Interpretable metaheuristic-optimized machine learning for predicting biodiversity indices in the Hyrcanian forest
- 1Department of Forest Sciences and Engineering, Faculty of Natural Resources, Sari Agricultural Sciences and Natural Resources University, Sari 4844174111, Iran; Corresponding authors.
- 2Research Institute of Forests and Rangelands, Agricultural Research, Education and Extension Organization (AREEO), Tehran 1496793612, Iran; Corresponding authors.
- 3Department of Forest Sciences and Engineering, Faculty of Natural Resources, Sari Agricultural Sciences and Natural Resources University, Sari 4844174111, Iran
Abstract
Operational biodiversity indicators are essential for tracking ecological change and evaluating forest management effectiveness. However, predicting multiple biodiversity indices remains challenging because their associations with environmental and stand-structural conditions are nonlinear, context-dependent, and index-specific. We developed an interpretable machine learning framework that integrates metaheuristic optimization, multi-index biodiversity assessment, and model-based ecological interpretation using data from 811 national forest inventory plots across the Hyrcanian forest of northern Iran. Species richness, Shannon–Wiener diversity, Gini–Simpson diversity, inverse Simpson diversity, and Pielou's evenness were derived from tree-level species composition, with basal-area proportions used where appropriate for the abundance-based indices. Topographic, stand structural, edaphic, and bioclimatic variables were used as predictors. Random forest (RF), support vector machine (SVM), and k-nearest neighbors (kNN) were independently optimized for each biodiversity index using four population-based metaheuristic algorithms to select model-specific hyperparameters by minimizing validation RMSE; final model performance was evaluated on held-out test data using R 2 , RMSE, and MAE. Predictive performance differed substantially among biodiversity indices: optimized SVM performed best for Shannon–Wiener, Gini–Simpson, and inverse Simpson diversity, with test R 2 values of 0.7408, 0.8472, and 0.7387, respectively, whereas RF achieved the highest test R 2 for species richness and Pielou's evenness, with values of 0.4125 and 0.2670, respectively. Thus, abundance-weighted diversity indices were considerably more predictable than richness and evenness, highlighting the need for index-specific predictive models rather than a single universal modeling approach. SHapley Additive exPlanations (SHAP), partial dependence, and interaction analyses consistently identified elevation as the dominant predictor across biodiversity indices, whereas diameter at breast height, basal area, and slope showed distinct nonlinear response patterns. By combining index-specific hyperparameter optimization with ecological interpretation, the proposed framework supports the comparison and interpretation of biodiversity predictions for monitoring and ecological indicator development in structurally complex forests.
Related
- A feature-optimized EEG framework using multiscale entropy and metaheuristic optimization for cognitive analysis.
- Predicting student academic performance using TabPFN and SHAP: An interpretable machine learning approach
- An interpretable machine learning model for predicting response to anti-GD2 combined with umbilical cord blood-derived natural killer cell immunotherapy in neuroblastoma
- How Much of the Forest Do Citizen Scientists Actually Record? A Decade of iNaturalist Sampling in the Hyrcanian Forests
- Seasonal variation in the density of the Persian leopard in the Hyrcanian forests of northern Iran
BibTeX
@article{asadi2026interpretable,
title = {{Interpretable metaheuristic-optimized machine learning for predicting biodiversity indices in the Hyrcanian forest}},
author = {Hamed Asadi and Abolfazl Jaafari and Mahya Tafazoli and Esmaeil Valizadeh},
journal = {Ecological Indicators},
year = {2026},
month = oct,
doi = {10.1016/j.ecolind.2026.115742},
url = {https://doi.org/10.1016/j.ecolind.2026.115742},
note = {CC BY},
}
RIS
TY - JOUR
TI - Interpretable metaheuristic-optimized machine learning for predicting biodiversity indices in the Hyrcanian forest
AU - Hamed Asadi
AU - Abolfazl Jaafari
AU - Mahya Tafazoli
AU - Esmaeil Valizadeh
PY - 2026
DA - 2026/10/30
JO - Ecological Indicators
DO - 10.1016/j.ecolind.2026.115742
UR - https://doi.org/10.1016/j.ecolind.2026.115742
AB - Operational biodiversity indicators are essential for tracking ecological change and evaluating forest management effectiveness. However, predicting multiple biodiversity indices remains challenging because their associations with environmental and stand-structural conditions are nonlinear, context-dependent, and index-specific. We developed an interpretable machine learning framework that integrates metaheuristic optimization, multi-index biodiversity assessment, and model-based ecological interpretation using data from 811 national forest inventory plots across the Hyrcanian forest of northern Iran. Species richness, Shannon–Wiener diversity, Gini–Simpson diversity, inverse Simpson diversity, and Pielou's evenness were derived from tree-level species composition, with basal-area proportions used where appropriate for the abundance-based indices. Topographic, stand structural, edaphic, and bioclimatic variables were used as predictors. Random forest (RF), support vector machine (SVM), and k-nearest neighbors (kNN) were independently optimized for each biodiversity index using four population-based metaheuristic algorithms to select model-specific hyperparameters by minimizing validation RMSE; final model performance was evaluated on held-out test data using R 2 , RMSE, and MAE. Predictive performance differed substantially among biodiversity indices: optimized SVM performed best for Shannon–Wiener, Gini–Simpson, and inverse Simpson diversity, with test R 2 values of 0.7408, 0.8472, and 0.7387, respectively, whereas RF achieved the highest test R 2 for species richness and Pielou's evenness, with values of 0.4125 and 0.2670, respectively. Thus, abundance-weighted diversity indices were considerably more predictable than richness and evenness, highlighting the need for index-specific predictive models rather than a single universal modeling approach. SHapley Additive exPlanations (SHAP), partial dependence, and interaction analyses consistently identified elevation as the dominant predictor across biodiversity indices, whereas diameter at breast height, basal area, and slope showed distinct nonlinear response patterns. By combining index-specific hyperparameter optimization with ecological interpretation, the proposed framework supports the comparison and interpretation of biodiversity predictions for monitoring and ecological indicator development in structurally complex forests.
SN - 1470-160X
SN - 1872-7034
ER -