IDENTIFICATION AND ESTIMATION OF RICE SOWN AREA IN GUNTUR DISTRICT USING SENTINEL 1A SATELLITE DATA
31 / 14
Authors
-
SUNIL KUMAR M
Geospatial Technology Centre, Regional Agricultural Research Station, Lam, Guntur Acharya N.G Ranga Agricultural University, Guntur, Andhra Pradesh, India
-
ASHA JYOTHI B
Geospatial Technology Centre, Regional Agricultural Research Station, Lam, Guntur Acharya N.G Ranga Agricultural University, Guntur, Andhra Pradesh, India
Keywords:
Crop classification, Random Forest, SAR, Rice, Sentinel-1AAbstract
Accurate estimation of rice-sown area is critical for informed agricultural planning,
particularly in Andhra Pradesh’s complex irrigated landscapes. This study mapped rice cultivation
in Guntur district using Sentinel-1A SAR (Synthetic Aperture Radar) data integrated with machine
learning classifiers. A total of 84 ground-truth observations supported supervised classification
using Random Forest (RF) and K-Nearest Neighbours (KNN). Both models overestimated rice
extent, but RF showed superior performance with 94% user’s accuracy, 96% producer’s accuracy
and kappa coefficient of 0.76. Overestimation by KNN was largely due to confusion with waterlogged
fallow areas. Results confirm the utility of SAR and RF for precise rice area assessment and
underscore the importance of localized model calibration in heterogeneous agroecosystems.
References
Benediktsson, J. A., Pesaresi, M, and Amato,
U. 2018. Advances in remote sensing for
precision agriculture: Current state and
future directions.Remote Sensing of
Environment, 205: 26-36.
Choudhary, B.U., Das, A., Maji, A.K. and
Bandyopadhyay, A. 2014. Remote
sensing and GIS for rice area estimation
and production forecasting: A review.
Journal of AgriSearch, 1(1): 1–10.
European Space Agency. 2024. Sentinel-1A
Synthetic Aperture Radar data.
Copernicus Data Space Ecosystem,
European Space Agency. Available at:
https://dataspace.copernicus.eu
(Accessed November 2024).
Gao, F., Liu, Y., and Zhao, X. 2017. Evaluation
of machine learning algorithms for land
cover classification using Sentinel-1 SAR
data.Journal of Remote Sensing, 39(12):
124-139.
Huang, X., Wang, L., & Zhang, X. 2021.
Mapping crop acreage using SAR data:
A review and analysis of classification
approaches.International Journal of
Remote Sensing, 42(15): 5530-5552.
Kumar, S.M., Podila, P. and Sireesha, G. 2022.
Response of the direct sown and
transplanted rice crop to multi-temporal
Sentinel-1A data and estimate the rice
sown area by synergetic use of Sentinel
1A and Sentinel-2. Scientist, 1(3):73-82
Li, X., Zhang, L., & Xu, L. 2021. Machine
learning techniques for crop classification
and mapping in agriculture: A review of
methods and applications. Computers
and Electronics in Agriculture, 184,
105865.
Liu, C.-A., Chen, Z.-X., Shao, Y., Chen, J.-S.,
Tuya Hasi and Pan, H.-Z. 2019. Research
advances of SAR remote sensing for
agriculture applications: A review. Journal
of Integrative Agriculture, 18(3): 506–525
Liu, D., Yang, H., and Liu, Y. 2020. Random
Forest for crop classification using
remote sensing data: A comparative
analysis. Remote Sensing Letters,11(5):
424-433.
Singh, R.P., Ghosh, S. and Roy, P.S. 2015.
Application of SAR data in agriculture: A
review. Journal of Environmental Biology,
36(2): 311–318.
Surya, S, M., Medida, S. K., Mrudhula, K. A.,
Sridhar, T.V. and Pradeep, K. M. 2024.
Estimation of rice area in KWD region
using geospatial tools. International
Journal of Environment, Agriculture and
Biotechnology, 9(5): 273–279.
Wang, C., Zhang, L., and Yu, Y. 2021. Multi
source remote sensing data fusion for
improving crop classification: A case
study using Sentinel-1 and Sentinel-2
data.Remote Sensing, 13(5): 909.
Yu, Y., Zhang, L., and Li, J. 2020. Remote
sensing-based Random Forest
classification for crop mapping: A case
study in a heterogeneous agricultural
area. Remote Sensing, 12(6), 1024.
Downloads
Submitted
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
The author owns the article's copyright until the article is accepted for publication. After acceptance, the author(s) assigns the article's copyright jointly to both the authors and the Publishers of the Journal of Research ANGRAU (ANGRAU) and licensed under a Creative Commons Attribution-Non Commercial-Share Alike 4.0 International License.
