Are unmanned aerial vehicle-based hyperspectral imaging and machine learning advancing crop science?

The past few years have seen increased interest in unmanned aerial vehicle (UAV)-based hyperspectral imaging (HSI) and machine learning (ML) in agricultural research, concomitant with an increase in published research on these topics. We provide an updated review, written for agriculturalists, highlighting the benefits in the retrieval of biophysical parameters of crops via UAVs relative to less sophisticated options. We reviewed >70 recent papers and found few consistent results between similar studies. Owing to their high complexity and cost, especially when applied to crops of low value, the benefits of most of the research reviewed are difficult to explain. Future effort will be necessary to distill research findings into lower-cost options for end-users.

Effects of Low-Grade Weirs on Soil Microbial Communities in Agricultural Drainage Ditches.

Agricultural fertilizer application throughout the Mississippi River basin has been identified as a major source of N pollution to the Gulf of Mexico. Using best management practices, such as low-grade weirs, has been identified as a potential solution to mitigate nutrient loads in agricultural runoff. This study assessed impacts of weir implementation in four agricultural drainage ditches (three with weirs and one control site) in the Mississippi Delta. Soil samples collected from field locations in spring 2013 were analyzed for denitrifier abundance using genes (16s ribosomal RNA [rRNA] genes, , , and ) via quantitative polymerase chain reaction (qPCR), microbial community profiles via terminal-restriction fragment length polymorphism (T-RFLP) of 16s rRNA genes, soil parameters (C, N, and moisture), and vegetation presence at sample locations. Gene quantification was successful, except for , which was found below detection limits (5000 gene copies g soil). Distance from weirs was negatively correlated with 16S rRNA genes and soil moisture, and soil moisture was positively correlated with 16s rRNA and S gene abundance. Results of empirical Bayesian kriging did not exhibit obvious patterns of microbial diversity in relation to weir proximity. Preliminary assessment of seasonal trends showed genes 16s rRNA and , soil N, and mean T-RF values to be greater in fall than in spring. Results highlight that weirs had no direct impact on microbial diversity or denitrification functional gene abundance. Correlations between microbial measures and environmental parameters suggest that adequate management of N runoff from agricultural landscapes will require ecological engineering beyond weirs to optimize N mitigation.