Deep Learning–Based Analysis of Soybean Crop Growth Using Sentinel-2 Vegetation Indices
Keywords:
NDVI, Deep Learning, Crop Growth, Sentinel-2Abstract
Remote sensing has become an important technology for crop development monitoring and assessment of vegetation health of current agriculture systems. By combining satellite imagery with advanced data analysis techniques, researchers are able to observe crop conditions on a large scale of agricultural areas with greater efficiency. In recent years, deep learning methodologies have shown a great potential for the decomposition of complex interrelationships between spectral characteristics and crop physiological attributes. The current investigation uses a framework of deep learning to study the growth of soybean using vegetation indices extracted from Sentinel 2 satellite imagery. The field experiment was conducted on a 4 acre soybean field located in Sillod region Maharashtra, India & used Sentinel 2 Multispectral Data collected on 1st October 2022 and 26th October 2022 to determine the temporal variations in crop status. Vegetation indices were extracted from the satellite imagery, Normalized Difference Vegetation Index (NDVI), Green Normalized Difference Vegetation Index (GNDVI), Normalized Difference Red Edge Index (NDRE) and Chlorophyll Index Green (CIgreen) were used to quantify vegetation vigor and chlorophyll activity. A deep learning autoencoder was used to determine latent vegetation features from these indices and identify hidden patterns of crop growth. A resulting model yielded two latent variables, which contained crop condition characteristics for two observation dates. Discernible temporal changes in soybean canopy condition were indicated from analysis of the latent features. DeepFeature1 had a small increase from 0.053 to 0.067 while DeepFeature2 showed a significant decrease from 1.0137 to 0.7911 between the two measurement occasions. The attenuation of DeepFeature2 represents a drop in the vigor and activity of the vegetation and the chlorophyll of the soybean plant at a later stage of its growth. These observations follow the expected phenological path of soybean crops approaching maturity. Consequently, the results validate that the feature extraction with deep learning could be effective for capturing temporal dynamics of crop growth using the vegetation indices derived from satellite remote sensing, and provides nice information for agricultural monitoring and precision farming practices.
Downloads
References
Weiss, M., Jacob, F., & Duveiller, G. (2020). Remote sensing for agricultural applications: A meta-review. Remote sensing of environment, 236, 111402.
Ma, L., Liu, Y., Zhang, X., Ye, Y., Yin, G., & Johnson, B. A. (2019). Deep learning in remote sensing applications: A meta-analysis and review. ISPRS journal of photogrammetry and remote sensing, 152, 166-177.
Tambe, P. C., Gavali, A. V., & Yadav, D. B. (2021). Growth and instability in area, production and productivity of soybean in Maharashtra. Int. J. Chem. Stud, 9, 3393-3395.
Segarra, J., Buchaillot, M. L., Araus, J. L., & Kefauver, S. C. (2020).Remote sensing for precision agriculture: Sentinel-2 improved features and applications. Agronomy, 10(5), 641. https://doi.org/10.3390/agronomy10050641
Kayad, A., Sozzi, M., Gatto, S., Marinello, F., & Pirotti, F. (2019). Monitoring within-field variability of corn yield using Sentinel-2 and machine learning techniques.Remote Sensing, 11(23), 2873. https://doi.org/10.3390/rs11232873
Holtgrave, A. K., & Förster, M. (2020). Comparing Sentinel-1 and Sentinel-2 data and indices for agricultural vegetation monitoring. Remote Sensing, 12(18), 2919. https://doi.org/10.3390/rs12182919
Abubakar, G. A., Wang, K., Shahtahamssebi, A., Xue, X., Belete, M., Gudo, A. J. A., ... & Gan, M. (2020). Mapping maize fields by using multi-temporal Sentinel-1A and Sentinel-2A images in Makarfi, Northern Nigeria, Africa. Sustainability, 12(6), 2539.
Tiede, D., Sudmanns, M., Augustin, H., & Baraldi, A. (2021). Investigating ESA Sentinel-2 products' systematic cloud cover overestimation in very high altitude areas. Remote Sensing of Environment, 252, 112163.
Řezník, T., Chytrý, J., & Trojanová, K. (2021). Machine learning-based processing proof-of-concept pipeline for semi-automatic sentinel-2 imagery download, cloudiness filtering, classifications, and updates of open land use/land cover datasets. ISPRS International Journal of Geo-Information, 10(2), 102.
Khoirunnisa, F., Supriatna, & Wibowo, A. (2020, March). Using NDVI algorithm in Sentinel-2A imagery for rice productivity estimation (Case study: Compreng sub-district, Subang Regency, West Java). In IOP Conference Series: Earth and Environmental Science (Vol. 481, No. 1, p. 012064). IOP Publishing.
Samsuri, Zaitunah, A., Meliani, S., Syahputra, O. K., Budiharta, S., Susilowati, A., ... & Azhar, I. (2021, November). Mapping of mangrove forest tree density using Sentinel 2A satelit image in remained natural mangrove forest of Sumatra eastern coastal. In IOP Conference Series: Earth and Environmental Science (Vol. 912, No. 1, p. 012001). IOP Publishing.
Crema, A., Boschetti, M., Nutini, F., Cillis, D., & Casa, R. (2020). Influence of soil properties on maize and wheat nitrogen status assessment from Sentinel-2 data. Remote Sensing, 12(14), 2175.
Erunova, M. G., & Gosteva, A. A. (2021). Use of high-resolution images in local area management tasks. GI SUPPORT OF SUSTAINABLE DEVELOPMENT OF TERRITORIES, 264.
Hamidi, M., Safari, A., & Homayouni, S. (2021). An auto-encoder based classifier for crop mapping from multitemporal multispectral imagery. International Journal of Remote Sensing, 42(3), 986-1016.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
