Carrie Laboski - Academia.edu (original) (raw)
Papers by Carrie Laboski
Soil Science Society of America Journal
Proceedings of the Integrated Crop Management Conference
Agronomy Journal
Reduced atmospheric S deposition, in conjunction with higher grain sale prices and steadily incre... more Reduced atmospheric S deposition, in conjunction with higher grain sale prices and steadily increasing yields of soybean [Glycine max (L.) Merr.], has many growers considering an increase in secondary and micronutrient applications. Limited information exists quantifying requirements of S, Mg, Ca, Zn, Mn, Cu, Fe, and B across a wide yield range for modern soybean production systems. Using six site-years and eight varieties, plants were sampled at six growth stages and partitioned into their respective plant parts and analyzed. Nutrients were acquired heavily (48-73%) from R1 through R5.5 with peak uptake rates near R3. Yet, uptake after R5.5 represented a greater portion of total S uptake as yield increased from the low (24.9%) to high (32.2%) yield level (3608 vs. 5483 kg ha-1). This coincided with seed S accumulation, which relied more heavily on continued uptake after R5.5 (58%) vs. vegetative S remobilization (42%). Across all environments (site × year) and varieties, total S uptake (0.004 kg S kg grain-1) and removal (0.003 kg S kg grain-1) showed moderate (R 2 = 0.58) and strong (R 2 = 0.76) relations with yield, respectively. These relations for each micronutrient were much weaker (R 2 = 0.13-0.66), due largely to the main effects of environment and variety along with their respective interactions with yield. Furthermore, micronutrient concentrations in leaf tissue varied considerably (CV = 28-46%) during recommend testing stages. Thus, previously reported inconsistent yield responses to foliar application of these micronutrients may primarily be due to the large variability in leaf tissue concentrations and nutrient requirements.
Soil Science Society of America Journal
Understanding the variables that affect the anaerobic potentially mineralizable N (PMN an) test s... more Understanding the variables that affect the anaerobic potentially mineralizable N (PMN an) test should lead to a standard procedure of sample collection and incubation length, improving PMN an as a tool in corn (Zea mays L.) N management. We evaluated the effect of soil sample timing (preplant and V5 corn development stage [V5]), N fertilization (0 and 180 kg ha −1) and incubation length (7, 14, and 28 d) on PMN an (0-30 cm) across a range of soil properties and weather conditions. Soil sample timing, N fertilization, and incubation length affected PMN an differently based on soil and weather conditions. Preplant vs. V5 PMN an tended to be greater at sites that received < 183 mm of precipitation or < 359 growing degree-days (GDD) between preplant and V5, or had soil C/N ratios > 9.7:1; otherwise, V5 PMN an tended to be greater than preplant PMN an. The PMN an tended to be greater in unfertilized vs. fertilized soil in sites with clay content > 9.5%, total C < 24.2 g kg −1 , soil organic Abbreviations: AWDR, Abundant and well-distributed rainfall; GDD, Growing degree-day; PMN an , Anaerobic potentially mineralizable N; SDI, Shannon diversity index; SOM, Soil organic matter. This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.
Agronomy Journal
Determining which corn (Zea mays L.) N fertilizer rate recommendation tools best predict crop N n... more Determining which corn (Zea mays L.) N fertilizer rate recommendation tools best predict crop N need would be valuable for maximizing profits and minimizing environmental consequences. Simultaneous comparisons of multiple tools across various environmental conditions have been limited. The objectives of this research were to evaluate the performance of publicly-available N fertilizer recommendation tools across diverse soil and weather conditions for: (i) prescribing N rates for planting and split-fertilizer applications, and (ii) economic and environmental effects. Corn N-response trials using standardized methods were conducted at 49 sites, spanning eight US Midwest states and three growing seasons. Nitrogen applications included eight rates in 45 kg N ha −1 increments all at-planting and matching rates with 45 kg N ha −1 at-planting plus at the V9 development stage. Tool performances were compared to the economically optimal N rate (EONR). Over this large geographic region, only 10 of 31 recommendation tools (mainly soil nitrate tests) produced N rate recommendations that weakly correlated to EONR (P ≤ .10; r 2 ≤ .20). With other metrics of performance, the Maximum Return to N (MRTN) soil nitrate tests, and canopy reflectance sensing came close to matching EONR. Economically, all tools but the Maize-N crop growth model had similar returns compared to EONR. Environmentally, yield goal based tools resulted in the highest environmental costs. Results show that no tool was universally reliable over this study's diverse growing environments, suggesting that additional tool development is needed to better represent N inputs and crop utilization at a larger regional level.
