Crop Phenology Extraction Using Big Geospatial Datacube

Phenology of crops is the study of specific stages in crop life cycles. Understanding the phenological changes of crops is vital for crop mapping and to monitor the impact of climate change on the crop cycle. The traditional remote sensing data processing method for large-scale spatial and temporal data analysis is complicated in both space and time. For reliable monitoring and analysis ofvegetation dynamics as well as the extraction of sensitive crop phenology variables, it is necessary to aggregate massive datasets with high temporal resolution. The current state of research in this topic is restricted by the need for long-term, high temporal resolution multispectral data collection and processing. Cloud computing technology has advanced and the platforms like Google Earth Engine are now available for cloud-based big spatial data analysis and processing, leveraging the Big Geospatial data-cube paradigm. GEE datacubes can be used to meet the computational and big data resource organization needed for long-term agricultural phenology extraction in a virtual server platform. Variations in the average temperature and other factors, such as rainfall, have affected the phenology of the wheat crop in Madhya Pradesh. Establishing effective and efficient agricultural methods, as well as for controlling water and nutrients, projecting yields, and managing crops, all depend heavily on the crop calendar and phenological parameters that were retrieved. This study has been conducted to extract and analyze changes in the wheat phenology parameters in order to better comprehend the impact of temperature stress on the wheat crop calendar. This study uses the Landsat 8 multispectral dataset, which has a geographical resolution of 30 m, to examine changes in wheat phenology over the course of five succeeding crop seasons. The phenological metrics extracted include the Early vegetative state, anthesis state, physiological maturity state, length of cropping season, asymmetry, green-up slope, and brown down slope. This study also offers two new perspectives for further work: the first is on crop classification using phenological criteria, and the second is a comprehensive methodology for monitoring crop phenology changes in contexts of impending climatic changes.