Convlstm Neural Network for Rice Field Classification from Sentinel-1A Sar Images

Document Type

Conference Item

Publication Date

1-1-2022

Abstract

Taiwan's agriculture is an important national economic industry. Ensuring food security and stabilizing the food supply are the government's primary goals. The Agriculture and Food Agency (AFA) of the Executive Yuan's Council of Agriculture has conducted agricultural and food surveys to address those issues. Synthetic aperture radar (SAR) images will not be affected by climatic factors, which makes them more suitable for the forecast of rice production. This research uses the spatial-temporal neural network convolutional long short-term memory network (ConvLSTM) to identify rice fields from SAR images. The results show that ConvLSTM can greatly reduce the proportion of model false positives to 51.16%, produced higher average precision of 95.70%, and F1-score of 0.9648. The ConvLSTM neural network has produced good results for rice field identification compared with state-of-the-art neural networks.

Keywords

Spatial temporal neural network, Synthetic aperture radar images, Sentinel-1A, Rice field classification

Divisions

sch_ecs

Funders

National Science and Technology Center for Disaster Reduction [Grant no. NCDR-S-110096],Ministry of Science and Technology, Taiwan [Grant no. 109-2116-M-027-004, 110-2119-M-027-001, 110-2221-E-027-101, 110-2622-E-027-025],National Space Organization [Grant no. NSPO-S-110244]

Publisher

IEEE

Publisher Location

345 E 47TH ST, NEW YORK, NY 10017 USA

Event Title

2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022

Event Location

Kuala Lumpur

Event Dates

17-22 July 2022

Event Type

conference

This document is currently not available here.

Share

COinS