Leveraging AI to improve evidence synthesis in conservation

Oded Berger-Tal; Bob B.M. Wong; Carrie Ann Adams; Daniel T. Blumstein; Ulrika Candolin; Matthew J. Gibson; Alison L. Greggor; Malgorzata Lagisz; Biljana Macura; Catherine J. Price; Breanna J. Putman; Lysanne Snijders; Shinichi Nakagawa

doi:10.1016/j.tree.2024.04.007

Leveraging AI to improve evidence synthesis in conservation

Oded Berger-Tal, Bob B.M. Wong, Carrie Ann Adams, Daniel T. Blumstein, Ulrika Candolin, Matthew J. Gibson, Alison L. Greggor, Malgorzata Lagisz, Biljana Macura, Catherine J. Price, Breanna J. Putman, Lysanne Snijders, Shinichi Nakagawa

School of Biological Sciences

Research output: Contribution to journal › Review Article › Research › peer-review

Abstract

Systematic evidence syntheses (systematic reviews and maps) summarize knowledge and are used to support decisions and policies in a variety of applied fields, from medicine and public health to biodiversity conservation. However, conducting these exercises in conservation is often expensive and slow, which can impede their use and hamper progress in addressing the current biodiversity crisis. With the explosive growth of large language models (LLMs) and other forms of artificial intelligence (AI), we discuss here the promise and perils associated with their use. We conclude that, when judiciously used, AI has the potential to speed up and hopefully improve the process of evidence synthesis, which can be particularly useful for underfunded applied fields, such as conservation science.

Original language	English
Pages (from-to)	548-557
Number of pages	10
Journal	Trends in Ecology & Evolution
Volume	39
Issue number	6
DOIs	https://doi.org/10.1016/j.tree.2024.04.007
Publication status	Published - Jun 2024

Keywords

artificial intelligence
biodiversity conservation
evidence synthesis
large language models
systematic reviews

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.tree.2024.04.007Licence: Unspecified

Cite this

@article{0c45aaf59d774667ae2a3cbb15d51b9e,

title = "Leveraging AI to improve evidence synthesis in conservation",

abstract = "Systematic evidence syntheses (systematic reviews and maps) summarize knowledge and are used to support decisions and policies in a variety of applied fields, from medicine and public health to biodiversity conservation. However, conducting these exercises in conservation is often expensive and slow, which can impede their use and hamper progress in addressing the current biodiversity crisis. With the explosive growth of large language models (LLMs) and other forms of artificial intelligence (AI), we discuss here the promise and perils associated with their use. We conclude that, when judiciously used, AI has the potential to speed up and hopefully improve the process of evidence synthesis, which can be particularly useful for underfunded applied fields, such as conservation science.",

keywords = "artificial intelligence, biodiversity conservation, evidence synthesis, large language models, systematic reviews",

author = "Oded Berger-Tal and Wong, {Bob B.M.} and Adams, {Carrie Ann} and Blumstein, {Daniel T.} and Ulrika Candolin and Gibson, {Matthew J.} and Greggor, {Alison L.} and Malgorzata Lagisz and Biljana Macura and Price, {Catherine J.} and Putman, {Breanna J.} and Lysanne Snijders and Shinichi Nakagawa",

note = "Funding Information: This paper emerged from a workshop conducted at Monash University's Prato Centre, partially supported by Monash University and Ben Gurion University of the Negev (to O.B-T. and B.B.M.W.) through a grant from the Pratt Foundation. We thank the staff at the Prato Centre for their wonderful hospitality and support. In addition, we acknowledge the following funding agencies for financial support: the Australian Research Council (FT190100014 and DP220100245 to B.B.M.W. DP210100812 and DP230101248 to M.L. and S.N. and DE220101316 to C.P.), a NASA Biodiversity grant (#80NSSC21K114 to C.A.), the Swedish Cultural Foundation in Finland (Nr 179446 to U.C.), and the Netherlands Organisation for Scientific Research (VI.Veni.192.018 to L.S). During the preparation of this work, we used Chat GPT 4.0, accessed through Microsoft Edge to develop a list of benefits of AI for decision making for conservation. We largely ignored the specific list and wrote this paper collectively using purely human-synthesized knowledge. Chat GPT 4.0 was also used as a resource to help understand key ideas and tools used in this rapidly growing field. The authors take full responsibility for the content of the publication. No interests are declared. Publisher Copyright: {\textcopyright} 2024 Elsevier Ltd",

year = "2024",

month = jun,

doi = "10.1016/j.tree.2024.04.007",

language = "English",

volume = "39",

pages = "548--557",

journal = "Trends in Ecology & Evolution",

issn = "0169-5347",

publisher = "Cell Press",

number = "6",

}

TY - JOUR

T1 - Leveraging AI to improve evidence synthesis in conservation

AU - Berger-Tal, Oded

AU - Wong, Bob B.M.

