Irrigation efficiency is facilitated by matching irrigation rates to crop water demand based on estimates of actual evapotranspiration (ET). In production settings, monitoring of water demand is typically accomplished by measuring reference ET rather than actual ET, which is then adjusted approximately using simplified crop coefficients based on calendars of crop maturation. Methods to determine actual ET are usually limited to use in research experiments for reasons of cost, labor and requisite user skill. To pair monitoring and research methods, we co-located eddy covariance sensors with on-farm weather stations over two different irrigated crops (vegetable beans and hazelnuts). Neural networks were used to train a neural network and utilize on-farm weather sensors to report actual ET as measured by the eddy covariance method. This approach was able to robustly estimate ET from as few as four sensor parameters (temperature, solar radiation, humidity and wind speed) with training time as brief as one week. An important limitation found with this machine learning method is that the trained network is only valid under environmental and crop conditions similar to the training period. The small number of required sensors and short training times demonstrate that this approach can estimate site-specific and crop specific ET. With additional field validation, this approach may offer a new method to monitor actual crop water demand for irrigation management.

Field experiments were conducted in north-central Oklahoma to evaluate the effects of MON 37500 at 35, 70, and 140 g ai/ha applied to wheat on rotational crops seeded no-till 16 to 29 mo after treatment (MAT). Wheat yields were not reduced by MON 37500 at site 1 but at site 2 were decreased 6, 11, and 24% by 35, 70, and 140 g/ha, respectively. Wheat yield reductions at site 2 were attributed to late seeding, small wheat growth stage, and cool, wet weather during the month after application. Corn and soybean seeded approximately 16 MAT were not visibly injured by residual MON 37500 at any rate at either site. At site 1 grain sorghum seeded 17 MAT was visibly injured by residual MON 37500 applied at 70 and 140 g/ha (soil pH value 6.4), and grain yield was reduced 58% by residual MON 37500 applied at 140 g/ha. Grain sorghum seeded 17 MAT was not visibly injured at site 2 (soil pH value 5.0), and that seeded 29 MAT was not injured at either site. Sunflower seeded 17 MAT at site 1 was visibly injured by residu...

Rapid changes in solar radiative forcing influence heat, scalar and momentum fluxes and thereby shift the trajectory of near-surface atmospheric transitions. Surface fluxes are difficult to obtain during atmospheric transitions by either bulk or eddy-covariance methods because both techniques assume quasi-stationarity in an atmospheric state and require sufficiently long blocks of data, typically on the order of 10–30 min, to obtain statistically significant results. These computational requirements limit the temporal resolution of atmospheric processes that researchers can examine using traditional measurement techniques. In this paper, we present a novel observational approach to calculate surface fluxes at sub-minute temporal resolutions. High-frequency data from a horizontal, log-spaced array of nine time-synchronized ultrasonic anemometers were used to perform spatial-temporal ensemble averaging and to obtain eddy-covariance turbulence fluxes at unprecedented time resolutions. The 2017 Great American Solar Eclipse event provided a “natural experiment” to test the ensemble-observation and averaging approach. A total eclipse is energetically well-constrained and, unlike day/night transitions, is a perturbation that quickly transitions from and back to a state of significant solar forcing, providing an ideal scenario for testing the space-timescales required for surface flux calculations. Additionally, two Doppler lidars and a vertically-oriented Distributed Temperature Sensing (DTS) system provided measurements to characterize near-surface atmospheric conditions. Results show that the ensemble-averaged sensible heat fluxes converged at timescales as short as 15 s. Additional analyses show that the timescale of the connection between the surface and the atmosphere is more rapid than previous measurements have been capable of showing and is on the order of 10 min or less. This experiment demonstrates that ensemble-flux measurements are capable of resolving fluctuations in surface fluxes during rapid atmospheric transitions.

Solar radiation received at the Earth’s surface provides the energy driving all micro-meteorological phenomena. Local solar radiation measurements are used to estimate energy mediated processes such as evapotranspiration (ET); this information is important in managing natural resources. However, the technical requirements to reliably measure solar radiation limits more extensive adoption of data-driven management. High-quality radiation sensors are expensive, delicate, and require skill to maintain. In contrast, low-cost sensors are widely available, but may lack long-term reliability and intra-sensor repeatability. As weather stations measure solar radiation and other parameters simultaneously, machine learning can be used to integrate various types of environmental data, identify periods of erroneous measurements, and estimate corrected values. We demonstrate two case studies in which we use neural networks (NN) to augment direct radiation measurements with data from co-located sensors, and generate radiation estimates with comparable accuracy to the data typically available from agro-meteorology networks. NN models that incorporated radiometer data reproduced measured radiation with an R² of 0.9–0.98, and RMSE less than 100 Wm⁻², while models using only weather parameters obtained R² less than 0.75 and RMSE greater than 140 Wm⁻². These cases show that a simple NN implementation can complement standard procedures for estimating solar radiation, create opportunities to measure radiation at low-cost, and foster adoption of data-driven management.