Monitoring the Oriental Migratory Locust Plague Based on the LAI Retrieved from Remotely Sensed Data

The oriental migratory locust plagues has became a serious problem during the last two decades. Remote sensing techniques can greatly facilitate monitoring locust population dynamics over a large geographic scale. In this paper, a model is presented to estimate leaf area index (LAI) of reed canopy from TM or ETM+ image data firstly. The model classifies the background of reed canopy into soil and water, then calculates and output a lookup table (LUT). Following it, LAI mapping was conducted based on the BP neural network model, which was trained using the data of actual measurement and LUT. On the base of accurately inversing LAI, the paper monitored the oriental migratory locust plague using two temporal LAI data and found the hazard domain and extent. The conclusion was obtained from this study: on the basis of retrieving LAI precisely, through detecting the variation of two temporal TM data, we can monitor the hazard domain and extent of the oriental migratory locust plague well and truly.