This page was generated from docs/Examples/Cpx_Cpx_Liq_Thermobarometry/MachineLearning_Cpx_Liq_Thermobarometry.ipynb. Interactive online version: .

Machine-Learning-based Clinopyroxene-only and Clinopyroxene-Liquid Thermobarometry.¶

This notebook goes through the options for clinopyroxene-Liquid thermobarometry and clinopyroxene-only thermobarometry
Cpx-Liq matching is not covered in this tutorial, there is a separate folder “Cpx_Liquid_melt_matching” for that
You can download the excel spreadsheet from: https://github.com/PennyWieser/Thermobar/blob/main/docs/Examples/Cpx_Cpx_Liq_Thermobarometry/Cpx_Liq_Example.xlsx

You need to install Thermobar once on your machine, if you haven’t done this yet, uncomment the line below (remove the #)¶

[1]:

!pip install Thermobar

For Machine learning, you also need to pip install the .pkl files that have saved the pretrained model. This is to keep Thermobar smaller so we can still release on Pip¶

[2]:

!pip install "https://github.com/PennyWieser/Thermobar_onnx/archive/refs/tags/0.02.zip"

First, load the necessary python things¶

[3]:

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import Thermobar as pt

Now, load the data¶

[4]:

out=pt.import_excel('Cpx_Liq_Example.xlsx', sheet_name="Sheet1")
my_input=out['my_input']
Liqs=out['Liqs']
Cpxs=out['Cpxs']

Using saved models¶

This uses pickles, the model will change with different versions of python
But, it does give you the voting approach of Jorgenson, with the median and standard deviation of the trees

[13]:

P_T_EqTests_pkl=pt.calculate_cpx_liq_press_temp(cpx_comps=Cpxs, liq_comps=Liqs,
                                                equationP="P_Petrelli2020_Cpx_Liq",
                                            equationT="T_Petrelli2020_Cpx_Liq",
                                                 T=1300,
                                             H2O_Liq=0, eq_tests=True)
P_T_EqTests_pkl

Youve selected a P-independent function
Youve selected a T-independent function
Youve selected a T-independent function
Using Fe3FeT from input file to calculate Kd Fe-Mg

[13]:

	P_kbar_calc	T_K_calc	Median_Trees_P	Std_Trees_P	IQR_Trees_P	Median_Trees_T	Std_Trees_T	IQR_Trees_T	Eq Tests Neave2017?	Delta_Kd_Put2008	...	Delta_EnFs_I_M_Mollo13	CaTs_Pred_Put1999	Delta_CaTs_I_M_Put1999	Delta_CrCaTs_I_M_Put1999	CaTi_Pred_Put1999	Delta_CaTi_I_M_Put1999	Jd_Pred_Put1999	Delta_Jd_Put1999	Delta_Jd_I_M_Put1999
0	2.012874	1436.353636	2.0	2.014248	2.014248	1434.15	37.734604	37.734604	False	0.047419	...	0.001449	0.013801	-0.016574	0.009562	0.042741	0.001728	0.016176	0.000880	0.000880
1	2.385743	1422.872182	2.0	2.516823	2.516823	1423.15	58.692923	58.692923	False	0.045964	...	0.006055	0.013802	-0.023015	0.004122	0.055375	0.010437	0.017422	0.000092	0.000092
2	2.031163	1388.809636	2.0	1.335548	1.335548	1398.15	100.495001	100.495001	False	0.048797	...	0.066580	0.017510	-0.074375	0.003245	0.028704	0.042963	0.018321	0.000236	0.000236
3	2.175246	1418.986727	2.0	2.290651	2.290651	1423.15	62.539834	62.539834	False	0.042372	...	0.002781	0.015006	-0.030821	0.003909	0.049805	0.008608	0.019322	0.002988	0.002988
4	2.194894	1358.247818	2.0	2.305614	2.305614	1373.15	80.220643	80.220643	False	0.030098	...	-0.007655	0.011571	-0.031539	0.001315	0.049482	0.013529	0.027939	0.005724	0.005724

5 rows × 136 columns

Using onnx models¶

-Using Onnx means you will always get the same answer. But, you dont get the voting results.

[14]:

P_T_EqTests_onnx=pt.calculate_cpx_liq_press_temp(cpx_comps=Cpxs, liq_comps=Liqs,
                                                equationP="P_Petrelli2020_Cpx_Liq",
                                            equationT="T_Petrelli2020_Cpx_Liq",
                                                 T=1300,
                                             H2O_Liq=0, eq_tests=True)
P_T_EqTests_onnx

Youve selected a P-independent function
Youve selected a T-independent function
Youve selected a T-independent function
Using Fe3FeT from input file to calculate Kd Fe-Mg

[14]:

	P_kbar_calc	T_K_calc	Median_Trees_P	Std_Trees_P	IQR_Trees_P	Median_Trees_T	Std_Trees_T	IQR_Trees_T	Eq Tests Neave2017?	Delta_Kd_Put2008	...	Delta_EnFs_I_M_Mollo13	CaTs_Pred_Put1999	Delta_CaTs_I_M_Put1999	Delta_CrCaTs_I_M_Put1999	CaTi_Pred_Put1999	Delta_CaTi_I_M_Put1999	Jd_Pred_Put1999	Delta_Jd_Put1999	Delta_Jd_I_M_Put1999
0	2.012874	1436.353636	2.0	2.014248	2.014248	1434.15	37.734604	37.734604	False	0.047419	...	0.001449	0.013801	-0.016574	0.009562	0.042741	0.001728	0.016176	0.000880	0.000880
1	2.385743	1422.872182	2.0	2.516823	2.516823	1423.15	58.692923	58.692923	False	0.045964	...	0.006055	0.013802	-0.023015	0.004122	0.055375	0.010437	0.017422	0.000092	0.000092
2	2.031163	1388.809636	2.0	1.335548	1.335548	1398.15	100.495001	100.495001	False	0.048797	...	0.066580	0.017510	-0.074375	0.003245	0.028704	0.042963	0.018321	0.000236	0.000236
3	2.175246	1418.986727	2.0	2.290651	2.290651	1423.15	62.539834	62.539834	False	0.042372	...	0.002781	0.015006	-0.030821	0.003909	0.049805	0.008608	0.019322	0.002988	0.002988
4	2.194894	1358.247818	2.0	2.305614	2.305614	1373.15	80.220643	80.220643	False	0.030098	...	-0.007655	0.011571	-0.031539	0.001315	0.049482	0.013529	0.027939	0.005724	0.005724

5 rows × 136 columns

[ ]: