Field-Based Calibration of Unmanned Aerial Vehicle Thermal Infrared Imagery with Temperature-Controlled References.

Accurate and reliable calibration methods are required when applying unmanned aerial vehicle (UAV)-based thermal remote sensing in precision agriculture for crop stress monitoring, irrigation planning, and harvesting. The primary objective of this study was to improve the calibration accuracies of UAV-based thermal images using temperature-controlled ground references. Two temperature-controlled ground references were installed in the field to serve as high- and low-temperature references, approximately spanning the expected range of crop surface temperatures during the growing season. Our results showed that the proposed method using temperature-controlled references was able to reduce errors due to ambient conditions from 9.29 to 1.68 °C, when tested with validation panels. There was a significant improvement in crop temperature estimation from the thermal image mosaic, as the error reduced from 14.0 °C in the un-calibrated image to 1.01 °C in the calibrated image. Furthermore, a multiple linear regression model (R2 = 0.78; p-value < 0.001; relative RMSE = 2.42%) was established to quantify soil moisture content based on canopy surface temperature and soil type, using UAV-based thermal image data and soil electrical conductivity (ECa) data as the predictor variables.

Accumulation and health risk of heavy metals in vegetables from harmless and organic vegetable production systems of China.

Heavy metal accumulation in vegetables is a growing concern for public health. Limited studies have elucidated the heavy metal accumulation characteristics and health risk of different vegetables produced in different facilities such as greenhouses and open-air fields and under different management modes such as harmless and organic. Given the concern over the aforementioned factors related to heavy metal accumulation, this study selected four typical greenhouse vegetable production bases, short-term harmless greenhouse vegetable base (SHGVB), middle-term harmless greenhouse vegetable base (MHGVB), long-term harmless greenhouse vegetable base (LHGVB), and organic greenhouse vegetable base (OGVB), in Nanjing City, China to study heavy metal accumulation in different vegetables and their associated health risks. Results showed that soils and vegetables from SHGVB and OGVB apparently accumulated fewer certain heavy metals than those from other bases, probably due to fewer planting years and special management, respectively. Greenhouse conditions significantly increased certain soil heavy metal concentrations relative to open-air conditions. However, greenhouse conditions did not significantly increase concentrations of As, Cd, Cu, Hg, and Zn in leaf vegetables. In fact, under greenhouse conditions, Pb accumulation was effectively reduced. The main source of soil heavy metals was the application of large amounts of low-grade fertilizer. There was larger health risk for producers' children to consume vegetables from the three harmless vegetable bases than those of residents' children. The hazard index (HI) over a large area exceeded 1 for these two kinds of children in the MHGVB and LHGVB. There was also a slight risk in the SHGVB for producers' children solely. However, the HI of the whole area of the OGVB for two kinds of children was below 1, suggesting low risk of heavy metal exposure through the food chain. Notably, the contribution rate of Cu and Zn to the HI were high in the four bases, yet current Chinese standards provide no limit for the concentrations of Cu and Zn; thus a potential health risk concerning these metals exists.

A Correlational Study of Two U.S. State Extension Professionals' Behavioral Intentions to Improve Sustainable Food Chains through Precision Farming Practices.

Precision farming provides one of the most important solutions for managing agricultural production to advance global food security. Extending professionals' competencies to promote precision farming practices can increase the adoption rate, ultimately impacting food security. Many studies have addressed barriers to the adoption of precision farming technologies from the farmers' perspective. However, few are available data on the perspectives of extension professionals. Agricultural extension professionals play an important role in innovative agricultural technology adoption. Thus, this study applied four constructs from the unified theory of acceptance and use of technology (UTAUT) model to investigate behavioral intentions to promote precision farming among extension professionals from two extension systems. In total, 102 (N = 102) agricultural extension professionals were surveyed. The results indicated that performance expectancy and social influence were individually significant predictors of extension professional behavioral intentions to promote precision farming technologies. There were no significant differences between the professionals of two extension systems. Gender, age, and years of service did not affect extension professionals' intention to promote precision agriculture technologies. The data suggested the need for training programs to develop advanced competencies to promote agricultural innovation. This study contributes to the future professional development programs for extension professionals on communicating innovations to address food security and sustainability issues.

Spatio-temporal variability of groundwater nitrate concentration in Texas: 1960 to 2010.

