Sequential-GM(1,N)-GA and NeuralODE-GM(1,1) models. These models reduce forecasting errors compared with the conventional Grey model. The forecasts confirm that both models are robust, with MAPEs of 1.16% and 2.5% respectively for gasoline and diesel obtained with the Sequential-GM(1,N)-GA, and 3.3% and 4.8% respectively for gasoline and diesel obtained with the NeuralODE-GM(1,1). We note that the Sequential-GM(1,N)-GA is more robust than NeuralODE-GM(1,1) with regard to MAPEs. The estimated consumption needs for gasoline and diesel in the road transport sector by 2030 are 294376818.5 and 381570061.5 litres respectively for the Sequential-GM(1,N)-GA and 264376818.5 and 375570061.5 litres for the NeuralODE-GM(1,1). Based on these results, securing the supply of PP in the road transport sector requires the development of the downstream petroleum sector. The development of alternative energies and the acquisition of hybrid vehicles. A policy encouraging mass transport in urban areas can considerably reduce energy consumption in this sector. This study adds to the literature through the simultaneous use of two new optimised grey models and their comparison in terms of predicting demand for PP in the Chadian road transport sector.

show abstract

Forecasting CO2 emissions from road fuel combustion using grey prediction models: A novel approach

Sapnken¹,

Noume²,

Tamba³

2023

MethodsX

View full text Add to dashboard Cite

A technique for improving petroleum products forecasts using grey convolution models and genetic algorithms

Cited by 4 publications

References 20 publications

Analysis of decarbonization path in New York state and forecasting carbon emissions using different machine learning algorithms

Analysis of decarbonization path in New York state and forecasting carbon emissions using different machine learning algorithms

Forecasting Petroleum Products Consumption in the Chadian Road Transport Sector using Optimised Grey Models

Forecasting CO2 emissions from road fuel combustion using grey prediction models: A novel approach

Contact Info

Product

Resources

About