Tecomella undulata under threat: The impact of climate change on the distribution of a valuable tree species using a machine learning model

PLOS One | https://doi.org/10.1371/journal.pone.0326609 July 9, 2025 1 / 18 OPEN ACCESS Citation: Ghafouri E, Ghanbarian G, Cerdà A, Ghafouri S (2025) Tecomella undulata under threat: The impact of climate change on the distribution of a valuable tree species using a machine learning model. PLoS One 20(7): e0326609. https://doi.org/10.1371/journal. pone.0326609 Editor: Clement Ameh Yaro, University of Uyo, NIGERIA Received: November 9, 2024 Accepted: June 2, 2025 Published: July 9, 2025 Copyright: © 2025 Ghafouri et al . This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Data availability statement: All relevant data are within the paper and its Supporting Information files. Funding: The author(s) received no specific funding for this work. RESEARCH ARTICLE Tecomella undulata under threat: The impact of climate change on the distribution of a valuable tree species using a machine learning model Ehsan Ghafouri 1, Gholamabbas Ghanbarian 1*, Artemi Cerdà 2, Saeideh Ghafouri 1 1 Department of Natural Resources and Environmental Engineering, School of Agriculture, Shiraz University, Shiraz, Iran, 2 Department of Geography, Soil Erosion and Degradation Research Group, University of Valencia, Valencia, Spain * g.ghanbarian@gmail.com, ghanbarian@shirazu.ac.ir Abstract Climate change has emerged as a significant driver of biodiversity loss, with pro-

found implications for species distribution. This study assessed the current and future distribution of Tecomella undulata (Desert teak), an economically and medicinally valuable species facing threats from climate change. MaxEnt model, built using 44 occurrence points and environmental data including bioclimatic factors and Digital Elevation Model (DEM), demonstrated an impressive Area Under the Curve (AUC) value of around 0.91 and a True Skill Statistic (TSS) value of 0.79, indicating excel- lent predictive performance. Temperature seasonality (Bio4) emerged as the most crucial variable, contributing 35.9% to the modeling, followed by the mean tempera- ture of the wettest quarter (Bio8) and precipitation seasonality (Bio15). The habitat suitability maps showed a strong presence of T. undulata in the southern regions of Iran, with Fars and Bushehr provinces being particularly conducive to its growth. Future projections under Shared Socioeconomic Pathways (SSP) scenarios SSP245 and SSP585 for 2030, 2050, 2070, and 2090 suggested a decline in suitable hab- itats for T. undulata, with high-suitability areas projected to decrease by up to 98% and unsuitable habitats predicted to increase. The study underscores the urgency for tailored conservation measures to mitigate the impacts of climate change on this valuable species. Introduction The loss of biodiversity, driven by habitat destruction, resource overexploitation, pollution, and invasive species [1,2], underscores the need for green technology

innovation in sectors like agriculture and industry, which are major contributors to environmental emissions [3,4]. While climate change is not currently the primary driver of biodiversity loss, its impact is increasing and is expected to become a major contributor in the near future [5,6]. The implications of this decline are far-reaching,