Countrywide Mapping of Plant Ecological Communities with 101 Legends including Land Cover Types for the First Time at 10 m Resolution through Convolutional Learning of Satellite Images

Abstract

This paper presents next-generation mapping of plant ecological communities including land cover and agricultural types at 10 m spatial resolution countrywide. This research introduces modelling and mapping of land cover and ecological communities separately in small regions-of-interest (prefecture level), and later integrating the outputs into a large scale (country level) for dealing with regional distribution characteristics of plant ecological communities effectively. The Sentinel-2 satellite images were processed for cloud masking and half-monthly median composite images consisting of ten multi-spectral bands and seven spectral indexes were generated. The reliable ground truth data were prepared from extant multi-source survey databases through the procedure of stratified sampling, cross-checking, and noisy-labels pruning. Deep convolutional learning of the time-series of the satellite data was employed for prefecture-wise classification and mapping of 29–62 classes. The classification accuracy computed with the 10-fold cross-validation method varied from 71.1–87.5% in terms of F1-score and 70.9–87.4% in terms of Kappa coefficient across 48 prefectural regions. This research produced seamless maps of 101 ecological communities including land cover and agricultural types for the first time at a country scale with an average accuracy of 80.5% F1-score.

Inversion of Soil Moisture Content in Cotton Fields Using GBR-RF Algorithm Combined with Sentinel-2 Satellite Spectral Data

“…In recent years, research on the inversion of soil moisture and other related indicators based on machine learning algorithms has drawn significant attention [14,15]. Remote sensing methods provide high-resolution spectral data, offering a wealth of information for the inversion of soil moisture content [16,17]. Kingsley John et al successfully estimated the variability in soil organic carbon in alluvial soils using machine learning algorithms in conjunction with environmental variables and soil nutrient indicators, achieving an optimal R 2 value of 0.68 [18].…”

Crop Classification Combining Object-Oriented Method and Random Forest Model Using Unmanned Aerial Vehicle (UAV) Multispectral Image

“…However, this method has drawbacks such as high cost, long time consumption, and difficulty in obtaining large-scale data [4]. In recent years, the rapid development of remote sensing technology has provided a new avenue for the accurate and rapid identification of crop species [5]. Nevertheless, traditional satellite remote sensing faces challenges, including low spatial and temporal resolutions, vulnerability to cloud cover, mixed pixel issues, and limited spectral discrimination, all of which can compromise the accuracy of crop extraction [6,7].…”