Nitrate (NO) is a major contaminant and threat to groundwater quality in Texas. High-NO groundwater used for irrigation and domestic purposes has serious environmental and health implications. The objective of this study was to evaluate spatio-temporal trends in groundwater NO concentrations in Texas on a county basis from 1960 to 2010 with special emphasis on the Texas Rolling Plains (TRP) using the Texas Water Development Board's groundwater quality database. Results indicated that groundwater NO concentrations have significantly increased in several counties since the 1960s. In 25 counties, >30% of the observations exceeded the maximum contamination level (MCL) for NO (44 mg L NO) in the 2000s as compared with eight counties in the 1960s. In Haskell and Knox Counties of the TRP, all observations exceeded the NO MCL in the 2000s. A distinct spatial clustering of high-NO counties has become increasingly apparent with time in the TRP, as indicated by different spatial indices. County median NO concentrations in the TRP region were positively correlated with county-based area estimates of crop lands, fertilized croplands, and irrigated croplands, suggesting a negative impact of agricultural practices on groundwater NO concentrations. The highly transmissive geologic and soil media in the TRP have likely facilitated NO movement and groundwater contamination in this region. A major hindrance in evaluating groundwater NO concentrations was the lack of adequate recent observations. Overall, the results indicated a substantial deterioration of groundwater quality by NO across the state due to agricultural activities, emphasizing the need for a more frequent and spatially intensive groundwater sampling.

Use of synthetic images for training a deep learning model for weed detection and biomass estimation in cotton.

Site-specific treatment of weeds in agricultural landscapes has been gaining importance in recent years due to economic savings and minimal impact on the environment. Different detection methods have been developed and tested for precision weed management systems, but recent developments in neural networks have offered great prospects. However, a major limitation with the neural network models is the requirement of high volumes of data for training. The current study aims at exploring an alternative approach to the use of real images to address this issue. In this study, synthetic images were generated with various strategies using plant instances clipped from UAV-borne real images. In addition, the Generative Adversarial Networks (GAN) technique was used to generate fake plant instances which were used in generating synthetic images. These images were used to train a powerful convolutional neural network (CNN) known as "Mask R-CNN" for weed detection and segmentation in a transfer learning mode. The study was conducted on morningglories (MG) and grass weeds (Grass) infested in cotton. The biomass for individual weeds was also collected in the field for biomass modeling using detection and segmentation results derived from model inference. Results showed a comparable performance between the real plant-based synthetic image (mean average precision for mask-mAPm: 0.60; mean average precision for bounding box-mAPb: 0.64) and real image datasets (mAPm: 0.80; mAPb: 0.81). However, the mixed dataset (real image  + real plant instance-based synthetic image dataset) resulted in no performance gain for segmentation mask whereas a very small performance gain for bounding box (mAPm: 0.80; mAPb: 0.83). Around 40-50 plant instances were sufficient for generating synthetic images that resulted in optimal performance. Row orientation of cotton in the synthetic images was beneficial compared to random-orientation. Synthetic images generated with automatically-clipped plant instances performed similarly to the ones generated with manually-clipped instances. Generative Adversarial Networks-derived fake plant instances-based synthetic images did not perform as effectively as real plant instance-based synthetic images. The canopy mask area predicted weed biomass better than bounding box area with R2 values of 0.66 and 0.46 for MG and Grass, respectively. The findings of this study offer valuable insights for guiding future endeavors oriented towards using synthetic images for weed detection and segmentation, and biomass estimation in row crops.

Long-term tillage effect on with-in season variations in soil conditions and respiration from dryland winter wheat and soybean cropping systems.

Soil respiration from agricultural soils is a major anthropogenic source of CO2 to the atmosphere. With-in season emission of soil CO2 from croplands are affected by changes in weather, tillage, plant row spacing, and plant growth stage. Tillage involves physical turning of soils which accelerate residue decomposition and CO2 emission. No-tillage lacks soil disturbance and residues undergo slower decomposition at the surface. In this study, we compared with-in season soil conditions (temperature and moisture) and soil respiration from two major crops (soybean and winter wheat) by making high temporal frequency measurements using automated chambers at half-hourly intervals. The experiment lasted for 179 days. Total number of measurements made from conventional and no-tillage soybean and winter wheat plots were 6480 and 4456, respectively. Average flux after the winter-dormancy period of wheat was 37% higher in tilled soil compared to no-till soil. However, average flux during the soybean growing season was 8% lower in conventional till compared to no-till soil. This differential response of soil respiration in wheat and soybean was primarily due to tillage-induced changes in surface characteristics (residue cover) and soil environmental conditions (soil temperature and soil moisture). Results from this study can help elucidate relationships for modeling and assessment of field-scale soil CO2 emissions from dryland wheat and soybean crops grown in sub-tropics.

Predicting carbon and water vapor fluxes using machine learning and novel feature ranking algorithms.

