Search for: All records

The use of small unmanned aerial system (UAS)-based structure-from-motion (SfM; photogrammetry) and LiDAR point clouds has been widely discussed in the remote sensing community. Here, we compared multiple aspects of the SfM and the LiDAR point clouds, collected concurrently in five UAS flights experimental fields of a short crop (snap bean), in order to explore how well the SfM approach performs compared with LiDAR for crop phenotyping. The main methods include calculating the cloud-to-mesh distance (C2M) maps between the preprocessed point clouds, as well as computing a multiscale model-to-model cloud comparison (M3C2) distance maps between the derived digital elevation models (DEMs) and crop height models (CHMs). We also evaluated the crop height and the row width from the CHMs and compared them with field measurements for one of the data sets. Both SfM and LiDAR point clouds achieved an average RMSE of ~0.02 m for crop height and an average RMSE of ~0.05 m for row width. The qualitative and quantitative analyses provided proof that the SfM approach is comparable to LiDAR under the same UAS flight settings. However, its altimetric accuracy largely relied on the number and distribution of the ground control points. 

Accurate, precise, and timely estimation of crop yield is key to a grower’s ability to proactively manage crop growth and predict harvest logistics. Such yield predictions typically are based on multi-parametric models and in-situ sampling. Here we investigate the extension of a greenhouse study, to low-altitude unmanned aerial systems (UAS). Our principal objective was to investigate snap bean crop (Phaseolus vulgaris) yield using imaging spectroscopy (hyperspectral imaging) in the visible to near-infrared (VNIR; 400–1000 nm) region via UAS. We aimed to solve the problem of crop yield modelling by identifying spectral features explaining yield and evaluating the best time period for accurate yield prediction, early in time. We introduced a Python library, named Jostar, for spectral feature selection. Embedded in Jostar, we proposed a new ranking method for selected features that reaches an agreement between multiple optimization models. Moreover, we implemented a well-known denoising algorithm for the spectral data used in this study. This study benefited from two years of remotely sensed data, captured at multiple instances over the summers of 2019 and 2020, with 24 plots and 18 plots, respectively. Two harvest stage models, early and late harvest, were assessed at two different locations in upstate New York, USA. Six varieties of snap bean were quantified using two components of yield, pod weight and seed length. We used two different vegetation detection algorithms. the Red-Edge Normalized Difference Vegetation Index (RENDVI) and Spectral Angle Mapper (SAM), to subset the fields into vegetation vs. non-vegetation pixels. Partial least squares regression (PLSR) was used as the regression model. Among nine different optimization models embedded in Jostar, we selected the Genetic Algorithm (GA), Ant Colony Optimization (ACO), Simulated Annealing (SA), and Particle Swarm Optimization (PSO) and their resulting joint ranking. The findings show that pod weight can be explained with a high coefficient of determination (R2 = 0.78–0.93) and low root-mean-square error (RMSE = 940–1369 kg/ha) for two years of data. Seed length yield assessment resulted in higher accuracies (R2 = 0.83–0.98) and lower errors (RMSE = 4.245–6.018 mm). Among optimization models used, ACO and SA outperformed others and the SAM vegetation detection approach showed improved results when compared to the RENDVI approach when dense canopies were being examined. Wavelengths at 450, 500, 520, 650, 700, and 760 nm, were identified in almost all data sets and harvest stage models used. The period between 44–55 days after planting (DAP) the optimal time period for yield assessment. Future work should involve transferring the learned concepts to a multispectral system, for eventual operational use; further attention should also be paid to seed length as a ground truth data collection technique, since this yield indicator is far more rapid and straightforward. 

