Mapping Crop Rotation by Using Deeply Synergistic Optical and SAR Time Series

Crop rotations, the farming practice of growing crops in sequential seasons, occupy a core position in agriculture management, showing a key influence on food security and agro-ecosystem sustainability. Despite the improvement in accuracy of identifying mono-agricultural crop distribution, crop rota...

Full description

Saved in:

Bibliographic Details
Published in:	Remote sensing (Basel, Switzerland) Switzerland), 2021-10, Vol.13 (20), p.4160
Main Authors:	Liu, Yiqing, Zhao, Wenzhi, Chen, Shuo, Ye, Tao
Format:	Article
Language:	eng
Subjects:	Ablation Agricultural ecosystems Agricultural management Agricultural practices Artificial neural networks Classification Crayfish Crop rotation crop rotation mapping Crops Deep learning dynamic feature extraction Ecosystem management Feature extraction Food security Long short-term memory Mapping Neural networks Phenology Remote sensing Rice SAR and optical time series Satellites Seasonal variations Sensors Sustainability Synergism Synthetic aperture radar Time series Vegetation mapping
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Crop rotations, the farming practice of growing crops in sequential seasons, occupy a core position in agriculture management, showing a key influence on food security and agro-ecosystem sustainability. Despite the improvement in accuracy of identifying mono-agricultural crop distribution, crop rotation patterns remain poorly mapped. In this study, a hybrid convolutional neural network (CNN) and long short-term memory (LSTM) architecture, namely crop rotation mapping (CRM), were proposed to synergize the synthetic aperture radar (SAR) and optical time series in a rotational mapping task. The proposed end-to-end architecture had reasonable accuracies (i.e., accuracy > 0.85) in mapping crop rotation, which outperformed other state-of-the-art non-deep or deep-learning solutions. For some confusing rotation types, such as fallow-single rice and crayfish-single rice, CRM showed substantial improvements from traditional methods. Furthermore, the deeply synergistic SAR-optical, time-series data, with a corresponding attention mechanism, were effective in extracting crop rotation features, with an overall gain of accuracy of four points compared with ablation models. Therefore, our proposed method added wisdom to dynamic crop rotation mapping and yields important information for the agro-ecosystem management of the study area.
ISSN:	2072-4292 2072-4292