Agronomy Journal
Abbreviations: EONR, economic optimal N rate; EONR single , economic optimal N rate using a singl... more Abbreviations: EONR, economic optimal N rate; EONR single , economic optimal N rate using a single N application; EONR split , economic optimal N rate using a split N application; NH 4-N inc , NH 4-N after the soil was incubated for 7, 14, or 28 d; NH 4-N initial , initial NH 4-N in the soil; PMN an , anaerobic potentially mineralizable N; PP 0N , pre-plant soil sampling with 0 kg N ha-1 applied at planting; V5 0N , V5 soil sampling with 0 kg N ha-1 applied at planting; V5 180N , V5 soil sampling with 180 kg N ha-1 applied at planting.
HortTechnology
Organic sweet corn (Zea mays) production is challenging for growers because of the high nitrogen ... more Organic sweet corn (Zea mays) production is challenging for growers because of the high nitrogen (N) requirements of sweet corn and the relatively low N content of organic soil amendments. Total N supplied and rate of mineralization throughout the growing season are two important aspects in determining the optimal N management program. Green manure (GrM) crops, composted manures, and commercially available organic fertilizers are used to manage N in organic production systems. Using a combination of these tactics can optimize N while minimizing cost. In this study, we used combinations of composted poultry manure (CPM) and two organic fertilizers (one high N and one with a balance of nutrients) with three GrM crops [rye (Secale cereale), alfalfa (Medicago sativa), and pea (Pisum sativum)] in a loamy sand soil for a 112-day laboratory incubation study. Total plant available N (PAN) was quantified at six times throughout the 16 weeks to determine total N mineralized and rate of N rele...
Soil Science Society of America Journal
Nitrogen provided to crops through mineralization is an important factor in N management guidelin... more Nitrogen provided to crops through mineralization is an important factor in N management guidelines. understanding of the interactive effects of soil and weather conditions on N mineralization needs to be improved. relationships between anaerobic potentially mineralizable N (PMN an) and soil and weather conditions were evaluated under the contrasting climates of eight uS Midwestern states. Soil was sampled (0-30 cm) for PMN an analysis before pre-plant N application (PP 0N) and at the V5 development stage from the pre-plant 0 (V5 0N) and 180 kg N ha −1 (V5 180N) rates and incubated for 7, 14, and 28 d. Even distribution of precipitation and warmer temperatures before soil sampling and greater soil organic matter (SOM) increased PMN an. Soil properties, including total C, SOM, and total N, had the strongest relationships with PMN an (R 2 ≤ 0.40), followed by temperature (R 2 ≤ 0.20) and precipitation (R 2 ≤ 0.18) variables. the strength of the relationships between soil properties and PMN an from PP 0N , V5 0N , and V5 180N varied by ≤10%. Including soil and weather in the model greatly increased PMN an predictability (R 2 ≤ 0.69), demonstrating the interactive effect of soil and weather on N mineralization at different times during the growing season regardless of N fertilization. Delayed soil sampling (V5 0N) and sampling after fertilization (V5 180N) reduced PMN an predictability. However, longer PMN an incubations improved PMN an predictability from both V5 soil samplings closer to the PMN an predictability from PP 0N , indicating the potential of PMN an from longer incubations to provide improved estimates of N mineralization when N fertilizer is applied.
