Search

Tar spot is a foliar disease of corn characterized by fungal fruiting bodies that resemble tar spots. The disease emerged in the U.S. in 2015, and severe outbreaks in 2018 caused an economic impact on corn yields throughout the Midwest. Adequate epidemiological surveillance and disease quantification are necessary to develop immediate and long-term management strategies. This study presents a measurement framework that evaluates the disease severity of tar spot using unmanned aircraft systems (UAS)-based plant phenotyping and regression techniques. UAS-based plant phenotypic information, such as canopy cover, canopy volume, and vegetation indices, were used as explanatory variables. Visual estimations of disease severity were performed by expert plant pathologists per experiment plot basis and used as response variables. Three regression methods, namely ordinary least squares (OLS), support vector regression (SVR), and multilayer perceptron (MLP), were used to determine an optimal regression method for UAS-based tar spot measurement. The cross-validation results showed that the regression model based on MLP provides the highest accuracy of disease measurements. By training and testing the model with spatially separated datasets, the proposed regression model achieved a Lin’s concordance correlation coefficient (ρc) of 0.82 and a root mean square error (RMSE) of 6.42. This study demonstrated that we could use the proposed UAS-based method for the disease quantification of tar spot, which shows a gradual spectral response as the disease develops.

Immense growth is witnessed in the application of unmanned aircraft systems (UAS) for precision agriculture in recent years. Though UAS can provide precise high spatial resolution data, large aerial coverage is still practically not feasible due to limited battery, flight time and large size of the data. Contrarily, satellite images cover larger area but provide coarser spatial resolution data compared to UAS imagery. The objective of this research was to combine UAS's ability to provide precise high spatial resolution data with the vast areal coverage provided by satellite data to estimate canopy parameters. Experimental field was divided into 10m x 10m grids to match Sentinel-2 pixel size. High resolution UAS data was collected covering the entire experimental field over which grid-wise canopy parameters were computed such as canopy height and canopy volume. Using artificial neural networks (ANN) based regression model, a relationship was developed between Sentinel-2 pixel values and UAS based canopy parameters with R2 greater than 0.9. ANN model results were also compared with support vector machine (SVM) regression model results.

Assessing plant population of cotton is important to make replanting decisions in low plant density areas, prone to yielding penalties. Since the measurement of plant population in the field is labor intensive and subject to error, in this study, a new approach of image-based plant counting is proposed, using unmanned aircraft systems (UAS; DJI Mavic 2 Pro, Shenzhen, China) data. The previously developed image-based techniques required a priori information of geometry or statistical characteristics of plant canopy features, while also limiting the versatility of the methods in variable field conditions. In this regard, a deep learning-based plant counting algorithm was proposed to reduce the number of input variables, and to remove requirements for acquiring geometric or statistical information. The object detection model named You Only Look Once version 3 (YOLOv3) and photogrammetry were utilized to separate, locate, and count cotton plants in the seedling stage. The proposed algorithm was tested with four different UAS datasets, containing variability in plant size, overall illumination, and background brightness. Root mean square error (RMSE) and R2 values of the optimal plant count results ranged from 0.50 to 0.60 plants per linear meter of row (number of plants within 1 m distance along the planting row direction) and 0.96 to 0.97, respectively. The object detection algorithm, trained with variable plant size, ground wetness, and lighting conditions generally resulted in a lower detection error, unless an observable difference of developmental stages of cotton existed. The proposed plant counting algorithm performed well with 0–14 plants per linear meter of row, when cotton plants are generally separable in the seedling stage. This study is expected to provide an automated methodology for in situ evaluation of plant emergence using UAS data.

Modern agriculture and food production systems are facing increasing pressures from climate change, land and water availability, and, more recently, a pandemic. These factors are threatening the environmental and economic sustainability of current and future food supply systems. Scientific and technological innovations are needed more than ever to secure enough food for a fast-growing global population. Scientific advances have led to a better understanding of how various components of the agricultural system interact, from the cell to the field level. Despite incredible advances in genetic tools over the past few decades, our ability to accurately assess crop status in the field, at scale, has been severely lacking until recently. Thanks to recent advances in remote sensing and Artificial Intelligence (AI), we can now quantify field scale phenotypic information accurately and integrate the big data into predictive and prescriptive management tools. This review focuses on the use of recent technological advances in remote sensing and AI to improve the resilience of agricultural systems, and we will present a unique opportunity for the development of prescriptive tools needed to address the next decade's agricultural and human nutrition challenges.

