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.

Best management practices are being implemented throughout the Lower Mississippi River Alluvial Valley with the aim of alleviating pressures placed on downstream aquatic systems by sediment and nutrient losses from agricultural land; however, research evaluating the performance of tailwater recovery (TWR) systems, an increasingly important practice, is limited. This study evaluated the ability of TWR systems to retain sediment and nutrients draining from agricultural landscapes. Composite flow-based samples were collected during flow events (precipitation or irrigation) over a two-year period in six TWR systems. Performance was evaluated by comparing concentrations and loads in water entering TWR systems (i.e., runoff or influent) from agricultural fields to water overflow exiting TWR systems (effluent). Tailwater recovery systems did not reduce concentrations of solids and nutrients, but did reduce loads of solids, phosphorus (P), and nitrogen (N) by 43%, 32%, and 44%, respectively. Annual mean load reductions were 1,142 kg solids, 0.7 kg of P, and 3.8 kg of N. Performance of TWR systems was influenced by effluent volume, system fullness, time since the previous event, and capacity of the TWR system. Mechanistically, TWR systems retain runoff on the agricultural landscape, thereby reducing the amount of sediment and nutrients entering downstream waterbodies. System performance can be improved through manipulation of influential parameters.

Increasing concern regarding environmental degradation in coastal areas that experience annual hypoxic zones has led to the need for mitigation of nutrient laden runoff from inland landscapes. An annual occurrence of a hypoxic zone in the Gulf of Mexico has led to the development and implementation of nutrient reduction strategies throughout the Mississippi River Basin (MRB). With federal, state, and private financial and technical assistance, landowners have implemented best management practices (BMPs) to combat nutrient and sediment nonpoint source pollution; however, the effectiveness of these BMPs alone or utilized together has not been quantified. This study uses a field-scale, paired watershed approach in two watersheds in the Mississippi Alluvial Valley to test for differences in sediment and nutrient runoff concentrations between four management systems. A total of 774 samples (415 baseflow samples and 359 stormflow samples) were collected from 2011 to 2015. Median baseflow concentrations across all sites within this study were 52 mg L⁻¹ for total suspended solids (TSS), 0.38 mg L⁻¹ for total phosphorus (TP), 0.09 mg L⁻¹ for nitrate-nitrite (NO₃⁻-NO₂⁻), and 0.81 mg L⁻¹ for ammonium (NH₄⁺). Median sediment and nutrient concentrations from stormflow samples across all sites within the study were greater than baseflow concentrations. Median stormflow concentrations across all sites were 985 mg L⁻¹ for TSS, 1.21 mg L⁻¹ for TP, 0.32 mg L⁻¹ for NO₃⁻-NO₂⁻, and 1.04 mg L⁻¹ for NH₄⁺. Results showed no strong improvements in water quality from agricultural landscapes where suites of BMPs had been implemented, rather the data showed variability in runoff concentrations indicative of strong influences from environmental and management variables. Study outcomes highlight opportunities to better capture nutrient dynamics at the field scale through adaptive management of BMPs for increased effectiveness of nonpoint source pollution reduction and monitoring.