Stateconet: Statistical ecology neural networks for species distribution modeling

Allbwn ymchwil: Pennod mewn Llyfr/Adroddiad/Trafodion CynhadleddCyfraniad i Gynhadleddadolygiad gan gymheiriaid

StandardStandard

Stateconet: Statistical ecology neural networks for species distribution modeling. / Seo, Eugene; Hutchinson, Rebecca A; Fu, Xiao et al.
Proceedings of the AAAI Conference on Artificial Intelligence. Cyfrol 35 2021. t. 513-521.

Allbwn ymchwil: Pennod mewn Llyfr/Adroddiad/Trafodion CynhadleddCyfraniad i Gynhadleddadolygiad gan gymheiriaid

HarvardHarvard

Seo, E, Hutchinson, RA, Fu, X, Li, C, Hallman, TA, Kilbride, J & Robinson, WD 2021, Stateconet: Statistical ecology neural networks for species distribution modeling. yn Proceedings of the AAAI Conference on Artificial Intelligence. cyfrol. 35, tt. 513-521. https://doi.org/10.1609/aaai.v35i1.16129

APA

Seo, E., Hutchinson, R. A., Fu, X., Li, C., Hallman, T. A., Kilbride, J., & Robinson, W. D. (2021). Stateconet: Statistical ecology neural networks for species distribution modeling. Yn Proceedings of the AAAI Conference on Artificial Intelligence (Cyfrol 35, tt. 513-521) https://doi.org/10.1609/aaai.v35i1.16129

CBE

Seo E, Hutchinson RA, Fu X, Li C, Hallman TA, Kilbride J, Robinson WD. 2021. Stateconet: Statistical ecology neural networks for species distribution modeling. Yn Proceedings of the AAAI Conference on Artificial Intelligence. tt. 513-521. https://doi.org/10.1609/aaai.v35i1.16129

MLA

Seo, Eugene et al. "Stateconet: Statistical ecology neural networks for species distribution modeling". Proceedings of the AAAI Conference on Artificial Intelligence. 2021, 513-521. https://doi.org/10.1609/aaai.v35i1.16129

VancouverVancouver

Seo E, Hutchinson RA, Fu X, Li C, Hallman TA, Kilbride J et al. Stateconet: Statistical ecology neural networks for species distribution modeling. Yn Proceedings of the AAAI Conference on Artificial Intelligence. Cyfrol 35. 2021. t. 513-521 doi: 10.1609/aaai.v35i1.16129

Author

Seo, Eugene ; Hutchinson, Rebecca A ; Fu, Xiao et al. / Stateconet: Statistical ecology neural networks for species distribution modeling. Proceedings of the AAAI Conference on Artificial Intelligence. Cyfrol 35 2021. tt. 513-521

RIS

TY - GEN

T1 - Stateconet: Statistical ecology neural networks for species distribution modeling

AU - Seo, Eugene

AU - Hutchinson, Rebecca A

AU - Fu, Xiao

AU - Li, Chelsea

AU - Hallman, Tyler A

AU - Kilbride, John

AU - Robinson, W Douglas

PY - 2021/5/18

Y1 - 2021/5/18

N2 - This paper focuses on a core task in computational sustainability and statistical ecology: species distribution modeling (SDM). In SDM, the occurrence pattern of a species on a landscape is predicted by environmental features based on observations at a set of locations. At first, SDM may appear to be a binary classification problem, and one might be inclined to employ classic tools (e.g., logistic regression, support vector machines, neural networks) to tackle it. However, wildlife surveys introduce structured noise (especially under-counting) in the species observations. If unaccounted for, these observation errors systematically bias SDMs. To address the unique challenges of SDM, this paper proposes a framework called StatEcoNet. Specifically, this work employs a graphical generative model in statistical ecology to serve as the skeleton of the proposed computational framework and carefully integrates neural networks under the framework. The advantages of StatEcoNet over related approaches are demonstrated on simulated datasets as well as bird species data. Since SDMs are critical tools for ecological science and natural resource management, StatEcoNet may offer boosted computational and analytical powers to a wide range of applications that have significant social impacts, e.g., the study and conservation of threatened species.

AB - This paper focuses on a core task in computational sustainability and statistical ecology: species distribution modeling (SDM). In SDM, the occurrence pattern of a species on a landscape is predicted by environmental features based on observations at a set of locations. At first, SDM may appear to be a binary classification problem, and one might be inclined to employ classic tools (e.g., logistic regression, support vector machines, neural networks) to tackle it. However, wildlife surveys introduce structured noise (especially under-counting) in the species observations. If unaccounted for, these observation errors systematically bias SDMs. To address the unique challenges of SDM, this paper proposes a framework called StatEcoNet. Specifically, this work employs a graphical generative model in statistical ecology to serve as the skeleton of the proposed computational framework and carefully integrates neural networks under the framework. The advantages of StatEcoNet over related approaches are demonstrated on simulated datasets as well as bird species data. Since SDMs are critical tools for ecological science and natural resource management, StatEcoNet may offer boosted computational and analytical powers to a wide range of applications that have significant social impacts, e.g., the study and conservation of threatened species.

U2 - 10.1609/aaai.v35i1.16129

DO - 10.1609/aaai.v35i1.16129

M3 - Conference contribution

VL - 35

SP - 513

EP - 521

BT - Proceedings of the AAAI Conference on Artificial Intelligence

ER -