UAV‐based training for fully fuzzy classification of Sentinel‐2 fluvial scenes. Issue 13 (18th August 2020)

• Record Type: Journal Article
• Authors: Carbonneau, P. E.; Belletti, B.; Micotti, M.; Lastoria, B.; Casaioli, M.; Mariani, S.; Marchetti, G.; Bizzi, S.
• Is Part Of: Earth surface processes and landforms. Volume 45:Issue 13(2020)
• Page Start: 3120
• Page End: 3140
• Publication Date: 2020-08-18
• Subjects: machine learning -- UAV -- fuzzy supervised classification -- Sentinel‐2 -- super‐resolution -- fluvial environments; Geomorphology -- Periodicals; 551.4
• DOI: 10.1002/esp.4955
• Languages: English
• ISSNs: 0197-9337

Abstract

Abstract: An estimated 76% of global stream area is occupied by channels with widths above 30 m. Sentinel‐2 imagery with resolutions of 10 m could supply information about the composition of river corridors at national and global scales. Fuzzy classification models that infer sub‐pixel composition could further be used to compensate for small channel widths imaged at 10 m of spatial resolution. A major challenge to this approach is the acquisition of suitable training data useable in machine learning models that can predict land‐cover type information from image radiance values. In this contribution, we present a method which combines unmanned aerial vehicles (UAVs) and Sentinel‐2 imagery in order to develop a fuzzy classification approach capable of large‐scale investigations. Our approach uses hyperspatial UAV imagery in order to derive high‐resolution class information that can be used to train fuzzy classification models for Sentinel‐2 data where all bands are super‐resolved to a spatial resolution of 10 m. We use a multi‐temporal UAV dataset covering an area of 5.25 km 2 . Using a novel convolutional neural network (CNN) classifier, we predict sub‐pixel membership for Sentinel‐2 pixels in the fluvial corridor as divided into classes of water, vegetation and dry sediment. Our CNN model can predict fuzzy class memberships with median errors from −5% to +3% and mean absolute errors from 10% to 20%. We also show that our CNN fuzzy predictor can be used to predict crisp classes with accuracies from 95.5% to 99.9%. Finally, we use an example to show how a fuzzy CNN model trained with localized UAV data can be applied to longer channel reaches and detect new vegetation growth. We therefore argue that the novel use of UAVs as field validation tools for freely available satellite data can bridge the scale gap between local and regional fluvial studies. © 2020 The Authors. Earth Surface Processes and Landforms published by John Wiley & Sons Ltd Abstract : We propose the use of UAV data to train fuzzy classification models applicable to Sentinel‐2 imagery. After testing several machine learning models, we find that a compact convolutional neural network (cCNN) can learn to predict fuzzy class membership for river corridor elements of water, vegetation or sediment. Our CNN model can predict semantic class with accuracies up to 99.9% and fuzzy class memberships with median errors from ‐5% to +3% and mean absolute errors from 10% to 20%.