Predicting the Potential Distribution of <i>Haloxylon ammodendron</i> under Climate Change Scenarios Using Machine Learning of a Maximum Entropy Model
<i>Haloxylon ammodendron (H. ammodendron)</i> is a second-class protected plant of national significance in China that is known for its growth in desert and semidesert regions, where it serves as a desert ecosystem guardian by playing a substantial role in maintaining ecosystem structure...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-12-01
|
Series: | Biology |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-7737/13/1/3 |
_version_ | 1797344529291935744 |
---|---|
author | Fengjin Xiao Qiufeng Liu Yun Qin |
author_facet | Fengjin Xiao Qiufeng Liu Yun Qin |
author_sort | Fengjin Xiao |
collection | DOAJ |
description | <i>Haloxylon ammodendron (H. ammodendron)</i> is a second-class protected plant of national significance in China that is known for its growth in desert and semidesert regions, where it serves as a desert ecosystem guardian by playing a substantial role in maintaining ecosystem structure and function. The changing global climate has substantially altered the growth conditions for <i>H. ammodendron</i>. This study focuses on identifying the key variables influencing the distribution of <i>H. ammodendron</i> and determining their potential impact on future distribution. We employed the Maxent model to evaluate the current climate suitability for <i>H. ammodendron</i> distribution and to project its future changes across various shared socioeconomic pathway (SSP) scenarios. Our findings indicate that precipitation during the warmest quarter and precipitation during the wettest month are the most influential variables affecting the potentially suitable habitats of <i>H. ammodendron</i>. The highly suitable habitat area for <i>H. ammodendron</i> currently covers approximately 489,800 km<sup>2</sup>. The Maxent model forecasts an expansion of highly suitable <i>H. ammodendron</i> habitat under all future SSP scenarios, with the extent of unsuitable areas increasing with greater global warming. The increased highly suitable habitats range from 40% (SSP585) to 80% (SSP126) by the 2070s (2060–2080). Furthermore, our results indicate a continued expansion of desertification areas due to global warming, highlighting the significant role of <i>H. ammodendron</i> in maintaining desert ecosystem stability. This study offers valuable insights into biodiversity preservation and ecological protection in the context of future climate change scenarios. |
first_indexed | 2024-03-08T11:05:01Z |
format | Article |
id | doaj.art-17cbad40772a440d980d8612db29f563 |
institution | Directory Open Access Journal |
issn | 2079-7737 |
language | English |
last_indexed | 2024-03-08T11:05:01Z |
publishDate | 2023-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Biology |
spelling | doaj.art-17cbad40772a440d980d8612db29f5632024-01-26T15:06:32ZengMDPI AGBiology2079-77372023-12-01131310.3390/biology13010003Predicting the Potential Distribution of <i>Haloxylon ammodendron</i> under Climate Change Scenarios Using Machine Learning of a Maximum Entropy ModelFengjin Xiao0Qiufeng Liu1Yun Qin2National Climate Center, Chinese Meteorological Administration, Beijing 100081, ChinaNational Climate Center, Chinese Meteorological Administration, Beijing 100081, ChinaNational Climate Center, Chinese Meteorological Administration, Beijing 100081, China<i>Haloxylon ammodendron (H. ammodendron)</i> is a second-class protected plant of national significance in China that is known for its growth in desert and semidesert regions, where it serves as a desert ecosystem guardian by playing a substantial role in maintaining ecosystem structure and function. The changing global climate has substantially altered the growth conditions for <i>H. ammodendron</i>. This study focuses on identifying the key variables influencing the distribution of <i>H. ammodendron</i> and determining their potential impact on future distribution. We employed the Maxent model to evaluate the current climate suitability for <i>H. ammodendron</i> distribution and to project its future changes across various shared socioeconomic pathway (SSP) scenarios. Our findings indicate that precipitation during the warmest quarter and precipitation during the wettest month are the most influential variables affecting the potentially suitable habitats of <i>H. ammodendron</i>. The highly suitable habitat area for <i>H. ammodendron</i> currently covers approximately 489,800 km<sup>2</sup>. The Maxent model forecasts an expansion of highly suitable <i>H. ammodendron</i> habitat under all future SSP scenarios, with the extent of unsuitable areas increasing with greater global warming. The increased highly suitable habitats range from 40% (SSP585) to 80% (SSP126) by the 2070s (2060–2080). Furthermore, our results indicate a continued expansion of desertification areas due to global warming, highlighting the significant role of <i>H. ammodendron</i> in maintaining desert ecosystem stability. This study offers valuable insights into biodiversity preservation and ecological protection in the context of future climate change scenarios.https://www.mdpi.com/2079-7737/13/1/3climate change<i>H. ammodendron</i>Maxent modelpotential distributionprediction |
spellingShingle | Fengjin Xiao Qiufeng Liu Yun Qin Predicting the Potential Distribution of <i>Haloxylon ammodendron</i> under Climate Change Scenarios Using Machine Learning of a Maximum Entropy Model Biology climate change <i>H. ammodendron</i> Maxent model potential distribution prediction |
title | Predicting the Potential Distribution of <i>Haloxylon ammodendron</i> under Climate Change Scenarios Using Machine Learning of a Maximum Entropy Model |
title_full | Predicting the Potential Distribution of <i>Haloxylon ammodendron</i> under Climate Change Scenarios Using Machine Learning of a Maximum Entropy Model |
title_fullStr | Predicting the Potential Distribution of <i>Haloxylon ammodendron</i> under Climate Change Scenarios Using Machine Learning of a Maximum Entropy Model |
title_full_unstemmed | Predicting the Potential Distribution of <i>Haloxylon ammodendron</i> under Climate Change Scenarios Using Machine Learning of a Maximum Entropy Model |
title_short | Predicting the Potential Distribution of <i>Haloxylon ammodendron</i> under Climate Change Scenarios Using Machine Learning of a Maximum Entropy Model |
title_sort | predicting the potential distribution of i haloxylon ammodendron i under climate change scenarios using machine learning of a maximum entropy model |
topic | climate change <i>H. ammodendron</i> Maxent model potential distribution prediction |
url | https://www.mdpi.com/2079-7737/13/1/3 |
work_keys_str_mv | AT fengjinxiao predictingthepotentialdistributionofihaloxylonammodendroniunderclimatechangescenariosusingmachinelearningofamaximumentropymodel AT qiufengliu predictingthepotentialdistributionofihaloxylonammodendroniunderclimatechangescenariosusingmachinelearningofamaximumentropymodel AT yunqin predictingthepotentialdistributionofihaloxylonammodendroniunderclimatechangescenariosusingmachinelearningofamaximumentropymodel |