Stable isotope analysis gives the criteria to define the characteristics of the coalbed gas. In this paper machine learning approach was applied for this purpose. There are two fundamental origins of coalbed gas, i.e., thermogenic and biogenic gas. Stable isotope analysis is the primary method to evaluate the origin of coalbed gas.Samples were collected from the previous literatures and artificial neural network (ANN) was developed for calculating stable isotopes of CH4, CO2 and H2. First model was trained with around 300 samples and then cross validated with 40 samples. Hydrocarbon, CO2-CH4 (CDMI), Dryness index, Depth and vitrinite reflectance (Ro) have been used as input parameters and stable isotope of three gases were determined. Feed forward back-propagation was extensively used as the optimum network for the effective results. Before feeding into the network, data was scaled down between 0 to 1 using linear normalization. The learning process used 80% of the data, 10% were used for validation and 10 % for testing. for all the process was above 0.9 and overall, it was observed that R2=0.97762. The stable isotope of coalbed gas was achieved through this method, viz. , and . Based on the stable isotope of coalbed gas, the coalbed gas was characterized and different results were obtained. The Bernard and CD diagrams were also plotted for the coalbed gas characterization. The validation of predicted values by actual values was also shown in the paper. The current research has vast application on coalbed methane fields as well as conventional and other unconventional gas resources. This is the first kind of research which provides the stable isotopes of coalbed gas using machine learning. As stable isotope of coalbed is necessary to recognize the types of coalbed gas. Stable isotope geochemistry of coalbed gas also gives the primary knowledge to management to assess the secondary recovery of methane. This study provides the thorough knowledge on stable isotope geochemistry of coalbed gas for judging the sweet spot for the secondary recovery of coalbed methane.

Coalbed gas is generated during coalification process and remain in the coal as an adsorbed form. This paper discusses the mechanism of generation of coalbed gas and identification of its origin. Two samples has been retrieved from exploratory borehole of Jharia Coalfield. Location of the study area was shown in figure 1. Gas content of these coal samples has been found and some gas is collected in glass bottle from desorption canister. After collection of this adsorbed gas, it was analyzed through gas chromatography and isotopic ratio mass spectrometer. Analyzed coalbed gas contains primarily CH4, ranges from 72.25% to 83.21% and CO2, ranges from 2.63% to 3.05%. Stable isotope geochemistry shows that isotopic fraction is between CH4, C2H6 and CO2. Stable isotopic fractionation and coalbed gas composition is shown in table 1. Isotope of δ13CO2 varies from -21.3% to -17.9%. CDMI and hydrocarbon index (CHC) was also calculated. CDMI index ranges from 3.51 to 3.54 which that coalbed gas might be of thermogenic origin. CHC index ranges from 68.77 to 95.07 % which shows generated CO2 is of organic in nature. Calculated dryness index ranges from 0.986 to 0.990 which shows that coalbed gas is dry to very dry in nature. Coal samples was characterized on the basis of petrochemical and petrographic for the coalbed methane recovery from Jharia Coalfield. Analyzed coalbed gas contains mainly thermogenic methane with substantial amount of biogenic methane. δ13CO2 for biogenic was assumed to be -20% to -15% for the samples. Biogenic proportion for the samples was observed 24.65% and 13.77% respectively while for thermogenic proportion, it was found around 75.35% and 86.23%.

Coalbed Methane is an attractive source of energy to mitigate the growing energy demand of India. It is often abbreviated as unconventional source of energy. In this paper two bore hole samples (J/01 & J/02) were collected and characterized for the isotherm studies to know the sorption capacity of the coal. Pure gas isotherm was constructed based on the manomateric method. Pure gas isotherm was constructed in indigenously fabricated setup. Langmuir model was used for the prediction of sorption capacity at particular pressure. Langmuir constants (PL & VL) were calculated using regression analysis. It was found that volume wise CO2 has 2.09 to 2.75 times more adsorption capacity than coal.Once pure gas isotherm was drawn and PL and VL was calculated. Langmuir constants were given as follows: CH4 -VL (scf/ton) of J/01 and J/02 are 227.27 and 454.55 respectively CH4 -PL (psi) of J/01 and J/02 are 128.54 and 173.68 CO2-VL (scf/ton) of J/01 and J/02 are 476.19 1250 respectively CO2-PL(psi) of J/01 and J/02 are 133.33 596.13 Binary mixture of CH4 and CO2 was modelled at different gas mixtures and at pressure of 2000 psi. Multicomponent iterative model (MIA) was proposed using Newton Raphson iteration to study the co adsorption isotherm of CH4 and CO2 at different binary mixtures. It was found that one CO2 mole fraction increases in gas phase. For sample J/01 Enhanced Coalbed Methane (ECBM) recovery will occur after 27.4 % of CO2 in gas phase while ECBM recovery will occur after 13.03% of CO2 in gas phase. Pure component isotherm and co adsorption isotherm is given in figure 1 & 2.