Agricultural crop discrimination in a heterogeneous low-mountain range region based on multi-temporal and multi-sensor satellite data

Abstract

Crop type information such as its location and spatial distribution is relevant for agricultural planning and decision making about food sustainability and security. This information can be obtained through the analysis of images obtained through optical satellite remote sensing. Activities such as accurate discrimination of crops require dense time-series of satellite data which can capture the diverse crop phenology. However, given the presence of clouds at important periods of crops’ development, the required time-series is impossible to obtain from just one optical satellite sensor. The Harmonized Landsat and Sentinel-2 (HLS) project by NASA provides fused data from both Operational Land Imager and Multispectral Instrument optical sensors of Landsat and Sentinel systems respectively. The present study used a multi-temporal HLS data and a target-oriented cross-validation (TOV) modelling approach with random forest algorithm to discriminate 13 crop types. 15 phenological metrics derived from time-series HLS data, together with 48 spectral and 2 topographic information were used as predictors in the model. A forward feature selection (FFS) procedure of the TOV was used to improve the classification model. 16 predictors comprising of spectral, phenological and topographic information were selected as useful for the crop discrimination. An independent accuracy assessment of the final model based on the selected predictors by the FFS procedure resulted in an overall accuracy of 76%. While most of the crop classes, achieved higher producer’s and user’s accuracies (>80%), the discrimination accuracies of potato, summer oat and winter triticale were comparatively low (<60%). Based on the outcome of the FFS, three models consisting of different predictor combinations, were further developed to ascertain the contribution of the predictors. A comparison of the models showed that the addition of phenological metrics increased the discrimination performance of the model as a whole and for cereals in particular. However, the inclusion of the topographic information did not have any significant effect on the overall model performance. Therefore, future crop type discrimination research in areas with similar terrain characteristics like Northern Hesse should reconsider the use of topographic predictors. Overall, our findings depict that the TOV modelling approach based on multi-temporal and multi-sensor data is promising for effective, accurate and practical crop type discrimination.