No 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.

No abstract

No abstract

Abstract. Flood extent delineation from RADAR images usually entails manual thresholding per scene, which is not feasible when tackling large-scale floods that often covers multiple RADAR scenes. It is also computationally intensive when processed through traditional remote sensing techniques that limit its use during emergency situations. To hasten the production of flood maps from RADAR images during flooding incidents, a deep learning model using Fully connected Convolutional Neural Network (FCNN) has been developed to delineate flooded areas with minimal human intervention. The model was formulated from the data gathered during a flooding event captured by both Sentinel-1A SAR satellite and Planet’s Dove optical satellites. Two pre-flood and one post-flood SAR scenes were used to detect the occurrence of water by analysing drops in backscatter values. The potential flood extents were verified using optical images which were then used to train the AI model. The model is currently being used operationally to map flood extent across the Philippines with no human intervention from data download to detection of flooded areas. The technique can detect floods across five Sentinel 1 scenes in less than four hours upon download of new satellite data.