Result Detail – Random Forest Help

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

Download Model (.pkl) Notebook

Result Information

Result ID: 138
Type: Random Forest
Status: completed
Dataset ID: 690
Created: 2026-09-21 02:11:08.707331
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) Help

Feature	Pearson r	Pearson p	Pearson FDR	Spearman ρ	Spearman FDR	ANOVA F	ANOVA FDR	Significant?
PLOT	-0.3566	0.0000	0.0000	-0.2676	0.0000	57.9998	0.0000	✓ Yes
LAT	0.3911	0.0000	0.0000	0.2634	0.0000	71.8502	0.0000	✓ Yes
LONG	0.3848	0.0000	0.0000	0.2388	0.0000	69.1789	0.0000	✓ Yes
ENV_SOILNH4	0.0824	0.0996	0.1208	0.1870	0.0002	2.7239	0.1208	✓ Yes
ENV_SOILNO3	0.0367	0.4639	0.5015	0.0933	0.0691	0.5376	0.5015	✗ No
ENV_SOILP	0.2028	0.0000	0.0001	0.1271	0.0133	17.0726	0.0001	✓ Yes
ENV_SOILOC	0.4830	0.0000	0.0000	0.4605	0.0000	121.1279	0.0000	✓ Yes
ENV_SOILTN	0.4801	0.0000	0.0000	0.4567	0.0000	119.2385	0.0000	✓ Yes
ENV_SOILTC	0.4829	0.0000	0.0000	0.4597	0.0000	121.0029	0.0000	✓ Yes
ENV_PH	-0.0157	0.7540	0.7540	-0.0332	0.5344	0.0983	0.7540	✗ No
ENV_SOILCLAY	0.3541	0.0000	0.0000	0.3538	0.0000	57.0470	0.0000	✓ Yes
ENV_SOILSILT	0.4306	0.0000	0.0000	0.4009	0.0000	90.5771	0.0000	✓ Yes
ENV_SOILSAND	-0.4124	0.0000	0.0000	-0.3838	0.0000	81.5668	0.0000	✓ Yes
ENV_SOILMOIS	0.4614	0.0000	0.0000	0.4451	0.0000	107.6683	0.0000	✓ Yes
RC_SHOOTMASS	0.5332	0.0000	0.0000	0.6073	0.0000	158.0640	0.0000	✓ Yes
RC_WOODMASS	0.1152	0.0212	0.0283	0.1585	0.0019	5.3525	0.0283	✓ Yes
RC_LITTERMASS	0.4564	0.0000	0.0000	0.3922	0.0000	104.7397	0.0000	✓ Yes
RC_LITTERWMASS	0.0591	0.2383	0.2724	0.1293	0.0120	1.3947	0.2724	✓ Yes
PC_WOODMASS	0.2348	0.0000	0.0000	0.2313	0.0000	23.2218	0.0000	✓ Yes
PC_LITTERMASS	0.4327	0.0000	0.0000	0.4261	0.0000	91.6693	0.0000	✓ Yes
PC_LITTERWMASS	0.1439	0.0039	0.0058	0.1252	0.0144	8.4115	0.0058	✓ Yes
PC_ROOTMASS	0.1007	0.0442	0.0571	0.2809	0.0000	4.0741	0.0571	✓ Yes
PC_HEIGHT	0.4465	0.0000	0.0000	0.4329	0.0000	99.0837	0.0000	✓ Yes
GH_COUNT	-0.2974	0.0000	0.0000	-0.2940	0.0000	38.6160	0.0000	✓ Yes
ENV_AIRTEMP	0.0247	0.6220	0.6379	-0.0142	0.7971	0.2435	0.6379	✗ No
COVER_RICHNESS_JUN	-0.1236	0.0134	0.0185	-0.2189	0.0000	6.1702	0.0185	✓ Yes
COVER_TOTAL_JUN	0.3239	0.0000	0.0000	0.3605	0.0000	46.6550	0.0000	✓ Yes
COVER_SHANNON_JUN	-0.1286	0.0100	0.0143	-0.2196	0.0000	6.6913	0.0143	✓ Yes
COVER_RICHNESS_JUL	-0.0938	0.0609	0.0761	-0.1713	0.0008	3.5336	0.0761	✓ Yes
COVER_TOTAL_JUL	0.3024	0.0000	0.0000	0.4263	0.0000	40.0461	0.0000	✓ Yes
COVER_SHANNON_JUL	-0.0286	0.5682	0.5981	-0.1044	0.0421	0.3263	0.5981	✓ Yes
COVER_RICHNESS_AUG	-0.1785	0.0003	0.0005	-0.2616	0.0000	13.0987	0.0005	✓ Yes
COVER_TOTAL_AUG	0.3798	0.0000	0.0000	0.4245	0.0000	67.0752	0.0000	✓ Yes
COVER_SHANNON_AUG	-0.1615	0.0012	0.0018	-0.2277	0.0000	10.6585	0.0018	✓ Yes
PASTURE_TOTALAREA	-0.3966	0.0000	0.0000	-0.3771	0.0000	74.3077	0.0000	✓ Yes
SUBPASTURE_TOTALAREA	-0.3128	0.0000	0.0000	-0.3020	0.0000	43.1698	0.0000	✓ Yes
PASTURE_FORESTAREA	0.2953	0.0000	0.0000	0.2456	0.0000	38.0232	0.0000	✓ Yes
PASTURE_WETLANDAREA	-0.0716	0.1531	0.1802	0.0093	0.8533	2.0486	0.1802	✗ No
SUBPASTURE_FORESTAREA	0.2507	0.0000	0.0000	0.2206	0.0000	26.6878	0.0000	✓ Yes
SUBPASTURE_WETLANDAREA	0.0440	0.3797	0.4219	0.0704	0.1730	0.7734	0.4219	✗ No

