Scientific- Research Quarterly of Geographical Data (SEPEHR)

Scientific- Research Quarterly of Geographical Data (SEPEHR)

Monitoring chlorophyll in rice fields using Sentinel 2 and UAV images and applying machine learning

Document Type : Research Paper

Authors
َAbdollah Ehsanpour 1
Ebadat Ghanbari Parmehr 2
Shamim Amini 3
1 MSc student ,Babol Noshirvani University of technology, Faculty of civil engineering, Babol, Iran
2 Assistant professor , Babol Noshirvani University of technology, Faculty of civil engineering, Babol, Iran
3 Advisor, Natural resources and watershed management organization, Sari, Iran
10.22131/sepehr.2025.2045093.3102
Abstract
Extended Abstract
Introduction
This study provides a comprehensive analysis of the relationship between vegetation indices and chlorophyll variation at different growth stages of rice fields in northern Iran, employing the latest advancements in remote sensing and precision agriculture technologies. Mineral nutrition plays a crucial role in plant growth and development, significantly influencing the yield and quality of rice crops. Understanding the dynamics of chlorophyll and its spatial distribution is crucial for optimizing fertilization practices, improving crop productivity, and ensuring sustainable agricultural practices.
Materials & Methods
In this research, a multifaceted approach that combined data from Sentinel-2 satellite imagery was utilized, UAV (Unmanned Aerial Vehicle) imagery equipped with RGB sensors, and ground-based SPAD (Soil Plant Analysis Development) measurements. Sentinel-2 imagery data is known for its high-resolution multispectral capabilities, which allow for detailed monitoring of vegetation health and land use changes over large geographical areas. The satellite's ability to capture multiple spectral bands enhances our capacity to assess various vegetation indices, including the Normalized Difference Vegetation Index (NDVI), which is widely used to evaluate plant health and growth conditions. UAV imagery complements the satellite data by providing high-resolution, fine-scale detail that can be captured at specific times during the crop's growth cycle. The flexibility of UAVs enables targeted data collection, allows monitoring critical growth stages and variations in chlorophyll levels that may not be detectable through satellite imagery alone. By integrating both data sources, it is aimed to generate a comprehensive understanding of the relationship between chlorophyll and vegetation indices across different spatial and temporal dimensions. The primary objective was to develop predictive models for NDVI, a key indicator of vegetation health that correlates closely with chlorophyll concentration and fertilization need in plants. To achieve this, three machine learning algorithms: Random Forest Regression (RFR), Support Vector Regression (SVR), and Multi-Layer Perceptron Regression (MLPR) was employed. Each algorithm offers unique strengths in handling complex datasets and capturing non-linear relationships, which are common in agronomic data.
Results & Discussion
The results of analysis indicated that the RFR algorithm outperformed the other two models, achieving a correlation coefficient of 0.80 when predicting NDVI from UAV imagery. This strong correlation suggests that RFR effectively captures the intricate relationships between the spectral reflectance values obtained from UAV images and the underlying nutrition content in the rice fields. The high predictive accuracy of the RFR model highlights its potential for practical applications in precision agriculture, where timely and accurate assessments of crop health are essential for informed decision-making. In addition to predicting NDVI, the Kriging spatial interpolation technique was utilized to generate detailed chlorophyll distribution maps based on the SPAD data collected from the field. Kriging is a powerful geostatistical method that allows for optimal estimation of unmeasured locations based on observed data, providing insights into spatial variations in chlorophyll across the rice fields. The generated chlorophyll maps revealed significant correlations with NDVI, confirming that remote sensing techniques can effectively monitor nutrient dynamics and assess the overall health of crops. The findings of this research underscore the potential of integrating UAV and satellite data through machine learning techniques and advanced image processing methods for resource management in agriculture. By providing farmers with precise information regarding chlorophyll levels and vegetation health, these technologies enable more informed decision-making processes. For instance, farmers can optimize fertilization strategies by applying mineral nutrition only where it is needed and in the appropriate amounts, thereby maximizing crop yield while minimizing environmental impacts. The integration of remote sensing and precision agriculture technologies can contribute to broader goals of sustainable agriculture. As the global population continues to rise, the demand for food production increases, necessitating innovative approaches to enhance agricultural productivity while conserving natural resources.
