SUBHRAJYOTI BHATTACHARYYA | Indian Institute of Technology Kharagpur (original) (raw)
Papers by SUBHRAJYOTI BHATTACHARYYA
Petroleum Science and Technology, Nov 25, 2021
Abstract The main objective of this paper is to develop a novel data-driven-based model that can ... more Abstract The main objective of this paper is to develop a novel data-driven-based model that can accurately predict the decline curves and EUR (Estimated Ultimate Recovery) for new wells based on the data collected from nearby wells. This is because decline curves are easier and faster alternative to complex reservoir simulators which perform computationally expensive operations. In contrast to this, decline curves require only a few parameters in the equation which can be easily collected from the existing data of the wells. The predictor variables were successfully linked to SEDM (Stretched Exponential Decline Model) decline curve parameters (n and τ) in a random set of oil field well data. The relative influences of various well parameters were also examined to determine the hidden relationship between them. The novelty in this study lies in the algorithm and dataset that we used for the rate decline prediction in Eagle Ford data set. Although, this paper has referenced some previous papers where machine learning has been used to make prediction, but this paper presents use of new algorithm as well as a new dataset. As more data get available, there is definitely extra room for further data analysis and improved results.
Heliyon, Apr 1, 2022
Traditional fossil fuels are our primary source of energy, but due to the rapidly increasing huma... more Traditional fossil fuels are our primary source of energy, but due to the rapidly increasing human population and their never-ending demands is diminishing the petroleum reserves quickly as they are in a limited stock inside the earth and the pollution caused by fossil fuels is a matter of great concern, so we need an alternative safe, clean & green source of fuel. Biodiesel is attracting everyone's eyes as an alternative and renewable energy. In this study, feedstock was prepared, and the oil was extracted from Thevetia peruviana seeds and transesterified. The transesterified biodiesel oil's physical and chemical properties were determined and compared with the universal standard values. The GC-MS and FTIR were used to determine fatty acids and esters present in the transesterified biodiesel oil. The novelty in this study is that the use of this novel method which produces an outstanding quality of Biodiesel oil, the methods employed in the analysis and determination of physicochemical properties and the chemical structure of the Thevetia Peruviana Biodiesel Oil and comparing these properties to check its usability as Biodiesel and the new type of non-edible oilseeds (Yellow Oleander) seeds used as a source of the biodiesel oil.
Upstream oil and gas technology, Feb 1, 2022
The main objective of this paper is to develop a novel machine learning based model that can accu... more The main objective of this paper is to develop a novel machine learning based model that can accurately predict the decline curves and EUR (Estimated Ultimate Recovery) for new wells based on the data collected from nearby wells. This is because decline curves are easier and faster alternative to complex reservoir simulators which perform computationally expensive operations. In contrast to this, decline curves require only a few parameters in the equation which can be easily collected from the existing data of the wells. In this study, first we collected the well data corresponding to well parameters such as initial monthly oil flow rate (qi), well completion parameters (i.e., no. of fracturing stages, completed length, amount of proppant used, amount of fracturing fluid used), well location parameters (TVD Heel-Toe Difference), reservoir fluid properties (Oil API Gravity, initial 24 h period Gas-Oil Ratio (GOR), initial 24 h period Gas Produced, initial 24 h period Oil Produced), flowing tubing pressure, casing pressure tubing size,choke size from publicly available databases of the Eagle Ford Shale formation Texas RRC (Railroad Commission of Texas). Wells were selected randomly and only those wells were finally included for the study whose data of the all the required parameters were available. The model parameters were estimated by fitting the production data to the decline curve models. Artificial Neural Network (ANN) was employed to build Machine learning models as a function of the above well parameters for the corresponding model parameters. The decline curves for new or existing wells were rapidly predicted using these models. In order to estimate the predictive accuracy of these models when applied to new or test wells cross validation technique such as k-fold cross validation was employed. These models were also used to predict EUR for the test wells. Additionally, feature selection was also done using algorithms such as Chi Square Test (χ2) and Minimum Redundancy Maximum Relevance (MRMR) Algorithm to determine the relative importance of predictor variables in predicting EUR. The predictor variables were successfully linked to SEDM (Stretched Exponential Decline Model) decline curve parameters (n and τ) in a random set of oil field well data. The relative influences of various well parameters were also examined to determine the hidden relationship between them. The novelty in this study lies in the algorithm and dataset that we used for the rate decline prediction in Eagle Ford data set. Although, this paper has referenced some previous papers where machine learning has been used to make prediction, but this paper presents use of new algorithm as well as a new dataset. As more data gets available, there is definitely extra room for further data analysis and improved results using machine learning methods. In future, the number of wells can be increased and the updated results can again be submitted after investing more time. It should be noted here that data downloading and preparing takes most of the time for such study especially when dealing with oil and gas data.
