Fuzzy clustering for the within-season estimation of cotton phenology

Abstract

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.

Understanding the Impacts of Crop Diversification in the Context of Climate Change: A Machine Learning Approach

“…Earth Observations are frequently used to engineer large-scale datasets featuring diverse information on agriculture, climate, society and economy (Choumos et al, 2022, Drivas et al, 2022. Artificial Intelligence (AI) techniques including Machine Learning (ML) are used to analyze such datasets, extract insights, and inform stakeholders (Sitokonstantinou et al, 2023, Sitokonstantinou et al, 2020. Since * Corresponding author impact assessment studies are fundamentally concerned with cause and effect, researchers have been recently using causal machine learning techniques to valorize EO data (Jerzak et al, 2023, Giannarakis et al, 2022a, Nanushi et al, 2022 while avoiding the caveats of correlation based ML methods (Pearl, 2009).…”