Hybrid AI-object zoning: Precision conservation planning in Abbas-Abad wildlife refuge

Articles in Press

Document Type : Research Paper

Authors

Department of Natural Resources, Isfahan University of Technology, Isfahan, I. R. Iran

Abstract

It details the progress of conservation zoning in the Abbas-Abad Wildlife Refuge (AWR) of central Iran through the application of artificial intelligence (AI) with a hybrid pixel- and object-based approach and the Ordered Weighted Averaging (OWA) method. Targeting the pristine conservation zone, Landsat-9 imagery (30 m resolution) was utilized to delineate 229 segments of optimal size from the perspective of ecological accuracy with respect to computational efficiency. Using MaxEnt, habitat suitability for keystone species was modeled, indicating high-elevation zones as critical habitat for biodiversity conservation. Multi-Criteria Decision-Making (MCDM) techniques with OWA in conjunction with AI models (machine learning models) lent themselves to a very precise spatial evaluation. The XGBoost model proved superior, providing a comprehensive accuracy of 0.93 and a Kappa value of 0.91, validated against sixty ground points found to be in strong agreement with the field observations. Suitability maps were rendered reliable due to the low inconsistency coefficient (< 0.1) of the OWA method and the strong emphasis on the fauna criteria. In contrast to classical pixel-based methods, often bearing salt-and-pepper noise, this hybrid approach provides cohesive zoning results toward managing complex arid landscapes. This AI framework represents a scalable conservation-planning model for protected areas that effectively bridges the divide between biodiversity preservation and implementation on the ground. Future studies might feature ever-changing environmental factors paired with climate change, involve local people in MCDM for alignment with socioeconomic viability, and include the exploration of deep learning, that a strong case for redefining paradigms toward sustainable management of the arid environment.

Graphical Abstract

Hybrid AI-object zoning: Precision conservation planning in Abbas-Abad wildlife refuge

