Result Detail – Random Forest

Back to Results Dashboard view Export CSV Export Excel Export PDF Download Full Report

Download Model (.pkl) Notebook

Result Information

Result ID: 139
Type: Random Forest
Status: completed
Dataset ID: 691
Created: 2026-09-21 02:11:43.291308
Saved Model: Available — Download .pkl

Possible data leakage detected:

Identifier-like column(s) used as features: PLOT. These are bookkeeping fields; high importance for them usually reflects row ordering, not biology. Consider excluding them.

Model Parameters

Model Type: regression
Estimators: 60
Max Depth: None

Pre-Modeling Statistics (Pearson, Spearman, ANOVA)

Feature	Pearson r	Pearson p	Pearson FDR	Spearman ρ	Spearman FDR	ANOVA F	ANOVA FDR	Significant?
PLOT	-0.3593	0.0000	0.0000	-0.2718	0.0000	58.9790	0.0000	✓ Yes
LAT	0.3916	0.0000	0.0000	0.2627	0.0000	72.0838	0.0000	✓ Yes
LONG	0.3854	0.0000	0.0000	0.2373	0.0000	69.4476	0.0000	✓ Yes
ENV_SOILNH4	0.0877	0.0799	0.0999	0.2005	0.0001	3.0819	0.0999	✓ Yes
ENV_SOILNO3	0.0442	0.3779	0.4319	0.1284	0.0122	0.7792	0.4319	✓ Yes
ENV_SOILP	0.2016	0.0000	0.0001	0.1183	0.0205	16.8693	0.0001	✓ Yes
ENV_SOILOC	0.4862	0.0000	0.0000	0.4628	0.0000	123.2109	0.0000	✓ Yes
ENV_SOILTN	0.4798	0.0000	0.0000	0.4546	0.0000	119.0503	0.0000	✓ Yes
ENV_SOILTC	0.4826	0.0000	0.0000	0.4582	0.0000	120.8380	0.0000	✓ Yes
ENV_PH	-0.0157	0.7537	0.7730	-0.0374	0.4929	0.0986	0.7730	✗ No
ENV_SOILCLAY	0.3541	0.0000	0.0000	0.3535	0.0000	57.0702	0.0000	✓ Yes
ENV_SOILSILT	0.4308	0.0000	0.0000	0.4012	0.0000	90.7079	0.0000	✓ Yes
ENV_SOILSAND	-0.4124	0.0000	0.0000	-0.3844	0.0000	81.5798	0.0000	✓ Yes
ENV_SOILMOIS	0.4611	0.0000	0.0000	0.4451	0.0000	107.4460	0.0000	✓ Yes
RC_SHOOTMASS	0.5347	0.0000	0.0000	0.6115	0.0000	159.3405	0.0000	✓ Yes
RC_WOODMASS	0.1176	0.0186	0.0248	0.1649	0.0012	5.5852	0.0248	✓ Yes
RC_LITTERMASS	0.4583	0.0000	0.0000	0.3950	0.0000	105.8490	0.0000	✓ Yes
RC_LITTERWMASS	0.0613	0.2212	0.2603	0.1522	0.0028	1.5011	0.2603	✓ Yes
PC_WOODMASS	0.2357	0.0000	0.0000	0.2247	0.0000	23.4100	0.0000	✓ Yes
PC_LITTERMASS	0.4340	0.0000	0.0000	0.4289	0.0000	92.3853	0.0000	✓ Yes
PC_LITTERWMASS	0.1460	0.0034	0.0051	0.1280	0.0122	8.6697	0.0051	✓ Yes
PC_ROOTMASS	0.0048	0.9231	0.9231	0.1531	0.0028	0.0093	0.9231	✓ Yes
PC_HEIGHT	0.4422	0.0000	0.0000	0.4293	0.0000	96.7659	0.0000	✓ Yes
GH_COUNT	-0.3024	0.0000	0.0000	-0.3168	0.0000	40.0569	0.0000	✓ Yes
ENV_AIRTEMP	0.0273	0.5868	0.6343	-0.0049	0.9216	0.2959	0.6343	✗ No
COVER_RICHNESS_JUN	-0.1231	0.0137	0.0189	-0.2223	0.0000	6.1274	0.0189	✓ Yes
COVER_TOTAL_JUN	0.3254	0.0000	0.0000	0.3623	0.0000	47.1195	0.0000	✓ Yes
COVER_SHANNON_JUN	-0.1282	0.0103	0.0147	-0.2210	0.0000	6.6513	0.0147	✓ Yes
COVER_RICHNESS_JUL	-0.0954	0.0565	0.0729	-0.1762	0.0005	3.6584	0.0729	✓ Yes
COVER_TOTAL_JUL	0.3014	0.0000	0.0000	0.4242	0.0000	39.7734	0.0000	✓ Yes
COVER_SHANNON_JUL	-0.0303	0.5459	0.6066	-0.1093	0.0320	0.3653	0.6066	✓ Yes
COVER_RICHNESS_AUG	-0.1786	0.0003	0.0005	-0.2620	0.0000	13.1200	0.0005	✓ Yes
COVER_TOTAL_AUG	0.3808	0.0000	0.0000	0.4256	0.0000	67.5107	0.0000	✓ Yes
COVER_SHANNON_AUG	-0.1613	0.0012	0.0019	-0.2300	0.0000	10.6297	0.0019	✓ Yes
PASTURE_TOTALAREA	-0.3969	0.0000	0.0000	-0.3752	0.0000	74.4068	0.0000	✓ Yes
SUBPASTURE_TOTALAREA	-0.3135	0.0000	0.0000	-0.3011	0.0000	43.3739	0.0000	✓ Yes
PASTURE_FORESTAREA	0.2967	0.0000	0.0000	0.2472	0.0000	38.4232	0.0000	✓ Yes
PASTURE_WETLANDAREA	-0.0709	0.1570	0.1903	0.0080	0.9185	2.0109	0.1903	✗ No
SUBPASTURE_FORESTAREA	0.2538	0.0000	0.0000	0.2108	0.0000	27.3930	0.0000	✓ Yes
SUBPASTURE_WETLANDAREA	0.0247	0.6222	0.6549	0.0052	0.9216	0.2432	0.6549	✗ No