Heliyon, Dec 1, 2022
Reservoir simulation is needed for forecasting hydrocarbon production, determining pressure and s... more Reservoir simulation is needed for forecasting hydrocarbon production, determining pressure and saturation, well planning, and field development, among other things. The primary objective is to estimate reservoir performance over a period of time and use that data to enhance hydrocarbon recovery under existing operating conditions. In commercial reservoir simulators, a large number of grid blocks are employed to capture the comprehensive information about a reservoir model, such as porosity and permeability, when the reservoir becomes heterogeneous and complicated. This large number of grid blocks is associated with a large number of mass balance equations that need to be solved simultaneously thereby increasing the amount of computational time it takes to solve them. During reservoir simulation, while moving from one-time level to the next requires a large number of iterations if the properties of reservoir fluids are pressure-sensitive. These further increases the computational cost needed during simulation. The primary objective of this paper is to present a novel approach for reservoir simulation that uses Random Forest (RF) which is one of the widely used Machine learning (ML) algorithm to reduce the number of iterations at each time step and speed up the process. This study investigated the benefits of employing the novel approach created using RF with an application to a conventional single-phase gas reservoir. The study's novelty is in developing a new ML-based reservoir simulator that will make reservoir simulation much faster and computationally more efficient. The standard physics-based system of equations has been included while the traditional reservoir simulation algorithm is modified.
Elsevier, 2022
Reservoir simulation is needed for forecasting hydrocarbon production, determining pressure and s... more Reservoir simulation is needed for forecasting hydrocarbon production, determining pressure and saturation, well planning, and field development, among other things. The primary objective is to estimate reservoir performance over a period of time and use that data to enhance hydrocarbon recovery under existing operating conditions. In commercial reservoir simulators, a large number of grid blocks are employed to capture the comprehensive information about a reservoir model, such as porosity and permeability, when the reservoir becomes heterogeneous and complicated. This large number of grid blocks is associated with a large number of mass balance equations that need to be solved simultaneously thereby increasing the amount of computational time it takes to solve them. During reservoir simulation, while moving from one-time level to the next requires a large number of iterations if the properties of reservoir fluids are pressure-sensitive. These further increases the computational cost needed during simulation. The primary objective of this paper is to present a novel approach for reservoir simulation that uses Random Forest (RF) which is one of the widely used Machine learning (ML) algorithm to reduce the number of iterations at each time step and speed up the process. This study investigated the benefits of employing the novel approach created using RF with an application to a conventional single-phase gas reservoir. The study's novelty is in developing a new ML-based reservoir simulator that will make reservoir simulation much faster and computationally more efficient. The standard physics-based system of equations has been included while the traditional reservoir simulation algorithm is modified.