Computers and Electronics in Agriculture
Nitrogen (N) fertilizer recommendation tools could be improved for estimating corn (Zea mays L.) ... more Nitrogen (N) fertilizer recommendation tools could be improved for estimating corn (Zea mays L.) N needs by incorporating site-specific soil and weather information. However, an evaluation of analytical methods is needed to determine the success of incorporating this information. The objectives of this research were to evaluate statistical and machine learning (ML) algorithms for utilizing soil and weather information for improving corn N recommendation tools. Eight algorithms [stepwise, ridge regression, least absolute shrinkage and selection operator (Lasso), elastic net regression, principal component regression (PCR), partial least squares regression (PLSR), decision tree, and random forest] were evaluated using a dataset containing measured soil and weather variables from a regional database. The performance was evaluated based on how well these algorithms predicted corn economically optimal N rates (EONR) from 49 sites in the U.S. Midwest. Multiple algorithm modeling scenarios were examined with and without adjustment for multicollinearity and inclusion of two-way interaction terms to identify the soil and weather variables that could improve three dissimilar N recommendation tools. Results showed the out-of-sample root-mean-square error (RMSE) for the decision tree and some random forest modeling scenarios were better than the stepwise or ridge regression, but not significantly different than any other algorithm. The best ML algorithm for adjusting N recommendation tools was the random forest approach (r2 increased between 0.72 and 0.84 and the RMSE decreased between 41 and 94 kg N ha−1). However, the ML algorithm that best adjusted tools while using a minimal amount of variables was the decision tree. This method was simple, needing only one or two variables (regardless of modeling scenario) and provided moderate improvement as r2 values increased between 0.15 and 0.51 and RMSE decreased between 16 and 66 kg N ha−1. Using ML algorithms to adjust N recommendation tools with soil and weather information shows promising results for better N management in the U.S. Midwest.
Agronomy Journal
Determination of in-season N requirement for corn (Zea mays L.) is challenging due to interaction... more Determination of in-season N requirement for corn (Zea mays L.) is challenging due to interactions of genotype, environment, and management. Machine learning (ML), with its predictive power to tackle complex systems, may solve this barrier in the development of locally based N recommendations. The objective of this study was to explore application of ML methodologies to predict economic optimum nitrogen rate (EONR) for corn using data from 47 experiments across the US Corn Belt. Two features, a water table adjusted available water capacity (AWC wt) and a ratio of in-season rainfall to AWC wt (RAWC wt), were created to capture the impact of soil hydrology on N dynamics. Four ML models-linear regression (LR), ridge regression (RR), least absolute shrinkage and selection operator (LASSO) regression, and gradient boost regression trees (GBRT)-were assessed and validated using "leave-one-location-out" (LOLO) and "leave-one-year-out" (LOYO) approaches. Generally, RR outperformed other models in predicting both at planting and split EONR times. Among the 47 tested sites, for 33 sites the predicted split EONR using RR fell within the 95% confidence interval, suggesting the chance of using the RR model to make an acceptable prediction of split EONR is ∼70%. When RR was used to test split EONR prediction with input weather features surrogated with 10 yr of historical weather data, the model demonstrated robustness (MAE, 33.6 kg ha-1 ; R 2 = 0.46). Incorporating mechanistically derived hydrological features significantly enhanced the ability of the ML procedures to model EONR. Improvement in estimating in-season soil hydrological status seems essential for success in modeling N demand. Disciplines
Agronomy Journal
T he goal of an N recommendation system is to accurately estimate the gap between the N provided ... more T he goal of an N recommendation system is to accurately estimate the gap between the N provided by the soil and the N required by the plant. Accurately estimating this gap depends on the ability of the recommendation system to accurately estimate fi eld or subfi eld specifi c economically optimal nitrogen rates (EONR). Current recommendation systems are not as accurate as needed to provide consistently reliable estimates of N needs across years at the fi eld or subfi eld scale. Uncontrollable factors like temperature, rainfall timing, intensity and amount, and interactions of temperature and rainfall with factors such as N source, timing and placement, plant genetics, and soil characteristics combine to make N rate recommendations for an individual fi eld or rates for subfi elds a process guided as much by science as by the best professional judgement of farmers and farm advisors. Substantial evidence has accumulated that EONRs can vary widely across fi elds, within fi elds and over years in the same fi eld for a wide range of crops and geographies. Examples