Conclusion
In conclusion, this study illustrates the effective use of remote sensing and machine learning technologies in analyzing the relationship between vegetation indices and chlorophyll variation in rice fields. The successful prediction of NDVI using the RFR algorithm, alongside the generation of chlorophyll distribution maps through Kriging, highlights the potential of these methods to enhance agricultural practices. Further research is needed to explore the applicability of these techniques across different crops and regions, paving the way for broader implementation of precision agriculture strategies. Ultimately, this research contributes to the growing body of knowledge on sustainable agricultural practices, emphasizing the role of technology in supporting farmers and promoting efficient resource management. By fostering greater collaboration between researchers, agricultural practitioners, and technology developers, the field of precision agriculture can advance and address the challenges faced by modern farming in a rapidly changing world.
Keywords
Rice
Precision agriculture
Chlorophyll
NDVI
Machine Learning Algorithms
Sentinel-2 Images
UAV Images
Subjects
1- Ata-Ul-Karim, S. T., Liu, X., Lu, Z., Zheng, H., Cao, W., & Zhu, Y. (2017). Estimation of nitrogen fertilizer requirement for rice crop using critical nitrogen dilution curve. Field Crops Research, 201, 32-40.
2- Beck, H. E., Zimmermann, N. E., McVicar, T. R., Vergopolan, N., Berg, A., & Wood, E. F. (2018). Present and future Köppen-Geiger climate classification maps at 1-km resolution. Scientific Data, 5(1), 180214. doi:10.1038/sdata.2018.214
3- Bendig, J., Yu, K., Aasen, H., Bolten, A., Bennertz, S., Broscheit, J., . . . Bareth, G. (2015). Combining UAV-based plant height from crop surface models, visible, and near infrared vegetation indices for biomass monitoring in barley. International Journal of Applied Earth Observation and Geoinformation, 39, 79-87.
4- Bilonick, R. A. (1991). An introduction to applied geostatistics. In: Taylor & Francis.
5- Breiman, L. (2001). Random forests. Machine learning, 45, 5-32.
6- Cui, P., Sheng, X., Chen, Z., Ning, Q., Zhang, H., Lu, H., & Zhang, H. (2024). Optimizing One-Time Nitrogen Fertilization for Rice Production Using Controlled-Release Urea and Urease Inhibitors. Agronomy, 14(1). doi:10.3390/agronomy14010067
7- Darzi-Naftchali, A. (2016). Rice Cultivation Management in Mazandaran Province under. Water Research in Agriculture, 14.
8- Drucker, H., Burges, C. J., Kaufman, L., Smola, A., & Vapnik, V. (1996). Support vector regression machines. Advances in neural information processing systems, 9.
9- Elansari, T., Ouanan, M., & Bourray, H. (2023). Modeling of Multilayer Perceptron Neural Network Hyperparameter Optimization and Training.
10- Eugenio, F. C., Grohs, M., Schuh, M., Venancio, L. P., Schons, C., Badin, T. L., . . . Fantinel, R. A. (2023). Estimated flooded rice grain yield and nitrogen content in leaves based on RPAS images and machine learning. Field Crops Research, 292, 108823. doi:https://doi.org/10.1016/j.fcr.2023.108823
11- FAO. (2023). RICE SCENARIO. Retrieved from https://www.fao.org/3/w8595t/w8595t05.htm
12- Gamon, J. A., & Surfus, J. S. (1999). Assessing leaf pigment content and activity with a reflectometer. The New Phytologist, 143(1), 105-117.