Scientific Reports (Nature Portfolio), 2022
Commercial reservoir simulators are required to solve discretized mass-balance equations. When th... more Commercial reservoir simulators are required to solve discretized mass-balance equations. When the
reservoir becomes heterogeneous and complex, more grid blocks can be used, which requires detailed
and accurate reservoir information, for e.g. porosity, permeability, and other parameters that are not
always available in the feld. Predicting the EUR (Estimated Ultimate Recovery) and rate decline for
a single well can therefore take hours or days, making them computationally expensive and timeconsuming. In contrast, decline curve models are a simpler and speedier option because they only
require a few variables in the equation that can be easily gathered from the wells’ current data. The
well data for this study was gathered from the Montana Board of Oil and Gas Conservation’s publicly
accessible databases. The SEDM (Stretched Exponential Decline Model) decline curve equation
variables specifcally designed for unconventional reservoirs variables were correlated to the predictor
parameters in a random oil feld well data set. The study examined the relative infuences of several
well parameters. The study’s novelty comes from developing an innovative machine learning (ML)
(random forest (RF)) based model for fast rate-decline and EUR prediction in Bakken Shale oil wells.
The successful application of this study relies highly on the availability of good quality and quantity of
the dataset.
Upstream Oil and Gas Technology (Elsevier), 2022
The main objective of this paper is to develop a novel machine learning based model that can accu... more The main objective of this paper is to develop a novel machine learning based model that can accurately predict
the decline curves and EUR (Estimated Ultimate Recovery) for new wells based on the data collected from nearby
wells. This is because decline curves are easier and faster alternative to complex reservoir simulators which
perform computationally expensive operations. In contrast to this, decline curves require only a few parameters
in the equation which can be easily collected from the existing data of the wells. In this study, first we collected
the well data corresponding to well parameters such as initial monthly oil flow rate (qi), well completion parameters (i.e., no. of fracturing stages, completed length, amount of proppant used, amount of fracturing fluid
used), well location parameters (TVD Heel-Toe Difference), reservoir fluid properties (Oil API Gravity, initial 24
h period Gas-Oil Ratio (GOR), initial 24 h period Gas Produced, initial 24 h period Oil Produced), flowing tubing
pressure, casing pressure tubing size,choke size from publicly available databases of the Eagle Ford Shale formation Texas RRC (Railroad Commission of Texas). Wells were selected randomly and only those wells were
finally included for the study whose data of the all the required parameters were available. The model parameters were estimated by fitting the production data to the decline curve models. Artificial Neural Network (ANN)
was employed to build Machine learning models as a function of the above well parameters for the corresponding
model parameters. The decline curves for new or existing wells were rapidly predicted using these models. In
order to estimate the predictive accuracy of these models when applied to new or test wells cross validation
technique such as k-fold cross validation was employed. These models were also used to predict EUR for the test
wells. Additionally, feature selection was also done using algorithms such as Chi Square Test (χ2) and Minimum
Redundancy Maximum Relevance (MRMR) Algorithm to determine the relative importance of predictor variables
in predicting EUR. The predictor variables were successfully linked to SEDM (Stretched Exponential Decline
Model) decline curve parameters (n and τ) in a random set of oil field well data. The relative influences of various
well parameters were also examined to determine the hidden relationship between them. The novelty in this
study lies in the algorithm and dataset that we used for the rate decline prediction in Eagle Ford data set.
Although, this paper has referenced some previous papers where machine learning has been used to make
prediction, but this paper presents use of new algorithm as well as a new dataset. As more data gets available,
there is definitely extra room for further data analysis and improved results using machine learning methods. In
future, the number of wells can be increased and the updated results can again be submitted after investing more
time. It should be noted here that data downloading and preparing takes most of the time for such study
especially when dealing with oil and gas data.
Petroleum Science and Technology (Taylor and Francis), 2022
The main objective of this paper is to develop a novel data driven based model that can accuratel... more The main objective of this paper is to develop a novel data driven based model that can accurately predict the decline curves and EUR (Estimated Ultimate Recovery) for new wells based on the data collected from nearby wells. This is because decline curves are easier and faster alternative to complex reservoir simulators which perform computationally expensive operations. In contrast to this, decline curves require only a few parameters in the equation which can be easily collected from the existing data of the wells. The predictor variables were successfully linked to SEDM (Stretched Exponential Decline Model) decline curve parameters (n and τ) in a random set of oil field well data. The relative influences of various well parameters were also examined to determine the hidden relationship between them. The novelty in this study lies in the algorithm and dataset that we used for the rate decline prediction in Eagle Ford data set. Although, this paper has referenced some previous papers where machine learning has been used to make prediction, but this paper presents use of new algorithm as well as a new dataset. As more data gets available, there is definitely extra room for further data analysis and improved results.