Agronomy Journal
Due to economic and environmental consequences of N lost from fertilizer applications in corn (Ze... more Due to economic and environmental consequences of N lost from fertilizer applications in corn (Zea mays L.), considerable public and industry attention has been devoted to the development of N decision tools. Needed are research and databases and associated metadata, at numerous locations and years to represent a wide geographic range of soil and weather scenarios, for evaluating tool performance. The goals of this research were to conduct standardized corn N rate response field studies to evaluate the performance of multiple public-domain N decision tools across diverse soils and environmental conditions, develop and publish new agronomic science for improved crop N management, and train new scientists. The geographic scope, scale, and unique collaborative arrangement warrant documenting details of this research. The objectives of this paper are to describe how the research was undertaken, reasons for the methods, and the project's anticipated value. The project was initiated in a partnership between eight U.S. Midwest land-grant universities, USDA-ARS, and DuPont Pioneer. Research using a standardized protocol was conducted over the 2014 through 2016 growing seasons, yielding a total of 49 sites. Preliminary observations of soil and crop variables measured from each site revealed a magnitude of differences in soil properties (e.g., texture and organic matter) as well as differences in agronomic and economic responses to applied N. The project has generated a valuable dataset across a wide array of weather and soils that allows investigators to perform robust evaluation of N use in corn and N decision tools.
Crop Science
T he fundamental soybean [Glycine max (L.) Merr.] aboveground dry matter (DM) and nutrient uptake... more T he fundamental soybean [Glycine max (L.) Merr.] aboveground dry matter (DM) and nutrient uptake and partitioning models were first developed from work conducted in the 1960s by Hanway and Weber (1971a, 1971b, 1971c). The average US soybean yield at this time was a mere 1670 kg ha-1 (USDA-NASS, 2012). This is ~50% of present-day national average yields and only 21% of the estimated genetic yield potential of current soybean varieties (Specht et al., 1999). Since this fundamental work, more producers are achieving soybean yield consistently above 5000 kg ha-1 due to modern production practices and genetics (production realities), which have likely affected soybean DM and nitrogen (N) uptake, partitioning, and removal patterns and rates. Hanway and Weber (1971c) reported an average total DM accumulation of 9680 kg ha-1 for a yield of 2983 kg ha-1 with a peak accumulation rate of ~88 to 149 kg ha-1 d-1 (Hanway and Weber, 1971b), which agrees with Hammond et al. (1951) (110 kg ha-1 d-1). At maturity (R8), this yield represents ~29% of the DM partitioned to the seed (harvest index [HI]), with the remaining allocated to the leaves (28%), stems (17%), petioles (15%), and pods (11%). Greater seed yields over the past half century can simply be explained as the product of increased total plant DM, greater HI,
Crop Science
D ue to the soybean [Glycine max (L.) Merr.] plant's ability to fix atmospheric nitrogen (N), pho... more D ue to the soybean [Glycine max (L.) Merr.] plant's ability to fix atmospheric nitrogen (N), phosphorus (P) and potassium (K) fertilization is likely the most critical annual management decision in a profitable soybean fertility program. The work by Hanway and Weber (1971a) in the 1960s has been the base understanding of soybean P and K utilization and requirements for decades. However, superior genetic yield potential (Rincker et al., 2014), extended reproductive growth period (Zeiher et al., 1982), and greater dry matter (DM) harvest index (Koester et al., 2014) of current varieties, in conjunction with better management practices (Rowntree et al., 2014), have increased the frequency of growers achieving yields >5000 kg ha −1. These factors have likely altered soybean P and K requirements and contributed to declining P and K soil-test levels of some US soybean production regions (Fixen et al., 2010) and possibly limited yield. Alternatively, total daily maximum loads within several major watersheds remains a critical issue for water quality, even though nutrient transport within certain watersheds has decreased within the past decade (Lerch et al., 2015). Regardless, accurate estimates of soybean P and K requirements have the potential to increase grower profitability and reduce environmental
Soil Science Society of America Journal
Proceedings of the Integrated Crop Management Conference
