2024
Sakti, A. D.; Adillah, K. P.; Santoso, C.; Faruqi, I. A.; Hendrawan, V. S. A.; Sofan, P.; Rustam, R.; Fauzi, A. I.; Setiawan, Y.; Utami, I.; Zain, A. F.; Kamal, M.
Modeling Proboscis monkey conservation sites on Borneo using ensemble machine learning Journal Article
In: Global Ecology and Conservation, vol. 54, 2024, ISSN: 23519894.
Abstract | Links | BibTeX | Tags: Borneo, Habitat suitability, Machine learning, Proboscis monkeys, Remote sensing
@article{Sakti2024,
title = {Modeling Proboscis monkey conservation sites on Borneo using ensemble machine learning},
author = {A. D. Sakti and K. P. Adillah and C. Santoso and I. A. Faruqi and V. S. A. Hendrawan and P. Sofan and R. Rustam and A. I. Fauzi and Y. Setiawan and I. Utami and A. F. Zain and M. Kamal},
doi = {10.1016/j.gecco.2024.e03101},
issn = {23519894},
year = {2024},
date = {2024-01-01},
journal = {Global Ecology and Conservation},
volume = {54},
abstract = {This study aimed to analyze the habitat suitability of the endangered Proboscis monkey (Nasalis larvatus) on Borneo using a multi-machine-learning approach. This study integrated physical, vegetational, meteorological, and human activity data to develop a comprehensive habitat suitability model. Four machine-learning algorithms, namely, maximum entropy (MaxEnt), random forest (RF), support vector machine (SVM), gradient tree boosting (GTB), and classification and regression trees (CART), were employed to model the habitat suitability index. A total of 1943 sample points were divided into training (70 %) and validation (30 %) sets for the analysis. This study included three main stages: geospatial database creation, spatial habitat modeling using multi-machine-learning algorithms, and habitat suitability evaluation. In addition, the pressure from human development on the habitat suitability index model was analyzed. This study identified a high level of suitability for Proboscis monkey habitats in nearshore areas. The maximum habitat suitability for Proboscis monkeys was observed to be 11.54 %, as evidenced by the consensus of the MaxEnt value and four machine-learning algorithms. Conversely, the minimum habitat suitability was recorded at 13.27 %, as indicated by disagreement among all algorithms. The AUC values for the machine-learning models ranged from 74 % to 90 %, indicating moderate to high predictive performance. This study provides valuable insights for the formulation of well-planned development programs for Proboscis monkeys. The results of this study will contribute to the accurate identification of potential Proboscis monkey habitats, thereby providing support for conservation efforts aimed at safeguarding this endangered species.},
keywords = {Borneo, Habitat suitability, Machine learning, Proboscis monkeys, Remote sensing},
pubstate = {published},
tppubtype = {article}
}
This study aimed to analyze the habitat suitability of the endangered Proboscis monkey (Nasalis larvatus) on Borneo using a multi-machine-learning approach. This study integrated physical, vegetational, meteorological, and human activity data to develop a comprehensive habitat suitability model. Four machine-learning algorithms, namely, maximum entropy (MaxEnt), random forest (RF), support vector machine (SVM), gradient tree boosting (GTB), and classification and regression trees (CART), were employed to model the habitat suitability index. A total of 1943 sample points were divided into training (70 %) and validation (30 %) sets for the analysis. This study included three main stages: geospatial database creation, spatial habitat modeling using multi-machine-learning algorithms, and habitat suitability evaluation. In addition, the pressure from human development on the habitat suitability index model was analyzed. This study identified a high level of suitability for Proboscis monkey habitats in nearshore areas. The maximum habitat suitability for Proboscis monkeys was observed to be 11.54 %, as evidenced by the consensus of the MaxEnt value and four machine-learning algorithms. Conversely, the minimum habitat suitability was recorded at 13.27 %, as indicated by disagreement among all algorithms. The AUC values for the machine-learning models ranged from 74 % to 90 %, indicating moderate to high predictive performance. This study provides valuable insights for the formulation of well-planned development programs for Proboscis monkeys. The results of this study will contribute to the accurate identification of potential Proboscis monkey habitats, thereby providing support for conservation efforts aimed at safeguarding this endangered species.