Heliyon
Yellow Oleander seeds were collected, and their oil was extracted. The oil was transesterified, a... more Yellow Oleander seeds were collected, and their oil was extracted. The oil was transesterified, and its physicochemical properties were determined. The oil properties were compared with the properties of Biodiesel, Diesel. The oil properties were compared with the properties of B10, B20.
Arabian Journal of Geosciences, Springer Nature, 2022
Sand production from oil and gas wells is a major operational problem leading to the spending of ... more Sand production from oil and gas wells is a major operational problem leading to the spending of millions of dollars each
year. Sand production can cause plugged wells, lead to erosion of equipment, and may reduce the well productivity. This
paper tries to evaluate efective sand control techniques through the use of novel methodology and tools which can be
employed in sand-producing felds. In this study, core samples of fve sand-producing oil wells of Assam Arakan Basin
were collected, and those samples were frst disintegrated with a hammer to obtain the sand grains. The sand samples
were then acid washed, decanted with water, and oven-dried to ensure that all the sand grains were disintegrated correctly and to make them ready for performing laboratory analysis. Particle size distribution (PSD) study was then carried
out through the dry sieving method. After the calculation of cumulative weight % and grain size in each of the sieves
from the ASTM sieve conversion chart, “S”-shaped distribution curve was constructed for each of the wells and well
completion parameters like (D10, D40, D50, D90, D95) were calculated from the curve. Sorting coefcient (SC), uniformity coefcient (UC), and fnes content were then calculated for each of the wells using the standard formulas used in the
industry, and by comparing the calculated values of these parameters with standard tables used in industry, the most
efective sand control technique was determined for each of these wells. In my study, D10 (<0.4 mm), D40 (<0.3 mm), D50
(<0.3 mm), D90 (<0.2 mm), D95 (<0.2 mm), (SC<5), (UC<2), (fnes<0.5%), and gravel size range from 1 to 2.2 mm
and by comparing these calculated values with standard tables, standalone alone screen (SAS) (wire-wrapped screen)
with screen slot size D50 and gravel pack of 12/20 US Mesh with screen size ranging from 500 to 540 micron was found
to be the most efective sand control technique for the fve sand-producing wells. Also, the collected sand samples contain
coarse sand (0.83–0.9%), fne sand (45.96–46.3%), medium sand (49–49.3%), very fne sand (3.1–3.39%), and slit and
clay (0.54–0.84%). Although this paper has referenced some previous papers where studies on production sand control
in oil wells have been performed, the novelty in this study lies in the use of simple tools and experimental methodology
employed for determining the most efective sand control technique for these wells located in a signifcant hydrocarbon
producing basin and oil feld.
Resource-Efficient Technologies, Tomsk Polytechnic University, 2020
During drilling, different problems are encountered that can interfere with smooth drilling proce... more During drilling, different problems are encountered that can interfere with smooth drilling processes, including the accumulation of
cuttings, reduced penetration rates, pipe sticking, loss of wellbore stability, and loss of circulation. These problems are generally encountered with conventional drilling mud, such as the bentonite–barite mud system. Formation damage is the most common problem
encountered in bentonite mud systems with high solid content. In this work, we aimed to formulate two low-solid nondispersed
(LSND) muds: carboxymethyl cellulose (CMC)–LSND mud and partially hydrolyzed polyacrylamide (PHPA)–LSND mud. A comparative analysis was performed to evaluate their property enhancements. LSND muds aid in maintaining hole stability and proper
cutting removal. The results of this work show that the addition of both CMC and PHPA helps to improve drilling fluid properties;
however, the PHPA–LSND mud was found to be superior. Shale swelling is a major concern in the petroleum industry, as it causes
various other problems, such as pipe sticking, low penetration rates, and bit wear. The effect of these two LSND polymer muds in
inhibiting shale swelling was analyzed using shale collected from the Champhai district of Mizoram, India.
