TY - JOUR
T1 - Comparison of three satellite sensors at three spatial scales to predict larval mosquito presence in Connecticut wetlands
AU - Brown, Heidi E.
AU - Diuk-Wasser, Maria A.
AU - Guan, Yongtao
AU - Caskey, Susan
AU - Fish, Durland
N1 - Funding Information:
We thank Kristi Kleinbeck, Estela Almanza, and Christopher Lundgren for their field collection efforts. We also thank Larry Bonneau at the Yale Center for Earth Observation and Heidi Smartt, Mark Aspelin, and Mark Wilson at Sandia National Laboratories for their contributions to the project. This work was supported by cooperative agreements with Sandia National Laboratories and USDA Agricultural Research Service (1USDA-58-1265-7-002). HEB was supported through the CDC Fellowship Training Program in Vector-Borne Disease at Yale University.
PY - 2008/5/15
Y1 - 2008/5/15
N2 - Satellite imagery can be used to identify suitable habitat for mosquitoes in areas inaccessible or lacking sufficient ground-based information about the environment but current applications are limited by the spatial and spectral resolution of the sensors. Here, models used to compare prediction of the presence of Anopheles punctipennis larvae in Connecticut wetlands were built using stepwise logistic regression and compared by Akaike's Information Criterion (AIC). Vegetation indices were extracted from three satellite sensor scenes (Hyperion, ASTER and Landsat-TM) at three scales (pixel, wetland perimeter, and wetland area). The best models were developed using ASTER (ROC = 0.80, p = 0.01, AIC 65.37) and Hyperion (ROC = 0.81, p < 0.01, AIC 66.40) at the wetland area level. The Disease Water Stress Index (DWSI), a measure of leaf water content, and Normalized Difference Vegetation Index (NDVI) were significant in many of the models. This comparison of satellite based models demonstrates higher spatial and spectral resolution of ASTER and Hyperion resulted in more parsimonious models than Landsat-TM models. The need for continued research and development into sensors with increased spatial and spectral resolution and the development of mosquito specific indices is discussed.
AB - Satellite imagery can be used to identify suitable habitat for mosquitoes in areas inaccessible or lacking sufficient ground-based information about the environment but current applications are limited by the spatial and spectral resolution of the sensors. Here, models used to compare prediction of the presence of Anopheles punctipennis larvae in Connecticut wetlands were built using stepwise logistic regression and compared by Akaike's Information Criterion (AIC). Vegetation indices were extracted from three satellite sensor scenes (Hyperion, ASTER and Landsat-TM) at three scales (pixel, wetland perimeter, and wetland area). The best models were developed using ASTER (ROC = 0.80, p = 0.01, AIC 65.37) and Hyperion (ROC = 0.81, p < 0.01, AIC 66.40) at the wetland area level. The Disease Water Stress Index (DWSI), a measure of leaf water content, and Normalized Difference Vegetation Index (NDVI) were significant in many of the models. This comparison of satellite based models demonstrates higher spatial and spectral resolution of ASTER and Hyperion resulted in more parsimonious models than Landsat-TM models. The need for continued research and development into sensors with increased spatial and spectral resolution and the development of mosquito specific indices is discussed.
KW - ASTER
KW - Disease Water Stress Index
KW - Hyperion
KW - Mosquito habitat
UR - http://www.scopus.com/inward/record.url?scp=41249087111&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=41249087111&partnerID=8YFLogxK
U2 - 10.1016/j.rse.2007.10.005
DO - 10.1016/j.rse.2007.10.005
M3 - Article
AN - SCOPUS:41249087111
SN - 0034-4257
VL - 112
SP - 2301
EP - 2308
JO - Remote Sensing of Environment
JF - Remote Sensing of Environment
IS - 5
ER -