Spatial-temporal Dynamic Changes of Agricultural Greenhouses in Shandong Province in Recent 30 Years Based on Google Earth Engine

Shandong Province is a large agricultural province in China. In recent years, agricultural greenhouses have developed rapidly. The promotion of greenhouse technology played an important role in increasing agricultural production and efficiency in Shandong Province. Therefore, it is necessary to monitor the dynamic changes of agricultural greenhouses in Shandong Province. However, accurately obtaining the distribution of agricultural greenhouses in a large-scale space and performing dynamic monitoring of long-term sequences are difficult, such as large data volume, low computational efficiency, and low precision. In response to the above problems, the Google Earth Engine (GEE) cloud platform was used to access and process massive satellite data. Based on multi-temporal Landsat images, time series spectral features and texture features were extracted. Random forests were used to complete the classification of agricultural greenhouses in Shandong Province. Finally, the thematic map of spatial distribution and spatial-temporal dynamic changes of agricultural greenhouses in Shandong Province in recent 30 years were generated. The experimental results showed that the classification process proposed had better classification accuracy with the average classification accuracy of 91.63% and the Kappa coefficient of 0.864 2. After analysis, the area of agricultural greenhouse in Shandong Province was increased from 6.67 km2 in 1990 to 9 919.40 km2 in 2018, with a growth rate of 354.03 km2 per year. By studying the dynamic changes of agricultural greenhouses in Shandong Province in recent 30 years, it can not only provide better planning suggestions for further development, but also provide reference for the development of agricultural greenhouses in other provinces in China. © 2020, Chinese Society of Agricultural Machinery. All right reserved.