Machine learning for ecosystem services

Willcock, Simon; Martínez‐López, Javier; Hooftman, Danny A. P.; Bagstad, Kenneth J.; Balbi, Stefano; Marzo, Alessia; Prato, Carlo; Sciandrello, Saverio; Signorello, Giovanni; Voigt, Brian; Villa, Ferdinando; Bullock, James M.; Athanasiadis, Ioannis N.

doi:10.1016/j.ecoser.2018.04.004

Cited by 135 publications

(63 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Recent advancement in machine learning has expanded data-driven research on landscape sustainability, allowing artificial intelligence to infer system behaviors and outcomes by computing and exploring variables correlations. Compared to general linear models, machine-learning algorithms such as Ran-domForests, MaxEnt, and TreeNet are especially helpful to answer key landscape sustainability questions with regards to species distribution (Drew et al 2010), conservation (Kampichler et al 2010), and ecosystem services (Willcock et al 2018) that often have emergent characteristics. In addition, machine learning can process a large number of variables and their interactions to identify major signals in the dataset (Cutler et al 2007).…”

Section: Methodological Innovation For Researchmentioning

confidence: 99%

Advancing landscape sustainability science: theoretical foundation and synergies with innovations in methodology, design, and application

et al. 2020

View full text Add to dashboard Cite

Section: Methodological Innovation For Researchmentioning

confidence: 99%

Advancing landscape sustainability science: theoretical foundation and synergies with innovations in methodology, design, and application

et al. 2020

View full text Add to dashboard Cite

“…Machine learning (McL) is widely used to solve problems in many fields, including ecology (Christin et al 2018;Willcock et al 2018) and population genetics (Saminadin-Peter et al 2012;Schrider and Kern 2016;Schrider and Kern 2018). We present a supervised machine learning (McL) framework (Bzdok et al 2018) to build a predictive model that distinguishes between ABR and IBR models, which is a challenge in molecular phylogenetics and phylogenomics.…”

Section: New Methodsmentioning

confidence: 99%

A new method for detecting autocorrelation of evolutionary rates in large phylogenies

Tao

Tamura

Battistuzzi

et al. 2018

Preprint

View full text Add to dashboard Cite

New species arise from pre-existing species and inherit similar genomes and environments. This predicts greater similarity of mutation rates and the tempo of molecular evolution between direct ancestors and descendants, resulting in autocorrelation of evolutionary rates within lineages in the tree of life. Surprisingly, molecular sequence data have not confirmed this expectation, possibly because available methods lack power to detect autocorrelated rates. Here we present a machine learning method to detect the presence evolutionary rate autocorrelation in large phylogenies. The new method is computationally efficient and performs better than the available state-ofthe-art methods. Application of the new method reveals extensive rate autocorrelation in DNA and amino acid sequence evolution of mammals, birds, insects, metazoans, plants, fungi, and prokaryotes. Therefore, rate autocorrelation is a common phenomenon throughout the tree of life. These findings suggest concordance between molecular and non-molecular evolutionary patterns and will foster unbiased and precise dating of the tree of life.

show abstract

“…• Advances in big-data processing and machine learning are making it feasible to process ever-greater quantities of data, and cope with the diversity of data sources in the environmental sciences (Lokers et al, 2016). • It is becoming increasingly feasible to model large and complex systems (Mattman, 2013), including agent-based simulations comprising many millions of agents (Abar et al, 2017;Melgar et al, 2014) or machine learning methods for data-driven modeling (Willcock et al, 2018).…”

Section: 8mentioning

confidence: 99%

Eight grand challenges in socio-environmental systems modeling

Elsawah

Filatova

Jakeman

et al. 2020

SESMO

Self Cite

131

120

View full text Add to dashboard Cite

Modeling is essential to characterize and explore complex societal and environmental issues in systematic and collaborative ways. Socio-environmental systems (SES) modeling integrates knowledge and perspectives into conceptual and computational tools that explicitly recognize how human decisions affect the environment. Depending on the modeling purpose, many SES modelers also realize that involvement of stakeholders and experts is fundamental to support social learning and decision-making processes for achieving improved environmental and social outcomes. The contribution of this paper lies in identifying and formulating grand challenges that need to be overcome to accelerate the development and adaptation of SES modeling. Eight challenges are delineated: bridging epistemologies across disciplines; multi-dimensional uncertainty assessment and management; scales and scaling issues; combining qualitative and quantitative methods and data; furthering the adoption and impacts of SES modeling on policy; capturing structural changes; representing human dimensions in SES; and leveraging new data types and sources. These challenges limit our ability to effectively use SES modeling to provide the knowledge and information essential for supporting decision making. Whereas some of these challenges are not unique to SES modeling and may be pervasive in other scientific fields, they still act as barriers as well as research opportunities for the SES modeling community. For each challenge, we outline basic steps that can be taken to surmount the underpinning barriers. Thus, the paper identifies priority research areas in SES modeling, chiefly related to progressing modeling products, processes and practices.

show abstract

Machine learning for ecosystem services

Cited by 135 publications

References 55 publications

Advancing landscape sustainability science: theoretical foundation and synergies with innovations in methodology, design, and application

Advancing landscape sustainability science: theoretical foundation and synergies with innovations in methodology, design, and application

A new method for detecting autocorrelation of evolutionary rates in large phylogenies

Eight grand challenges in socio-environmental systems modeling

Contact Info

Product

Resources

About