This study presents a comparative study of multispectral and RGB (red, green, and blue) sensor-based cotton canopy cover modelling using multi-temporal unmanned aircraft systems (UAS) imagery. Additionally, a canopy cover model using an RGB sensor is proposed that combines an RGB-based vegetation index with morphological closing. The field experiment was established in 2017 and 2018, where the whole study area was divided into approximately 1 x 1 m size grids. Grid-wise percentage canopy cover was computed using both RGB and multispectral sensors over multiple flights during the growing season of the cotton crop. Initially, the normalized difference vegetation index (NDVI)-based canopy cover was estimated, and this was used as a reference for the comparison with RGB-based canopy cover estimations. To test the maximum achievable performance of RGB-based canopy cover estimation, a pixel-wise classification method was implemented. Later, four RGB-based canopy cover estimation methods were implemented using RGB images, namely Canopeo, the excessive greenness index, the modified red green vegetation index and the red green blue vegetation index. The performance of RGB-based canopy cover estimation was evaluated using NDVI-based canopy cover estimation. The multispectral sensor-based canopy cover model was considered to be a more stable and accurately estimating canopy cover model, whereas the RGB-based canopy cover model was very unstable and failed to identify canopy when cotton leaves changed color after canopy maturation. The application of a morphological closing operation after the thresholding significantly improved the RGB-based canopy cover modeling. The red green blue vegetation index turned out to be the most efficient vegetation index to extract canopy cover with very low average root mean square error (2.94% for the 2017 dataset and 2.82% for the 2018 dataset), with respect to multispectral sensor-based canopy cover estimation. The proposed canopy cover model provides an affordable alternate of the multispectral sensors which are more sensitive and expensive.

Unmanned aerial vehicle (UAV) platforms with sensors covering the red-edge and near-infrared (NIR) bands to measure vegetation indices (VIs) have been recently introduced in agriculture research. Consequently, VIs originally developed for traditional airborne and spaceborne sensors have become applicable to UAV systems. In this study, we investigated the difference in tillage treatments for cotton and sorghum using various RGB and NIR VIs. Minimized tillage has been known to increase farm sustainability and potentially optimize productivity over time; however, repeated tillage is the most commonly-adopted management practice in agriculture. To this day, quantitative comparisons of plant growth patterns between conventional tillage (CT) and no tillage (NT) fields are often inconsistent. In this study, high-resolution and multi-temporal UAV data were used for the analysis of tillage effects on plant health and the performance of various vegetation indices investigated. Time series data over ten dates were acquired on a weekly basis by RGB and multispectral (MS) UAV platforms: a DJI Phantom 4 Pro and a DJI Matrice 100 with the SlantRange 3p sensor. Ground reflectance panels and an ambient illumination sensor were used for the radiometric calibration of RGB and MS orthomosaic images, respectively. Various RGB and NIR-based vegetation indices were then calculated for the comparison between CT and NT treatments. In addition, a one-tailed Z-test was conducted to check the significance of VIs’ difference between CT and NT treatments. The results showed distinct differences in VIs between tillage treatments during the whole growing season. NIR-based VIs showed better discrimination performance than RGB-based VIs. Out of 13 VIs, the modified soil adjusted vegetation index (MSAVI) and optimized soil adjusted vegetation index (OSAVI) showed better performance in terms of quantitative difference measurements and the Z-test between tillage treatments. The modified green red vegetation index (MGRVI) and excess green (ExG) showed reliable separability and can be an alternative for economic RGB UAV application.

A partitional clustering-based segmentation is used to carry out supervised classification for hyperspectral images. The main contribution of this study lies in the use of projected and correlation partitional clustering techniques to perform image segmentation. These types of clustering techniques have the capability to concurrently perform clustering and feature/band reduction, and are also able to identify different sets of relevant features for different clusters. Using these clustering techniques segmentation map is obtained, which is combined with the pixel-level support vector machines (SVM) classification result, using majority voting. Experiments are conducted over two hyperspectral images. Combination of pixel-level classification result with the segmentation maps leads to significant improvement of accuracies in both the images. Additionally, it is also observed that, classified maps obtained using SVM combined with projected and correlation clustering techniques results in higher accur...