Predicting wheat yield from 2001 to 2020 in Hebei Province at county and pixel levels based on synthesized time series images of Landsat and MODIS

To obtain seasonable and precise crop yield information with fine resolution is very important for ensuring the food security. However, the quantity and quality of available images and the selection of prediction variables often limit the performance of yield prediction. In our study, the synthesize...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhang, Guanjin, Roslan, Siti Nur Aliaa, Mohd Shafri, Helmi Zulhaidi, Zhao, Yanxi, Wang, Ci, Quan, Ling
Format: Article
Language:English
Published: Nature Research 2024
Online Access:http://psasir.upm.edu.my/id/eprint/113651/1/113651.pdf
http://psasir.upm.edu.my/id/eprint/113651/
https://www.nature.com/articles/s41598-024-67109-3?error=cookies_not_supported&code=6d6376c9-830c-438a-a658-4424ae8aea9e
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Universiti Putra Malaysia
Language: English
id my.upm.eprints.113651
record_format eprints
spelling my.upm.eprints.1136512024-11-25T02:02:54Z http://psasir.upm.edu.my/id/eprint/113651/ Predicting wheat yield from 2001 to 2020 in Hebei Province at county and pixel levels based on synthesized time series images of Landsat and MODIS Zhang, Guanjin Roslan, Siti Nur Aliaa Mohd Shafri, Helmi Zulhaidi Zhao, Yanxi Wang, Ci Quan, Ling To obtain seasonable and precise crop yield information with fine resolution is very important for ensuring the food security. However, the quantity and quality of available images and the selection of prediction variables often limit the performance of yield prediction. In our study, the synthesized images of Landsat and MODIS were used to provide remote sensing (RS) variables, which can fill the missing values of Landsat images well and cover the study area completely. The deep learning (DL) was used to combine different vegetation index (VI) with climate data to build wheat yield prediction model in Hebei Province (HB). The results showed that kernel NDVI (kNDVI) and near-infrared reflectance (NIRv) slightly outperform normalized difference vegetation index (NDVI) in yield prediction. And the regression algorithm had a more prominent effect on yield prediction, while the yield prediction model using Long Short-Term Memory (LSTM) outperformed the yield prediction model using Light Gradient Boosting Machine (LGBM). The model combining LSTM algorithm and NIRv had the best prediction effect and relatively stable performance in single year. The optimal model was then used to generate 30 m resolution wheat yield maps in the past 20 years, with higher overall accuracy. In addition, we can define the optimum prediction time at April, which can consider simultaneously the performance and lead time. In general, we expect that this prediction model can provide important information to understand and ensure food security. Nature Research 2024-07 Article PeerReviewed text en cc_by_nc_nd_4 http://psasir.upm.edu.my/id/eprint/113651/1/113651.pdf Zhang, Guanjin and Roslan, Siti Nur Aliaa and Mohd Shafri, Helmi Zulhaidi and Zhao, Yanxi and Wang, Ci and Quan, Ling (2024) Predicting wheat yield from 2001 to 2020 in Hebei Province at county and pixel levels based on synthesized time series images of Landsat and MODIS. Scientific Reports, 14 (1). art. no. 16212. pp. 1-12. ISSN 2045-2322; eISSN: 2045-2322 https://www.nature.com/articles/s41598-024-67109-3?error=cookies_not_supported&code=6d6376c9-830c-438a-a658-4424ae8aea9e 10.1038/s41598-024-67109-3
institution Universiti Putra Malaysia
building UPM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Putra Malaysia
content_source UPM Institutional Repository
url_provider http://psasir.upm.edu.my/
language English
description To obtain seasonable and precise crop yield information with fine resolution is very important for ensuring the food security. However, the quantity and quality of available images and the selection of prediction variables often limit the performance of yield prediction. In our study, the synthesized images of Landsat and MODIS were used to provide remote sensing (RS) variables, which can fill the missing values of Landsat images well and cover the study area completely. The deep learning (DL) was used to combine different vegetation index (VI) with climate data to build wheat yield prediction model in Hebei Province (HB). The results showed that kernel NDVI (kNDVI) and near-infrared reflectance (NIRv) slightly outperform normalized difference vegetation index (NDVI) in yield prediction. And the regression algorithm had a more prominent effect on yield prediction, while the yield prediction model using Long Short-Term Memory (LSTM) outperformed the yield prediction model using Light Gradient Boosting Machine (LGBM). The model combining LSTM algorithm and NIRv had the best prediction effect and relatively stable performance in single year. The optimal model was then used to generate 30 m resolution wheat yield maps in the past 20 years, with higher overall accuracy. In addition, we can define the optimum prediction time at April, which can consider simultaneously the performance and lead time. In general, we expect that this prediction model can provide important information to understand and ensure food security.
format Article
author Zhang, Guanjin
Roslan, Siti Nur Aliaa
Mohd Shafri, Helmi Zulhaidi
Zhao, Yanxi
Wang, Ci
Quan, Ling
spellingShingle Zhang, Guanjin
Roslan, Siti Nur Aliaa
Mohd Shafri, Helmi Zulhaidi
Zhao, Yanxi
Wang, Ci
Quan, Ling
Predicting wheat yield from 2001 to 2020 in Hebei Province at county and pixel levels based on synthesized time series images of Landsat and MODIS
author_facet Zhang, Guanjin
Roslan, Siti Nur Aliaa
Mohd Shafri, Helmi Zulhaidi
Zhao, Yanxi
Wang, Ci
Quan, Ling
author_sort Zhang, Guanjin
title Predicting wheat yield from 2001 to 2020 in Hebei Province at county and pixel levels based on synthesized time series images of Landsat and MODIS
title_short Predicting wheat yield from 2001 to 2020 in Hebei Province at county and pixel levels based on synthesized time series images of Landsat and MODIS
title_full Predicting wheat yield from 2001 to 2020 in Hebei Province at county and pixel levels based on synthesized time series images of Landsat and MODIS
title_fullStr Predicting wheat yield from 2001 to 2020 in Hebei Province at county and pixel levels based on synthesized time series images of Landsat and MODIS
title_full_unstemmed Predicting wheat yield from 2001 to 2020 in Hebei Province at county and pixel levels based on synthesized time series images of Landsat and MODIS
title_sort predicting wheat yield from 2001 to 2020 in hebei province at county and pixel levels based on synthesized time series images of landsat and modis
publisher Nature Research
publishDate 2024
url http://psasir.upm.edu.my/id/eprint/113651/1/113651.pdf
http://psasir.upm.edu.my/id/eprint/113651/
https://www.nature.com/articles/s41598-024-67109-3?error=cookies_not_supported&code=6d6376c9-830c-438a-a658-4424ae8aea9e
_version_ 1817844656088547328