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: 147
Type: Random Forest
Status: completed
Dataset ID: 701
Created: 2026-09-21 02:15:26.727584
Saved Model: Available — Download .pkl

Possible data leakage detected:

Feature "ENV_SOILTN" is almost perfectly correlated with the target "ENV_SOILOC" (r = 0.916) — likely data leakage or a duplicate measurement; consider excluding it.
Feature "ENV_SOILTC" is almost perfectly correlated with the target "ENV_SOILOC" (r = 0.916) — likely data leakage or a duplicate measurement; consider excluding it.
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.
Spatial confounding risk: coordinate column(s) LAT, LONG rank among the most important features. The model may be learning field position rather than biological signal; interpret with care or exclude coordinates.

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	-0.8324	0.0000	0.0000	-0.7063	0.0000	850.8679	0.0000	✓ Yes
ENV_SOILNH4	0.1119	0.0294	0.0349	0.2807	0.0000	4.7799	0.0349	✓ Yes
ENV_SOILNO3	0.1083	0.0351	0.0401	0.2490	0.0000	4.4739	0.0401	✓ Yes
ENV_SOILP	0.2322	0.0000	0.0000	0.1698	0.0011	21.4913	0.0000	✓ Yes
ENV_SOILTN	0.9158	0.0000	0.0000	0.8935	0.0000	1960.6586	0.0000	✓ Yes
ENV_SOILTC	0.9164	0.0000	0.0000	0.8919	0.0000	1975.6368	0.0000	✓ Yes
ENV_PH	-0.0959	0.0622	0.0686	-0.0243	0.6372	3.4986	0.0686	✗ No
ENV_SOILCLAY	0.7606	0.0000	0.0000	0.7451	0.0000	517.3123	0.0000	✓ Yes
ENV_SOILSILT	0.8564	0.0000	0.0000	0.8749	0.0000	1037.4390	0.0000	✓ Yes
ENV_SOILSAND	-0.8471	0.0000	0.0000	-0.8524	0.0000	958.0954	0.0000	✓ Yes
ENV_SOILMOIS	0.8774	0.0000	0.0000	0.8593	0.0000	1261.3165	0.0000	✓ Yes
PC_SHOOTMASS	0.4871	0.0000	0.0000	0.4725	0.0000	117.3000	0.0000	✓ Yes
PC_WOODMASS	0.1623	0.0015	0.0020	0.1020	0.0521	10.1947	0.0020	✓ Yes
PC_LITTERMASS	0.1241	0.0156	0.0192	0.1238	0.0181	5.8986	0.0192	✓ Yes
PC_ROOTMASS	0.0481	0.3501	0.3734	0.3477	0.0000	0.8754	0.3734	✓ Yes
RC_SHOOTMASS	0.4787	0.0000	0.0000	0.5200	0.0000	112.0859	0.0000	✓ Yes
RC_LITTERMASS	0.1792	0.0005	0.0006	0.1452	0.0055	12.5133	0.0006	✓ Yes
COVER_TOTAL_JUL	0.2802	0.0000	0.0000	0.4157	0.0000	32.1096	0.0000	✓ Yes
COVER_RICHNESS_JUL	-0.0405	0.4314	0.4453	-0.0630	0.2278	0.6203	0.4453	✗ No
COVER_SHANNON_JUL	-0.0281	0.5853	0.5853	-0.0814	0.1211	0.2983	0.5853	✗ No
PASTURE_TOTALAREA	-0.8406	0.0000	0.0000	-0.7705	0.0000	907.7367	0.0000	✓ Yes
PASTURE_FORESTAREA	0.6833	0.0000	0.0000	0.6443	0.0000	330.1362	0.0000	✓ Yes
LAT	0.8661	0.0000	0.0000	0.6962	0.0000	1132.2787	0.0000	✓ Yes
LONG	0.8638	0.0000	0.0000	0.7128	0.0000	1107.8382	0.0000	✓ Yes
SOIL_EC_uS_cm	-0.3277	0.0000	0.0000	-0.3597	0.0000	45.3592	0.0000	✓ Yes
SOIL_CO2_mg_per_g	0.3131	0.0000	0.0000	0.3484	0.0000	40.9863	0.0000	✓ Yes
BACTERIAL_NECROMASS_C	0.3851	0.0000	0.0000	0.3578	0.0000	65.6436	0.0000	✓ Yes
FUNGAL_NECROMASS_C	0.3834	0.0000	0.0000	0.3671	0.0000	64.9804	0.0000	✓ Yes
MICROBIAL_NECROMASS_C	0.3930	0.0000	0.0000	0.3986	0.0000	68.8465	0.0000	✓ Yes
ENV_PROBEMOIS_AUG	0.8261	0.0000	0.0000	0.7813	0.0000	810.1030	0.0000	✓ Yes
ENV_PROBEMOIS_JUL	0.7635	0.0000	0.0000	0.7345	0.0000	526.8705	0.0000	✓ Yes
ENV_PROBEMOIS_JUN	0.5300	0.0000	0.0000	0.5856	0.0000	147.2532	0.0000	✓ Yes