13- Gardner, M. W., & Dorling, S. R. (1998). Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences. Atmospheric environment, 32(14-15), 2627-2636.
14- Gitelson, A. A., Kaufman, Y. J., Stark, R., & Rundquist, D. (2002). Novel algorithms for remote estimation of vegetation fraction. Remote Sensing of Environment, 80(1), 76-87. doi:https://doi.org/10.1016/S0034-4257(01)00289-9
15- Habibi, E., Niknejad, Y., Fallah, H., Dastan, S., & Tari, D. B. (2019). Life cycle assessment of rice production systems in different paddy field size levels in north of Iran. Environmental Monitoring and Assessment, 191(4), 202. doi:10.1007/s10661-019-7344-0
16- Harwin, S., & Lucieer, A. (2012). Assessing the accuracy of georeferenced point clouds produced via multi-view stereopsis from unmanned aerial vehicle (UAV) imagery. Remote Sensing, 4(6), 1573-1599.
17- Hawkesford, M. J. (2014). Reducing the reliance on nitrogen fertilizer for wheat production. Journal of cereal science, 59(3), 276-283.
18- Ho, T. K. (1998). The random subspace method for constructing decision forests. IEEE transactions on pattern analysis and machine intelligence, 20(8), 832-844.
19- Janssen, B. H. (1998). Efficient use of nutrients: an art of balancing. Field Crops Research, 56(1-2), 197-201.
20- Ju, X. T., Kou, C. L., Zhang, F. S., & Christie, P. (2006). Nitrogen balance and groundwater nitrate contamination: comparison among three intensive cropping systems on the North China Plain. Environmental pollution, 143(1), 117-125.
21- Li, Z., Jin, X., Yang, G., Drummond, J., Yang, H., Clark, B., . . . Zhao, C. (2018). Remote sensing of leaf and canopy nitrogen status in winter wheat (Triticum aestivum L.) based on N-PROSAIL model. Remote Sensing, 10(9), 1463.
22- Luo, S., Jiang, X., Yang, K., Li, Y., & Fang, S. (2022). Multispectral remote sensing for accurate acquisition of rice phenotypes: Impacts of radiometric calibration and unmanned aerial vehicle flying altitudes. Frontiers in Plant Science, 13, 958106.
23- Metheron, G. (1963). Principles of geostatistics, economic geology. Economic Geology, 58(8), 1246-1266.
24- Meyer, G. E., & Neto, J. C. (2008). Verification of color vegetation indices for automated crop imaging applications. Computers and Electronics in Agriculture, 63(2), 282-293.
25- Mountrakis, G., Im, J., & Ogole, C. (2011). Support vector machines in remote sensing: A review. ISPRS Journal of Photogrammetry and Remote Sensing, 66(3), 247-259.
26- Ouyang, Q., Lu, W., Xin, X., Zhang, Y., Cheng, W., & Yu, T. (2016). Monthly rainfall forecasting using EEMD-SVR based on phase-space reconstruction. Water resources management, 30, 2311-2325.
27- Paliwal, A., Laborte, A., Nelson, A., & Singh, R. (2019). Salinity stress detection in rice crops using time series MODIS VI data. International journal of remote sensing, 40(21), 8186-8202.
28- Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., . . . Dubourg, V. (2011). Scikit-learn: Machine learning in Python. the Journal of machine Learning research, 12, 2825-2830.
29- Penalun, F. E., Hermawan, A., & Avianto, D. (2023). Perbandingan Random Forest Regression dan Support Vector Regression Pada Prediksi Laju Penguapan. JURNAL FASILKOM, 13(02), 104-111.
30- Possoch, M., Bieker, S., Hoffmeister, D., Bolten, A., Schellberg, J., & Bareth, G. (2016). Multi-temporal crop surface models combined with the RGB vegetation index from UAV-based images for forage monitoring in grassland. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 41, 991-998.
