Sugarcane Plantation Mapping Using Dynamic Time Warping From Multi-Temporal Sentinel-1a Radar Images

Abstract

Abstract. Updating of seasonal agricultural crop map is limited by the local knowledge of the mapper. Mapping of previously unaccounted agricultural plots involve massive field works aided by very high-resolution images. The phenological cycle of seasonal crops like sugarcane, with a range of ten (10) to twelve (12) months from planting to harvesting, exhibit a unique characteristic in terms of radar backscatter and time. In this paper, a pattern matching algorithm was tested to detect sugarcane plantations. Dynamic Time Warping (DTW), which was originally used for voice recognition, was used to detect sugarcane plantations from multitemporal Sentinel-1A images. Using known sugarcane plots, temporal signatures were gathered and used to detect other plantations in the area. The result helped the Sugar Regulatory Administration (SRA) in updating the inventory of sugarcane plantations faster with detection accuracy of more than 92 percent.

COHERENCE and BACKSCATTER BASED CROPLAND MAPPING USING MULTI-TEMPORAL SENTINEL-1 with DYNAMIC TIME WARPING

“…Compared to the previous studies, backscatter values gave lower results which might be due to the amount of crop parcel and crop number. Olfindo et al (2020) achieved 92% accuracy for sugarcane and non-sugarcane plantation mapping using a stack of dual-polarized backscatter of Sentinel-1. The study of Li and Bijker (2019) resulted in 80% overall accuracy using a combination of backscatter and decomposition.…”

“…As a result, they reported good results in the classification without time constraints. Olfindo et al (2020) classified sugarcane parcels using the DTW technique and backscatter of Sentinel-1 data. As a result of the study, they obtained 92.75% overall accuracy.…”