RESUMO
Sustainable fertilizer management in precision agriculture is essential for both economic and environmental reasons. To effectively manage fertilizer input, various methods are employed to monitor and track plant nutrient status. One such method is hyperspectral imaging, which has been on the rise in recent times. It is a remote sensing tool used to monitor plant physiological changes in response to environmental conditions and nutrient availability. However, conventional hyperspectral processing mainly focuses on either the spectral or spatial information of plants. This study aims to develop a hybrid convolution neural network (CNN) capable of simultaneously extracting spatial and spectral information from quinoa and cowpea plants to identify their nutrient status at different growth stages. To achieve this, a nutrient experiment with four treatments (high and low levels of nitrogen and phosphorus) was conducted in a glasshouse. A hybrid CNN model comprising a 3D CNN (extracts joint spectral-spatial information) and a 2D CNN (for abstract spatial information extraction) was proposed. Three pre-processing techniques, including second-order derivative, standard normal variate, and linear discriminant analysis, were applied to selected regions of interest within the plant spectral hypercube. Together with the raw data, these datasets were used as inputs to train the proposed model. This was done to assess the impact of different pre-processing techniques on hyperspectral-based nutrient phenotyping. The performance of the proposed model was compared with a 3D CNN, a 2D CNN, and a Hybrid Spectral Network (HybridSN) model. Effective wavebands were selected from the best-performing dataset using a greedy stepwise-based correlation feature selection (CFS) technique. The selected wavebands were then used to retrain the models to identify the nutrient status at five selected plant growth stages. From the results, the proposed hybrid model achieved a classification accuracy of over 94% on the test dataset, demonstrating its potential for identifying nitrogen and phosphorus status in cowpea and quinoa at different growth stages.
RESUMO
Image segmentation is a fundamental but critical step for achieving automated high- throughput phenotyping. While conventional segmentation methods perform well in homogenous environments, the performance decreases when used in more complex environments. This study aimed to develop a fast and robust neural-network-based segmentation tool to phenotype plants in both field and glasshouse environments in a high-throughput manner. Digital images of cowpea (from glasshouse) and wheat (from field) with different nutrient supplies across their full growth cycle were acquired. Image patches from 20 randomly selected images from the acquired dataset were transformed from their original RGB format to multiple color spaces. The pixels in the patches were annotated as foreground and background with a pixel having a feature vector of 24 color properties. A feature selection technique was applied to choose the sensitive features, which were used to train a multilayer perceptron network (MLP) and two other traditional machine learning models: support vector machines (SVMs) and random forest (RF). The performance of these models, together with two standard color-index segmentation techniques (excess green (ExG) and excess green-red (ExGR)), was compared. The proposed method outperformed the other methods in producing quality segmented images with over 98%-pixel classification accuracy. Regression models developed from the different segmentation methods to predict Soil Plant Analysis Development (SPAD) values of cowpea and wheat showed that images from the proposed MLP method produced models with high predictive power and accuracy comparably. This method will be an essential tool for the development of a data analysis pipeline for high-throughput plant phenotyping. The proposed technique is capable of learning from different environmental conditions, with a high level of robustness.
RESUMO
Globally it has been estimated that only one third of applied N is recovered in the harvested component of grain crops. This represents an incredible waste of resource and the overuse has detrimental environmental and economic consequences. There is substantial variation in nutrient use efficiency (NUE) from region to region, between crops and in different cropping systems. As a consequence, both local and crop specific solutions will be required for NUE improvement at local as well as at national and international levels. Strategies to improve NUE will involve improvements to germplasm and optimized agronomy adapted to climate and location. Essential to effective solutions will be an understanding of genetics (G), environment (E), and management (M) and their interactions (G x E x M). Implementing appropriate solutions will require agronomic management, attention to environmental factors and improved varieties, optimized for current and future climate scenarios. As NUE is a complex trait with many contributing processes, identifying the correct trait for improvement is not trivial. Key processes include nitrogen capture (uptake efficiency), utilization efficiency (closely related to yield), partitioning (harvest index: biochemical and organ-specific) and trade-offs between yield and quality aspects (grain nitrogen content), as well as interactions with capture and utilization of other nutrients. A long-term experiment, the Broadbalk experiment at Rothamsted, highlights many factors influencing yield and nitrogen utilization in wheat over the last 175 years, particularly management and yearly variation. A more recent series of trials conducted over the past 16 years has focused on separating the key physiological sub-traits of NUE, highlighting both genetic and seasonal variation. This perspective describes these two contrasting studies which indicate G x E x M interactions involved in nitrogen utilization and summarizes prospects for the future including the utilization of high throughput phenotyping technology.