Modeling habitat suitability for endangered herb (Salvia leriifolia Benth) using Innovative hybrid machine learning algorithms
Mapping habitat suitability is critical for conserving endangered medicinal and aromatic plants (MAPs) in degraded ecosystems. This study evaluated habitat suitability for Salvia leriifolia, an endangered herb in Khorasan Razavi, Iran, by comparing individual machine learning models (Random Forest [...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Environmental and Sustainability Indicators |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2665972725001151 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849713156772855808 |
|---|---|
| author | Emran Dastres Hamidreza Rabiei-Dastjerdi Hassan Esmaeili Mahdis Amiri Ali Sonboli Mohammad Hossein Mirjalili |
| author_facet | Emran Dastres Hamidreza Rabiei-Dastjerdi Hassan Esmaeili Mahdis Amiri Ali Sonboli Mohammad Hossein Mirjalili |
| author_sort | Emran Dastres |
| collection | DOAJ |
| description | Mapping habitat suitability is critical for conserving endangered medicinal and aromatic plants (MAPs) in degraded ecosystems. This study evaluated habitat suitability for Salvia leriifolia, an endangered herb in Khorasan Razavi, Iran, by comparing individual machine learning models (Random Forest [RF], Boosted Regression Tree [BRT], Generalized Linear Model [GLM]) with hybrid ensemble models (FDA-GLM-MDA and RF-CART-BRT). Using GIS, we compiled a dataset of 23 environmental and anthropogenic variables. Variable importance was assessed via Elastic Net (ENET), while model performance was evaluated using ROC-AUC metrics. Results identified distance from roads, calcium (Ca), organic matter (OM), and potassium (K) as the most influential predictors of habitat suitability. The individual RF model (AUC = 0.983) and hybrid RF-CART-BRT model (AUC = 0.970) demonstrated the highest predictive accuracy, underscoring the efficacy of tree-based and ensemble approaches in ecological modeling. However, while high-accuracy models offer precise predictions, their complexity may challenge practical application by conservation practitioners. This highlights the need to balance technical precision with operational feasibility in conservation planning. Although focused on Khorasan Razavi, the methodology is transferable to regions facing similar ecological pressures. By identifying key drivers of habitat suitability, this work enabled scalable strategies for protecting endangered MAPs. These insights offered actionable strategies for resource managers and agricultural planners to sustainably protect and cultivate S. leriifolia, while addressing predictive model implementation challenges. |
| format | Article |
| id | doaj-art-79b801c200024b20b4e4a38b9971a3bb |
| institution | DOAJ |
| issn | 2665-9727 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Environmental and Sustainability Indicators |
| spelling | doaj-art-79b801c200024b20b4e4a38b9971a3bb2025-08-20T03:14:02ZengElsevierEnvironmental and Sustainability Indicators2665-97272025-06-012610069410.1016/j.indic.2025.100694Modeling habitat suitability for endangered herb (Salvia leriifolia Benth) using Innovative hybrid machine learning algorithmsEmran Dastres0Hamidreza Rabiei-Dastjerdi1Hassan Esmaeili2Mahdis Amiri3Ali Sonboli4Mohammad Hossein Mirjalili5Department of Agriculture, Medicinal Plants and Drugs Research Institute, Shahid Beheshti University, 1983969411, Tehran, IranSchool of History and Geography, Faculty of Humanities and Social Sciences, Dublin City University (DCU), Dublin, Ireland; Corresponding author.Department of Agriculture, Medicinal Plants and Drugs Research Institute, Shahid Beheshti University, 1983969411, Tehran, Iran; Corresponding author.Department of Watershed and Arid Zone Management, Gorgan University of Agricultural Sciences & Natural Resources, Gorgan, IranDepartment of Biology, Medicinal Plants and Drugs Research Institute, Shahid Beheshti University, 1983969411, Tehran, IranDepartment of Agriculture, Medicinal Plants and Drugs Research Institute, Shahid Beheshti University, 1983969411, Tehran, IranMapping