Goune Achille Clovice
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Goune Achille Clovice has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Germain Hubert Ben-Bolie
Laboratory of Nuclear, Atomic and Molecular Physics, Department of Physics, Faculty of Science, University of Yaounde I, Yaounde, Cameroon
5 shared publications - Jean Calvin Seutche
University of Yaoundé I- Cameroon
5 shared publications - Nsouandele Jean Luc
Department of Renewable Energy, National Advanced School of Engineering of Maroua, University of Maroua, PO Box 58 Maroua, Cameroon. | Department of Energy, National Advanced School of Engineering of Douala, University of Douala, Douala, Cameroon
5 shared publications - Bathelemy Essombo Essombo
University of Yaoundé I- Cameroon
3 shared publications - Ekani Roger Yannick
University of Douala
3 shared publications - Essombo Essombo Bathelemy
Department of Marine Energy Engineering, National Higher School of Maritime and Oceanic Technical Sciences of Kribi (NASMOST), University of Ebolowa, EBOLOWA, Cameroon
2 shared publications
Latest Publications
- Open Access
- 7 November 2026
- Published by Springer Nature in Discover Soil
- Vol. 3 (1) , 212
Estimate of the impact of rainwater on unsealed road degradation in the Mbanya catchment area using an artificial intelligence model
- 7 November 2026
- Published by Springer Nature in Discover Soil
- Vol. 3 (1) , 212
Open AccessEstimate of the impact of rainwater on unsealed road degradation in the Mbanya catchment area using an artificial intelligence model
- Open Access
- 26 June 2025
- Published by Springer Nature in Research Square
Estimate of the Impact of Rainwater on Road Degradation in the Mbanya Catchment Area Using an Artificial Intelligence Model
This article is part of the sustainable development of road infrastructure. It assesses the effects of rainwater on unpaved roads in the Mbanya catchment area between January 2019 and December 2023, and proposes mitigation measures. July is the month when the risk of deterioration on these unsealed roads is highest. The aim of the work is to limit the impact of rainwater on the deterioration of roads in the Mbanya catchment area. To this end, an experimental study was carried out to determine the initial water content in the soil and the quantity of quicklime needed to stabilise the soil. Genetic algorithms and neural networks were used to estimate the water content at different depths in the soil. The square correlation coefficient, with a value of around 0.72, and the root mean square error, with a value of around 0.37 on all the test data are performance indicators that demonstrate the high accuracy of the coupled genetic algorithm-neural network model. Porosity was used as input parameter for the model, and the results show that porosity have an influence on the evolution of the water content in the soil. The pavement construction project is possible on these unsealed roads in the Mbanya watershed, as the soils have a bearing capacity P ≥ 20MPa. However, the increase in water content can weaken as well as reduce the bearing capacity of the soil. The results of this work contribute to improving soil treatment prior to the design phase of the road construction project, in order to ensure the long-term sustainability of infrastructure in the Mbanya watershed.
- 26 June 2025
- Published by Springer Nature in Research Square
Open AccessEstimate of the Impact of Rainwater on Road Degradation in the Mbanya Catchment Area Using an Artificial Intelligence Model
This article is part of the sustainable development of road infrastructure. It assesses the effects of rainwater on unpaved roads in the Mbanya catchment area between January 2019 and December 2023, and proposes mitigation measures. July is the month when the risk of deterioration on these unsealed roads is highest. The aim of the work is to limit the impact of rainwater on the deterioration of roads in the Mbanya catchment area. To this end, an experimental study was carried out to determine the initial water content in the soil and the quantity of quicklime needed to stabilise the soil. Genetic algorithms and neural networks were used to estimate the water content at different depths in the soil. The square correlation coefficient, with a value of around 0.72, and the root mean square error, with a value of around 0.37 on all the test data are performance indicators that demonstrate the high accuracy of the coupled genetic algorithm-neural network model. Porosity was used as input parameter for the model, and the results show that porosity have an influence on the evolution of the water content in the soil. The pavement construction project is possible on these unsealed roads in the Mbanya watershed, as the soils have a bearing capacity P ≥ 20MPa. However, the increase in water content can weaken as well as reduce the bearing capacity of the soil. The results of this work contribute to improving soil treatment prior to the design phase of the road construction project, in order to ensure the long-term sustainability of infrastructure in the Mbanya watershed.
