Positional error propagation analysis in habitat distribution modelling

Babak Naimi, A.K. Skidmore, N.A.S. Hamm, T.A. Groen

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

This study examines how robust habitat distribution models are to uncertainty in the position of species occurrence. An artificial species was simulated and mapped in southern Spain (Malaga) and error was introduced to the location of samples. Three commonly used habitat distribution modelling algorithms (GAM, BRT, and MaxEnf) were selected. The propagation of error into the predictions was then analyzed using Monte Carlo (MC) simulation. The models were evaluated for overall performance using the area under receiver operating characteristic curve (AUC). The Root Mean Square Error (RMSE) was also calculated to assess the accuracy of probabilities predicted at grid cells. The results indicate only a small decline in the performance of models with introduced error in species position. Visualizing of RMSEs at grid cells indicates that uncertainty varies with location.

Original languageEnglish
Title of host publicationProceedings of the Ninth International Symposium on Spatial Accuracy Assessment in Natural Resources and Environmental Sciences
EditorsN.J. Tate, P.F. Fisher
PublisherInternational Spatial Accuracy Research Association
Pages409-412
Number of pages4
Publication statusPublished - 1 Jan 2010
Event9th International Symposium on Spatial Accuracy Assessment in Natural Resources and Environmental Sciences, Accuracy 2010 - Leicester, United Kingdom
Duration: 20 Jul 201023 Jul 2010
Conference number: 9

Conference

Conference9th International Symposium on Spatial Accuracy Assessment in Natural Resources and Environmental Sciences, Accuracy 2010
Abbreviated titleAccuracy
CountryUnited Kingdom
CityLeicester
Period20/07/1023/07/10

Fingerprint

habitat
modeling
species occurrence
prediction
simulation
distribution
analysis

Keywords

  • Habitat distribution modeling
  • Positional uncertainty
  • Spatial error propagation

Cite this

Naimi, B., Skidmore, A. K., Hamm, N. A. S., & Groen, T. A. (2010). Positional error propagation analysis in habitat distribution modelling. In N. J. Tate, & P. F. Fisher (Eds.), Proceedings of the Ninth International Symposium on Spatial Accuracy Assessment in Natural Resources and Environmental Sciences (pp. 409-412). International Spatial Accuracy Research Association.
Naimi, Babak ; Skidmore, A.K. ; Hamm, N.A.S. ; Groen, T.A. / Positional error propagation analysis in habitat distribution modelling. Proceedings of the Ninth International Symposium on Spatial Accuracy Assessment in Natural Resources and Environmental Sciences. editor / N.J. Tate ; P.F. Fisher. International Spatial Accuracy Research Association, 2010. pp. 409-412
@inproceedings{b47b5676e4684f68ae659d01c1ee5f04,
title = "Positional error propagation analysis in habitat distribution modelling",
abstract = "This study examines how robust habitat distribution models are to uncertainty in the position of species occurrence. An artificial species was simulated and mapped in southern Spain (Malaga) and error was introduced to the location of samples. Three commonly used habitat distribution modelling algorithms (GAM, BRT, and MaxEnf) were selected. The propagation of error into the predictions was then analyzed using Monte Carlo (MC) simulation. The models were evaluated for overall performance using the area under receiver operating characteristic curve (AUC). The Root Mean Square Error (RMSE) was also calculated to assess the accuracy of probabilities predicted at grid cells. The results indicate only a small decline in the performance of models with introduced error in species position. Visualizing of RMSEs at grid cells indicates that uncertainty varies with location.",
keywords = "Habitat distribution modeling, Positional uncertainty, Spatial error propagation",
author = "Babak Naimi and A.K. Skidmore and N.A.S. Hamm and T.A. Groen",
year = "2010",
month = "1",
day = "1",
language = "English",
pages = "409--412",
editor = "N.J. Tate and P.F. Fisher",
booktitle = "Proceedings of the Ninth International Symposium on Spatial Accuracy Assessment in Natural Resources and Environmental Sciences",
publisher = "International Spatial Accuracy Research Association",

}

Naimi, B, Skidmore, AK, Hamm, NAS & Groen, TA 2010, Positional error propagation analysis in habitat distribution modelling. in NJ Tate & PF Fisher (eds), Proceedings of the Ninth International Symposium on Spatial Accuracy Assessment in Natural Resources and Environmental Sciences. International Spatial Accuracy Research Association, pp. 409-412, 9th International Symposium on Spatial Accuracy Assessment in Natural Resources and Environmental Sciences, Accuracy 2010, Leicester, United Kingdom, 20/07/10.

Positional error propagation analysis in habitat distribution modelling. / Naimi, Babak; Skidmore, A.K.; Hamm, N.A.S.; Groen, T.A.

Proceedings of the Ninth International Symposium on Spatial Accuracy Assessment in Natural Resources and Environmental Sciences. ed. / N.J. Tate; P.F. Fisher. International Spatial Accuracy Research Association, 2010. p. 409-412.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Positional error propagation analysis in habitat distribution modelling

AU - Naimi, Babak

AU - Skidmore, A.K.

AU - Hamm, N.A.S.

AU - Groen, T.A.

PY - 2010/1/1

Y1 - 2010/1/1

N2 - This study examines how robust habitat distribution models are to uncertainty in the position of species occurrence. An artificial species was simulated and mapped in southern Spain (Malaga) and error was introduced to the location of samples. Three commonly used habitat distribution modelling algorithms (GAM, BRT, and MaxEnf) were selected. The propagation of error into the predictions was then analyzed using Monte Carlo (MC) simulation. The models were evaluated for overall performance using the area under receiver operating characteristic curve (AUC). The Root Mean Square Error (RMSE) was also calculated to assess the accuracy of probabilities predicted at grid cells. The results indicate only a small decline in the performance of models with introduced error in species position. Visualizing of RMSEs at grid cells indicates that uncertainty varies with location.

AB - This study examines how robust habitat distribution models are to uncertainty in the position of species occurrence. An artificial species was simulated and mapped in southern Spain (Malaga) and error was introduced to the location of samples. Three commonly used habitat distribution modelling algorithms (GAM, BRT, and MaxEnf) were selected. The propagation of error into the predictions was then analyzed using Monte Carlo (MC) simulation. The models were evaluated for overall performance using the area under receiver operating characteristic curve (AUC). The Root Mean Square Error (RMSE) was also calculated to assess the accuracy of probabilities predicted at grid cells. The results indicate only a small decline in the performance of models with introduced error in species position. Visualizing of RMSEs at grid cells indicates that uncertainty varies with location.

KW - Habitat distribution modeling

KW - Positional uncertainty

KW - Spatial error propagation

UR - http://www.scopus.com/inward/record.url?scp=84975764049&partnerID=8YFLogxK

UR - https://ezproxy2.utwente.nl/login?url=https://webapps.itc.utwente.nl/library/2010/conf/skidmore_pos.pdf

M3 - Conference contribution

SP - 409

EP - 412

BT - Proceedings of the Ninth International Symposium on Spatial Accuracy Assessment in Natural Resources and Environmental Sciences

A2 - Tate, N.J.

A2 - Fisher, P.F.

PB - International Spatial Accuracy Research Association

ER -

Naimi B, Skidmore AK, Hamm NAS, Groen TA. Positional error propagation analysis in habitat distribution modelling. In Tate NJ, Fisher PF, editors, Proceedings of the Ninth International Symposium on Spatial Accuracy Assessment in Natural Resources and Environmental Sciences. International Spatial Accuracy Research Association. 2010. p. 409-412