Habitat monitoring to evaluate crop disease and pest distributions based on multi-source satellite remote sensing imagery

Habitat monitoring can be used to evaluate the potential occurrence and distribution of plant diseases and pests in a region. Here, we present a new method for monitoring crop diseases and pests based on Worldview 2 and Landsat 8 satellite data. As a case study, the method was applied to wheat fields in Zhou Jiazhuang, Jinzhou City, Hebei Province. Crop growth indices (GNDVI and VARI d-edge, land environmental features (Wetness, Greenness, and LST) were used describe habitat, and an independent t-test was used to evaluate the performances of these five features in representing crop diseases and pests. Field measurements were used to evaluate the validity of the method. An FLDA model incorporating both vegetation and environmental indices was more accurate for monitoring crop disease and pest occurrence compared with a model based on vegetation indices alone (71% vs. 82% accuracy). Future work should include multiple forms of information (e.g., meteorological data and web sensor networks) to further improve regional-scale monitoring of crop diseases and pests. (C) 2017 Elsevier GmbH. All rights reserved.