Petroleum Science and Technology, Nov 25, 2021
Abstract The main objective of this paper is to develop a novel data-driven-based model that can ... more Abstract The main objective of this paper is to develop a novel data-driven-based model that can accurately predict the decline curves and EUR (Estimated Ultimate Recovery) for new wells based on the data collected from nearby wells. This is because decline curves are easier and faster alternative to complex reservoir simulators which perform computationally expensive operations. In contrast to this, decline curves require only a few parameters in the equation which can be easily collected from the existing data of the wells. The predictor variables were successfully linked to SEDM (Stretched Exponential Decline Model) decline curve parameters (n and τ) in a random set of oil field well data. The relative influences of various well parameters were also examined to determine the hidden relationship between them. The novelty in this study lies in the algorithm and dataset that we used for the rate decline prediction in Eagle Ford data set. Although, this paper has referenced some previous papers where machine learning has been used to make prediction, but this paper presents use of new algorithm as well as a new dataset. As more data get available, there is definitely extra room for further data analysis and improved results.
Heliyon, Apr 1, 2022
Traditional fossil fuels are our primary source of energy, but due to the rapidly increasing huma... more Traditional fossil fuels are our primary source of energy, but due to the rapidly increasing human population and their never-ending demands is diminishing the petroleum reserves quickly as they are in a limited stock inside the earth and the pollution caused by fossil fuels is a matter of great concern, so we need an alternative safe, clean & green source of fuel. Biodiesel is attracting everyone's eyes as an alternative and renewable energy. In this study, feedstock was prepared, and the oil was extracted from Thevetia peruviana seeds and transesterified. The transesterified biodiesel oil's physical and chemical properties were determined and compared with the universal standard values. The GC-MS and FTIR were used to determine fatty acids and esters present in the transesterified biodiesel oil. The novelty in this study is that the use of this novel method which produces an outstanding quality of Biodiesel oil, the methods employed in the analysis and determination of physicochemical properties and the chemical structure of the Thevetia Peruviana Biodiesel Oil and comparing these properties to check its usability as Biodiesel and the new type of non-edible oilseeds (Yellow Oleander) seeds used as a source of the biodiesel oil.
Upstream oil and gas technology, Feb 1, 2022
The main objective of this paper is to develop a novel machine learning based model that can accu... more The main objective of this paper is to develop a novel machine learning based model that can accurately predict the decline curves and EUR (Estimated Ultimate Recovery) for new wells based on the data collected from nearby wells. This is because decline curves are easier and faster alternative to complex reservoir simulators which perform computationally expensive operations. In contrast to this, decline curves require only a few parameters in the equation which can be easily collected from the existing data of the wells. In this study, first we collected the well data corresponding to well parameters such as initial monthly oil flow rate (qi), well completion parameters (i.e., no. of fracturing stages, completed length, amount of proppant used, amount of fracturing fluid used), well location parameters (TVD Heel-Toe Difference), reservoir fluid properties (Oil API Gravity, initial 24 h period Gas-Oil Ratio (GOR), initial 24 h period Gas Produced, initial 24 h period Oil Produced), flowing tubing pressure, casing pressure tubing size,choke size from publicly available databases of the Eagle Ford Shale formation Texas RRC (Railroad Commission of Texas). Wells were selected randomly and only those wells were finally included for the study whose data of the all the required parameters were available. The model parameters were estimated by fitting the production data to the decline curve models. Artificial Neural Network (ANN) was employed to build Machine learning models as a function of the above well parameters for the corresponding model parameters. The decline curves for new or existing wells were rapidly predicted using these models. In order to estimate the predictive accuracy of these models when applied to new or test wells cross validation technique such as k-fold cross validation was employed. These models were also used to predict EUR for the test wells. Additionally, feature selection was also done using algorithms such as Chi Square Test (χ2) and Minimum Redundancy Maximum Relevance (MRMR) Algorithm to determine the relative importance of predictor variables in predicting EUR. The predictor variables were successfully linked to SEDM (Stretched Exponential Decline Model) decline curve parameters (n and τ) in a random set of oil field well data. The relative influences of various well parameters were also examined to determine the hidden relationship between them. The novelty in this study lies in the algorithm and dataset that we used for the rate decline prediction in Eagle Ford data set. Although, this paper has referenced some previous papers where machine learning has been used to make prediction, but this paper presents use of new algorithm as well as a new dataset. As more data gets available, there is definitely extra room for further data analysis and improved results using machine learning methods. In future, the number of wells can be increased and the updated results can again be submitted after investing more time. It should be noted here that data downloading and preparing takes most of the time for such study especially when dealing with oil and gas data.
