Search

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.

Synthesis and quantification of disciplinary knowledge at the whole system level, via the process models of agricultural systems, are critical to achieving improved and dynamic management and production systems that address the environmental concerns and global issues of the 21st century. Soil physicists have made significant contributions in this area in the past, and are uniquely capable of making the much-needed and exciting new contributions. Most of the exciting new research opportunities are trans-disciplinary, that is, lie on the interracial boundaries of soil physics and other disciplines, especially in quantifying interactions among soil physical processes, plant and atmospheric processes, and agricultural management practices. Some important knowledge-gap and catting-edge areas of such research are: (1) quantification and modeling the effects of various management practices (e.g., tillage, no-tillage, crop residues, and rooting patterns) on soil properties and soil--plant--atmosphere processes; (2) the dynamics of soil structure, especially soil cracks and biochannels, and their effects on surface runoff of water and mass, and preferential water and chemical transport to subsurface waters; (3) biophysics of changes in properties and processes at the soil--plant and plant--atmosphere interfaces; (4) modeling contributions of agricultural soils to climate change and effects of climate change on soil environment and agriculture; and (5) physical (cause-effect) quantification of spatial variability of soil properties and their outcomes, new methods of parameterizing a variable field for field-scale modeling, and new innovative methods of aggregating output results from plots to fields to larger scales. The current status of the various aspects of these research areas is reviewed briefly. The future challenges are identified that will require both experimental research and development of new concepts, theories, and models.

The effects of CO2 enrichment on the growth and physiology of maize were investigated at the molecular, biochemical, leaf, and canopy levels. Maize plants were grown in sunlit soil–plant–atmosphere research (SPAR) chambers at ambient (370 μmol mol−1) or elevated (750 μmol mol−1) atmospheric carbon dioxide concentration ( Ca) under well-watered and fertilized conditions. Canopy gas exchange rates and leaf temperatures were monitored continuously during the growing season. CO2 enrichment did not enhance the growth or canopy photosynthesis of maize plants. However, canopy evapotranspiration rates decreased by 22% and daytime leaf temperatures were increased about 1°C in response to CO2 enrichment. Leaf carboxylation efficiency and leaf nitrogen concentration also decreased at elevated Ca. Transcription profiling using maize cDNA microarrays revealed that approximately 5% of tested genes responded to CO2 enrichment. Of the altered transcripts, several were known to encode proteins involved in stomatal development or photosynthesis. For the majority of the altered transcripts, however, it was difficult to link their functions with specific physiological factors partly because many of these genes encoded unknown proteins. We conclude that maize did not exhibit enhanced growth or photosynthesis in response to CO2 enrichment but a number of molecular and physiological processes including those involved in stomatal relations were affected by growth in elevated Ca. [ABSTRACT FROM AUTHOR]

Abstract: Global atmospheric carbon dioxide concentrations (C a) are rising. As a consequence, recent climate models have projected that global surface air temperature may increase 1.4–5.8°C with the doubling of C a by the end of the century. Because, changes in C a and temperature are likely to occur concomitantly, it is important to evaluate how the temperature dependence of key physiological processes are affected by rising C a in major crop plants including maize (Zea mays L.), a globally important grain crop with C4 photosynthetic pathway. We investigated the temperature responses of photosynthesis, growth, and development of maize plants grown at five temperature regimes ranging from 19/13 to 38.5/32.5°C under current (370μmolmol−1) and doubled (750μmolmol−1) C a throughout the vegetative stages using sunlit controlled environmental chambers in order to test if the temperature dependence of these processes was altered by elevated C a. Leaf and canopy photosynthetic rates, C4 enzyme activities, leaf appearance rates, above ground biomass accumulation and leaf area were measured. We then applied temperature response functions (e.g., Arrhenius and Beta distribution models) to fit the measured data in order to provide parameter estimates of the temperature dependence for modeling photosynthesis and development at current and elevated C a in maize. Biomass, leaf area, leaf appearance rate, and photosynthesis measured at growth C a was not changed in response to CO2 enrichment. Carboxylation efficiency and the activities of C4 enzymes were reduced with CO2 enrichment indicating possible photosynthetic acclimation of the C4 cycle. All measured parameters responded to growth temperatures. Leaf appearance rate and leaf photosynthesis showed curvilinear response with optimal temperatures near 32 and 34°C, respectively. Total above ground biomass and leaf area were negatively correlated with growth temperature. The dependence of leaf appearance rate, biomass, leaf area, leaf and canopy photosynthesis, and C4 enzyme activities on growth temperatures was comparable between current and elevated C a. The results of this study suggest that the temperature effects on growth, development, and photosynthesis may remain unchanged in elevated C a compared with current C a in maize. [Copyright &y& Elsevier]