A new method for broad‐scale modeling and projection of plant assemblages under climatic, biotic, and environmental cofiltering. Issue 2 (23rd August 2021)
- Record Type:
- Journal Article
- Title:
- A new method for broad‐scale modeling and projection of plant assemblages under climatic, biotic, and environmental cofiltering. Issue 2 (23rd August 2021)
- Main Title:
- A new method for broad‐scale modeling and projection of plant assemblages under climatic, biotic, and environmental cofiltering
- Authors:
- Ferrarini, Alessandro
Bai, Yang
Dai, Junhu
Alatalo, Juha M. - Abstract:
- Abstract: There is increasing interestin broad‐scale analysis, modeling, and prediction of the distribution and composition of plant species assemblages under climatic, environmental, and biotic change, particularly for conservation purposes. We devised a method to reliably predict the impact of climate change on large assemblages of plant communities, while also considering competing biotic and environmental factors. To this purpose, we first used multilabel algorithms in order to convert the task of explaining a large assemblage of plant communities into a classification framework able to capture with high cross‐validated accuracy the pattern of species distributions under a composite set of biotic and abiotic factors. We applied our model to a large set of plant communities in the Swiss Alps. Our model explained presences and absences of 175 plant species in 608 plots with >87% cross‐validated accuracy, predicted decreases in α, β, and γ diversity by 2040 under both moderate and extreme climate scenarios, and identified likely advantaged and disadvantaged plant species under climate change. Multilabel variable selection revealed the overriding importance of topography, soils, and temperature extremes (rather than averages) in determining the distribution of plant species in the study area and their response to climate change. Our method addressed a number of challenging research problems, such as scaling to large numbers of species, considering species relationships andAbstract: There is increasing interestin broad‐scale analysis, modeling, and prediction of the distribution and composition of plant species assemblages under climatic, environmental, and biotic change, particularly for conservation purposes. We devised a method to reliably predict the impact of climate change on large assemblages of plant communities, while also considering competing biotic and environmental factors. To this purpose, we first used multilabel algorithms in order to convert the task of explaining a large assemblage of plant communities into a classification framework able to capture with high cross‐validated accuracy the pattern of species distributions under a composite set of biotic and abiotic factors. We applied our model to a large set of plant communities in the Swiss Alps. Our model explained presences and absences of 175 plant species in 608 plots with >87% cross‐validated accuracy, predicted decreases in α, β, and γ diversity by 2040 under both moderate and extreme climate scenarios, and identified likely advantaged and disadvantaged plant species under climate change. Multilabel variable selection revealed the overriding importance of topography, soils, and temperature extremes (rather than averages) in determining the distribution of plant species in the study area and their response to climate change. Our method addressed a number of challenging research problems, such as scaling to large numbers of species, considering species relationships and rarity, and addressing an overwhelming proportion of absences in presence–absence matrices. By handling hundreds to thousands of plants and plots simultaneously over large areas, our method can inform broad‐scale conservation of plant species under climate change because it allows species that require urgent conservation action (assisted migration, seed conservation, and ex situ conservation) to be detected and prioritized. Our method also increases the practicality of assisted colonization of plant species by helping to prevent ill‐advised introduction of plant species with limited future survival probability. Abstract : Article impact statement : Broad‐scale analysis and modeling of plant assemblages under climatic‐biotic‐environmental cofiltering identifies species for early conservation. Abstract : Un Método Nuevo para el Modelado y Proyección a Gran Escala de Ensambles de Plantas Bajo Cofiltrado Climático, Biótico y Ambiental Resumen: Hay un creciente interés en el análisis, modelado y predicción a gran escala de la distribución y composición de ensambles de especies de plantas bajo cambio climático, ambiental y biótico, particularmente con fines de conservación. Diseñamos un método para predecir confiablemente el impacto del cambio climático sobre ensambles grandes de comunidades de plantas, considerando también factores bióticos y ambientales. Para ello, primero utilizamos algoritmos multi‐etiqueta para convertir la tarea de explicar un ensamble grande de comunidades vegetales en un marco de clasificación capaz de capturar, con alta precisión validad, el patrón de distribuciones de especies bajo un conjunto de factores bióticos y abióticos. Aplicamos nuestro modelo a un conjunto grande comunidades vegetales de los Alpes Suizos. Nuestro modelo explicó la presencia y ausencia de 175 especies de plantas en 608 parcelas con una precisión validada de >87%, predijo disminuciones de diversidad α, β, y γ en 2040 bajo escenarios tanto moderados como extremos e identificó especies de plantas potencialmente ventajosas y desventajosas por el cambio climático. La selección de variables multi‐etiqueta reveló la importancia primordial de la topografía, suelos y extremos de temperatura (en lugar de los promedios) para determinar la distribución de especies de plantas en el área de estudio y su respuesta al cambio climático. Nuestro método abordó un número de problemas de investigación desafiantes, tal como escalar a un número mayor de especies, considerar las relaciones entre especies y rareza, y atender una proporción enorme de ausencias en las matrices de presencia‐ausencia. Al manejar cientos o miles de plantas y parcelas simultáneamente, nuestro método puede informar la conservación a gran escala de especies de plantas bajo el cambio climático porque permite detectar y priorizar especies que requieren acción urgente de conservación (migración asistida, conservación de semillas, conservación ex situ). Nuestro método también incrementa la utilidad de la colonización asistida de especies de plantas al ayudar a prevenir la introducción mal aconsejada de especies de plantas con una probabilidad de supervivencia futura limitada. 一种气候、生物和环境共约束下植物物种组合的大尺度建模和预测新方法 : 中文摘要 近年来, 人们对气候、环境和生物变化下植物物种组合分布和结构的大尺度分析、建模和预测越来越感兴趣, 特别是出于植物保护的目的。在本文中, 我们设计了一种方法来可靠地预测气候变化对植物群落的影响, 同时也考虑到生物和环境因素的作用。为此, 我们首先使用多标签算法, 将解释大型植物群落组合的任务转换为一个分类框架, 该框架能够在生物和非生物因素组织下以较高的交叉验证精度把握物种分布模式。我们将此模型应用于瑞士阿尔卑斯山的一系列植物群落组合研究上。 该模型以 >87% 的交叉验证精度解释了608 个样地中 175 种植物的存在与否的问题, 预测了到 2040 年温和和极端气候情景下α、β和γ多样性的减少情况, 并确定了气候变化下可能的获益或受损物种。 多标签变量的选择揭示了地形、土壤和极端温度(而非平均温度)在决定研究区植物物种分布及其对气候变化的响应方面的绝对重要作用。我们的方法解决了许多具有挑战性科学问题, 如变尺度到大量物种, 考虑物种关系和稀有性, 并解决了存在‐缺失矩阵中绝大部分的缺失。通过在大范围内同时处理成百上千种植物和样地, 我们的方法可以为气候变化下植物物种的大范围保护提供参考, 因为它允许对需要紧急保护行动(辅助迁移、种子保护、迁地保护)的物种进行检测和优先级排序。我们的方法有助于防止不合理引进未来存活概率较小的物种, 从而提升了植物物种辅助定殖的实际可操作性。 关键词: 分类器链, 气候变化, 多标签模拟, 植物物种保护, 稀有物种, 瑞士阿尔卑斯山 … (more)
- Is Part Of:
- Conservation biology. Volume 36:Issue 2(2022)
- Journal:
- Conservation biology
- Issue:
- Volume 36:Issue 2(2022)
- Issue Display:
- Volume 36, Issue 2 (2022)
- Year:
- 2022
- Volume:
- 36
- Issue:
- 2
- Issue Sort Value:
- 2022-0036-0002-0000
- Page Start:
- n/a
- Page End:
- n/a
- Publication Date:
- 2021-08-23
- Subjects:
- classifier chains -- climate change -- multilabel modeling -- plant species conservation -- rare species -- Swiss Alps -- Cadenas de clasificación -- cambió climático -- conservación de especies de plantas -- modelado multi‐etiqueta
Conservation biology -- Periodicals
333.9516 - Journal URLs:
- http://onlinelibrary.wiley.com/journal/10.1111/(ISSN)1523-1739 ↗
http://onlinelibrary.wiley.com/ ↗ - DOI:
- 10.1111/cobi.13797 ↗
- Languages:
- English
- ISSNs:
- 0888-8892
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 3417.999000
British Library DSC - BLDSS-3PM
British Library STI - ELD Digital store - Ingest File:
- 21316.xml