Agronomy Journal
Reduced atmospheric S deposition, in conjunction with higher grain sale prices and steadily incre... more Reduced atmospheric S deposition, in conjunction with higher grain sale prices and steadily increasing yields of soybean [Glycine max (L.) Merr.], has many growers considering an increase in secondary and micronutrient applications. Limited information exists quantifying requirements of S, Mg, Ca, Zn, Mn, Cu, Fe, and B across a wide yield range for modern soybean production systems. Using six site-years and eight varieties, plants were sampled at six growth stages and partitioned into their respective plant parts and analyzed. Nutrients were acquired heavily (48-73%) from R1 through R5.5 with peak uptake rates near R3. Yet, uptake after R5.5 represented a greater portion of total S uptake as yield increased from the low (24.9%) to high (32.2%) yield level (3608 vs. 5483 kg ha-1). This coincided with seed S accumulation, which relied more heavily on continued uptake after R5.5 (58%) vs. vegetative S remobilization (42%). Across all environments (site × year) and varieties, total S uptake (0.004 kg S kg grain-1) and removal (0.003 kg S kg grain-1) showed moderate (R 2 = 0.58) and strong (R 2 = 0.76) relations with yield, respectively. These relations for each micronutrient were much weaker (R 2 = 0.13-0.66), due largely to the main effects of environment and variety along with their respective interactions with yield. Furthermore, micronutrient concentrations in leaf tissue varied considerably (CV = 28-46%) during recommend testing stages. Thus, previously reported inconsistent yield responses to foliar application of these micronutrients may primarily be due to the large variability in leaf tissue concentrations and nutrient requirements.
Soil Science Society of America Journal
Understanding the variables that affect the anaerobic potentially mineralizable N (PMN an) test s... more Understanding the variables that affect the anaerobic potentially mineralizable N (PMN an) test should lead to a standard procedure of sample collection and incubation length, improving PMN an as a tool in corn (Zea mays L.) N management. We evaluated the effect of soil sample timing (preplant and V5 corn development stage [V5]), N fertilization (0 and 180 kg ha −1) and incubation length (7, 14, and 28 d) on PMN an (0-30 cm) across a range of soil properties and weather conditions. Soil sample timing, N fertilization, and incubation length affected PMN an differently based on soil and weather conditions. Preplant vs. V5 PMN an tended to be greater at sites that received < 183 mm of precipitation or < 359 growing degree-days (GDD) between preplant and V5, or had soil C/N ratios > 9.7:1; otherwise, V5 PMN an tended to be greater than preplant PMN an. The PMN an tended to be greater in unfertilized vs. fertilized soil in sites with clay content > 9.5%, total C < 24.2 g kg −1 , soil organic Abbreviations: AWDR, Abundant and well-distributed rainfall; GDD, Growing degree-day; PMN an , Anaerobic potentially mineralizable N; SDI, Shannon diversity index; SOM, Soil organic matter. This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.
Agronomy Journal
Determining which corn (Zea mays L.) N fertilizer rate recommendation tools best predict crop N n... more Determining which corn (Zea mays L.) N fertilizer rate recommendation tools best predict crop N need would be valuable for maximizing profits and minimizing environmental consequences. Simultaneous comparisons of multiple tools across various environmental conditions have been limited. The objectives of this research were to evaluate the performance of publicly-available N fertilizer recommendation tools across diverse soil and weather conditions for: (i) prescribing N rates for planting and split-fertilizer applications, and (ii) economic and environmental effects. Corn N-response trials using standardized methods were conducted at 49 sites, spanning eight US Midwest states and three growing seasons. Nitrogen applications included eight rates in 45 kg N ha −1 increments all at-planting and matching rates with 45 kg N ha −1 at-planting plus at the V9 development stage. Tool performances were compared to the economically optimal N rate (EONR). Over this large geographic region, only 10 of 31 recommendation tools (mainly soil nitrate tests) produced N rate recommendations that weakly correlated to EONR (P ≤ .10; r 2 ≤ .20). With other metrics of performance, the Maximum Return to N (MRTN) soil nitrate tests, and canopy reflectance sensing came close to matching EONR. Economically, all tools but the Maize-N crop growth model had similar returns compared to EONR. Environmentally, yield goal based tools resulted in the highest environmental costs. Results show that no tool was universally reliable over this study's diverse growing environments, suggesting that additional tool development is needed to better represent N inputs and crop utilization at a larger regional level.
