Accurate predictions of crop yield are critical for developing effective agricultural and food policies at the regional and global scales. We evaluated a machine-learning method, Random Forests (RF), for its ability to predict crop yield responses to climate and biophysical variables at global and regional scales in wheat, maize, and potato in comparison with multiple linear regressions (MLR) serving as a benchmark. We used crop yield data from various sources and regions for model training and testing: 1) gridded global wheat grain yield, 2) maize grain yield from US counties over thirty years, and 3) potato tuber and maize silage yield from the northeastern seaboard region. RF was found highly capable of predicting crop yields and outperformed MLR benchmarks in all performance statistics that were compared. For example, the root mean square errors (RMSE) ranged between 6 and 14% of the average observed yield with RF models in all test cases whereas these values ranged from 14% to 49% for MLR models. Our results show that RF is an effective and versatile machine-learning method for crop yield predictions at regional and global scales for its high accuracy and precision, ease of use, and utility in data analysis. RF may result in a loss of accuracy when predicting the extreme ends or responses beyond the boundaries of the training data.
Knowledge of temperature effects on whole canopy photosynthesis, growth, and development of potato (Solanum tuberosum L.) is important for crop model development and evaluation. The objective of this study was to quantify the effects of temperature on canopy photosynthesis, development, growth, and partitioning of potato cv. Atlantic under elevated atmospheric CO 2 concentration (700 mL L 21 CO 2 ). Potato plants were grown in day-lit plant growth chambers at six constant day/night temperatures, (12, 16, 20, 24, 28, and 32°C) during a 52-d experimental period in 1999 in Beltsville, MD. Main stem length and main stem expanded leaf number were measured nondestructively at 4 d intervals while leaf, stem, root, and tuber weights were obtained by destructive harvesting at biweekly time intervals. Canopy level net photosynthesis (P N ) was obtained from gas exchange measurements. The optimum temperature for canopy photosynthesis was 24°C early in the growth period and shifted to lower temperatures as the plants aged. Total end-of-season biomass was highest in the 20°C treatment. End-of-season tuber mass and the ratio of tuber to total biomass decreased with increasing temperature above 24°C. Accumulated biomass was a linear function of total C gain with a common slope for all treatments. However, the proportion of C allocated to tubers decreased with increasing temperatures. High respiration losses decreased total C gain at higher temperatures. When simulating photosynthesis and C assimilation in crop models, source-sink relationships with temperature and photosynthesis need to be accounted for.
Mature potato (Solanum tuberosum L. cv. Kennebec) canopies are composed of leaves originating from main-and axillary-stem branches. Canopy leaf distribution and its corresponding contribution to wholecanopy photosynthetic rates have not been quantified. An experiment using SPAR (Soil-Plant-Atmosphere-Research) chambers maintained at 16-h day/night thermoperiods of 14/10, 17/12, 20/15, 23/18, 28/23, and 34/29°C was conducted. Mature canopies were divided into three horizontal layers of equal depth. Canopies were defoliated at each layer, from the ground upward, on successive days. Response curves for photosynthetic rate vs. irradiance were obtained after each defoliation. Leaf area within each layer followed a quadratic relationship with temperature. The largest areas were between 16.6 and 22.1°C. Main-stem leaves accounted for .50% of the total leaf area at temperatures ,22°C, while the proportion of axillary-stem leaf area in each layer increased with temperature. Canopy maximum gross photosynthetic rates, A MAX , before harvest ranged from 9.5 to 34.8 mmol CO 2 m 22 s 21 (production-area basis) and were higher at 14/10, 17/12, and 20/15°C temperatures than at 23/18, 28/23, and 34/29°C. These values were largely related to the quantity of leaf area in each chamber. The value of A MAX and canopy light use efficiency declined as successive canopy layers were removed, primarily due to decreases in canopy light interception. These results indicate that the relative proportion of main-or axillary-stem leaves are not as important for potato canopy modeling considerations as is the need to simulate the correct quantity of leaf area.