AU - Adams, Carrie Ann

AU - Blumstein, Daniel T.

AU - Candolin, Ulrika

AU - Gibson, Matthew J.

AU - Greggor, Alison L.

AU - Lagisz, Malgorzata

AU - Macura, Biljana

AU - Price, Catherine J.

AU - Putman, Breanna J.

AU - Snijders, Lysanne

AU - Nakagawa, Shinichi

N1 - Funding Information: This paper emerged from a workshop conducted at Monash University's Prato Centre, partially supported by Monash University and Ben Gurion University of the Negev (to O.B-T. and B.B.M.W.) through a grant from the Pratt Foundation. We thank the staff at the Prato Centre for their wonderful hospitality and support. In addition, we acknowledge the following funding agencies for financial support: the Australian Research Council (FT190100014 and DP220100245 to B.B.M.W. DP210100812 and DP230101248 to M.L. and S.N. and DE220101316 to C.P.), a NASA Biodiversity grant (#80NSSC21K114 to C.A.), the Swedish Cultural Foundation in Finland (Nr 179446 to U.C.), and the Netherlands Organisation for Scientific Research (VI.Veni.192.018 to L.S). During the preparation of this work, we used Chat GPT 4.0, accessed through Microsoft Edge to develop a list of benefits of AI for decision making for conservation. We largely ignored the specific list and wrote this paper collectively using purely human-synthesized knowledge. Chat GPT 4.0 was also used as a resource to help understand key ideas and tools used in this rapidly growing field. The authors take full responsibility for the content of the publication. No interests are declared. Publisher Copyright: © 2024 Elsevier Ltd

PY - 2024/6

Y1 - 2024/6

N2 - Systematic evidence syntheses (systematic reviews and maps) summarize knowledge and are used to support decisions and policies in a variety of applied fields, from medicine and public health to biodiversity conservation. However, conducting these exercises in conservation is often expensive and slow, which can impede their use and hamper progress in addressing the current biodiversity crisis. With the explosive growth of large language models (LLMs) and other forms of artificial intelligence (AI), we discuss here the promise and perils associated with their use. We conclude that, when judiciously used, AI has the potential to speed up and hopefully improve the process of evidence synthesis, which can be particularly useful for underfunded applied fields, such as conservation science.

AB - Systematic evidence syntheses (systematic reviews and maps) summarize knowledge and are used to support decisions and policies in a variety of applied fields, from medicine and public health to biodiversity conservation. However, conducting these exercises in conservation is often expensive and slow, which can impede their use and hamper progress in addressing the current biodiversity crisis. With the explosive growth of large language models (LLMs) and other forms of artificial intelligence (AI), we discuss here the promise and perils associated with their use. We conclude that, when judiciously used, AI has the potential to speed up and hopefully improve the process of evidence synthesis, which can be particularly useful for underfunded applied fields, such as conservation science.

KW - artificial intelligence

KW - biodiversity conservation

KW - evidence synthesis

KW - large language models

KW - systematic reviews

UR - http://www.scopus.com/inward/record.url?scp=85193925350&partnerID=8YFLogxK

U2 - 10.1016/j.tree.2024.04.007

DO - 10.1016/j.tree.2024.04.007

M3 - Review Article

AN - SCOPUS:85193925350

SN - 0169-5347

VL - 39

SP - 548

EP - 557

JO - Trends in Ecology & Evolution

JF - Trends in Ecology & Evolution

IS - 6

ER -

Leveraging AI to improve evidence synthesis in conservation

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Endocrine disruption in wildlife: a sexual selection perspective

How drugs in the wild affect animal behaviour, ecosystems, and evolution

Cite this

Leveraging AI to improve evidence synthesis in conservation

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Projects

Endocrine disruption in wildlife: a sexual selection perspective

How drugs in the wild affect animal behaviour, ecosystems, and evolution

Cite this