- Open Access
- 24 January 2025
- Published by Springer Nature in Research Square
Estimate of the Reduction in the Impact of Rainwater on Road Degradation in the Mbanya Catchment Area
This article is part of the sustainable development of road infrastructure. It assesses the effects of rainwater on unpaved roads in the Mbanya catchment area between January 2019 and December 2023, and proposes mitigation measures. July is the month when the risk of deterioration on these unsealed roads is highest. The aim of the work is to limit the impact of rainwater on the deterioration of roads in the Mbanya catchment area. To this end, an experimental study was carried out to determine the initial water content in the soil and the quantity of quicklime needed to stabilise the soil. Genetic algorithms and neural networks were used to estimate the water content at different depths in the soil. The square correlation coefficient, with a value of around 0.72, and the root mean square error, with a value of around 0.37 on all the test data are performance indicators that demonstrate the high accuracy of the coupled genetic algorithm-neural network model. Porosity and the quantity of lime were used as input parameters for the model, and the results show that porosity and the quantity of lime have an influence on the evolution of the water content in the soil. The pavement construction project is possible on these unsealed roads in the Mbanya watershed, as the soils have a bearing capacity P ≥ .20MPa. However, the increase in water content can weaken as well as reduce the bearing capacity of the soil. Treating the soil with quicklime can lower the water content after water consumption and strengthen the bearing capacity.
- 24 January 2025
- Published by Springer Nature in Research Square
Open AccessEstimate of the Reduction in the Impact of Rainwater on Road Degradation in the Mbanya Catchment Area
This article is part of the sustainable development of road infrastructure. It assesses the effects of rainwater on unpaved roads in the Mbanya catchment area between January 2019 and December 2023, and proposes mitigation measures. July is the month when the risk of deterioration on these unsealed roads is highest. The aim of the work is to limit the impact of rainwater on the deterioration of roads in the Mbanya catchment area. To this end, an experimental study was carried out to determine the initial water content in the soil and the quantity of quicklime needed to stabilise the soil. Genetic algorithms and neural networks were used to estimate the water content at different depths in the soil. The square correlation coefficient, with a value of around 0.72, and the root mean square error, with a value of around 0.37 on all the test data are performance indicators that demonstrate the high accuracy of the coupled genetic algorithm-neural network model. Porosity and the quantity of lime were used as input parameters for the model, and the results show that porosity and the quantity of lime have an influence on the evolution of the water content in the soil. The pavement construction project is possible on these unsealed roads in the Mbanya watershed, as the soils have a bearing capacity P ≥ .20MPa. However, the increase in water content can weaken as well as reduce the bearing capacity of the soil. Treating the soil with quicklime can lower the water content after water consumption and strengthen the bearing capacity.
- 21 May 2024
- Published by Springer Nature in Environmental Monitoring and Assessment
- Vol. 196 (6) , 1-20
Estimated greenhouse gas emissions in the Mbalmayo thermal power plant between 2016–2020 using the genetic-Gaussian algorithm coupling
The greenhouse gas (GHG) emissions inventories in our context result from the production of electricity from fuel oil at the Mbalmayo thermal power plant between 2016 and 2020. Our study area is located in the Central Cameroon region. The empirical method of the second level of industrialisation was applied to estimate GHG emissions and the application of the genetic algorithm-Gaussian (GA-Gaussian) coupling method was used to optimise the estimation of GHG emissions. Our work is of an experimental nature and aims to estimate the quantities of GHG produced by the Mbalmayo thermal power plant during its operation. The search for the best objective function using genetic algorithms is designed to bring us closer to the best concentration, and the Gaussian model is used to estimate the concentration level. The results obtained show that the average monthly emissions in kilograms (kg) of GHGs from the Mbalmayo thermal power plant are: 526 kg for carbon dioxide (CO2), 971.41 kg for methane (CH4) and 309.41 kg for nitrous oxide (N2O), for an average monthly production of 6058.12 kWh of energy. Evaluation of the stack height shows that increasing the stack height helps to reduce local GHG concentrations. According to the Cameroonian standards published in 2021, the limit concentrations of GHGs remain below 30 mg/m3 for CO2 and 200 μg/m3 for N2O, while for CH4 we reach the limit value of 60 μg/m3. These results will enable the authorities to take appropriate measures to reduce GHG concentrations.