Agronomy Journal
Abbreviations: EONR, economic optimal N rate; EONR single , economic optimal N rate using a singl... more Abbreviations: EONR, economic optimal N rate; EONR single , economic optimal N rate using a single N application; EONR split , economic optimal N rate using a split N application; NH 4-N inc , NH 4-N after the soil was incubated for 7, 14, or 28 d; NH 4-N initial , initial NH 4-N in the soil; PMN an , anaerobic potentially mineralizable N; PP 0N , pre-plant soil sampling with 0 kg N ha-1 applied at planting; V5 0N , V5 soil sampling with 0 kg N ha-1 applied at planting; V5 180N , V5 soil sampling with 180 kg N ha-1 applied at planting.
HortTechnology
Organic sweet corn (Zea mays) production is challenging for growers because of the high nitrogen ... more Organic sweet corn (Zea mays) production is challenging for growers because of the high nitrogen (N) requirements of sweet corn and the relatively low N content of organic soil amendments. Total N supplied and rate of mineralization throughout the growing season are two important aspects in determining the optimal N management program. Green manure (GrM) crops, composted manures, and commercially available organic fertilizers are used to manage N in organic production systems. Using a combination of these tactics can optimize N while minimizing cost. In this study, we used combinations of composted poultry manure (CPM) and two organic fertilizers (one high N and one with a balance of nutrients) with three GrM crops [rye (Secale cereale), alfalfa (Medicago sativa), and pea (Pisum sativum)] in a loamy sand soil for a 112-day laboratory incubation study. Total plant available N (PAN) was quantified at six times throughout the 16 weeks to determine total N mineralized and rate of N rele...
Soil Science Society of America Journal
Nitrogen provided to crops through mineralization is an important factor in N management guidelin... more Nitrogen provided to crops through mineralization is an important factor in N management guidelines. understanding of the interactive effects of soil and weather conditions on N mineralization needs to be improved. relationships between anaerobic potentially mineralizable N (PMN an) and soil and weather conditions were evaluated under the contrasting climates of eight uS Midwestern states. Soil was sampled (0-30 cm) for PMN an analysis before pre-plant N application (PP 0N) and at the V5 development stage from the pre-plant 0 (V5 0N) and 180 kg N ha −1 (V5 180N) rates and incubated for 7, 14, and 28 d. Even distribution of precipitation and warmer temperatures before soil sampling and greater soil organic matter (SOM) increased PMN an. Soil properties, including total C, SOM, and total N, had the strongest relationships with PMN an (R 2 ≤ 0.40), followed by temperature (R 2 ≤ 0.20) and precipitation (R 2 ≤ 0.18) variables. the strength of the relationships between soil properties and PMN an from PP 0N , V5 0N , and V5 180N varied by ≤10%. Including soil and weather in the model greatly increased PMN an predictability (R 2 ≤ 0.69), demonstrating the interactive effect of soil and weather on N mineralization at different times during the growing season regardless of N fertilization. Delayed soil sampling (V5 0N) and sampling after fertilization (V5 180N) reduced PMN an predictability. However, longer PMN an incubations improved PMN an predictability from both V5 soil samplings closer to the PMN an predictability from PP 0N , indicating the potential of PMN an from longer incubations to provide improved estimates of N mineralization when N fertilizer is applied.