Download CSV

Feature Importance (Random Forest) Help

Rank	Feature	Importance (Mean)	SD
1	ENV_SOILTC	0.2909	0.0853
2	ENV_SOILTN	0.1949	0.1238
3	LONG	0.1295	0.0246
4	ENV_SOILSAND	0.0587	0.0289
5	PLOT	0.0555	0.0547
6	LAT	0.0419	0.0317
7	ENV_SOILSILT	0.0416	0.0322
8	ENV_SOILMOIS	0.0374	0.0198
9	PASTURE_TOTALAREA	0.0365	0.0263
10	ENV_PROBEMOIS_AUG	0.0359	0.0143
11	ENV_SOILCLAY	0.0251	0.0302
12	ENV_SOILNH4	0.0055	0.0016
13	ENV_PH	0.0046	0.0013
14	ENV_SOILP	0.0040	0.0010
15	ENV_SOILNO3	0.0039	0.0010
16	ENV_PROBEMOIS_JUN	0.0039	0.0007
17	RC_SHOOTMASS	0.0038	0.0022
18	ENV_PROBEMOIS_JUL	0.0038	0.0001
19	RC_LITTERMASS	0.0034	0.0010
20	COVER_TOTAL_JUL	0.0030	0.0012
21	PC_SHOOTMASS	0.0024	0.0004
22	PC_LITTERMASS	0.0024	0.0006
23	PC_WOODMASS	0.0022	0.0009
24	PC_ROOTMASS	0.0020	0.0012
25	COVER_SHANNON_JUL	0.0016	0.0000
26	PASTURE_FORESTAREA	0.0015	0.0006
27	COVER_RICHNESS_JUL	0.0014	0.0004
28	MICROBIAL_NECROMASS_C	0.0012	0.0003
29	FUNGAL_NECROMASS_C	0.0007	0.0002
30	BACTERIAL_NECROMASS_C	0.0004	0.0002
31	SOIL_EC_uS_cm	0.0002	0.0000
32	SOIL_CO2_mg_per_g	0.0002	0.0001