Heliyon, Dec 1, 2022
Reservoir simulation is needed for forecasting hydrocarbon production, determining pressure and s... more Reservoir simulation is needed for forecasting hydrocarbon production, determining pressure and saturation, well planning, and field development, among other things. The primary objective is to estimate reservoir performance over a period of time and use that data to enhance hydrocarbon recovery under existing operating conditions. In commercial reservoir simulators, a large number of grid blocks are employed to capture the comprehensive information about a reservoir model, such as porosity and permeability, when the reservoir becomes heterogeneous and complicated. This large number of grid blocks is associated with a large number of mass balance equations that need to be solved simultaneously thereby increasing the amount of computational time it takes to solve them. During reservoir simulation, while moving from one-time level to the next requires a large number of iterations if the properties of reservoir fluids are pressure-sensitive. These further increases the computational cost needed during simulation. The primary objective of this paper is to present a novel approach for reservoir simulation that uses Random Forest (RF) which is one of the widely used Machine learning (ML) algorithm to reduce the number of iterations at each time step and speed up the process. This study investigated the benefits of employing the novel approach created using RF with an application to a conventional single-phase gas reservoir. The study's novelty is in developing a new ML-based reservoir simulator that will make reservoir simulation much faster and computationally more efficient. The standard physics-based system of equations has been included while the traditional reservoir simulation algorithm is modified.
Elsevier, 2022
Reservoir simulation is needed for forecasting hydrocarbon production, determining pressure and s... more Reservoir simulation is needed for forecasting hydrocarbon production, determining pressure and saturation, well planning, and field development, among other things. The primary objective is to estimate reservoir performance over a period of time and use that data to enhance hydrocarbon recovery under existing operating conditions. In commercial reservoir simulators, a large number of grid blocks are employed to capture the comprehensive information about a reservoir model, such as porosity and permeability, when the reservoir becomes heterogeneous and complicated. This large number of grid blocks is associated with a large number of mass balance equations that need to be solved simultaneously thereby increasing the amount of computational time it takes to solve them. During reservoir simulation, while moving from one-time level to the next requires a large number of iterations if the properties of reservoir fluids are pressure-sensitive. These further increases the computational cost needed during simulation. The primary objective of this paper is to present a novel approach for reservoir simulation that uses Random Forest (RF) which is one of the widely used Machine learning (ML) algorithm to reduce the number of iterations at each time step and speed up the process. This study investigated the benefits of employing the novel approach created using RF with an application to a conventional single-phase gas reservoir. The study's novelty is in developing a new ML-based reservoir simulator that will make reservoir simulation much faster and computationally more efficient. The standard physics-based system of equations has been included while the traditional reservoir simulation algorithm is modified.
Scientific Reports (Nature Portfolio), 2022
Commercial reservoir simulators are required to solve discretized mass-balance equations. When th... more Commercial reservoir simulators are required to solve discretized mass-balance equations. When the
reservoir becomes heterogeneous and complex, more grid blocks can be used, which requires detailed
and accurate reservoir information, for e.g. porosity, permeability, and other parameters that are not
always available in the feld. Predicting the EUR (Estimated Ultimate Recovery) and rate decline for
a single well can therefore take hours or days, making them computationally expensive and timeconsuming. In contrast, decline curve models are a simpler and speedier option because they only
require a few variables in the equation that can be easily gathered from the wells’ current data. The
well data for this study was gathered from the Montana Board of Oil and Gas Conservation’s publicly
accessible databases. The SEDM (Stretched Exponential Decline Model) decline curve equation
variables specifcally designed for unconventional reservoirs variables were correlated to the predictor
parameters in a random oil feld well data set. The study examined the relative infuences of several
well parameters. The study’s novelty comes from developing an innovative machine learning (ML)
(random forest (RF)) based model for fast rate-decline and EUR prediction in Bakken Shale oil wells.