Computers and Electronics in Agriculture
Nitrogen (N) fertilizer recommendation tools could be improved for estimating corn (Zea mays L.) ... more Nitrogen (N) fertilizer recommendation tools could be improved for estimating corn (Zea mays L.) N needs by incorporating site-specific soil and weather information. However, an evaluation of analytical methods is needed to determine the success of incorporating this information. The objectives of this research were to evaluate statistical and machine learning (ML) algorithms for utilizing soil and weather information for improving corn N recommendation tools. Eight algorithms [stepwise, ridge regression, least absolute shrinkage and selection operator (Lasso), elastic net regression, principal component regression (PCR), partial least squares regression (PLSR), decision tree, and random forest] were evaluated using a dataset containing measured soil and weather variables from a regional database. The performance was evaluated based on how well these algorithms predicted corn economically optimal N rates (EONR) from 49 sites in the U.S. Midwest. Multiple algorithm modeling scenarios were examined with and without adjustment for multicollinearity and inclusion of two-way interaction terms to identify the soil and weather variables that could improve three dissimilar N recommendation tools. Results showed the out-of-sample root-mean-square error (RMSE) for the decision tree and some random forest modeling scenarios were better than the stepwise or ridge regression, but not significantly different than any other algorithm. The best ML algorithm for adjusting N recommendation tools was the random forest approach (r2 increased between 0.72 and 0.84 and the RMSE decreased between 41 and 94 kg N ha−1). However, the ML algorithm that best adjusted tools while using a minimal amount of variables was the decision tree. This method was simple, needing only one or two variables (regardless of modeling scenario) and provided moderate improvement as r2 values increased between 0.15 and 0.51 and RMSE decreased between 16 and 66 kg N ha−1. Using ML algorithms to adjust N recommendation tools with soil and weather information shows promising results for better N management in the U.S. Midwest.
Agronomy Journal
Determination of in-season N requirement for corn (Zea mays L.) is challenging due to interaction... more Determination of in-season N requirement for corn (Zea mays L.) is challenging due to interactions of genotype, environment, and management. Machine learning (ML), with its predictive power to tackle complex systems, may solve this barrier in the development of locally based N recommendations. The objective of this study was to explore application of ML methodologies to predict economic optimum nitrogen rate (EONR) for corn using data from 47 experiments across the US Corn Belt. Two features, a water table adjusted available water capacity (AWC wt) and a ratio of in-season rainfall to AWC wt (RAWC wt), were created to capture the impact of soil hydrology on N dynamics. Four ML models-linear regression (LR), ridge regression (RR), least absolute shrinkage and selection operator (LASSO) regression, and gradient boost regression trees (GBRT)-were assessed and validated using "leave-one-location-out" (LOLO) and "leave-one-year-out" (LOYO) approaches. Generally, RR outperformed other models in predicting both at planting and split EONR times. Among the 47 tested sites, for 33 sites the predicted split EONR using RR fell within the 95% confidence interval, suggesting the chance of using the RR model to make an acceptable prediction of split EONR is ∼70%. When RR was used to test split EONR prediction with input weather features surrogated with 10 yr of historical weather data, the model demonstrated robustness (MAE, 33.6 kg ha-1 ; R 2 = 0.46). Incorporating mechanistically derived hydrological features significantly enhanced the ability of the ML procedures to model EONR. Improvement in estimating in-season soil hydrological status seems essential for success in modeling N demand. Disciplines
Agronomy Journal
T he goal of an N recommendation system is to accurately estimate the gap between the N provided ... more T he goal of an N recommendation system is to accurately estimate the gap between the N provided by the soil and the N required by the plant. Accurately estimating this gap depends on the ability of the recommendation system to accurately estimate fi eld or subfi eld specifi c economically optimal nitrogen rates (EONR). Current recommendation systems are not as accurate as needed to provide consistently reliable estimates of N needs across years at the fi eld or subfi eld scale. Uncontrollable factors like temperature, rainfall timing, intensity and amount, and interactions of temperature and rainfall with factors such as N source, timing and placement, plant genetics, and soil characteristics combine to make N rate recommendations for an individual fi eld or rates for subfi elds a process guided as much by science as by the best professional judgement of farmers and farm advisors. Substantial evidence has accumulated that EONRs can vary widely across fi elds, within fi elds and over years in the same fi eld for a wide range of crops and geographies. Examples
