Integrated model for predicting rice yield with climate change release_wudxzufjbvcn3i4bmpdlgr6pvm

by Jin-Ki Park, Amrita Das, Jong-Hwa Park

Published in International Agrophysics by Walter de Gruyter GmbH.

2018   Volume 32, p203-215

Abstract

<jats:title>Abstract</jats:title> Rice is the chief agricultural product and one of the primary food source. For this reason, it is of pivotal importance for worldwide economy and development. Therefore, in a decision-support-system both for the farmers and in the planning and management of the country's economy, forecasting yield is vital. However, crop yield, which is a dependent of the soil-bio-atmospheric system, is difficult to represent in statistical language. This paper describes a novel approach for predicting rice yield using artificial neural network, spatial interpolation, remote sensing and GIS methods. Herein, the variation in the yield is attributed to climatic parameters and crop health, and the normalized difference vegetation index from MODIS is used as an indicator of plant health and growth. Due importance was given to scaling up the input parameters using spatial interpolation and GIS and minimising the sources of error in every step of the modelling. The low percentage error (2.91) and high correlation (0.76) signifies the robust performance of the proposed model. This simple but effective approach is then used to estimate the influence of climate change on South Korean rice production. As proposed in the RCP8.5 scenario, an upswing in temperature may increase the rice yield throughout South Korea.
In application/xml+jats format

Archived Files and Locations

application/pdf  1.4 MB
file_rby6hzy5b5fc3fvqxgsriq4zgy
www.international-agrophysics.org (web)
web.archive.org (webarchive)
application/pdf  1.4 MB
file_q6rgjfxvdrcwddtsspn4icgxqe
web.archive.org (webarchive)
content.sciendo.com (web)
Read Archived PDF
Preserved and Accessible
Type  article-journal
Stage   published
Date   2018-04-01
Container Metadata
Open Access Publication
In DOAJ
In ISSN ROAD
In Keepers Registry
ISSN-L:  0236-8722
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: b7abe5bf-ee64-412e-a607-5608e7a97de2
API URL: JSON