Skip to main content

Science – Society – Technology

Table 6 New improved gas geothermometers proposed in this research work

From: GaS_GeoT: A computer program for an effective use of newly improved gas geothermometers in predicting reliable geothermal reservoir temperatures

Neural network model New gas geothermometer nomenclature (GasGi) Input variables Number of inputs neurons Number of hidden neurons Number of outputs neurons ANN architecture
1 2 3 4 5
ANN-7 GasG1 ln(H2S/CO2)
46.32%
ln(CH4/CO2)
24.84%
ln(H2/CO2)
28.84%
   3 18 1 [3–18-1]
ANN-9 GasG2 ln(CO2/CH4)
42%
ln(H2S/CH4)
31.02%
ln(H2/CH4)
26.97%
   3 15 1 [3–15-1]
ANN-20 GasG3 ln(H2S/CO2) 39.12% ln(CH4/CO2) 37.68% ln(H2/CO2) 23.2%    3 18 1 [3–18-1]
ANN-22 GasG4 ln(CO2/CH4) 33.05% ln(H2S/CH4) 34.51% ln(H2/CH4) 32.44%    3 34 1 [3–34-1]
ANN-23 GasG5 ln(CO2/H2) 24.6% ln(H2S/H2) 50.2% ln(CH4/H2) 25.21%    3 15 1 [3–15-1]
ANN12 GasG6 ln(CO2) 26.18% ln(H2S) 30.19% ln(CH4) 15.37% ln(H2) 28.26%   4 13 1 [4–13-1]
ANN-25 GasG7 ln(CO2) 27.83% ln(H2S) 12.81% ln(CH4) 25.87% ln(H2) 33.48%   4 10 1 [4–10-1]
ANN-13 GasG8 ln(H2S/CO2) 25.13% ln(CH4/CO2) 5.11% ln(H2/CO2) 10.29% ln(H2S) 42.86% ln(H2S/H2) 16.61% 5 9 1 [5-9-1]
  1. According to the Garson's method (Garson 1991), the relative contribution for each input variable was determined in subsequent calculations of the geothermal reservoir temperatures. This value appears in percentage units below each input variable