Timely and accurate monitoring has the potential to streamline crop management, harvest planning, and processing in the growing table beet industry of New York state. We used unmanned aerial system (UAS) combined with a multispectral imager to monitor table beet (Beta vulgaris ssp. vulgaris) canopies in New York during the 2018 and 2019 growing seasons. We assessed the optimal pairing of a reflectance band or vegetation index with canopy area to predict table beet yield components of small sample plots using leave-one-out cross-validation. The most promising models were for table beet root count and mass using imagery taken during emergence and canopy closure, respectively. We created augmented plots, composed of random combinations of the study plots, to further exploit the importance of early canopy growth area. We achieved a R2 = 0.70 and root mean squared error (RMSE) of 84 roots (~24%) for root count, using 2018 emergence imagery. The same model resulted in a RMSE of 127 roots (~35%) when tested on the unseen 2019 data. Harvested root mass was best modeled with canopy closing imagery, with a R2 = 0.89 and RMSE = 6700 kg/ha using 2018 data. We applied the model to the 2019 full-field imagery and found an average yield of 41,000 kg/ha (~40,000 kg/ha average for upstate New York). This study demonstrates the potential for table beet yield models using a combination of radiometric and canopy structure data obtained at early growth stages. Additional imagery of these early growth stages is vital to develop a robust and generalized model of table beet root yield that can handle imagery captured at slightly different growth stages between seasons. 

The agricultural industry suffers from a significant amount of food waste, some of which originates from an inability to apply site-specific management at the farm-level. Snap bean, a broad-acre crop that covers hundreds of thousands of acres across the USA, is not exempt from this need for informed, within-field, and spatially-explicit management approaches. This study aimed to assess the utility of machine learning algorithms for growth stage and pod maturity classification of snap bean (cv. Huntington), as well as detecting and discriminating spectral and biophysical features that lead to accurate classification results. Four major growth stages and six main sieve size pod maturity levels were evaluated for growth stage and pod maturity classification, respectively. A point-based in situ spectroradiometer in the visible-near-infrared and shortwave-infrared domains (VNIR-SWIR; 400–2500 nm) was used and the radiance values were converted to reflectance to normalize for any illumination change between samples. After preprocessing the raw data, we approached pod maturity assessment with multi-class classification and growth stage determination with binary and multi-class classification methods. Results from the growth stage assessment via the binary method exhibited accuracies ranging from 90–98%, with the best mathematical enhancement method being the continuum-removal approach. The growth stage multi-class classification method used raw reflectance data and identified a pair of wavelengths, 493 nm and 640 nm, in two basic transforms (ratio and normalized difference), yielding high accuracies (~79%). Pod maturity assessment detected narrow-band wavelengths in the VIS and SWIR region, separating between not ready-to-harvest and ready-to-harvest scenarios with classification measures at the ~78% level by using continuum-removed spectra. Our work is a best-case scenario, i.e., we consider it a stepping-stone to understanding snap bean harvest maturity assessment via hyperspectral sensing at a scalable level (i.e., airborne systems). Future work involves transferring the concepts to unmanned aerial system (UAS) field experiments and validating whether or not a simple multispectral camera, mounted on a UAS, could incorporate < 10 spectral bands to meet the need of both growth stage and pod maturity classification in snap bean production. 

Farmers and growers typically use approaches based on the crop environment and local meteorology, many of which are labor-intensive, to predict crop yield. These approaches have found broad acceptance but lack real-time and physiological feedback for near-daily management purposes. This is true for broad-acre crops, such as snap bean, which is valued at hundreds of millions of dollars in the annual agricultural market. We aim to investigate the relationships between snap bean yield and plant spectral and biophysical information, collected using a hyperspectral spectroradiometer (400 to 2500 nm). The experiment focused on 48 single snap bean plants (cv. Huntington) in a controlled greenhouse environment during the growth period (69 days). We used applicable accuracy and precision metrics from partial least squares regression and cross-validation methods to evaluate the predictive ability of two harvest stages, namely an early-harvest and late-harvest stage, against our yield indicator (bean pod weight). Four different spectral data sets were used to investigate whether such oversampled, hyperspectral data sets could accurately and precisely model observed variability in yield, in terms of the coefficient of determination (R2) and root-mean-square error (RMSE). The objective of our approach hinges on the philosophy that selected spectral bands from this study, i.e., those that best explain yield variability, can be downsampled from a hyperspectral system for use in a more cost-effective, operational multispectral sensor. Our results suggested the optimal period for spectral evaluation of snap bean yield is 20 to 25 or 32 days prior to harvest for the early- and late-harvest stages, respectively, with the best model performing at a low RMSE (3.02 g/plant) and a high coefficient of determination (R2 = 0.72). An unmanned aerial systems-mounted, affordable, and wavelength-programmable multispectral imager, with bands corresponding to those identified, could provide a near real-time and reliable yield estimate prior to harvest.