Gap-filling eddy covariance flux data using quantitative approaches has increased over the past decade. Numerous methods have been proposed previously, including look-up table approaches, parametric methods, process-based models, and machine learning. Particularly, the REddyProc package from the Max Planck Institute for Biogeochemistry and ONEFlux package from AmeriFlux have been widely used in many studies. However, there is no consensus regarding the optimal model and feature selection method that could be used for predicting different flux targets (Net Ecosystem Exchange, NEE; or Evapotranspiration -ET), due to the limited systematic comparative research based on the identical site-data. Here, we compared NEE and ET gap-filling/prediction performance of the least-square-based linear model, artificial neural network, random forest (RF), and support vector machine (SVM) using data obtained from four major row-crop and forage agroecosystems located in the subtropical or the climate-transition zones in the US. Additionally, we tested the impacts of different training-testing data partitioning settings, including a 10-fold time-series sequential (10FTS), a 10-fold cross validation (CV) routine with single data point (10FCV), daily (10FCVD), weekly (10FCVW) and monthly (10FCVM) gap length, and a 7/14-day flanking window (FW) approach; and implemented a novel Sliced Inverse Regression-based Recursive Feature Elimination algorithm (SIRRFE). We benchmarked the model performance against REddyProc and ONEFlux-produced results. Our results indicated that accurate NEE and ET prediction models could be systematically constructed using SVM/RF and only a few top informative features. The gap-filling performance of ONEFlux is generally satisfactory (R2 = 0.39-0.71), but results from REddyProc could be very limited or even unreliable in many cases (R2 = 0.01-0.67). Overall, SIRRFE-refined SVM models yielded excellent results for predicting NEE (R2 = 0.46-0.92) and ET (R2 = 0.74-0.91). Finally, the performance of various models was greatly affected by the types of ecosystem, predicting targets, and training algorithms; but was insensitive towards training-testing partitioning. Our research provided more insights into constructing novel gap-filling models and understanding the underlying drivers affecting boundary layer carbon/water fluxes on an ecosystem level.

Unmanned aerial systems-based remote sensing for monitoring sorghum growth and development.

Unmanned Aerial Vehicles and Systems (UAV or UAS) have become increasingly popular in recent years for agricultural research applications. UAS are capable of acquiring images with high spatial and temporal resolutions that are ideal for applications in agriculture. The objective of this study was to evaluate the performance of a UAS-based remote sensing system for quantification of crop growth parameters of sorghum (Sorghum bicolor L.) including leaf area index (LAI), fractional vegetation cover (fc) and yield. The study was conducted at the Texas A&M Research Farm near College Station, Texas, United States. A fixed-wing UAS equipped with a multispectral sensor was used to collect image data during the 2016 growing season (April-October). Flight missions were successfully carried out at 50 days after planting (DAP; 25 May), 66 DAP (10 June) and 74 DAP (18 June). These flight missions provided image data covering the middle growth period of sorghum with a spatial resolution of approximately 6.5 cm. Field measurements of LAI and fc were also collected. Four vegetation indices were calculated using the UAS images. Among those indices, the normalized difference vegetation index (NDVI) showed the highest correlation with LAI, fc and yield with R2 values of 0.91, 0.89 and 0.58 respectively. Empirical relationships between NDVI and LAI and between NDVI and fc were validated and proved to be accurate for estimating LAI and fc from UAS-derived NDVI values. NDVI determined from UAS imagery acquired during the flowering stage (74 DAP) was found to be the most highly correlated with final grain yield. The observed high correlations between UAS-derived NDVI and the crop growth parameters (fc, LAI and grain yield) suggests the applicability of UAS for within-season data collection of agricultural crops such as sorghum.

Unmanned Aerial Vehicles for High-Throughput Phenotyping and Agronomic Research.

Advances in automation and data science have led agriculturists to seek real-time, high-quality, high-volume crop data to accelerate crop improvement through breeding and to optimize agronomic practices. Breeders have recently gained massive data-collection capability in genome sequencing of plants. Faster phenotypic trait data collection and analysis relative to genetic data leads to faster and better selections in crop improvement. Furthermore, faster and higher-resolution crop data collection leads to greater capability for scientists and growers to improve precision-agriculture practices on increasingly larger farms; e.g., site-specific application of water and nutrients. Unmanned aerial vehicles (UAVs) have recently gained traction as agricultural data collection systems. Using UAVs for agricultural remote sensing is an innovative technology that differs from traditional remote sensing in more ways than strictly higher-resolution images; it provides many new and unique possibilities, as well as new and unique challenges. Herein we report on processes and lessons learned from year 1-the summer 2015 and winter 2016 growing seasons-of a large multidisciplinary project evaluating UAV images across a range of breeding and agronomic research trials on a large research farm. Included are team and project planning, UAV and sensor selection and integration, and data collection and analysis workflow. The study involved many crops and both breeding plots and agronomic fields. The project's goal was to develop methods for UAVs to collect high-quality, high-volume crop data with fast turnaround time to field scientists. The project included five teams: Administration, Flight Operations, Sensors, Data Management, and Field Research. Four case studies involving multiple crops in breeding and agronomic applications add practical descriptive detail. Lessons learned include critical information on sensors, air vehicles, and configuration parameters for both. As the first and most comprehensive project of its kind to date, these lessons are particularly salient to researchers embarking on agricultural research with UAVs.