Combining Simple Phenotyping and Photothermal Algorithm for the Prediction of Soybean Phenology: Application to a Range of Common Cultivars Grown in Europe

European soybean to benefit people and the environment

Europe imports large amounts of soybean that are predominantly used for livestock feed, mainly sourced from Brazil, USA and Argentina. In addition, the demand for GM-free soybean for human consumption is project to increase. Soybean has higher protein quality and digestibility than other legumes, along with high concentrations of isoflavones, phytosterols and minerals that enhance the nutritional value as a human food ingredient. Here, we examine the potential to increase soybean production across Europe for livestock feed and direct human consumption, and review possible effects on the environment and human health. Simulations and field data indicate rainfed soybean yields of 3.1 ± 1.2 t ha-1 from southern UK through to southern Europe (compared to a 3.5 t ha-1 average from North America). Drought-prone southern regions and cooler northern regions require breeding to incorporate stress-tolerance traits. Literature synthesized in this work evidenced soybean properties important to human nutrition, health, and traits related to food processing compared to alternative protein sources. While acknowledging the uncertainties inherent in any modelling exercise, our findings suggest that further integrating soybean into European agriculture could reduce GHG emissions by 37-291 Mt CO2e year-1 and fertiliser N use by 0.6-1.2 Mt year-1, concurrently improving human health and nutrition.

Future area expansion outweighs increasing drought risk for soybean in Europe

The European Union is highly dependent on soybean imports from overseas to meet its protein demands. Individual Member States have been quick to declare self-sufficiency targets for plant-based proteins, but detailed strategies are still lacking. Rising global temperatures have painted an image of a bright future for soybean production in Europe, but emerging climatic risks such as drought have so far not been included in any of those outlooks. Here, we present simulations of future soybean production and the most prominent risk factors across Europe using an ensemble of climate and soybean growth models. Projections suggest a substantial increase in potential soybean production area and productivity in Central Europe, while southern European production would become increasingly dependent on supplementary irrigation. Average productivity would rise by 8.3% (RCP 4.5) to 8.7% (RCP 8.5) as a result of improved growing conditions (plant physiology benefiting from rising temperature and CO₂ levels) and farmers adapting to them by using cultivars with longer phenological cycles. Suitable production area would rise by 31.4% (RCP 4.5) to 37.7% (RCP 8.5) by the mid-century, contributing considerably more than productivity increase to the production potential for closing the protein gap in Europe. While wet conditions at harvest and incidental cold spells are the current key challenges for extending soybean production, the models and climate data analysis anticipate that drought and heat will become the dominant limitations in the future. Breeding for heat-tolerant and water-efficient genotypes is needed to further improve soybean adaptation to changing climatic conditions.

Data-driven projections suggest large opportunities to improve Europe's soybean self-sufficiency under climate change

The rapid expansion of soybean-growing areas across Europe raises questions about the suitability of agroclimatic conditions for soybean production. Here, using data-driven relationships between climate and soybean yield derived from machine-learning, we made yield projections under current and future climate with moderate (Representative Concentration Pathway (RCP) 4.5) to intense (RCP 8.5) warming, up to the 2050s and 2090s time horizons. The selected model showed high R² (>0.9) and low root-mean-squared error (0.35 t ha^-1) between observed and predicted yields based on cross-validation. Our results suggest that a self-sufficiency level of 50% (100%) would be achievable in Europe under historical and future climate if 4-5% (9-11%) of the current European cropland were dedicated to soybean production. The findings could help farmers, extension services, policymakers and agribusiness to reorganize the production area distribution. The environmental benefits and side effects, and the impacts of soybean expansion on land-use change, would need further research.

Evapotranspiration of Irrigated Crops under Warming and Elevated Atmospheric CO2: What Is the Direction of Change?

Future changes in crop evapotranspiration (ETc) are of interest to water management stakeholders. However, long-term projections are complex and merit further investigation due to uncertainties in climate data, differential responses of crops to climate and elevated atmospheric CO2, and adaptive agricultural management. We conducted factor-control simulation experiments using the process-based CropSyst model and investigated the contribution of each of these factors. Five major irrigated crops in the Columbia Basin Project area of the USA Pacific Northwest were selected as a case study and fifteen general circulation models (GCM) under two representative concentration pathways (RCP) were used as the climate forcing. Results indicated a wide range in ETc change, depending on the time frame, crop type, planting dates, and CO2 assumptions. Under the 2090s RCP8.5 scenario, ETc changes were crop-specific: +14.3% (alfalfa), +8.1% (potato), −5.1% (dry bean), −8.1% (corn), and −12.5% (spring wheat). Future elevated CO2 concentrations decreased ETc for all crops while earlier planting increased ETc for all crops except spring wheat. Changes in reference ET (ETo) only partially explains changes in ETc because crop responses are an important modulating factor; therefore, caution must be exercised in interpreting ETo changes as a proxy for ETc changes.