Download CSV

Feature Importance (Random Forest) Help

Rank	Feature	Importance (Mean)	SD
1	RC_SHOOTMASS	0.2429	0.0214
2	RC_LITTERMASS	0.1557	0.0600
3	PC_LITTERMASS	0.0539	0.0008
4	ENV_SOILTN	0.0484	0.0119
5	COVER_TOTAL_JUL	0.0456	0.0106
6	PC_WOODMASS	0.0441	0.0071
7	ENV_SOILOC	0.0399	0.0283
8	ENV_SOILTC	0.0322	0.0034
9	ENV_SOILSILT	0.0281	0.0095
10	COVER_TOTAL_AUG	0.0208	0.0048
11	LAT	0.0165	0.0024
12	COVER_TOTAL_JUN	0.0146	0.0051
13	PASTURE_FORESTAREA	0.0142	0.0083
14	PC_HEIGHT	0.0134	0.0036
15	COVER_SHANNON_JUL	0.0132	0.0015
16	COVER_RICHNESS_JUN	0.0131	0.0039
17	SUBPASTURE_TOTALAREA	0.0127	0.0017
18	COVER_SHANNON_JUN	0.0124	0.0014
19	COVER_SHANNON_AUG	0.0120	0.0005
20	ENV_SOILP	0.0120	0.0010
21	ENV_PH	0.0118	0.0012
22	SUBPASTURE_WETLANDAREA	0.0111	0.0039
23	PC_LITTERWMASS	0.0110	0.0049
24	COVER_RICHNESS_AUG	0.0106	0.0012
25	ENV_SOILMOIS	0.0106	0.0030
26	COVER_RICHNESS_JUL	0.0103	0.0021
27	ENV_SOILNH4	0.0101	0.0021
28	SUBPASTURE_FORESTAREA	0.0092	0.0032
29	PLOT	0.0084	0.0016
30	PASTURE_TOTALAREA	0.0083	0.0033
31	ENV_SOILNO3	0.0075	0.0006
32	LONG	0.0071	0.0005
33	ENV_SOILSAND	0.0067	0.0017
34	PASTURE_WETLANDAREA	0.0060	0.0042
35	ENV_SOILCLAY	0.0060	0.0010
36	RC_LITTERWMASS	0.0045	0.0019
37	GH_COUNT	0.0040	0.0003
38	RC_WOODMASS	0.0039	0.0016
39	ENV_AIRTEMP	0.0036	0.0002
40	PC_ROOTMASS	0.0035	0.0018

