Evaluation of Object-Based Greenhouse Mapping Using WorldView-3 VNIR and SWIR Data: A Case Study from Almería (Spain)

Plastic covered greenhouse (PCG) mapping via remote sensing has received a great deal of attention over the past decades. The WorldView-3 (WV3) satellite is very high resolution (VHR) sensor with eight multispectral bands in visible and near-infrared (VNIR) spectral range, additional short-wave infrared (SWIR) region. A few studies have already established importance indices based on some these SWIR to detect urban plastic materials hydrocarbons which are also related plastics. This paper aims investigate capability WV3 (VNIR SWIR) for direct PCG detection following an object-based image analysis (OBIA) approach. Three strategies were carried out: (i) using object features only derived from VNIR (VNIR); (ii) (SWIR), (iii) both (All Features). results showed that majority predictive power was attributed indices, especially Normalized Difference Index (NDPI). Overall, accuracy values 90.85%, 96.79% 97.38% attained VNIR, All Features strategies, respectively. main misclassification problem agricultural practice whitewash (greenhouse shading) temporally masked signature film.