Soybean Nodulation Response to Cropping Interval and Inoculation in European Cropping Systems

To support the adaption of soybean [Glycine max (L) Merrill] cultivation across Central Europe, the availability of compatible soybean nodulating Bradyrhizobia (SNB) is essential. Little is known about the symbiotic potential of indigenous SNB in Central Europe and the interaction with an SNB inoculum from commercial products. The objective of this study was to quantify the capacity of indigenous and inoculated SNB strains on the symbiotic performance of soybean in a pot experiment, using soils with and without soybean history. Under controlled conditions in a growth chamber, the study focused on two main factors: a soybean cropping interval (time since the last soybean cultivation; SCI) and inoculation with commercial Bradyrhizobia strains. Comparing the two types of soil, without soybean history and with 1-4 years SCI, we found out that plants grown in soil with soybean history and without inoculation had significantly more root nodules and higher nitrogen content in the plant tissue. These parameters, along with the leghemoglobin content, were found to be a variable among soils with 1-4 years SCI and did not show a trend over the years. Inoculation in soil without soybean history showed a significant increase in a nodulation rate, leghemoglobin content, and soybean tissue nitrogen concentration. The study found that response to inoculation varied significantly as per locations in soil with previous soybean cultivation history. An inoculated soybean grown on loamy sandy soils from the location Müncheberg had significantly more nodules as well as higher green tissue nitrogen concentration compared with non-inoculated plants. No significant improvement in a nodulation rate and tissue nitrogen concentration was observed for an inoculated soybean grown on loamy sandy soils from the location Fehrow. These results suggest that introduced SNB strains remained viable in the soil and were still symbiotically competent for up to 4 years after soybean cultivation. However, the symbiotic performance of the SNB remaining in the soils was not sufficient in all cases and makes inoculation with commercial products necessary. The SNB strains found in the soil of Central Europe could also be promising candidates for the development of inoculants and already represent a contribution to the successful cultivation of soybeans in Central Europe.

Machine Learning Techniques for Soybean Charcoal Rot Disease Prediction

Early prediction of pathogen infestation is a key factor to reduce the disease spread in plants. Macrophomina phaseolina (Tassi) Goid, as one of the main causes of charcoal rot disease, suppresses the plant productivity significantly. Charcoal rot disease is one of the most severe threats to soybean productivity. Prediction of this disease in soybeans is very tedious and non-practical using traditional approaches. Machine learning (ML) techniques have recently gained substantial traction across numerous domains. ML methods can be applied to detect plant diseases, prior to the full appearance of symptoms. In this paper, several ML techniques were developed and examined for prediction of charcoal rot disease in soybean for a cohort of 2,000 healthy and infected plants. A hybrid set of physiological and morphological features were suggested as inputs to the ML models. All developed ML models were performed better than 90% in terms of accuracy. Gradient Tree Boosting (GBT) was the best performing classifier which obtained 96.25% and 97.33% in terms of sensitivity and specificity. Our findings supported the applicability of ML especially GBT for charcoal rot disease prediction in a real environment. Moreover, our analysis demonstrated the importance of including physiological featured in the learning. The collected dataset and source code can be found in https://github.com/Elham-khalili/Soybean-Charcoal-Rot-Disease-Prediction-Dataset-code.

Combining Experimental and Modeling Approaches to Understand Genotype x Sowing Date x Environment Interaction Effects on Emergence Rates and Grain Yield of Soybean

Soybean emergence and yield may be affected by many factors. A better understanding of the cultivar x sowing date x environment interactions could shed light into the competitiveness of soybean with other crops, notably, to help manage major biotic and abiotic factors that limit soybean production. We conducted a 2-year field experiments to measure emergence dynamics and final rates of three soybean cultivars from different maturity groups, with early and conventional sowing dates and across three locations. We also measured germination parameter values of the three soybean cultivars from different maturity groups under controlled experiments to parametrize the SIMPLE crop emergence model. This allowed us to assess the prediction quality of the model for emergence rates and to perform simulations. Final emergence rates under field conditions ranged from 62% to 92% and from 51% to 94% for early and conventional sowing, respectively. The model finely predicted emergence courses and final rates (root mean square error of prediction (RMSEP), efficiency (EF), and mean deviation (MD) ranging between 2% to 18%, 0.46% to 0.99%, and -10% to 15%, respectively) across a wide range of the sowing conditions tested. Differences in the final emergence rates were found, not only among cultivars but also among locations for the same cultivar, although no clear trend or consistent ranking was found in this regard. Modeling suggests that seedling mortality rates were dependent on the soil type with up to 35% and 14% of mortality in the silty loam soil, due to a soil surface crust and soil aggregates, respectively. Non-germination was the least important cause of seedling mortality in all soil types (up to 3% of emergence losses), while no seedling mortality due to drought was observed. The average grain yield ranged from 3.1 to 4.0 t ha^-1, and it was significantly affected by the irrigation regime (p < 0.001) and year (p < 0.001) but not by locations, sowing date or cultivars. We conclude that early sowing is unlikely to affect soybean emergence in South-West of France and therefore may represent an important agronomic lever to escape summer drought that markedly limit soybean yield in this region.