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.