No abstract

Water is a very important natural resource and it supports all life forms on earth. It is used by humans in various ways including drinking, agriculture and for scientific research. The aim of this research was to develop a routine to automatically extract water masks from RapidEye images, which could be used for further investigation such as water quality monitoring and change detection. A Python-based algorithm was therefore developed for this particular purpose. The developed routine combines three spectral indices namely Simple Ratios (SRs), Normalized Green Index (NGI) and Normalized Difference Water Index (NDWI). The two SRs are calculated between the NIR and green band, and between the NIR and red band. The NGI is calculated by rationing the green band to the sum of all bands in each image. The NDWI is calculated by differencing the green to the NIR and dividing by the sum of the green and NIR bands. The routine generates five intermediate water masks, which are spatially intersected to create a single intermediate water mask. In order to remove very small waterbodies and any remaining gaps in the intermediate water mask, morphological opening and closing were performed to generate the final water mask. This proposed algorithm was used to extract water masks from some RapidEye images. It yielded an Overall Accuracy of 95% and a mean Kappa Statistic of 0.889 using the confusion matrix approach.

Image segmentation is a cost-effective way to obtain information about the sizes and structural composition of agricultural parcels in an area. To accurately obtain such information, the parameters of the segmentation algorithm ought to be optimized using supervised or unsupervised methods. The difficulty in obtaining reference data makes unsupervised methods indispensable. In this study, we evaluated an existing unsupervised evaluation metric that minimizes a global score (GS), which is computed by summing up the intra-segment uniformity and inter-segment dissimilarity within a segmentation output. We modified this metric and proposed a new metric that uses absolute difference to compute the GS. We compared this proposed metric with the existing metric in two optimization approaches based on the Multiresolution Segmentation (MRS) algorithm to optimally delineate agricultural parcels from Sentinel-2 images in Lower Saxony, Germany. The first approach searches for optimal scale while keeping shape and compactness constant, while the second approach uses Bayesian optimization to optimize the three main parameters of the MRS algorithm. Based on a reference data of agricultural parcels, the optimal segmentation result of each optimization approach was evaluated by calculating the quality rate, over-segmentation, and under-segmentation. For both approaches, our proposed metric outperformed the existing metric in different agricultural landscapes. The proposed metric identified optimal segmentations that were less under-segmented compared to the existing metric. A comparison of the optimal segmentation results obtained in this study to existing benchmark results generated via supervised optimization showed that the unsupervised Bayesian optimization approach based on our proposed metric can potentially be used as an alternative to supervised optimization, particularly in geographic regions where reference data is unavailable or an automated evaluation system is sought.

The Group on Earth Observations Global Agricultural Monitoring Initiative (GEOGLAM) considers agricultural fields as one of the essential variables that can be derived from satellite data. We evaluated the accuracy at which agricultural fields can be delineated from Sentinel-1 (S1) and Sentinel-2 (S2) images in different agricultural landscapes throughout the growing season. We used supervised segmentation based on the multiresolution segmentation (MRS) algorithm to first identify the optimal feature set from S1 and S2 images for field delineation. Based on this optimal feature set, we analyzed the segmentation accuracy of the fields delineated with increasing data availability between March and October of 2018. From the S1 feature sets, the combination of the two polarizations and two radar indices attained the best segmentation results. For S2, the best results were achieved using a combination of all bands (coastal aerosol, water vapor, and cirrus bands were excluded) and six spectral indices. Combining the radar and spectral indices further improved the results. Compared to the single-period dataset in March, using the dataset covering the whole season led to a significant increase in the segmentation accuracy. For very small fields (< 0.5 ha), the segmentation accuracy obtained was 27.02%, for small fields (0.5 -1.5 ha), the accuracy was 57.65%, for medium fields (1.5 ha -15 ha), the accuracy was 75.71%, and for large fields (> 15 ha), the accuracy stood at 68.31%. As a use case, the segmentation result was used to aggregate and improve a pixel-based crop type map in Lower Saxony, Germany.

No abstract