Search

Accurate estimation of reference evapotranspiration (ETr) is important for irrigation planning, water resource management, and preserving agricultural and forest habitats. The widely used Penman–Monteith equation (ASCE-PM) estimates ETr across various timescales using ground weather station data. However, discrepancies persist between estimated ETr and measured ETr obtained from weighing lysimeters (ETr-lys), particularly in advective environments. This study assessed different machine learning (ML) models in comparison to ASCE-PM for ETr estimation in highly advective conditions. Various variable combinations, representing both radiation and aerodynamic components, were organized for evaluation. Eleven datasets (DT) were created for the daily timescale, while seven were established for hourly and quarter-hourly timescales. ML models were optimized by a genetic algorithm (GA) and included support vector regression (GA-SVR), random forest (GA-RF), artificial neural networks (GA-ANN), and extreme learning machines (GA-ELM). Meteorological data and direct measurements of well-watered alfalfa grown under reference ET conditions obtained from weighing lysimeters and a nearby weather station in Bushland, Texas (1996–1998), were used for training and testing. Model performance was assessed using metrics such as root mean square error (RMSE), mean absolute error (MAE), mean bias error (MBE), and coefficient of determination (R2). ASCE-PM consistently underestimated alfalfa ET across all timescales (above 7.5 mm/day, 0.6 mm/h, and 0.2 mm/h daily, hourly, and quarter-hourly, respectively). On hourly and quarter-hourly timescales, datasets predominantly composed of radiation components or a blend of radiation and aerodynamic components demonstrated superior performance. Conversely, datasets primarily composed of aerodynamic components exhibited enhanced performance on a daily timescale. Overall, GA-ELM outperformed the other models and was thus recommended for ETr estimation at all timescales. The findings emphasize the significance of ML models in accurately estimating ETr across varying temporal resolutions, crucial for effective water management, water resources, and agricultural planning. [ABSTRACT FROM AUTHOR]

Knowledge of evapotranspiration (ET) is vital for the management of our freshwater resources. One method for determining ET is through the measurement of the soil water balance, where ET is the residual calculated from the change in soil water storage plus precipitation and irrigation and minus drainage and runoff The objective of this research was to compare the ET calculations where the change in soil water storage was measured using the neutron moisture meter (NMM), or [ET.sub.NMM], vs. using weighing lysimeters ([ET.sub.LYS]) in four soils. Cotton (Gossypium hirsutum L.) was grown in 2006 and 2007 in weighing lysimeters with NMM access tubes and drainage systems. The soil textures ranged from fine sand to clay loam. The [ET.sub.NMM] was [less than or equal to]4% of the [ET.sub.LYS] for the clay loam and sandy loam soils, but [ET.sub.NMM] was 8% less than [ET.sub.LYS] in the fine sand due to errors created by the timing of drainage and NMM measurements. At [ET.sub.LYS] amounts Abbreviations: ET, evapotranspiration; [ET.sub.LYS], ET with change in soil water storage determined using lysimetry; [ET.sub.NMM], ET with change in soil water storage determined using the neutron moisture meter; NMM, neutron moisture meter.

Wheat (Triticum aestivum L.) cultivars with high canopy temperature depression (CTD) tend to have higher grain yield under dry, hot conditions. Therefore, CTD has been used as a selection criterion to improve adaptation to drought and heat. The CTD is a result of the leaf's energy balance, which includes terms determined by environment and physiological traits. We hypothesized that one or more of several physiological traits contributed to consistent CTD differences among three closely-related winter wheat lines grown under dryland conditions. For three years we measured several leaf traits, including CTD, leaf dimension, gas exchange rates, and carbon-13 isotope discrimination ([DELTA]). Soil water content was also monitored. Data showed that daytime CTD was related to the leaf size in these wheat lines. The most drought-tolerant line, TX86A8072, had consistently smaller and narrower leaves than TX86A5606, the least drought tolerant. For TX86A8072, dryland and irrigated average noon CTD was -0.8[degrees]C, and average flag leaf area (LA) 11 [cm.sup.2], for TX86A5606, values were -1.7[degrees]C and 12.5 [cm.sup.2], respectively. However, TX86A8072 also had higher CTD (i.e., lower temperatures) than TX86A5606 at night, despite a theoretically greater sensible heat transfer coefficient, suggesting greater nighttime transpiration (T). Implications of these traits on nighttime leaf energy balance and possible adaptive roles of nighttime T are discussed.

Abstract: A center pivot was completely automated using the temperature-time-threshold method of irrigation scheduling. An array of infrared thermometers was mounted on the center pivot, and these were used to remotely determine the crop leaf temperature as an indicator of crop water stress. We describe methods used to automatically collect and analyze the canopy temperature data and control the moving irrigation system based on the data analysis. Automatic irrigation treatments were compared with manually scheduled irrigation treatments under the same center pivot during the growing seasons of 2004 and 2005. Manual irrigations were scheduled on a weekly basis using the neutron probe to determine the profile water content and the amount of water needed to replenish the profile to field capacity. In both years, there was no significant difference between manual and automatic treatments in soybean water use efficiency or irrigation water use efficiency. The automatic irrigation system has the potential to simplify management, while maintaining the yields of intensely managed irrigation. DOI: 10.1061/(ASCE)0733-9437(2008)134:3(286) CE Database subject headings: Irrigation scheduling; Temperature; Time factors; Automation; Crops.

Canopy temperature depression (CTD--air temperature [Ta]--canopy temperature [Tc]) has been used to estimate crop yield and to rank genotypes for tolerance to heat and drought, but when to measure CTD for breeding selection has seldom been addressed. Our objectives were to evaluate the suitability of CTD for the Texas High Plains environment and to determine optimal measurement times in relation to growth stage, time of day, and weather. Three years of CTD and weather data were used to assess regression models of grain yield in three wheat (Triticum aestivum L.) lines. Under dryland agriculture, long-term mean CTD at noon and yield were correlated in 2000 and 2001. The relation of short-term CTD readings to grain yield was highly variable. Poor correlation was associated with days of low solar irradiance, high wind speed, and rain events. Genotype effects on CTD were detected for all hours of day and night. Genotype x hour interaction was insignificant at night, suggesting that nighttime measurements may provide more stable conditions for CTD comparison among genotypes. In general, tree regression assessed grain yield from short-term CTD measurements better than linear regression and suggested that the best times to measure CTD were 0900, 1300, and 1800 h. Tree regression models provided a heuristic interpretation of crop water status under different scenarios of soil water availability.