Download CSV

Feature Importance (Random Forest)

Rank	Feature	Importance (Mean)	SD
1	RC_SHOOTMASS	0.2550	0.0178
2	RC_LITTERMASS	0.1509	0.0596
3	ENV_SOILTN	0.0505	0.0114
4	PC_LITTERMASS	0.0502	0.0030
5	COVER_TOTAL_JUL	0.0436	0.0039
6	PC_WOODMASS	0.0419	0.0060
7	ENV_SOILOC	0.0404	0.0255
8	ENV_SOILTC	0.0306	0.0068
9	ENV_SOILSILT	0.0278	0.0111
10	COVER_TOTAL_AUG	0.0206	0.0057
11	COVER_SHANNON_JUL	0.0151	0.0020
12	COVER_RICHNESS_JUN	0.0142	0.0049
13	LAT	0.0139	0.0027
14	COVER_TOTAL_JUN	0.0139	0.0052
15	PASTURE_FORESTAREA	0.0136	0.0061
16	PC_HEIGHT	0.0129	0.0024
17	COVER_SHANNON_AUG	0.0125	0.0003
18	ENV_SOILP	0.0123	0.0012
19	SUBPASTURE_TOTALAREA	0.0123	0.0007
20	ENV_SOILMOIS	0.0121	0.0035
21	PC_LITTERWMASS	0.0120	0.0053
22	ENV_PH	0.0115	0.0022
23	ENV_SOILNH4	0.0115	0.0008
24	COVER_SHANNON_JUN	0.0111	0.0020
25	COVER_RICHNESS_AUG	0.0099	0.0016
26	COVER_RICHNESS_JUL	0.0097	0.0029
27	SUBPASTURE_WETLANDAREA	0.0091	0.0032
28	SUBPASTURE_FORESTAREA	0.0090	0.0021
29	LONG	0.0082	0.0012
30	ENV_SOILNO3	0.0081	0.0023
31	PASTURE_TOTALAREA	0.0081	0.0044
32	PLOT	0.0081	0.0023
33	ENV_SOILCLAY	0.0072	0.0013
34	ENV_SOILSAND	0.0060	0.0014
35	PASTURE_WETLANDAREA	0.0060	0.0036
36	ENV_AIRTEMP	0.0047	0.0008
37	RC_LITTERWMASS	0.0042	0.0015
38	GH_COUNT	0.0038	0.0002
39	PC_ROOTMASS	0.0038	0.0014
40	RC_WOODMASS	0.0035	0.0006

