A machine learning approach for mapping the very shallow theoretical geothermal potential

Geothermal Energy

Science – Society – Technology

Table 3 Testing RMSE (\(E_{\text {R}}\)), NRMSE (\(E_{\text {NR}}\), in percentage) and OOB score for Random Forest models trained for monthly ground temperature at multiple depths

Month	5 cm			10 cm			20 cm			50 cm			100 cm
Month	E_R (°C)	E_NR (%)	OOB (−)	E_R (°C)	E_NR (%)	OOB (−)	E_R (°C)	E_NR (%)	OOB (−)	E_R (°C)	E_NR (%)	OOB (−)	E_R (°C)	E_NR (%)	OOB (−)
Jan.	0.81	25.40	0.17	0.69	20.81	0.46	0.57	19.18	0.43	0.63	23.17	0.25	0.87	17.55	0.26
Feb.	0.57	18.69	0.15	0.65	20.20	0.48	0.69	22.24	0.34	0.66	26.88	0.27	0.86	20.27	0.24
Mar.	0.78	13.74	0.35	0.94	16.24	0.46	1.34	20.44	0.40	1.32	35.38	0.40	1.04	20.58	0.44
Apr.	0.88	08.49	0.59	1.12	10.62	0.46	1.35	12.30	0.46	2.00	32.11	0.44	1.11	15.36	0.52
May.	1.48	10.38	0.52	0.97	06.62	0.34	1.35	08.86	0.34	1.80	17.21	0.33	1.19	11.58	0.47
Jun.	2.34	12.48	0.56	1.22	06.41	0.42	1.22	06.35	0.42	2.02	14.62	0.31	1.34	09.95	0.47
Jul.	2.22	10.55	0.46	1.08	05.06	0.48	1.18	05.59	0.40	2.21	13.77	0.25	1.54	09.74	0.40
Aug.	1.68	08.28	0.53	1.22	05.95	0.48	0.96	04.62	0.46	2.09	12.47	0.29	1.51	08.88	0.37
Sep.	1.10	06.57	0.46	1.02	05.86	0.45	1.05	05.99	0.38	1.90	12.90	0.23	1.44	09.03	0.42
Oct.	0.83	06.61	0.37	0.87	06.66	0.34	0.71	05.43	0.28	1.57	13.65	0.33	1.12	08.25	0.46
Nov.	0.93	11.90	0.24	0.86	10.44	0.32	0.60	07.18	0.31	1.19	16.35	0.30	1.14	11.25	0.38
Dec.	1.10	29.08	0.06	0.78	18.89	0.35	0.60	14.27	0.43	0.80	19.53	0.32	1.05	15.31	0.39