Research on the Inversion of Key Growth Parameters of Rice Based on Multisource Remote Sensing Data and Deep Learning

Jian Li, Jian Lu, Hongkun Fu, Wenlong Zou, Weijian Zhang, Weilin Yu and Yuxuan Feng ()
Additional contact information
Jian Li: College of Information Technology, Jilin Agricultural University, Changchun 130118, China
Jian Lu: College of Agriculture, Jilin Agricultural University, Changchun 130118, China
Hongkun Fu: College of Agriculture, Jilin Agricultural University, Changchun 130118, China
Wenlong Zou: College of Information Technology, Jilin Agricultural University, Changchun 130118, China
Weijian Zhang: College of Information Technology, Jilin Agricultural University, Changchun 130118, China
Weilin Yu: College of Information Technology, Jilin Agricultural University, Changchun 130118, China
Yuxuan Feng: College of Information Technology, Jilin Agricultural University, Changchun 130118, China

Agriculture, 2024, vol. 14, issue 12, 1-23

Abstract: This study accurately inverts key growth parameters of rice, including Leaf Area Index (LAI), chlorophyll content (SPAD) value, and height, by integrating multisource remote sensing data (including MODIS and ERA5 imagery) and deep learning models. Dehui City in Jilin Province, China, was selected as the case study area, where multidimensional data including vegetation indices, ecological function parameters, and environmental variables were collected, covering seven key growth stages of rice. Data analysis and parameter prediction were conducted using a variety of machine learning and deep learning models including Partial Least Squares (PLSs), Support Vector Machine (SVM), Random Forest (RF), and Long Short-Term Memory Networks (LSTM), among which the LSTM model demonstrated superior performance, particularly at multiple critical time points. The results show that the LSTM performed best in inverting the three parameters, with the LAI inversion accuracy on 21 August reaching a coefficient of determination (R 2 ) of 0.72, root mean square error (RMSE) of 0.34, and mean absolute error (MAE) of 0.27. The SPAD inversion accuracy on the same date achieved an R 2 of 0.69, RMSE of 1.45, and MAE of 1.16. The height inversion accuracy on 25 July reached an R 2 of 0.74, RMSE of 2.30, and MAE of 2.08. This study not only verifies the effectiveness of combining multisource data and advanced algorithms but also provides a scientific basis for the precision management and decision-making of rice cultivation.

Keywords: multisource remote sensing data; deep learning; LSTM; crop growth parameter inversion (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2077-0472/14/12/2326/pdf (application/pdf)
https://www.mdpi.com/2077-0472/14/12/2326/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:14:y:2024:i:12:p:2326-:d:1547358

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().