Download CSV

Permutation Importance

Rank	Feature	Perm. Importance (Mean)	SD
1	RC_SHOOTMASS	0.1913	0.0390
2	RC_LITTERMASS	0.1174	0.0192
3	PC_LITTERMASS	0.0470	0.0129
4	PC_WOODMASS	0.0338	0.0126
5	COVER_TOTAL_JUL	0.0310	0.0106
6	ENV_SOILOC	0.0160	0.0066
7	ENV_SOILTN	0.0111	0.0122
8	SUBPASTURE_TOTALAREA	0.0080	0.0058
9	PASTURE_TOTALAREA	0.0053	0.0019
10	PC_HEIGHT	0.0042	0.0058
11	ENV_SOILSAND	0.0041	0.0036
12	PASTURE_FORESTAREA	0.0028	0.0022
13	ENV_SOILSILT	0.0028	0.0054
14	LONG	0.0027	0.0023
15	ENV_SOILCLAY	0.0026	0.0005
16	ENV_SOILNO3	0.0023	0.0035
17	ENV_SOILNH4	0.0021	0.0017
18	LAT	0.0018	0.0010
19	PASTURE_WETLANDAREA	0.0018	0.0017
20	COVER_SHANNON_JUL	0.0018	0.0006
21	COVER_SHANNON_JUN	0.0016	0.0017
22	ENV_SOILP	0.0016	0.0035
23	COVER_RICHNESS_JUN	0.0015	0.0055
24	COVER_RICHNESS_AUG	0.0013	0.0026
25	SUBPASTURE_WETLANDAREA	0.0013	0.0014
26	COVER_TOTAL_AUG	0.0013	0.0013
27	COVER_SHANNON_AUG	0.0011	0.0018
28	PLOT	0.0011	0.0017
29	COVER_TOTAL_JUN	0.0009	0.0007
30	SUBPASTURE_FORESTAREA	0.0005	0.0005
31	ENV_AIRTEMP	-0.0002	0.0015
32	RC_LITTERWMASS	-0.0002	0.0019
33	ENV_SOILTC	-0.0008	0.0062
34	PC_LITTERWMASS	-0.0008	0.0018
35	GH_COUNT	-0.0009	0.0008
36	RC_WOODMASS	-0.0019	0.0015
37	PC_ROOTMASS	-0.0026	0.0022
38	COVER_RICHNESS_JUL	-0.0027	0.0040
39	ENV_PH	-0.0028	0.0052
40	ENV_SOILMOIS	-0.0028	0.0018

Download CSV

SHAP Feature Importance

Rank	Feature	SHAP Mean \|Abs\|
1	RC_SHOOTMASS	3.3931
2	PC_LITTERMASS	0.8451
3	ENV_SOILTN	0.7347
4	COVER_TOTAL_JUL	0.7055
5	RC_LITTERMASS	0.6047
6	PC_WOODMASS	0.4848
7	COVER_TOTAL_AUG	0.3982
8	ENV_SOILTC	0.2403
9	ENV_SOILOC	0.2214
10	LAT	0.1991
11	PC_LITTERWMASS	0.1931
12	ENV_PH	0.1922
13	COVER_RICHNESS_AUG	0.1833
14	COVER_RICHNESS_JUN	0.1736
15	ENV_SOILMOIS	0.1376
16	SUBPASTURE_WETLANDAREA	0.1333
17	PC_HEIGHT	0.1311
18	COVER_SHANNON_AUG	0.1120
19	ENV_SOILNH4	0.1117
20	SUBPASTURE_TOTALAREA	0.1086
21	COVER_SHANNON_JUL	0.1069
22	SUBPASTURE_FORESTAREA	0.1042
23	PASTURE_TOTALAREA	0.1030
24	ENV_SOILSILT	0.0959
25	COVER_SHANNON_JUN	0.0942
26	PLOT	0.0926
27	COVER_TOTAL_JUN	0.0865
28	PASTURE_FORESTAREA	0.0805
29	ENV_SOILCLAY	0.0771
30	ENV_SOILP	0.0610
31	ENV_SOILSAND	0.0572
32	COVER_RICHNESS_JUL	0.0546
33	ENV_SOILNO3	0.0506
34	RC_WOODMASS	0.0480
35	LONG	0.0472
36	ENV_AIRTEMP	0.0402
37	PC_ROOTMASS	0.0305
38	PASTURE_WETLANDAREA	0.0301
39	GH_COUNT	0.0281
40	RC_LITTERWMASS	0.0257

Download CSV

Model Metrics

Split	R²	MSE
Split 1	0.5627	44.2704
Split 2	0.5164	40.0521
Split 3	0.5244	36.0524
Mean	0.5345	40.1250

Download CSV

Figures

Feature importance Download PNG

Permutation importance Download PNG

SHAP summary Download PNG

Observed vs predicted (out-of-fold) Download PNG

Cross-validation score distribution Download PNG

Pathway Analysis (same dataset)

Run Pathway Analysis

Method & Provenance

Method: Random Forest (Regression)
Method key: random_forest (result type: random_forest, result #139)
Engine: Python · scikit-learn v1.8.0
Dataset(s): #691 gallery — cat_g_field_data_plots.csv (preprocessed)
Status: completed
Permanent link: https://cat-g-omxpert.wishartlab.com/results/by-token/4ae9de70c16e41858d39d893714e9650 Bookmark or share this URL — it does not depend on your session.
Created: 2026-09-21 02:11:43.291308

Parameters used

Parameter	Value
`task_type`	regression
`model_type`	regression
`target_column`	PC_SHOOTMASS
`n_estimators`	60
`n_splits`	3
`test_size`	0.25
`run_univariate`	True
`run_permutation`	True
`run_shap`	True
`permutation_repeats`	10
`fdr_threshold`	0.05

Execution trace

Reconstructed from the parameters stored with this result — represents the Python/R calls the analysis service made.

from sklearn.ensemble import RandomForestRegressor

model = RandomForestRegressor(n_estimators=60, random_state=42)

scores = sklearn.model_selection.cross_val_score(model, X, y, cv=3)