31- Qin, Y., Xiao, X., Dong, J., Zhou, Y., Zhu, Z., Zhang, G., . . . Wang, J. (2015). Mapping paddy rice planting area in cold temperate climate region through analysis of time series Landsat 8 (OLI), Landsat 7 (ETM+) and MODIS imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 105, 220-233.
32- Rabatel, G., Gorretta, N., & Labbé, S. (2011). Getting NDVI spectral bands from a single standard RGB digital camera: a methodological approach.
33- Sandunil, K., Bennour, Z., Ben Mahmud, H., & Giwelli, A. (2023). Effects of Tuning Hyperparameters in Random Forest Regression on Reservoir’s Porosity Prediction. Case Study: Volve Oil Field, North Sea.
34- Sellaro, R., Crepy, M., Trupkin, S. A., Karayekov, E., Buchovsky, A. S., Rossi, C., & Casal, J. J. (2010). Cryptochrome as a sensor of the blue/green ratio of natural radiation in Arabidopsis. Plant physiology, 154(1), 401-409.
35- Soltani, A., Alimagham, S. M., Nehbandani, A., Torabi, B., Zeinali, E., Zand, E., . . . van Ittersum, M. K. (2020). Future food self-sufficiency in Iran: A model-based analysis. Global Food Security, 24, 100351. doi:https://doi.org/10.1016/j.gfs.2020.100351
36- Suykens, J. A. K., & Vandewalle, J. (1999). Least squares support vector machine classifiers. Neural processing letters, 9, 293-300.
37- Swan, A. (1998). GOOVAERTS, P. 1997. Geostatistics for Natural Resources Evaluation. Applied Geostatistics Series. xiv+ 483 pp. New York, Oxford: Oxford University Press. Price£ 46.95 (hard covers). ISBN 0 19 511538 4. Geological Magazine, 135(6), 819-842.
38- Verma, A., & Kumar, D. (2020). Multilayer Perceptron Artificial Neural Network: A Review. In (pp. 1-38).
39- Wei, F., Yan, Z., & Xia, Y. (2008). Monitoring plant nitrogen accumulation dynamics with hyperspectral remote sensing in wheat. Scientia Agricultura Sinica.
40- Woebbecke, D. M., Meyer, G. E., Von Bargen, K., & Mortensen, D. A. (1993). Plant species identification, size, and enumeration using machine vision techniques on near-binary images.
41- Woebbecke, D. M., Meyer, G. E., Von Bargen, K., & Mortensen, D. A. (1995). Color indices for weed identification under various soil, residue, and lighting conditions. Transactions of the ASAE, 38(1), 259-269.
42- Wolfe, A. H., & Patz, J. A. (2002). Reactive nitrogen and human health: acute and long-term implications. Ambio: A journal of the human environment, 31(2), 120-125.
43- Yang, G., Li, Y., Yuan, S., Zhou, C., Xiang, H., Zhao, Z., . . . Xu, L. (2024). Enhancing direct-seeded rice yield prediction using UAV-derived features acquired during the reproductive phase. Precision Agriculture, 25(2), 1014-1037.
44- Yuan, Y., Wang, X., Shi, M., & Wang, P. (2022). Performance comparison of RGB and multispectral vegetation indices based on machine learning for estimating Hopea hainanensis SPAD values under different shade conditions. Frontiers in Plant Science, 13, 928953.
45- Zhao, Q., Lenz-Wiedemann, V. I. S., Yuan, F., Jiang, R., Miao, Y., Zhang, F., & Bareth, G. (2015). Investigating Within-Field Variability of Rice from High Resolution Satellite Imagery in Qixing Farm County, Northeast China. ISPRS International Journal of Geo-Information, 4(1), 236-261. doi:10.3390/ijgi4010236
46- Zhao, R., Li, Y., & Ma, M. (2021). Mapping paddy rice with satellite remote sensing: a review. Sustainability, 13(2), 503.