- 21 May 2024
- Published by Springer Nature in Environmental Monitoring and Assessment
- Vol. 196 (6) , 1-20
Estimated greenhouse gas emissions in the Mbalmayo thermal power plant between 2016–2020 using the genetic-Gaussian algorithm coupling
The greenhouse gas (GHG) emissions inventories in our context result from the production of electricity from fuel oil at the Mbalmayo thermal power plant between 2016 and 2020. Our study area is located in the Central Cameroon region. The empirical method of the second level of industrialisation was applied to estimate GHG emissions and the application of the genetic algorithm-Gaussian (GA-Gaussian) coupling method was used to optimise the estimation of GHG emissions. Our work is of an experimental nature and aims to estimate the quantities of GHG produced by the Mbalmayo thermal power plant during its operation. The search for the best objective function using genetic algorithms is designed to bring us closer to the best concentration, and the Gaussian model is used to estimate the concentration level. The results obtained show that the average monthly emissions in kilograms (kg) of GHGs from the Mbalmayo thermal power plant are: 526 kg for carbon dioxide (CO2), 971.41 kg for methane (CH4) and 309.41 kg for nitrous oxide (N2O), for an average monthly production of 6058.12 kWh of energy. Evaluation of the stack height shows that increasing the stack height helps to reduce local GHG concentrations. According to the Cameroonian standards published in 2021, the limit concentrations of GHGs remain below 30 mg/m3 for CO2 and 200 μg/m3 for N2O, while for CH4 we reach the limit value of 60 μg/m3. These results will enable the authorities to take appropriate measures to reduce GHG concentrations.
- Open Access
- 31 May 2023
- Published by Springer Nature in SN Applied Sciences
- Vol. 5 (6) , 1-13
Assessment of the activity of the mbalmayo thermal power plant on groundwater quality
Groundwater is essential for daily life in Cameroon, but pollution sources can harm its quality through infiltration and dispersal of contaminants in the ground. This study focuses on estimating groundwater quality near the Mbalmayo Thermal Power Plant using a predictive model combining genetic algorithms and neural networks. The genetic algorithms were used to optimize the objective function, while neural networks learned the data to predict concentration values. From January 2017 to December 2021, several moisture content values were experimentally determined using collected dried and weighed soil samples. The results showed that moisture content varied from 1 to 82%. During this study period, the model takes into account the water content of the soil, porosity and permeability which have the same effect on the concentration level of the fuel oil in the groundwater. The average concentration of fuel oil was below 50 mg/l, which is the World Health Organisation standard However, there is a risk of groundwater pollution by fuel oil in the event of heavy activity at the Mbalmayo thermal power plant in the 0-445 m range. For protection during this period, the results show that the installation of populations on a perimeter located beyond 445 m and the construction of a water purification station are recommended. The results are decision support tools for the authorities.
- 31 May 2023
- Published by Springer Nature in SN Applied Sciences
- Vol. 5 (6) , 1-13
Open AccessAssessment of the activity of the mbalmayo thermal power plant on groundwater quality
Groundwater is essential for daily life in Cameroon, but pollution sources can harm its quality through infiltration and dispersal of contaminants in the ground. This study focuses on estimating groundwater quality near the Mbalmayo Thermal Power Plant using a predictive model combining genetic algorithms and neural networks. The genetic algorithms were used to optimize the objective function, while neural networks learned the data to predict concentration values. From January 2017 to December 2021, several moisture content values were experimentally determined using collected dried and weighed soil samples. The results showed that moisture content varied from 1 to 82%. During this study period, the model takes into account the water content of the soil, porosity and permeability which have the same effect on the concentration level of the fuel oil in the groundwater. The average concentration of fuel oil was below 50 mg/l, which is the World Health Organisation standard However, there is a risk of groundwater pollution by fuel oil in the event of heavy activity at the Mbalmayo thermal power plant in the 0-445 m range. For protection during this period, the results show that the installation of populations on a perimeter located beyond 445 m and the construction of a water purification station are recommended. The results are decision support tools for the authorities.