Agronomy Journal
Due to economic and environmental consequences of N lost from fertilizer applications in corn (Ze... more Due to economic and environmental consequences of N lost from fertilizer applications in corn (Zea mays L.), considerable public and industry attention has been devoted to the development of N decision tools. Needed are research and databases and associated metadata, at numerous locations and years to represent a wide geographic range of soil and weather scenarios, for evaluating tool performance. The goals of this research were to conduct standardized corn N rate response field studies to evaluate the performance of multiple public-domain N decision tools across diverse soils and environmental conditions, develop and publish new agronomic science for improved crop N management, and train new scientists. The geographic scope, scale, and unique collaborative arrangement warrant documenting details of this research. The objectives of this paper are to describe how the research was undertaken, reasons for the methods, and the project's anticipated value. The project was initiated in a partnership between eight U.S. Midwest land-grant universities, USDA-ARS, and DuPont Pioneer. Research using a standardized protocol was conducted over the 2014 through 2016 growing seasons, yielding a total of 49 sites. Preliminary observations of soil and crop variables measured from each site revealed a magnitude of differences in soil properties (e.g., texture and organic matter) as well as differences in agronomic and economic responses to applied N. The project has generated a valuable dataset across a wide array of weather and soils that allows investigators to perform robust evaluation of N use in corn and N decision tools.
Crop Science
T he fundamental soybean [Glycine max (L.) Merr.] aboveground dry matter (DM) and nutrient uptake... more T he fundamental soybean [Glycine max (L.) Merr.] aboveground dry matter (DM) and nutrient uptake and partitioning models were first developed from work conducted in the 1960s by Hanway and Weber (1971a, 1971b, 1971c). The average US soybean yield at this time was a mere 1670 kg ha-1 (USDA-NASS, 2012). This is ~50% of present-day national average yields and only 21% of the estimated genetic yield potential of current soybean varieties (Specht et al., 1999). Since this fundamental work, more producers are achieving soybean yield consistently above 5000 kg ha-1 due to modern production practices and genetics (production realities), which have likely affected soybean DM and nitrogen (N) uptake, partitioning, and removal patterns and rates. Hanway and Weber (1971c) reported an average total DM accumulation of 9680 kg ha-1 for a yield of 2983 kg ha-1 with a peak accumulation rate of ~88 to 149 kg ha-1 d-1 (Hanway and Weber, 1971b), which agrees with Hammond et al. (1951) (110 kg ha-1 d-1). At maturity (R8), this yield represents ~29% of the DM partitioned to the seed (harvest index [HI]), with the remaining allocated to the leaves (28%), stems (17%), petioles (15%), and pods (11%). Greater seed yields over the past half century can simply be explained as the product of increased total plant DM, greater HI,
Crop Science
D ue to the soybean [Glycine max (L.) Merr.] plant's ability to fix atmospheric nitrogen (N), pho... more D ue to the soybean [Glycine max (L.) Merr.] plant's ability to fix atmospheric nitrogen (N), phosphorus (P) and potassium (K) fertilization is likely the most critical annual management decision in a profitable soybean fertility program. The work by Hanway and Weber (1971a) in the 1960s has been the base understanding of soybean P and K utilization and requirements for decades. However, superior genetic yield potential (Rincker et al., 2014), extended reproductive growth period (Zeiher et al., 1982), and greater dry matter (DM) harvest index (Koester et al., 2014) of current varieties, in conjunction with better management practices (Rowntree et al., 2014), have increased the frequency of growers achieving yields >5000 kg ha −1. These factors have likely altered soybean P and K requirements and contributed to declining P and K soil-test levels of some US soybean production regions (Fixen et al., 2010) and possibly limited yield. Alternatively, total daily maximum loads within several major watersheds remains a critical issue for water quality, even though nutrient transport within certain watersheds has decreased within the past decade (Lerch et al., 2015). Regardless, accurate estimates of soybean P and K requirements have the potential to increase grower profitability and reduce environmental