Direction Estimation in 3D Outdoor Air-Air Wireless Channels through Machine Learning.

UAVs need to communicate along three dimensions (3D) with other aerial vehicles, ranging from above to below, and often need to connect to ground stations. However, wireless transmission in 3D space significantly dissipates power, often hindering the range required for these types of links. Directional transmission is one way to efficiently use available wireless channels to achieve the desired range. While multiple-input multiple-output (MIMO) systems can digitally steer the beam through channel matrix manipulation without needing directional awareness, the power resources required for operating multiple radios on a UAV are often logistically challenging. An alternative approach to streamline resources is the use of phased arrays to achieve directionality in the analog domain, but this requires beam sweeping and results in search-time delay. The complexity and search time can increase with the dynamic mobility pattern of the UAVs in aerial networks. However, if the direction of the receiver is known at the transmitter, the search time can be significantly reduced. In this work, multi-antenna channels between two UAVs in A2A links are analyzed, and based on these findings, an efficient machine learning-based method for estimating the direction of a transmitting node using channel estimates of 4 antennas (2 × 2 MIMO) is proposed. The performance of the proposed method is validated and verified through in-field drone-to-drone measurements. Findings indicate that the proposed method can estimate the direction of the transmitter in the A2A link with 86% accuracy. Further, the proposed direction estimation method is deployable for UAV-based massive MIMO systems to select the directional beam without the need to sweep or search for optimal communication performance.

Assessing Variation in US Soybean Seed Composition (Protein and Oil).

Soybean [Glycine max (L.) Merr.] seed composition and yield are a function of genetics (G), environment (E), and management (M) practices, but contribution of each factor to seed composition and yield are not well understood. The goal of this synthesis-analysis was to identify the main effects of G, E, and M factors on seed composition (protein and oil concentration) and yield. The entire dataset (13,574 data points) consisted of 21 studies conducted across the United States (US) between 2002 and 2017 with varying treatments and all reporting seed yield and composition. Environment (E), defined as site-year, was the dominant factor accounting for more than 70% of the variation for both seed composition and yield. Of the crop management factors: (i) delayed planting date decreased oil concentration by 0.007 to 0.06% per delayed week (R 2∼0.70) and a 0.01 to 0.04 Mg ha-1 decline in seed yield per week, mainly in northern latitudes (40-45 N); (ii) crop rotation (corn-soybean) resulted in an overall positive impact for both seed composition and yield (1.60 Mg ha-1 positive yield difference relative to continuous soybean); and (iii) other management practices such as no-till, seed treatment, foliar nutrient application, and fungicide showed mixed results. Fertilizer N application in lower quantities (10-50 kg N ha-1) increased both oil and protein concentration, but seed yield was improved with rates above 100 kg N ha-1. At southern latitudes (30-35 N), trends of reduction in oil and increases in protein concentrations with later maturity groups (MG, from 3 to 7) was found. Continuing coordinated research is critical to advance our understanding of G × E × M interactions.