The successful application of this study relies highly on the availability of good quality and quantity of
the dataset.
Upstream Oil and Gas Technology (Elsevier), 2022
The main objective of this paper is to develop a novel machine learning based model that can accu... more The main objective of this paper is to develop a novel machine learning based model that can accurately predict
the decline curves and EUR (Estimated Ultimate Recovery) for new wells based on the data collected from nearby
wells. This is because decline curves are easier and faster alternative to complex reservoir simulators which
perform computationally expensive operations. In contrast to this, decline curves require only a few parameters
in the equation which can be easily collected from the existing data of the wells. In this study, first we collected
the well data corresponding to well parameters such as initial monthly oil flow rate (qi), well completion parameters (i.e., no. of fracturing stages, completed length, amount of proppant used, amount of fracturing fluid
used), well location parameters (TVD Heel-Toe Difference), reservoir fluid properties (Oil API Gravity, initial 24
h period Gas-Oil Ratio (GOR), initial 24 h period Gas Produced, initial 24 h period Oil Produced), flowing tubing
pressure, casing pressure tubing size,choke size from publicly available databases of the Eagle Ford Shale formation Texas RRC (Railroad Commission of Texas). Wells were selected randomly and only those wells were
finally included for the study whose data of the all the required parameters were available. The model parameters were estimated by fitting the production data to the decline curve models. Artificial Neural Network (ANN)
was employed to build Machine learning models as a function of the above well parameters for the corresponding
model parameters. The decline curves for new or existing wells were rapidly predicted using these models. In
order to estimate the predictive accuracy of these models when applied to new or test wells cross validation
technique such as k-fold cross validation was employed. These models were also used to predict EUR for the test
wells. Additionally, feature selection was also done using algorithms such as Chi Square Test (χ2) and Minimum
Redundancy Maximum Relevance (MRMR) Algorithm to determine the relative importance of predictor variables
in predicting EUR. The predictor variables were successfully linked to SEDM (Stretched Exponential Decline
Model) decline curve parameters (n and τ) in a random set of oil field well data. The relative influences of various
well parameters were also examined to determine the hidden relationship between them. The novelty in this
study lies in the algorithm and dataset that we used for the rate decline prediction in Eagle Ford data set.
Although, this paper has referenced some previous papers where machine learning has been used to make
prediction, but this paper presents use of new algorithm as well as a new dataset. As more data gets available,
there is definitely extra room for further data analysis and improved results using machine learning methods. In
future, the number of wells can be increased and the updated results can again be submitted after investing more
time. It should be noted here that data downloading and preparing takes most of the time for such study
especially when dealing with oil and gas data.
Petroleum Science and Technology (Taylor and Francis), 2022
The main objective of this paper is to develop a novel data driven based model that can accuratel... more The main objective of this paper is to develop a novel data driven based model that can accurately predict the decline curves and EUR (Estimated Ultimate Recovery) for new wells based on the data collected from nearby wells. This is because decline curves are easier and faster alternative to complex reservoir simulators which perform computationally expensive operations. In contrast to this, decline curves require only a few parameters in the equation which can be easily collected from the existing data of the wells. The predictor variables were successfully linked to SEDM (Stretched Exponential Decline Model) decline curve parameters (n and τ) in a random set of oil field well data. The relative influences of various well parameters were also examined to determine the hidden relationship between them. The novelty in this study lies in the algorithm and dataset that we used for the rate decline prediction in Eagle Ford data set. Although, this paper has referenced some previous papers where machine learning has been used to make prediction, but this paper presents use of new algorithm as well as a new dataset. As more data gets available, there is definitely extra room for further data analysis and improved results.
