Development of a software based on automatic multi-temporal aerial images classification to assess retrospective environmental exposures to pesticides in epidemiological studies - Archive ouverte HAL Access content directly
Journal Articles Epidemiology and Public Health = Revue d'Epidémiologie et de Santé Publique Year : 2018

Development of a software based on automatic multi-temporal aerial images classification to assess retrospective environmental exposures to pesticides in epidemiological studies

Abstract

Environmental exposure to agricultural pesticides (EEAP) resulting from the drift of agricultural pesticides from treated farmland is suspected to be a risk factor for several diseases, including cancers. The long latency period of cancer development, and evidence on the impact of early exposures stress the need for historical exposure information to capture these exposures. Geographic Information Systems (GIS) are increasingly used in environmental epidemiology studies to assess EEAP. Crop acreage proximate to subjects residences has been suggested as a surrogate for EEAP. Retrospective characterization of EEAP is then essential. While Corine Land Cover (CLC) provides land cover data since 1990, earlier data are lacking limiting the capacity to capture the life-course effects of exposure. The use of satellite images or historical aerial images has been suggested. However, characterization of land use from theses images is time and resource consuming. Thereby, this study aim to develop an innovative automated software to analyze the historical monochromatic aerial images in order to reconstruct the historical land cover to characterize EEAP retrospectively

Dates and versions

hal-01832582 , version 1 (08-07-2018)

Identifiers

Cite

Élodie Faure, R. Ratajczak, Carlos F Crispim-Junior, O. Pérol, L. Tougne, et al.. Development of a software based on automatic multi-temporal aerial images classification to assess retrospective environmental exposures to pesticides in epidemiological studies. Epidemiology and Public Health = Revue d'Epidémiologie et de Santé Publique, 2018, 66, ⟨10.1016/j.respe.2018.05.529⟩. ⟨hal-01832582⟩
172 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More