Keywords

Main Subjects

References

Acreman, M., Hughes, K. A., Arthington, A. H., Tickner, D., & Dueñas, M. A. (2020). Protected areas and freshwater biodiversity: A novel systematic review distils eight lessons for effective conservation. Conservation Letters, 13(1), e12684. https://doi.org/10.1111/conl.12684
Allen, L. R., Wright, B. A., Seno, S., & Nankaya, J. (2023). Linking workforce capacity development with protected area management effectiveness assessments. Environment Systems and Decisions, 43(1), 107-114. https://doi.org/10.1007/s10669-023-09894-2
Asadi, H., Soffianian, A., Hemami, M. R., Fakheran, S., Akbari Feizabadi, H., & Corcoran, F. (2022). A hybrid GIS-OWA and DANP method for the identification and evaluation of ecotourism attractions: The case study of Abbas-Abad Wildlife Refuge, Iran. GeoJournal, 87(6), 5179-5196. https://doi.org/10.1007/s10708-021-10564-6
Belgiu, M., & Drăguţ, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114, 24-31. https://doi.org/10.1016/j.isprsjprs.2016.01.011
Bui, D. H., & Mucsi, L. (2021). From land cover map to land use map: A combined pixel-based and object-based approach using multi-temporal Landsat data, a random forest classifier, and decision rules. Remote Sensing, 13(9), 1700. https://doi.org/10.3390/rs13091700
Chi, Y., Zhang, Z., Wang, J., Xie, Z., & Gao, J. (2020). Island protected area zoning based on ecological importance and tenacity. Ecological Indicators, 112, 106139. https://doi.org/10.1016/j.ecolind.2020.106139
Ding, X., Hasanipanah, M., & Ulrikh, D. V. (2024). Hybrid metaheuristic optimization algorithms with least-squares support vector machine and boosted regression tree models for prediction of air-blast due to mine blasting. Natural Resources Research, 33(3), 1349-1363. https://doi.org/10.1007/s11053-024-10329-1
Dornik, A., Drăguţ, L., & Urdea, P. (2018). Classification of soil types using geographic object-based image analysis and random forests. Pedosphere, 28(6), 913-925. https://doi.org/10.1016/S1002-0160(17)60377-1
Geldmann, J., Manica, A., Burgess, N. D., Coad, L., & Balmford, A. (2019). A global-level assessment of the effectiveness of protected areas at resisting anthropogenic pressures. Proceedings of the National Academy of Sciences, 116(46), 23209-23215. https://doi.org/10.1073/pnas.1908221116
Gray, C. L., Hill, S. L., Newbold, T., Hudson, L. N., Börger, L., Contu, S., Scharlemann, J. P., et al. (2016). Local biodiversity is higher inside than outside terrestrial protected areas worldwide. Nature Communications, 7(1), 12306. https://doi.org/10.1038/ncomms12306
Kang, B., Deng, Y., Hewage, K., & Sadiq, R. (2018). Generating Z‐number based on OWA weights using maximum entropy. International Journal of Intelligent Systems, 33(8), 1745-1755. https://doi.org/10.1002/int.21995.v
Karampour, M., Halabian, A., Hosseini, A., & Mosapoor, M. (2024). Comparing the performance of fuzzy operators in the object-based image analysis and support vector machine kernel functions for the snow cover estimation in Alvand Mountain. Theoretical and Applied Climatology, 155(3), 1729-1737. https://doi.org/10.1007/s00704-023-04724-6
Lerm, R. E., Ehlers Smith, D. A., Thompson, D. I., & Downs, C. T. (2023). Human infrastructure, surface water and tree cover are important drivers of bird diversity across a savanna protected area-mosaic landscape. Landscape Ecology, 38(8), 1991-2004. https://doi.org/10.1007/s10980-023-01674-2
Li, S., Zhang, H., Zhou, X., Yu, H., & Li, W. (2020). Enhancing protected areas for biodiversity and ecosystem services in the Qinghai–Tibet Plateau. Ecosystem Services, 43, 101090. https://doi.org/10.1016/j.ecoser.2020.101090
Loch, A., Scholz, G., Auricht, C., Sexton, S., O’Connor, P., & Imgraben, S. (2023). Valuing protected area tourism ecosystem services using big data. Environmental Management, 71(2), 260-273. https://doi.org/10.1007/s00267-022-01746-0
Masoudi, M., Centeri, C., Jakab, G., Nel, L., & Mojtahedi, M. (2021). GIS-based multi-criteria and multi-objective evaluation for sustainable land-use planning (case study: Qaleh Ganj County, Iran) “landuse planning using mce and mola.” International Journal of Environmental Research, 15, 457-474. https://doi.org/10.1007/s41742-021-00326-0
Mosadeghi, R., Warnken, J., Tomlinson, R., & Mirfenderesk, H. (2015). Comparison of fuzzy-AHP and AHP in a spatial multi-criteria decision making model for urban land-use planning. Computers, Environment and Urban Systems, 49, 54-65. https://doi.org/10.1016/j.compenvurbsys.2014.10.001
Nguyen, T. T., Verdoodt, A., Van Y, T., Delbecque, N., Tran, T. C., & Van Ranst, E. (2015). Design of a GIS and multi-criteria based land evaluation procedure for sustainable land-use planning at the regional level. Agriculture, Ecosystems & Environment, 200, 1-11. https://doi.org/10.1016/j.agee.2014.10.015
Pant, D. R., Techato, K., Pradit, S., Gyawali, S., & Baniya, B. (2025). Assessment on factors affecting human wild animal coexistence and associated mitigation measures in the buffer zone community of Shivapuri Nagarjun national park, Nepal. Environmental and Sustainability Indicators, 25, 100552. https://doi.org/10.1016/j.indic.2024.100552
Peykanpour Fard, R., Moradi, H., Lotfi, A., Pourmanafi, S., & Bihamta Toosi, N. (2023). Advancing the mapping of optimal land use structure in industrialized areas: Incorporating AERMOD modeling and MCE approach. GeoJournal, 88(2), 1979-1995. https://doi.org/10.1007/s10708-022-10716-2
Peykanpour Fard, R., Soffianian, A., Ahmadi, M., & Pourmanafi, S. (2025). From pixels to objects: Integrated indicators for balancing sustainable management in protected areas. Ecological Informatics, 103371, 1-13. https://doi.org/10.1016/j.ecoinf.2025.103371
Rezaei, J. (2015). Best-worst multi-criteria decision-making method. Omega, 53, 49-57. https://doi.org/10.1016/j.omega.2014.11.009
Ripley, B., Venables, W., & Ripley, M. B. (2016). Package ‘nnet’. R Package Version, 7(3–12), 700.
Sang, X., Guo, Q., Wu, X., Fu, Y., Xie, T., He, C., & Zang, J. (2019). Intensity and stationarity analysis of land use change based on CART algorithm. Scientific Reports, 9(1), 12279. https://doi.org/10.1038/s41598-019-48586-3
Stephen, S., & Haldar, D. (2024). Categorisation of mango orchard age groups using Object-Based Image Analysis. Arabian Journal of Geosciences, 17(2), 62. https://doi.org/10.1007/s12517-024-11857-z
Subandi, E. L., & Ardiansyah, M. (2019). Use of WLC (Weighted Linear Combination) to determine land priorities for development of paddy fields in Gorontalo Regency, Indonesia. International Journal of Engineering and Management Research (IJEMR), 9(3), 58-63. https://doi.org/10.31033/ijemr.9.3.8
Talebi, M., Majnounian, B., Makhdoum, M., Abdi, E., Omid, M., Marchi, E., & Laschi, A. (2019). A GIS-MCDM-based road network planning for tourism development and management in Arasbaran forest, Iran. Environmental Monitoring and Assessment, 191, 1-15. https://doi.org/10.1007/s10661-019-7831-3
Tong, J., Wu, L., Li, B., Jiang, N., Huang, J., Wu, D., Pei, X., (2024). Image-based vegetation analysis of desertified area by using a combination of ImageJ and Photoshop software. Environmental Monitoring and Assessment, 196(3), 306. https://doi.org/10.1007/s10661-024-12479-4
Xu, W., Li, X., Pimm, S. L., Hull, V., Zhang, J., Zhang, L., Ouyang, Z., et al. (2016). The effectiveness of the zoning of China's protected areas. Biological Conservation, 204, 231-236. https://doi.org/10.1016/j.biocon.2016.10.028
Zhang, C., Yu, S., & Zhang, J. (2025). Research on urban sustainability based on neural network models and GIS methods. Sustainability, 17(2), 397. https://doi.org/10.3390/su17020397
Iran Agricultural Research

Articles in Press, Accepted Manuscript
Available Online from 22 June 2026

Files

Share

How to cite

Statistics