Semantic Segmentation of Sentinel-2 Imagery for Mapping Irrigation Center Pivots

• Published in: Remote sensing (Basel, Switzerland) Vol. 12; no. 23; p. 3937
• Main Authors: Graf, Lukas, Bach, Heike, Tiede, Dirk
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01-12-2020
• Subjects: Accuracy; Agricultural production; Agriculture; Algorithms; Aquifers; Artificial intelligence; center pivot systems; Classification; Climate change; Computer applications; Crops; Deep learning; Image processing; Image segmentation; Irrigation; Irrigation systems; Land use; Learning algorithms; Machine learning; Mapping; Model accuracy; neural network; Neural networks; Precipitation; Principal components analysis; Rain; Reduction; Remote sensing; Semantic segmentation; Semantics; Training; U-NET; Vegetation; Water shortages; Water use; Brazil; South Africa; United States > US; Texas; Spain; Nebraska
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs12233937

Estimating the number and size of irrigation center pivot systems (CPS) from remotely sensed data, using artificial intelligence (AI), is a potential information source for assessing agricultural water use. In this study, we identified two technical challenges in the neural-network-based classification: Firstly, an effective reduction of the feature space of the remote sensing data to shorten training times and increase classification accuracy is required. Secondly, the geographical transferability of the AI algorithms is a pressing issue if AI is to replace human mapping efforts one day. Therefore, we trained the semantic image segmentation algorithm U-NET on four spectral channels (U-NET SPECS) and the first three principal components (U-NET principal component analysis (PCA)) of ESA/Copernicus Sentinel-2 images on a study area in Texas, USA, and assessed the geographic transferability of the trained models to two other sites: the Duero basin, in Spain, and South Africa. U-NET SPECS outperformed U-NET PCA at all three study areas, with the highest f1-score at Texas (0.87, U-NET PCA: 0.83), and a value of 0.68 (U-NET PCA: 0.43) in South Africa. At the Duero, both models showed poor classification accuracy (f1-score U-NET PCA: 0.08; U-NET SPECS: 0.16) and segmentation quality, which was particularly evident in the incomplete representation of the center pivot geometries. In South Africa and at the Duero site, a high rate of false positive and false negative was observed, which made the model less useful, especially at the Duero test site. Thus, geographical invariance is not an inherent model property and seems to be mainly driven by the complexity of land-use pattern. We do not consider PCA a suited spectral dimensionality reduction measure in this. However, shorter training times and a more stable training process indicate promising prospects for reducing computational burdens. We therefore conclude that effective dimensionality reduction and geographic transferability are important prospects for further research towards the operational usage of deep learning algorithms, not only regarding the mapping of CPS.