Fuzzy clustering for the within-season estimation of cotton phenology.

Crop phenology is crucial information for crop yield estimation and agricultural management. Traditionally, phenology has been observed from the ground; however Earth observation, weather and soil data have been used to capture the physiological growth of crops. In this work, we propose a new approach for the within-season phenology estimation for cotton at the field level. For this, we exploit a variety of Earth observation vegetation indices (derived from Sentinel-2) and numerical simulations of atmospheric and soil parameters. Our method is unsupervised to address the ever-present problem of sparse and scarce ground truth data that makes most supervised alternatives impractical in real-world scenarios. We applied fuzzy c-means clustering to identify the principal phenological stages of cotton and then used the cluster membership weights to further predict the transitional phases between adjacent stages. In order to evaluate our models, we collected 1,285 crop growth ground observations in Orchomenos, Greece. We introduced a new collection protocol, assigning up to two phenology labels that represent the primary and secondary growth stage in the field and thus indicate when stages are transitioning. Our model was tested against a baseline model that allowed to isolate the random agreement and evaluate its true competence. The results showed that our model considerably outperforms the baseline one, which is promising considering the unsupervised nature of the approach. The limitations and the relevant future work are thoroughly discussed. The ground observations are formatted in an ready-to-use dataset and will be available at https://github.com/Agri-Hub/cotton-phenology-dataset upon publication.

Increasing the Sentinel-2 potential for marine plastic litter monitoring through image fusion techniques.

Sentinel-2 (S2) images have been used in several projects to detect large accumulations of marine litter and plastic targets. Their limited spatial resolution though hinders the detection of relatively small floating accumulations of marine debris. Thus, this study aims at overcoming this limit through the exploration of fusion with very high-resolution WorldView-2/3 (WV-2/3) images. Various state-of-the-art approaches (component substitution, spectral unmixing, deep learning) were applied on data collected in synchronized acquisitions of plastic targets of various sizes and materials in seawater. The fused images were evaluated for spectral and spatial distortions, as well as their ability to spectrally discriminate plastics from water. Several WV-2/3 band combinations were investigated and five litter indexes were applied. Results showed that: a) the VNIR combination is the optimal one, b) the smallest observable plastic target is 0.6 × 0.6 m2 and c) SWIR bands are important for marine litter detection.