Abstract
Accurate and reliable greenhouse mapping using remotely sensed data and image classification methods has a significant role since it can comprehensively improve the urban and rural planning, and sustainable natural resource and agricultural management. This research is mainly focused on the determination of greenhouses from SPOT-7 and Sentinel-2 MultiSpectral Instrument (MSI) images by using an object-based image classification method with three different classifiers which are k-nearest neighbor (KNN), random forest (RF), and support vector machine (SVM) in the selected test region. First, the image acquired by using multi-resolution segmentation. Second, spectral features, textural features, and remote sensing indices were obtained for each image object. Third, different classifiers were employed to classify greenhouses. Then, classification accuracy assessment analysis was conducted to test the agreement between the classified data and field collected data using the confusion matrix. The results highlighted that the KNN and RF classifier have a slightly higher overall accuracy (OA) and Kappa statistics for SPOT-7 image with the 91.43% and 0.88. Furthermore, the KNN classifier for Sentinel-2 MSI image has the highest OA and Kappa statistics of 88.38% and 0.83. The achieved results underlined the potential of Sentinel-2 MSI and SPOT-7 data for object-based greenhouse mapping using different machine learning classifiers in the Mediterranean Region.
Highlights
T HE economıc and strategic role of greenhouse activities in agricultural improvement is increasing worldwide, especially as it increases crop yields
We found that scale parameter (SP) 39 is appropriate for detecting greenhouses from Sentinel-2 MultiSpectral Instrument (MSI) after testing different SP values while keeping the compactness parameter at 0.5 and shape at 0.3
As a result of the four combinations mentioned in the methodology section, the SP calculated from estimation of SP-2 (ESP-2) tool had values ranging from 140 to 199
Summary
T HE economıc and strategic role of greenhouse activities in agricultural improvement is increasing worldwide, especially as it increases crop yields. The extensive and sustained usage of greenhouses results in transformations in the surrounding environment and agricultural areas, together with the essential infrastructure for their commercial operation [1]. Proper spatial development planning is inevitable to identify and minimize the effects of these agricultural structures [1]–[3]. Remote sensing is a rising data acquisition technique for detecting greenhouses and other land cover types with several spatial and temporal resolutions [4], [5]. Greenhouse mapping using remotely sensed data is still a challenging and popular research area because of its specific spectral signatures based on its material or local agricultural practices [6]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