Heliyon
Yellow Oleander seeds were collected, and their oil was extracted. The oil was transesterified, a... more Yellow Oleander seeds were collected, and their oil was extracted. The oil was transesterified, and its physicochemical properties were determined. The oil properties were compared with the properties of Biodiesel, Diesel. The oil properties were compared with the properties of B10, B20.
Arabian Journal of Geosciences, Springer Nature, 2022
Sand production from oil and gas wells is a major operational problem leading to the spending of ... more Sand production from oil and gas wells is a major operational problem leading to the spending of millions of dollars each
year. Sand production can cause plugged wells, lead to erosion of equipment, and may reduce the well productivity. This
paper tries to evaluate efective sand control techniques through the use of novel methodology and tools which can be
employed in sand-producing felds. In this study, core samples of fve sand-producing oil wells of Assam Arakan Basin
were collected, and those samples were frst disintegrated with a hammer to obtain the sand grains. The sand samples
were then acid washed, decanted with water, and oven-dried to ensure that all the sand grains were disintegrated correctly and to make them ready for performing laboratory analysis. Particle size distribution (PSD) study was then carried
out through the dry sieving method. After the calculation of cumulative weight % and grain size in each of the sieves
from the ASTM sieve conversion chart, “S”-shaped distribution curve was constructed for each of the wells and well
completion parameters like (D10, D40, D50, D90, D95) were calculated from the curve. Sorting coefcient (SC), uniformity coefcient (UC), and fnes content were then calculated for each of the wells using the standard formulas used in the
industry, and by comparing the calculated values of these parameters with standard tables used in industry, the most
efective sand control technique was determined for each of these wells. In my study, D10 (<0.4 mm), D40 (<0.3 mm), D50
(<0.3 mm), D90 (<0.2 mm), D95 (<0.2 mm), (SC<5), (UC<2), (fnes<0.5%), and gravel size range from 1 to 2.2 mm
and by comparing these calculated values with standard tables, standalone alone screen (SAS) (wire-wrapped screen)
with screen slot size D50 and gravel pack of 12/20 US Mesh with screen size ranging from 500 to 540 micron was found
to be the most efective sand control technique for the fve sand-producing wells. Also, the collected sand samples contain
coarse sand (0.83–0.9%), fne sand (45.96–46.3%), medium sand (49–49.3%), very fne sand (3.1–3.39%), and slit and
clay (0.54–0.84%). Although this paper has referenced some previous papers where studies on production sand control
in oil wells have been performed, the novelty in this study lies in the use of simple tools and experimental methodology
employed for determining the most efective sand control technique for these wells located in a signifcant hydrocarbon
producing basin and oil feld.
Resource-Efficient Technologies, Tomsk Polytechnic University, 2020
During drilling, different problems are encountered that can interfere with smooth drilling proce... more During drilling, different problems are encountered that can interfere with smooth drilling processes, including the accumulation of
cuttings, reduced penetration rates, pipe sticking, loss of wellbore stability, and loss of circulation. These problems are generally encountered with conventional drilling mud, such as the bentonite–barite mud system. Formation damage is the most common problem
encountered in bentonite mud systems with high solid content. In this work, we aimed to formulate two low-solid nondispersed
(LSND) muds: carboxymethyl cellulose (CMC)–LSND mud and partially hydrolyzed polyacrylamide (PHPA)–LSND mud. A comparative analysis was performed to evaluate their property enhancements. LSND muds aid in maintaining hole stability and proper
cutting removal. The results of this work show that the addition of both CMC and PHPA helps to improve drilling fluid properties;
however, the PHPA–LSND mud was found to be superior. Shale swelling is a major concern in the petroleum industry, as it causes
various other problems, such as pipe sticking, low penetration rates, and bit wear. The effect of these two LSND polymer muds in
inhibiting shale swelling was analyzed using shale collected from the Champhai district of Mizoram, India.