Greenhouse mapping through remote sensing has received extensive attention over the last decades. In this article, the innovative goal relies on mapping greenhouses through the combined use of very high resolution satellite data (WorldView-2) and Landsat 8 Operational Land Imager (OLI) time series within a context of an object-based image analysis (OBIA) and decision tree classification. Thus, WorldView-2 was mainly used to segment the study area focusing on individual greenhouses. Basic spectral information, spectral and vegetation indices, textural features, seasonal statistics and a spectral metric (Moment Distance Index, MDI) derived from Landsat 8 time series and/or WorldView-2 imagery were computed on previously segmented image objects. In order to test its temporal stability, the same approach was applied for two different years, 2014 and 2015. In both years, MDI was pointed out as the most important feature to detect greenhouses. Moreover, the threshold value of this spectral metric turned to be extremely stable for both Landsat 8 and WorldView-2 imagery. A simple decision tree always using the same threshold values for features from Landsat 8 time series and WorldView-2 was finally proposed. Overall accuracies of 93.0% and 93.3% and kappa coefficients of 0.856 and 0.861 were attained for 2014 and 2015 datasets, respectively.

The total area of plastic-covered crops of 3019 million hectares has been increasing steadily around the world, particularly in the form of crops maintained under plastic-covered greenhouses to control their environmental conditions and their growth, thereby increasing production. This work analyzes the worldwide research dynamics on remote sensing-based mapping of agricultural greenhouses and plastic-mulched crops throughout the 21st century. In this way, a bibliometric analysis was carried out on a total of 107 publications based on the Scopus database. Different aspects of these publications were studied, such as type of publication, characteristics, categories and journal/conference name, countries, authors, and keywords. The results showed that “articles” were the type of document mostly found, while the number of published documents has exponentially increased over the last four years, growing from only one document published in 2001 to 22 in 2019. The main Scopus categories relating to the topic analyzed were Earth and Planetary Sciences (53%), Computer Science (30%), and Agricultural and Biological Sciences (28%). The most productive journal in this field was “Remote Sensing”, with 22 documents published, while China, Italy, Spain, USA, and Turkey were the five countries with the most publications. Among the main research institutions belonging to these five most productive countries, there were eight institutions from China, four from Italy, one from Spain, two from Turkey, and one from the USA. In conclusion, the evolution of the number of publications on Remote Sensing of Agricultural Greenhouses and Plastic-Mulched Farmland found throughout the period 2000–2019 allows us to classify the subject studied as an emerging research topic that is attracting an increasing level of interest worldwide, although its relative significance is still very limited within the remote sensing discipline. However, the growing demand for information on the arrangement and spatio-temporal dynamics of this increasingly important model of intensive agriculture is likely to drive this line of research in the coming years.

A workflow headed up to identify crops growing under plastic-covered greenhouses (PCG) and based on multi-temporal and multi-sensor satellite data is developed in this article. This workflow is made up of four steps: (i) data pre-processing, (ii) PCG segmentation, (iii) binary pre-classification between greenhouses and non-greenhouses, and (iv) classification of horticultural crops under greenhouses regarding two agronomic seasons (autumn and spring). The segmentation stage was carried out by applying a multi-resolution segmentation algorithm on the pre-processed WorldView-2 data. The free access AssesSeg command line tool was used to determine the more suitable multi-resolution algorithm parameters. Two decision tree models mainly based on the Plastic Greenhouse Index were developed to perform greenhouse/non-greenhouse binary classification from Landsat 8 and Sentinel-2A time series, attaining overall accuracies of 92.65% and 93.97%, respectively. With regards to the classification of crops under PCG, pepper in autumn, and melon and watermelon in spring provided the best results (F_β around 84% and 95%, respectively). Data from the Sentinel-2A time series showed slightly better accuracies than those from Landsat 8.

Remote sensing techniques based on medium resolution satellite imagery are being widely applied for mapping plastic covered greenhouses (PCG). This article aims at testing the spectral consistency of surface reflectance values of Sentinel-2 MSI (S2 L2A) and Landsat 8 OLI (L8 L2 and the pansharpened and atmospherically corrected product from L1T product; L8 PANSH) data in PCG areas located in Spain, Morocco, Italy and Turkey. The six corresponding bands of S2 and L8, together with the normalized difference vegetation index (NDVI), were generated through an OBIA approach for each PCG study site. The coefficient of determination (r²) and the root mean square error (RMSE) were computed in sixteen cloud-free simultaneously acquired image pairs from the four study sites to evaluate the coherence between the two sensors. It was found that the S2 and L8 correlation (r² > 0.840, RMSE < 9.917%) was quite good in most bands and NDVI. However, the correlation of the two sensors fluctuated between study sites, showing occasional sun glint effects on PCG roofs related to the sensor orbit and sun position. Moreover, higher surface reflectance discrepancies between L8 L2 and L8 PANSH data, mainly in the visible bands, were always observed in areas with high-level aerosol values derived from the aerosol quality band included in the L8 L2 product (SR aerosol). In this way, the consistency between L8 PANSH and S2 L2A was improved mainly in high-level aerosol areas according to the SR aerosol band.

This letter presents the capabilities of a command line tool created to assess the quality of segmented digital images. The executable source code, called AssesSeg, was written in Python 2.7 using open source libraries. AssesSeg (University of Almeria, Almeria, Spain; Politecnico di Bari, Bari, Italy) implements a modified version of the supervised discrepancy measure named Euclidean Distance 2 (ED2) and was tested on different satellite images (Sentinel-2, Landsat 8, and WorldView-2). The segmentation was applied to plastic covered greenhouse detection in the south of Spain (Almería). AssesSeg outputs were utilized to find the best band combinations for the performed segmentations of the images and showed a clear positive correlation between segmentation accuracy and the quantity of available reference data. This demonstrates the importance of a high number of reference data in supervised segmentation accuracy assessment problems.