Machine learning for ecosystem services

Allbwn ymchwil: Cyfraniad at gyfnodolynErthygladolygiad gan gymheiriaid

StandardStandard

Machine learning for ecosystem services. / Willcock, Simon; Martinez-Lopez, Javier; Hooftman, Danny et al.
Yn: Ecosystem Services, Cyfrol 33 pt B, 10.2018, t. 165-174.

Allbwn ymchwil: Cyfraniad at gyfnodolynErthygladolygiad gan gymheiriaid

HarvardHarvard

Willcock, S, Martinez-Lopez, J, Hooftman, D, Bagstad, K, Balbi, S, Marzo, A, Prato, C, Sciandrello, S, Signorello, G, Voigt, B, Villa, F, Bullock, J & Athanasiadis, I 2018, 'Machine learning for ecosystem services', Ecosystem Services, cyfrol. 33 pt B, tt. 165-174. https://doi.org/10.1016/j.ecoser.2018.04.004

APA

Willcock, S., Martinez-Lopez, J., Hooftman, D., Bagstad, K., Balbi, S., Marzo, A., Prato, C., Sciandrello, S., Signorello, G., Voigt, B., Villa, F., Bullock, J., & Athanasiadis, I. (2018). Machine learning for ecosystem services. Ecosystem Services, 33 pt B, 165-174. https://doi.org/10.1016/j.ecoser.2018.04.004

CBE

Willcock S, Martinez-Lopez J, Hooftman D, Bagstad K, Balbi S, Marzo A, Prato C, Sciandrello S, Signorello G, Voigt B, et al. 2018. Machine learning for ecosystem services. Ecosystem Services. 33 pt B:165-174. https://doi.org/10.1016/j.ecoser.2018.04.004

MLA

VancouverVancouver

Willcock S, Martinez-Lopez J, Hooftman D, Bagstad K, Balbi S, Marzo A et al. Machine learning for ecosystem services. Ecosystem Services. 2018 Hyd;33 pt B:165-174. Epub 2018 Mai 5. doi: 10.1016/j.ecoser.2018.04.004

Author

Willcock, Simon ; Martinez-Lopez, Javier ; Hooftman, Danny et al. / Machine learning for ecosystem services. Yn: Ecosystem Services. 2018 ; Cyfrol 33 pt B. tt. 165-174.

RIS

TY - JOUR

T1 - Machine learning for ecosystem services

AU - Willcock, Simon

AU - Martinez-Lopez, Javier

AU - Hooftman, Danny

AU - Bagstad, Kenneth

AU - Balbi, Stefano

AU - Marzo, Alessia

AU - Prato, Carlo

AU - Sciandrello, Saverio

AU - Signorello, Giovanni

AU - Voigt, Brian

AU - Villa, Ferdinando

AU - Bullock, James

AU - Athanasiadis, Ioannis

PY - 2018/10

Y1 - 2018/10

N2 - Recent developments in machine learning have expanded data-driven modelling (DDM) capabilities, allowing artificial intelligence to infer the behaviour of a system by computing and exploiting correlations between observed variables within it. Machine learning algorithms may enable the use of increasingly available ‘big data’ and assist applying ecosystem service models across scales, analysing and predicting the flows of these services to disaggregated beneficiaries. We use the Weka and ARIES software to produce two examples of DDM: firewood use in South Africa and biodiversity value in Sicily, respectively. Our South African example demonstrates that DDM (64-91% accuracy) can identify the areas where firewood use is within the top quartile with comparable accuracy as conventional modelling techniques (54-77% accuracy). The Sicilian example highlights how DDM can be made more accessible to decision makers, who show both capacity and willingness to engage with uncertainty information. Uncertainty estimates, produced as part of the DDM process, allow decision makers to determine what level of uncertainty is acceptable to them and to use their own expertise for potentially contentious decisions. We conclude that DDM has a clear role to play when modelling ecosystem services, helping produce interdisciplinary models and holistic solutions to complex socio-ecological issues.

AB - Recent developments in machine learning have expanded data-driven modelling (DDM) capabilities, allowing artificial intelligence to infer the behaviour of a system by computing and exploiting correlations between observed variables within it. Machine learning algorithms may enable the use of increasingly available ‘big data’ and assist applying ecosystem service models across scales, analysing and predicting the flows of these services to disaggregated beneficiaries. We use the Weka and ARIES software to produce two examples of DDM: firewood use in South Africa and biodiversity value in Sicily, respectively. Our South African example demonstrates that DDM (64-91% accuracy) can identify the areas where firewood use is within the top quartile with comparable accuracy as conventional modelling techniques (54-77% accuracy). The Sicilian example highlights how DDM can be made more accessible to decision makers, who show both capacity and willingness to engage with uncertainty information. Uncertainty estimates, produced as part of the DDM process, allow decision makers to determine what level of uncertainty is acceptable to them and to use their own expertise for potentially contentious decisions. We conclude that DDM has a clear role to play when modelling ecosystem services, helping produce interdisciplinary models and holistic solutions to complex socio-ecological issues.

KW - ARIES

KW - Artificial intelligence

KW - Big data

KW - Data driven modelling

KW - data science

KW - Machine learning

KW - Mapping

KW - Modelling

KW - Uncertainty

KW - Weka

U2 - 10.1016/j.ecoser.2018.04.004

DO - 10.1016/j.ecoser.2018.04.004

M3 - Article

VL - 33 pt B

SP - 165

EP - 174

JO - Ecosystem Services

JF - Ecosystem Services

SN - 2212-0416

ER -