Multi-Temporal Hyperspectral Classification of Grassland Using Transformer Network
Open Access
Abstract
In recent years, grassland monitoring has shifted from traditional field surveys to remote-sensing-based methods, but the desired level of accuracy has not yet been obtained. Multi-temporal hyperspectral data contain valuable information about species and growth season differences, making it a promising tool for grassland classification. Transformer networks can directly extract long-sequence features, which is superior to other commonly used analysis methods. This study aims to explore the transformer network’s potential in the field of multi-temporal hyperspectral data by fine-tuning it and introducing it into high-powered grassland detection tasks. Subsequently, the multi-temporal hyperspectral classification of grassland samples using the transformer network (MHCgT) is proposed. To begin, a total of 16,800 multi-temporal hyperspectral data were collected from grassland samples at different growth stages over several years using a hyperspectral imager in the wavelength range of 400–1000 nm. Second, the MHCgT network was established, with a hierarchical architecture, which generates a multi-resolution representation that is beneficial for grass hyperspectral time series’ classification. The MHCgT employs a multi-head self-attention mechanism to extract features, avoiding information loss. Finally, an ablation study of MHCgT and comparative experiments with state-of-the-art methods were conducted. The results showed that the proposed framework achieved a high accuracy rate of 98.51% in identifying grassland multi-temporal hyperspectral which outperformed CNN, LSTM-RNN, SVM, RF, and DT by 6.42–26.23%. Moreover, the average classification accuracy of each species was above 95%, and the August mature period was easier to identify than the June growth stage. Overall, the proposed MHCgT framework shows great potential for precisely identifying multi-temporal hyperspectral species and has significant applications in sustainable grassland management and species diversity assessment.Keywords
Funding Information
- National Natural Science Foundation of China (61962048, 61562067, 52079063, 2020CG0054, 2019JQ06, NMGIRT2313, 1610332020020)
- National Natural Science Foundation of China (61962048, 61562067, 52079063, 2020CG0054, 2019JQ06, NMGIRT2313, 1610332020020)
- National Natural Science Foundation of China (61962048, 61562067, 52079063, 2020CG0054, 2019JQ06, NMGIRT2313, 1610332020020)
- Technological Achievements of Inner Mongolia Autonomous Region of China (61962048, 61562067, 52079063, 2020CG0054, 2019JQ06, NMGIRT2313, 1610332020020)
- Natural Science Foundation of Inner Mongolia Autonomous Region of China (61962048, 61562067, 52079063, 2020CG0054, 2019JQ06, NMGIRT2313, 1610332020020)
- Program for Innovative Research Teams in Universities of Inner Mongolia Autonomous Region (61962048, 61562067, 52079063, 2020CG0054, 2019JQ06, NMGIRT2313, 1610332020020)
- Central Public Interest Scientific Institution Basal Research Found (61962048, 61562067, 52079063, 2020CG0054, 2019JQ06, NMGIRT2313, 1610332020020)
This publication has 42 references indexed in Scilit:
- Spatio-temporal variations in vegetation types based on a climatic grassland classification system during the past 30 years in Inner Mongolia, ChinaCATENA, 2020
- Evaluation of Evapotranspiration over a Semiarid Region Using Multiresolution Data SourcesJournal of Hydrometeorology, 2019
- Classification of Lowland Native Grassland Communities Using Hyperspectral Unmanned Aircraft System (UAS) Imagery in the Tasmanian MidlandsDrones, 2019
- Classification of Expansive Grassland Species in Different Growth Stages Based on Hyperspectral and LiDAR DataRemote Sensing, 2018
- Superpixel-Based Semisupervised Active Learning for Hyperspectral Image ClassificationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018
- Hyperspectral Image Classification With Deep Learning ModelsIEEE Transactions on Geoscience and Remote Sensing, 2018
- Multi-temporal mesoscale hyperspectral data of mixed agricultural and grassland regions for anomaly detectionISPRS Journal of Photogrammetry and Remote Sensing, 2017
- Classification of Tundra Vegetation in the Krkonoše Mts. National Park Using APEX, AISA Dual and Sentinel-2A DataEuropean Journal of Remote Sensing, 2017
- Classification of Grassland Successional Stages Using Airborne Hyperspectral ImageryRemote Sensing, 2014
- Multi-temporal hyperspectral mixture analysis and feature selection for invasive species mapping in rainforestsRemote Sensing of Environment, 2013