Filling the agronomic data gap through a minimum data collection approach.

Context: Agronomic data such as applied inputs, management practices, and crop yields are needed for assessing productivity, nutrient balances, resource use efficiency, as well as other aspects of environmental and economic performance of cropping systems. In many instances, however, these data are only available at a coarse level of aggregation or simply do not exist. Objectives: Here we developed an approach that identifies sites for agronomic data collection for a given crop and country, seeking a balance between minimizing data collection efforts and proper representation of the main crop producing areas. Methods: The developed approach followed a stratified sampling method based on a spatial framework that delineates major climate zones and crop area distribution maps, which guides selection of sampling areas (SA) until half of the national harvested area is covered. We provided proof of concept about the robustness of the approach using three rich databases including data on fertilizer application rates for maize, wheat, and soybean in Argentina, soybean in the USA, and maize in Kenya, which were collected via local experts (Argentina) and field surveys (USA and Kenya). For validation purposes, fertilizer rates per crop and nutrient derived at (sub-) national level following our approach were compared against those derived using all data collected from the whole country. Results: Application of the approach in Argentina, USA, and Kenya resulted in selection of 12, 28, and 10 SAs, respectively. For each SA, three experts or 20 fields were sufficient to give a robust estimate of average fertilizer rates applied by farmers. Average rates at national level derived from our approach compared well with those derived using the whole database ( ± 10 kg N, ± 2 kg P, ± 1 kg S, and ± 5 kg K per ha) requiring less than one third of the observations. Conclusions: The developed minimum crop data collection approach can fill the agronomic data gaps in a cost-effective way for major crop systems both in large- and small-scale systems. Significance: The proposed approach is generic enough to be applied to any crop-country combination to guide collection of key agricultural data at national and subnational levels with modest investment especially for countries that do not currently collect data.

Integration of Row Spacing, Seeding Rates, and Fungicide Applications for Control of Sclerotinia Stem Rot in Glycine max.

Soybean (Glycine max) farmers in the Upper Midwest region of the United States often experience severe yield losses due to Sclerotinia stem rot (SSR). Previous studies have revealed benefits of individual management practices for SSR. This study examined the integration of multiple control practices on the development of SSR, yield, and the economic implications of these practices. Combinations of row spacings, seeding rates, and fungicide applications were examined in multisite field trials across the Upper Midwest from 2017 to 2019. These trials revealed that wide row spacing and low seeding rates individually reduced SSR levels but also reduced yields. Yields were similar across the three highest seeding rates examined. However, site-years where SSR developed showed the highest partial profits at the intermediate seeding rates. This finding indicates that partial profits in diseased fields were reduced by high seeding rates, but this trend was not observed when SSR did not develop. Fungicides strongly reduced the development of SSR while also increasing yields. However, there was a reduction in partial profits due to their use at a low soybean sale price, but at higher sale prices fungicide use was similar to not treating. Additionally, the production of new inoculum was predicted from disease incidence, serving as an indicator of increased risk for SSR development in future years. Overall, this study suggests using wide rows and low seeding rates in fields with a history of SSR while reserving narrow rows and higher seeding rates for fields without a history of SSR.

A machine learning interpretation of the contribution of foliar fungicides to soybean yield in the north-central United States.

Foliar fungicide usage in soybeans in the north-central United States increased steadily over the past two decades. An agronomically-interpretable machine learning framework was used to understand the importance of foliar fungicides relative to other factors associated with realized soybean yields, as reported by growers surveyed from 2014 to 2016. A database of 2738 spatially referenced fields (of which 30% had been sprayed with foliar fungicides) was fit to a random forest model explaining soybean yield. Latitude (a proxy for unmeasured agronomic factors) and sowing date were the two most important factors associated with yield. Foliar fungicides ranked 7th out of 20 factors in terms of relative importance. Pairwise interactions between latitude, sowing date and foliar fungicide use indicated more yield benefit to using foliar fungicides in late-planted fields and in lower latitudes. There was a greater yield response to foliar fungicides in higher-yield environments, but less than a 100 kg/ha yield penalty for not using foliar fungicides in such environments. Except in a few production environments, yield gains due to foliar fungicides sufficiently offset the associated costs of the intervention when soybean prices are near-to-above average but do not negate the importance of disease scouting and fungicide resistance management.

Advancing agricultural research using machine learning algorithms.

Rising global population and climate change realities dictate that agricultural productivity must be accelerated. Results from current traditional research approaches are difficult to extrapolate to all possible fields because they are dependent on specific soil types, weather conditions, and background management combinations that are not applicable nor translatable to all farms. A method that accurately evaluates the effectiveness of infinite cropping system interactions (involving multiple management practices) to increase maize and soybean yield across the US does not exist. Here, we utilize extensive databases and artificial intelligence algorithms and show that complex interactions, which cannot be evaluated in replicated trials, are associated with large crop yield variability and thus, potential for substantial yield increases. Our approach can accelerate agricultural research, identify sustainable practices, and help overcome future food demands.