Download CSV

Permutation Importance Help

Rank	Feature	Perm. Importance (Mean)	SD
1	ENV_SOILTC	0.1352	0.0127
2	ENV_SOILSILT	0.0739	0.0186
3	ENV_SOILTN	0.0645	0.0159
4	ENV_PROBEMOIS_AUG	0.0378	0.0345
5	LONG	0.0297	0.0190
6	ENV_SOILSAND	0.0225	0.0090
7	ENV_SOILMOIS	0.0119	0.0099
8	PLOT	0.0117	0.0180
9	LAT	0.0107	0.0076
10	PASTURE_TOTALAREA	0.0098	0.0053
11	ENV_PH	0.0028	0.0009
12	RC_SHOOTMASS	0.0022	0.0043
13	ENV_SOILNO3	0.0020	0.0008
14	ENV_SOILCLAY	0.0018	0.0042
15	COVER_RICHNESS_JUL	0.0009	0.0001
16	PASTURE_FORESTAREA	0.0003	0.0004
17	PC_ROOTMASS	0.0003	0.0007
18	PC_WOODMASS	0.0002	0.0009
19	BACTERIAL_NECROMASS_C	-0.0000	0.0002
20	FUNGAL_NECROMASS_C	-0.0001	0.0001
21	SOIL_EC_uS_cm	-0.0001	0.0001
22	COVER_SHANNON_JUL	-0.0001	0.0003
23	SOIL_CO2_mg_per_g	-0.0002	0.0002
24	PC_LITTERMASS	-0.0002	0.0006
25	MICROBIAL_NECROMASS_C	-0.0003	0.0004
26	ENV_PROBEMOIS_JUL	-0.0005	0.0007
27	PC_SHOOTMASS	-0.0005	0.0018
28	RC_LITTERMASS	-0.0005	0.0020
29	ENV_PROBEMOIS_JUN	-0.0009	0.0027
30	ENV_SOILP	-0.0018	0.0015
31	COVER_TOTAL_JUL	-0.0019	0.0032
32	ENV_SOILNH4	-0.0020	0.0034

Download CSV

SHAP Feature Importance Help

Rank	Feature	SHAP Mean \|Abs\|
1	ENV_SOILTC	0.7278
2	ENV_SOILTN	0.7022
3	LONG	0.2015
4	ENV_PROBEMOIS_AUG	0.1999
5	ENV_SOILSILT	0.1138
6	ENV_SOILSAND	0.0749
7	ENV_SOILMOIS	0.0484
8	ENV_SOILNH4	0.0214
9	ENV_PROBEMOIS_JUN	0.0193
10	ENV_PH	0.0185
11	PC_SHOOTMASS	0.0176
12	PASTURE_TOTALAREA	0.0169
13	PLOT	0.0168
14	RC_LITTERMASS	0.0151
15	LAT	0.0125
16	ENV_PROBEMOIS_JUL	0.0122
17	ENV_SOILCLAY	0.0121
18	COVER_TOTAL_JUL	0.0118
19	ENV_SOILNO3	0.0111
20	PC_LITTERMASS	0.0106
21	PC_WOODMASS	0.0102
22	ENV_SOILP	0.0091
23	PC_ROOTMASS	0.0081
24	RC_SHOOTMASS	0.0078
25	PASTURE_FORESTAREA	0.0069
26	COVER_SHANNON_JUL	0.0068
27	FUNGAL_NECROMASS_C	0.0040
28	MICROBIAL_NECROMASS_C	0.0036
29	COVER_RICHNESS_JUL	0.0027
30	BACTERIAL_NECROMASS_C	0.0015
31	SOIL_EC_uS_cm	0.0010
32	SOIL_CO2_mg_per_g	0.0006

Download CSV

Model Metrics

Split	R²	MSE
Split 1	0.8679	0.6967
Split 2	0.8642	0.6186
Split 3	0.7738	0.9879
Mean	0.8353	0.7677

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 #147)
Engine: Python · scikit-learn v1.8.0
Dataset(s): #701 gallery — catg_example_06_soil_carbon_credits.csv
Status: completed
Permanent link: https://cat-g-omxpert.wishartlab.com/results/by-token/0af7a5128668442fb3b9c296168aaf7d Bookmark or share this URL — it does not depend on your session.
Created: 2026-09-21 02:15:26.727584

Parameters used

Parameter	Value
`task_type`	regression
`model_type`	regression
`target_column`	ENV_SOILOC
`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)