Uranium (U) contamination of groundwater poses a serious environmental problem in uranium mining areas and in the vicinity of nuclear processing facilities. Preliminary laboratory experiments and treatability studies indicated that the roots of terrestrial plants could be efficiently used to remove U from aqueous streams (rhizofiltration). Certain sunflower plants were found to have a high affinity for U and were selected for treatment of contaminated water. Almost all of the U removed from the water in the laboratory was concentrated in the roots. Bioaccumulation coefficients based on the ratios of U concentrations in the roots vs U concentrations in the aqueous phase reached 30 000. Rhizofiltration technology has been tested in the field with U-contaminated water at concentrations of 21−874 μg/L at a former U processing facility in Ashtabula, OH. The pilot-scale rhizofiltration system provided final treatment to the site source water and reduced U concentration to <20 μg/L (EPA Water Quality Standard) before discharge to the environment. System performance was subsequently evaluated under different flow rates permitting the development of effectiveness estimates for the approach.
Plant mineral nutrients such as phosphorus may exert major control on crop responses to the rising atmospheric carbon dioxide (CO 2) concentrations. To evaluate the growth, nutrient dynamics, and efficiency responses to CO 2 and phosphorus nutrition, soybean (Glycine max (L.) Merr.) was grown in controlled environment growth chambers with sufficient (0.50 mM) and deficient (0.10 and 0.01 mM) phosphate (Pi) supply under ambient and elevated CO 2 (aCO 2 , 400 and eCO 2 , 800 µmol mol −1 , respectively). The CO 2 Â Pi interaction was detected for leaf area, leaf and stem dry weight, and total plant biomass. The severe decrease in plant biomass in Pi-deficient plants (10-76%) was associated with reduced leaf area and photosynthesis (P net). The degree of growth stimulation (0-55% total biomass) by eCO 2 was dependent upon the severity of Pi deficiency and was closely associated with the increased phosphorus utilization efficiency. With the exception of leaf and root biomass, Pi deficiency decreased the biomass partitioning to other plant organs with the maximum decrease observed in seed weight (8-42%) across CO 2 levels. The increased tissue nitrogen (N) concentration in Pi-deficient plants was accredited to the lower biomass and increased nutrient uptake due to the larger root to shoot ratio. The tissue P and N concentration tended to be lower at eCO 2 versus aCO 2 and did not appear to be the main cause of the lack of CO 2 response of growth and P net under severe Pi deficiency. The leaf N/P ratio of >16 was detrimental to soybean growth. The tissue P concentration needed to attain the maximum productivity for biomass and seed yield tended to be higher at eCO 2 versus aCO 2. Therefore, the eCO 2 is likely to increase the leaf critical P concentration for maximum biomass productivity and yield in soybean.
Phosphorous deficiency in soil limits crop growth and productivity in the majority of arable lands worldwide and may moderate the growth enhancement effect of rising atmospheric carbon dioxide (CO 2 ) concentration. To evaluate the interactive effect of these two factors on cotton (Gossypium hirsutum) growth and physiology, plants were grown in controlled environment growth chambers with three levels of phosphate (Pi) supply (0.20, 0.05 and 0.01 mM) under ambient and elevated (400 and 800 lmol mol À1 , respectively) CO 2 . Phosphate stress caused stunted growth and resulted in early leaf senescence with severely decreased leaf area and photosynthesis. Phosphate stress led to over 77 % reduction in total biomass across CO 2 levels. There was a below-ground (roots) shift in biomass partitioning under Pi deficiency. While tissue phosphorus (P) decreased, tissue nitrogen (N) content tended to increase under Pi deficiency. The CO 2 9 Pi interactions were significant on leaf area, photosynthesis and biomass accumulation. The stimulatory effect of elevated CO 2 on growth and photosynthesis was reduced or highly depressed suggesting an increased sensitivity of cotton to Pi deficiency under elevated CO 2 . Although, tissue P and stomatal conductance were lower at elevated CO 2 , these did not appear to be the main causes of cotton unresponsiveness to elevated CO 2 under severe Pi-stress. The alteration in the uptake and utilization of N was suggested due to a consistent reduction (18-21 %) in the cotton plant tissue N content under elevated CO 2 .
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.