Abstract
The work focuses on developing a classification tree approach for in-season crop mapping during early summer, by integrating optical (Landsat 8 OLI) and X-band SAR (COSMO-SkyMed) data acquired over a test site in Northern Italy. The approach is based on a classification tree scheme fed with a set of synoptic seasonal features (minimum, maximum and average, computed over the multi-temporal datasets) derived from vegetation and soil condition proxies for optical (three spectral indices) and X-band SAR (backscatter) data. Best performing input features were selected based on crop type separability and preliminary classification tests. The final outputs are crop maps identifying seven crop types, delivered during the early growing season (mid-July). Validation was carried out for two seasons (2013 and 2014), achieving overall accuracy greater than 86%. Results highlighted the contribution of the X-band backscatter (σ°) in improving mapping accuracy and promoting the transferability of the algorithm over a different year, when compared to using only optical features.
Highlights
The increasing demand for information on crop acreage for agricultural monitoring in support of private and public decision makers requires the production of reliable crop maps [1,2]
This paper describes a classification tree approach for in-season crop mapping, which exploits features derived from multi-temporal optical, Landsat 8 Operational Land Imager (OLI), and X-band
As regards separability achieved by using optical and Synthetic Aperture Radar (SAR) proxies together, an increment is observed adding σ° to the full optical feature set; since separability is already close to the maximum value (J-MDIST~2) the increment is lower for maize and soybean classes (+0.007 to +0.010)
Summary
The increasing demand for information on crop acreage for agricultural monitoring in support of private and public decision makers requires the production of reliable crop maps [1,2]. Up-to-date information on agricultural land use is necessary for crop planning and management: e.g., for estimating biomass and yield, analyzing agronomic practices, assessing soil productivity, monitoring crop phenology and stress. EO data are available already during the growing season, whereas official statistics on crop acreages are often provided at the end of the season or later, being not useful for supporting in-season crop management. Since crop productivity quickly responds to unfavorable growing conditions, timeliness in delivering information on crop status is an important operational requirement [4,5], e.g., for mitigating the impact of crop stress conditions, especially for summer crops, which are prone to water stress in the dry summer months [6,7]
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.
