Abstract
Agricultural greenhouse (AG), one of the fastest-growing technology-based approaches worldwide in terms of controlling the environmental conditions of crops, plays an essential role in food production, resource conservation and the rural economy, but has also caused environmental and socio-economic problems due to policy promotion and market demand. Therefore, long-term monitoring of AG is of utmost importance for the sustainable management of protected agriculture, and previous efforts have verified the effectiveness of remote sensing-based techniques for mono-temporal AG mapping in a relatively small area. However, currently, a continuous annual AG remote sensing-based dataset at large-scale is generally unavailable. In this study, an annual AG mapping method oriented to the provincial area and long-term period was developed to produce the first Landsat-derived annual AG dataset in Shandong province, China from 1989 to 2018 on the Google Earth Engine (GEE) platform. The mapping window for each year was selected based on the vegetation growth and the phenological information, which was critical in distinguishing AG from other misclassified categories. Classification for each year was carried out initially based on the random forest classifier after the feature optimization. A temporal consistency correction algorithm based on classification probability was then proposed to the classified AG maps for further improvement. Finally, the average User’s Accuracy, Producer’s Accuracy and F1-score of AG based on visually-interpreted samples over 30 years reached 96.56%, 86.64% and 0.911, respectively. Furthermore, we also found that the ranked features via calculating the importance of each tested feature resulted in the highest accuracy and the strongest stability in the initial classification stage, and the proposed temporal consistency correction algorithm improved the final products by approximately five percent on average. In general, the resultant AG sequence dataset from our study has revealed the expansion of this typical object of “Human–Nature” interaction in agriculture and has a potential application in use of greenhouse-related technology and the scientific planning of protected agriculture.
Highlights
We found that Normalized Difference Tillage Index (NDTI) (0.88) and Normalized Burn Ratio (NBR) (0.46), which were first applied to remote sensing recognition of Agricultural greenhouse (AG), ranked first and seventh in the average importance respectively
All features were divided into four combinations based on the ranked order, including ranked features with one average importance greater than 0.5 (NDTI, GREEN, BLUE), ranked features with two average importance greater than 0.4 (NDTI, GREEN, BLUE, PGI, RED, shortwave infrared 1 (SWIR1), NBR, NIR, sum average (SAVG)), ranked features with three average importance greater than 0.3 (NDTI, GREEN, BLUE, PGI, RED, SWIR1, NBR, NIR, SAVG, SWIR2, CON, Retrogressive Plastic Greenhouse Index (RPGI), Enhanced Vegetation Index (EVI), PlasticMulched Landcover Index (PMLI), Green Red Vegetation indices (GRVI), MNDWI, DISS), and ranked features with 4 average importance greater than 0.2 (NDTI, GREEN, BLUE, PGI, RED, SWIR1, NBR, NIR, SAVG, SWIR2, CON, RPGI, EVI, PMLI, GRVI, MNDWI, DISS, CORR, VAR, Vegetable Land Extraction (VI), Green NDVI (GNDVI), angular second moment (ASM), ENT, inverse difference moment (IDM), Normalized Difference Built-up Index (NDBI), Normalized Difference Vegetation Index (NDVI))
Previous efforts to map AG have generally used visual interpretation and supervised, and unsupervised methods, and mono-temporal or multi-temporal images at regional scales, while fine-resolution annual AG maps at large scales have rarely been investigated in the current literature
Summary
Agricultural greenhouses (AG), as the most typical object of protected agriculture, has been steadily increased throughout the world and reached about at a total area of 3.02 × 106 ha in 2016 [2]. Since it has played a great role in the balanced annual supply of food, the utilization of agricultural resources, the increase of farmers’ income and the employment of rural labor, the Chinese government has been vigorously promoting the construction of AG since the late 1980s. In order to prevent and control the surface source pollution caused by the disorderly development of AG, optimize the layout of land for protected agriculture, balance the relationship between non-grain cultivation, ensuring food security, and promoting the sustainable development of agricultural resource utilization, it is urgent to track the long-term dynamics of the AG in the typically protected agriculture regions
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