Download CSV

Permutation Importance Help

Rank	Feature	Perm. Importance (Mean)	SD
1	RC_SHOOTMASS	0.1785	0.0372
2	RC_LITTERMASS	0.1239	0.0229
3	PC_LITTERMASS	0.0505	0.0164
4	PC_WOODMASS	0.0372	0.0128
5	COVER_TOTAL_JUL	0.0311	0.0122
6	ENV_SOILOC	0.0129	0.0088
7	ENV_SOILTN	0.0117	0.0021
8	SUBPASTURE_TOTALAREA	0.0090	0.0039
9	LAT	0.0077	0.0018
10	COVER_SHANNON_AUG	0.0044	0.0036
11	ENV_SOILTC	0.0042	0.0076
12	PASTURE_TOTALAREA	0.0041	0.0047
13	PC_HEIGHT	0.0039	0.0016
14	COVER_SHANNON_JUN	0.0039	0.0016
15	ENV_SOILNH4	0.0036	0.0027
16	COVER_RICHNESS_AUG	0.0033	0.0015
17	PASTURE_FORESTAREA	0.0030	0.0016
18	ENV_SOILSILT	0.0030	0.0072
19	LONG	0.0015	0.0015
20	SUBPASTURE_WETLANDAREA	0.0015	0.0018
21	ENV_SOILCLAY	0.0014	0.0009
22	COVER_TOTAL_AUG	0.0010	0.0007
23	ENV_SOILP	0.0009	0.0025
24	PASTURE_WETLANDAREA	0.0009	0.0025
25	SUBPASTURE_FORESTAREA	0.0007	0.0012
26	COVER_SHANNON_JUL	0.0005	0.0016
27	ENV_SOILSAND	0.0004	0.0015
28	COVER_RICHNESS_JUN	0.0003	0.0051
29	PLOT	0.0003	0.0007
30	COVER_TOTAL_JUN	0.0003	0.0039
31	RC_LITTERWMASS	0.0003	0.0017
32	GH_COUNT	0.0002	0.0005
33	RC_WOODMASS	-0.0005	0.0008
34	ENV_SOILNO3	-0.0006	0.0028
35	COVER_RICHNESS_JUL	-0.0010	0.0054
36	ENV_AIRTEMP	-0.0013	0.0007
37	PC_ROOTMASS	-0.0024	0.0030
38	PC_LITTERWMASS	-0.0029	0.0028
39	ENV_PH	-0.0030	0.0033
40	ENV_SOILMOIS	-0.0030	0.0005

Download CSV

SHAP Feature Importance Help

Rank	Feature	SHAP Mean \|Abs\|
1	RC_SHOOTMASS	3.1732
2	PC_LITTERMASS	0.8018
3	ENV_SOILTN	0.7207
4	COVER_TOTAL_JUL	0.6951
5	RC_LITTERMASS	0.6325
6	PC_WOODMASS	0.5116
7	COVER_TOTAL_AUG	0.4220
8	ENV_SOILTC	0.3008
9	LAT	0.2414
10	COVER_RICHNESS_AUG	0.2336
11	PC_LITTERWMASS	0.1972
12	ENV_PH	0.1740
13	COVER_RICHNESS_JUN	0.1478
14	COVER_SHANNON_JUN	0.1476
15	PASTURE_TOTALAREA	0.1467
16	COVER_SHANNON_AUG	0.1447
17	ENV_SOILSILT	0.1302
18	PC_HEIGHT	0.1216
19	SUBPASTURE_FORESTAREA	0.1195
20	SUBPASTURE_TOTALAREA	0.1193
21	COVER_SHANNON_JUL	0.1121
22	SUBPASTURE_WETLANDAREA	0.1056
23	ENV_SOILOC	0.1040
24	ENV_SOILNH4	0.0991
25	ENV_SOILMOIS	0.0987
26	PLOT	0.0864
27	COVER_TOTAL_JUN	0.0828
28	RC_WOODMASS	0.0776
29	COVER_RICHNESS_JUL	0.0771
30	ENV_SOILNO3	0.0682
31	ENV_SOILCLAY	0.0612
32	ENV_SOILP	0.0552
33	PASTURE_FORESTAREA	0.0550
34	LONG	0.0506
35	ENV_AIRTEMP	0.0450
36	PASTURE_WETLANDAREA	0.0433
37	GH_COUNT	0.0429
38	ENV_SOILSAND	0.0366
39	PC_ROOTMASS	0.0328
40	RC_LITTERWMASS	0.0257

Download CSV

Model Metrics

Split	R²	MSE
Split 1	0.5598	44.4866
Split 2	0.5284	39.0723
Split 3	0.5442	34.5514
Mean	0.5441	39.3701

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) Help

Run Pathway Analysis

Method & Provenance

Method: Random Forest (Regression)
Method key: random_forest (result type: random_forest, result #138)
Engine: Python · scikit-learn v1.8.0
Dataset(s): #690 gallery — cat_g_field_data_plots.csv
Status: completed
Permanent link: https://cat-g-omxpert.wishartlab.com/results/by-token/e38fdc04752c42c5a01d7772f67245f3 Bookmark or share this URL — it does not depend on your session.
Created: 2026-09-21 02:11:08.707331

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)