Neonicotinoid seed treatments of soybean provide negligible benefits to US farmers.

Neonicotinoids are the most widely used insecticides worldwide and are typically deployed as seed treatments (hereafter NST) in many grain and oilseed crops, including soybeans. However, there is a surprising dearth of information regarding NST effectiveness in increasing soybean seed yield, and most published data suggest weak, or inconsistent yield benefit. The US is the key soybean-producing nation worldwide and this work includes soybean yield data from 194 randomized and replicated field studies conducted specifically to evaluate the effect of NSTs on soybean seed yield at sites within 14 states from 2006 through 2017. Here we show that across the principal soybean-growing region of the country, there are negligible and management-specific yield benefits attributed to NSTs. Across the entire region, the maximum observed yield benefits due to fungicide (FST = fungicide seed treatment) + neonicotinoid use (FST + NST) reached 0.13 Mg/ha. Across the entire region, combinations of management practices affected the effectiveness of FST + NST to increase yield but benefits were minimal ranging between 0.01 to 0.22 Mg/ha. Despite widespread use, this practice appears to have little benefit for most of soybean producers; across the entire region, a partial economic analysis further showed inconsistent evidence of a break-even cost of FST or FST + NST. These results demonstrate that the current widespread prophylactic use of NST in the key soybean-producing areas of the US should be re-evaluated by producers and regulators alike.

Defining Optimal Soybean Sowing Dates across the US.

Global crop demand is expected to increase by 60-110% by 2050. Climate change has already affected crop yields in some countries, and these effects are expected to continue. Identification of weather-related yield-limiting conditions and development of strategies for agricultural adaptation to climate change is essential to mitigate food security concerns. Here we used machine learning on US soybean yield data, collected from cultivar trials conducted in 27 states from 2007 to 2016, to examine crop sensitivity to varying in-season weather conditions. We identified the month-specific negative effect of drought via increased water vapor pressure deficit. Excluding Texas and Mississippi, where later sowing increased yield, sowing 12 days earlier than what was practiced during this decade across the US would have resulted in 10% greater total yield and a cumulative monetary gain of ca. US$9 billion. Our data show the substantial nation- and region-specific yield and monetary effects of adjusting sowing timing and highlight the importance of continuously quantifying and adapting to climate change. The magnitude of impact estimated in our study suggest that policy makers (e.g., federal crop insurance) and laggards (farmers that are slow to adopt) that fail to acknowledge and adapt to climate change will impact the national food security and economy of the US.

Climate Change and ENSO Effects on Southeastern US Climate Patterns and Maize Yield.

Climate change has a strong influence on weather patterns and significantly affects crop yields globally. El Niño Southern Oscillation (ENSO) has a strong influence on the U.S. climate and is related to agricultural production variability. ENSO effects are location-specific and in southeastern U.S. strongly connect with climate variability. When combined with climate change, the effects on growing season climate patterns and crop yields might be greater than expected. In our study, historical monthly precipitation and temperature data were coupled with non-irrigated maize yield data (33-43 years depending on the location) to show a potential yield suppression of ~15% for one °C increase in southeastern U.S. growing season maximum temperature. Yield suppression ranged between -25 and -2% among locations suppressing the southeastern U.S. average yield trend since 1981 by 17 kg ha(-1)year(-1) (~25%), mainly due to year-to-year June temperature anomalies. Yields varied among ENSO phases from 1971-2013, with greater yields observed during El Niño phase. During La Niña years, maximum June temperatures were higher than Neutral and El Niño, whereas June precipitation was lower than El Niño years. Our data highlight the importance of developing location-specific adaptation strategies quantifying both, climate change and ENSO effects on month-specific growing season climate conditions.

Climate-induced reduction in US-wide soybean yields underpinned by region- and in-season-specific responses.

The United States is one of the largest soybean exporters in the world. Production is concentrated in the upper Midwest(1). Much of this region is not irrigated, rendering soybean production systems in the area highly sensitive to in-season variations in weather. Although the influence of in-season weather trends on the yields of crops such as soybean, wheat and maize has been explored in several countries(2-6), the potentially confounding influence of genetic improvements on yields has been overlooked. Here we assess the effect of in-season weather trends on soybean yields in the United States between 1994 and 2013, using field trial data, meteorological data and information on crop management practices, including the adoption of new cultivars. We show that in-season temperature trends had a greater impact on soybean yields than in-season precipitation trends over the measurement period. Averaging across the United States, we show that soybean yields fell by around 2.4% for every 1 °C rise in growing season temperature. However, the response varied significantly among individual states, ranging from -22% to +9%, and also with the month of the year in which the warming occurred. We estimate that year-to-year changes in precipitation and temperature combined suppressed the US average yield gain by around 30% over the measurement period, leading to a loss of US$11 billion. Our data highlight the importance of developing location-specific adaptation strategies for climate change based on early-, mid- and late-growing season climate trends.