habitat suitability is critical for conserving endangered medicinal and aromatic plants (MAPs) in degraded ecosystems. This study evaluated habitat suitability for Salvia leriifolia, an endangered herb in Khorasan Razavi, Iran, by comparing individual machine learning models (Random Forest [RF], Boosted Regression Tree [BRT], Generalized Linear Model [GLM]) with hybrid ensemble models (FDA-GLM-MDA and RF-CART-BRT). Using GIS, we compiled a dataset of 23 environmental and anthropogenic variables. Variable importance was assessed via Elastic Net (ENET), while model performance was evaluated using ROC-AUC metrics. Results identified distance from roads, calcium (Ca), organic matter (OM), and potassium (K) as the most influential predictors of habitat suitability. The individual RF model (AUC = 0.983) and hybrid RF-CART-BRT model (AUC = 0.970) demonstrated the highest predictive accuracy, underscoring the efficacy of tree-based and ensemble approaches in ecological modeling. However, while high-accuracy models offer precise predictions, their complexity may challenge practical application by conservation practitioners. This highlights the need to balance technical precision with operational feasibility in conservation planning. Although focused on Khorasan Razavi, the methodology is transferable to regions facing similar ecological pressures. By identifying key drivers of habitat suitability, this work enabled scalable strategies for protecting endangered MAPs. These insights offered actionable strategies for resource managers and agricultural planners to sustainably protect and cultivate S. leriifolia, while addressing predictive model implementation challenges.http://www.sciencedirect.com/science/article/pii/S2665972725001151Habitat suitabilityMachine learningMedicinal plantEnvironmental managementGISSalvia leriifolia |
| spellingShingle | Emran Dastres Hamidreza Rabiei-Dastjerdi Hassan Esmaeili Mahdis Amiri Ali Sonboli Mohammad Hossein Mirjalili Modeling habitat suitability for endangered herb (Salvia leriifolia Benth) using Innovative hybrid machine learning algorithms Environmental and Sustainability Indicators Habitat suitability Machine learning Medicinal plant Environmental management GIS Salvia leriifolia |
| title | Modeling habitat suitability for endangered herb (Salvia leriifolia Benth) using Innovative hybrid machine learning algorithms |
| title_full | Modeling habitat suitability for endangered herb (Salvia leriifolia Benth) using Innovative hybrid machine learning algorithms |
| title_fullStr | Modeling habitat suitability for endangered herb (Salvia leriifolia Benth) using Innovative hybrid machine learning algorithms |
| title_full_unstemmed | Modeling habitat suitability for endangered herb (Salvia leriifolia Benth) using Innovative hybrid machine learning algorithms |
| title_short | Modeling habitat suitability for endangered herb (Salvia leriifolia Benth) using Innovative hybrid machine learning algorithms |
| title_sort | modeling habitat suitability for endangered herb salvia leriifolia benth using innovative hybrid machine learning algorithms |
| topic | Habitat suitability Machine learning Medicinal plant Environmental management GIS Salvia leriifolia |
| url | http://www.sciencedirect.com/science/article/pii/S2665972725001151 |
| work_keys_str_mv | AT emrandastres modelinghabitatsuitabilityforendangeredherbsalvialeriifoliabenthusinginnovativehybridmachinelearningalgorithms AT hamidrezarabieidastjerdi modelinghabitatsuitabilityforendangeredherbsalvialeriifoliabenthusinginnovativehybridmachinelearningalgorithms AT hassanesmaeili modelinghabitatsuitabilityforendangeredherbsalvialeriifoliabenthusinginnovativehybridmachinelearningalgorithms AT mahdisamiri modelinghabitatsuitabilityforendangeredherbsalvialeriifoliabenthusinginnovativehybridmachinelearningalgorithms AT alisonboli modelinghabitatsuitabilityforendangeredherbsalvialeriifoliabenthusinginnovativehybridmachinelearningalgorithms AT mohammadhosseinmirjalili modelinghabitatsuitabilityforendangeredherbsalvialeriifoliabenthusinginnovativehybridmachinelearningalgorithms |