Machine learning for environmental toxicology: a call for integration and innovation

Thomas H. Miller; Matteo D. Gallidabino; James I. Macrae; Christer Hogstrand; Nicolas R. Bury; Leon P. Barron; Jason R. Snape; Stewart F. Owen

doi:10.1021/acs.est.8b05382

Machine learning for environmental toxicology: a call for integration and innovation

Thomas H. Miller^*, Matteo D. Gallidabino, James I. Macrae, Christer Hogstrand, Nicolas R. Bury, Leon P. Barron, Jason R. Snape, Stewart F. Owen

^*Corresponding author for this work

Applied Sciences

Research output: Contribution to journal › Article

23 Citations (Scopus)

13 Downloads (Pure)

Abstract

Recent advances in computing power have enabled the application of machine learning (ML) across all areas of science. A step change from a data-rich landscape to one where new hypotheses, relationships, and knowledge is emerging as a result. While ML is related to artificial intelligence (AI), they are not the same. ML is a branch of AI involving the application of statistical algorithms to enable a system to learn. Learning can involve data interpretation, identification of patterns and decision making. However, application and acceptance of ML within environmental toxicology, and more specifically for our viewpoint, environmental risk assessment (ERA), remains low. ML is an example of a disruptive research technology, which is urgently needed to cope with the complexity and scale of work required.

Original language	English
Pages (from-to)	12953-12955
Journal	Environmental Science and Technology
Volume	52
Issue number	22
Early online date	19 Oct 2018
DOIs	https://doi.org/10.1021/acs.est.8b05382
Publication status	Published - 20 Nov 2018

Access to Document

10.1021/acs.est.8b05382

Miller_EST-52-12953ssAccepted author manuscript, 256 KB

Cite this

@article{c1ca409dab76460bb07678c9cc169942,

title = "Machine learning for environmental toxicology: a call for integration and innovation",

abstract = "Recent advances in computing power have enabled the application of machine learning (ML) across all areas of science. A step change from a data-rich landscape to one where new hypotheses, relationships, and knowledge is emerging as a result. While ML is related to artificial intelligence (AI), they are not the same. ML is a branch of AI involving the application of statistical algorithms to enable a system to learn. Learning can involve data interpretation, identification of patterns and decision making. However, application and acceptance of ML within environmental toxicology, and more specifically for our viewpoint, environmental risk assessment (ERA), remains low. ML is an example of a disruptive research technology, which is urgently needed to cope with the complexity and scale of work required.",

author = "Miller, {Thomas H.} and Gallidabino, {Matteo D.} and Macrae, {James I.} and Christer Hogstrand and Bury, {Nicolas R.} and Barron, {Leon P.} and Snape, {Jason R.} and Owen, {Stewart F.}",

year = "2018",

month = nov,

day = "20",

doi = "10.1021/acs.est.8b05382",

language = "English",

volume = "52",

pages = "12953--12955",

journal = "Environmental Science & Technology",

issn = "0013-936X",

publisher = "American Chemical Society",

number = "22",

}

TY - JOUR

T1 - Machine learning for environmental toxicology

T2 - a call for integration and innovation

AU - Miller, Thomas H.

AU - Gallidabino, Matteo D.

AU - Macrae, James I.

AU - Hogstrand, Christer

AU - Bury, Nicolas R.

AU - Barron, Leon P.

AU - Snape, Jason R.

AU - Owen, Stewart F.

PY - 2018/11/20

Y1 - 2018/11/20

N2 - Recent advances in computing power have enabled the application of machine learning (ML) across all areas of science. A step change from a data-rich landscape to one where new hypotheses, relationships, and knowledge is emerging as a result. While ML is related to artificial intelligence (AI), they are not the same. ML is a branch of AI involving the application of statistical algorithms to enable a system to learn. Learning can involve data interpretation, identification of patterns and decision making. However, application and acceptance of ML within environmental toxicology, and more specifically for our viewpoint, environmental risk assessment (ERA), remains low. ML is an example of a disruptive research technology, which is urgently needed to cope with the complexity and scale of work required.

AB - Recent advances in computing power have enabled the application of machine learning (ML) across all areas of science. A step change from a data-rich landscape to one where new hypotheses, relationships, and knowledge is emerging as a result. While ML is related to artificial intelligence (AI), they are not the same. ML is a branch of AI involving the application of statistical algorithms to enable a system to learn. Learning can involve data interpretation, identification of patterns and decision making. However, application and acceptance of ML within environmental toxicology, and more specifically for our viewpoint, environmental risk assessment (ERA), remains low. ML is an example of a disruptive research technology, which is urgently needed to cope with the complexity and scale of work required.

U2 - 10.1021/acs.est.8b05382

DO - 10.1021/acs.est.8b05382

M3 - Article

AN - SCOPUS:85055496550

VL - 52

SP - 12953

EP - 12955

JO - Environmental Science & Technology

JF - Environmental Science & Technology

SN - 0013-936X

IS - 22

ER -

Machine learning for environmental toxicology: a call for integration and innovation

Abstract

Access to Document

Fingerprint

Cite this