Model Performance
Historical/manual baseline results
Best Model
Gradient Boosting
Tuned final classifier
Validation Accuracy
68.18%
F1 Score: 0.5333
Validation Recall
0.5714
High-risk detection rate
Train / Test Records
173 / 44
Final validation split
Model Comparison
Evaluation results for the three flood-risk classifiers
Metric details: Accuracy, precision, recall, and F1 results for each supported flood classifier.
Validation Results
Gradient Boosting
Metric details: Final scores calculated from hold-out records that were not used to fit the model.
Feature Importance
Top Gradient Boosting flood classification features
Barangay name length
0.2781
Municipality avg. landslide score
0.1920
Landslide score
0.1593
Municipality: Samal
0.0669
Municipality: City Of Balanga
0.0627
Municipality landslide-prone count
0.0501
Municipality: Abucay
0.0399
Municipality total barangays
0.0395
Validation Results
Gradient Boosting
| Class | Precision | Recall | F1 | Support |
|---|---|---|---|---|
| Low Risk | 0.7857 | 0.7333 | 0.7586 | 30 |
| High Risk | 0.5000 | 0.5714 | 0.5333 | 14 |
| accuracy | - | - | 0.6818 | 44 |
| macro avg | 0.6429 | 0.6524 | 0.6460 | 44 |
| weighted avg | 0.6948 | 0.6818 | 0.6869 | 44 |
Confusion Matrix
Model comparison
Logistic Regression
Accuracy: 70.05% | F1: 0.3299
136
True Low
14
False High
51
False Low
16
True High
Random Forest
Accuracy: 65.44% | F1: 0.4000
117
True Low
33
False High
42
False Low
25
True High
Gradient Boosting
Accuracy: 65.90% | F1: 0.4032
118
True Low
32
False High
42
False Low
25
True High
Confusion Matrix
Gradient Boosting
22
True Low
8
False High
6
False Low
8
True High
Matrix details: Dark cells are correct classifications; error cells contain false-high and false-low classifications.
Final Train/Test Distribution
Development and untouched validation records
Flood Model Usage Notes
Screening purpose, validation errors, and probability output
Use for screening:
The model can prioritize barangays for awareness and monitoring, but final decisions should still be validated by technical staff.
The model can prioritize barangays for awareness and monitoring, but final decisions should still be validated by technical staff.
Watch false negatives:
6 high-risk validation records were predicted as low risk, so low-risk output should not remove a barangay from monitoring.
6 high-risk validation records were predicted as low risk, so low-risk output should not remove a barangay from monitoring.
Focus on high probability:
Barangays with higher predicted probability should be shown first in risk awareness and preparedness recommendations.
Barangays with higher predicted probability should be shown first in risk awareness and preparedness recommendations.
Historical baseline · Regression
Crops / Hectares Model Performance
Production in metric tons is evaluated with training-only model selection and an untouched 2023–2025 validation period.
Selected modelGradient Boosting Regressor
Selected Model
Gradient Boosting Regressor
Lowest training-only CV RMSE
Validation MAE
5,545.96
MT · lower is better
Validation RMSE
6,225.71
MT · lower is better
Validation R2
0.9855
2023–2025 · 6 records
Historical Dataset
2015–2025 · 22 records
2015–2025 · 22 records
Training Period
2017–2022 · 12 records
2017–2022 · 12 records
Validation Period
2023–2025 · 6 records
2023–2025 · 6 records
Best Tuned CV RMSE
1,833.49 MT
1,833.49 MT
Training-Only Cross-Validation
Candidate MAE and RMSE · validation years excluded
Training and Validation Distribution
Two crop records per year
Palay: Actual vs Predicted
Final validation · 2023–2025
Corn: Actual vs Predicted
Final validation · 2023–2025
Tuned Model Parameters
Gradient Boosting Regressor
| Parameter | Selected Value |
|---|---|
| learning_rate | 0.1 |
| max_depth | 1 |
| min_samples_leaf | 1 |
| n_estimators | 100 |
Final Validation Summary
Regression metrics only
| MAE | 5,545.9569 MT |
| RMSE | 6,225.7109 MT |
| R2 Score | 0.9855 |
| Selected Model | Gradient Boosting Regressor |
Final Validation RecordsActual and predicted production for 2023–2025Open table
| Crop | Year | Actual Production (MT) | Predicted Production (MT) | Absolute Error (MT) |
|---|---|---|---|---|
| Corn | 2023 | 5,025.53 | 6,948.59 | 1,923.06 |
| Palay | 2023 | 109,195.30 | 115,095.20 | 5,899.90 |
| Corn | 2024 | 4,509.81 | 6,948.59 | 2,438.78 |
| Palay | 2024 | 107,111.35 | 115,095.20 | 7,983.85 |
| Corn | 2025 | 1,821.80 | 6,948.59 | 5,126.79 |
| Palay | 2025 | 105,191.85 | 115,095.20 | 9,903.35 |