Search

Soybean seed yield and protein concentration are functions of the genetic, environmental, and management interactions. Both traits are frequently reported as negatively correlated since increases in seed yield are normally not accompanied by increases in seed protein concentration. The main goal of this study was to explore the impact of practical management decisions like (i) nutrition at sowing, and (ii) foliar fertilization at the beginning of seed-filling on seed yield and protein concentration of GMO and non-GMO soybean, across two regions with contrasting historical seed yield and protein concentrations: (i) high yielding and low protein region – Central region, and (ii) low yielding and high protein region – North-West region of Argentina. Within regions, fields were further classified as high and low productivity according to farmers' expertise. For Central region, improved nutrition at sowing yielded 5.4% (p < 0.05) and showed 0.9% more seed protein concentration than conventional treatment (p < 0.001). Non-GMO genotypes presented 9.6% less seed yield but 0,7% more seed protein concentration than GMO ones (p < 0.01). Seed yield differences between foliar treatments were variable between field productivities (p < 0.05) with no effects on seed protein concentration. High productivity fields showed ∼16% more seed yield and 0.7% higher seed protein concentration than low productivity fields (p < 0.001). For North-West region, seed yield was not affected by sowing treatments. Seed protein concentration of improved treatment was 0.3% higher than conventional treatment at sowing (p < 0.05). Likewise, non-GMO genotypes showed 0.7% more seed protein concentration than GMO ones (p < 0.001). Regardless of the region, changes in seed protein concentration due to the changes in tested factors were not correlated with changes in seed yield (p > 0.05). Our findings highlighted that (i) fertilization and inoculation constitute practical options for farmers to modify soybean productivity and seed quality, (ii) the effectiveness of changes in some input practices like foliar fertilization depended on the region where soybean was cultivated and (iii) not all changes in tested factors that allowed increased yields, impacted negatively on soybean seed protein concentration. • Nutrition practices effects on seed yield and seed protein concentration varied with region in Argentina. • Nutrition practices did not affect yields in North-West region of Argentina. • Non-GMO genotypes showed less or equal yield but more protein concentration than GMOs. • Foliar fertilization increased seed yield in low productivity fields of Central region. • Fertilization at sowing and seed treatment increased seed protein without yield penalty. [ABSTRACT FROM AUTHOR]

When soybean is grown in soils with high heavy metal concentrations, it may introduce those contaminants into the human food chain, posing risks to human health. This study evaluated the effect of tilling the soil with high Cu, Zn, and Mn levels on soybean physiology and metal accumulation in seeds. Disturbed and undisturbed soil samples were collected in two different sites: a vineyard with high heavy metal concentration and a grassland area, containing natural vegetation. Two soybean cultivars were sown and grown in the greenhouse. Photosynthetic parameters and biochemical analysis of oxidative stress were performed. Cu, Zn, and Mn in leaves and seeds, dry mass, and weight of seeds were evaluated. Soil structure had a high influence on plant growth and physiology, while soil site had a high impact on heavy metal accumulation in leaves and seeds. Soybean plants that grown in vineyard soils with high heavy metal concentrations, accumulated 50% more Zn in leaves and seeds, 70% more Cu in leaves, and 90% more Cu in seeds, than those plants grown in grassland soils. Besides, Zn concentration in seeds was higher than the permissible limit. Moreover, the disturbance of both vineyard soil and grassland soil was not good for plant growth and physiology, which have increased TBARS and H 2 O 2 concentration in plants, transpiration rate, metal concentration in leaves and seeds. Soil disturbance may have caused organic matter oxidation and changes in the composition and quantity of soil microorganisms and it affects the availability of other nutrients in the soil. [Display omitted] • We cultivate soybean in vineyard soil with high heavy metal concentration. • Disturbed soil structure was more deleterious to plants than undisturbed one. • Metals injury plant physiology and accumulate in seeds poising risks to our health. • Zinc concentration in soybean seeds exceeded the permissible limit. [ABSTRACT FROM AUTHOR]

• Soybean yield at municipality-level was forecasted using satellite and weather data. • LSTM neural networks outperformed conventional machine learning algorithms in soybean yield prediction. • The model accuracy decreased as we anticipated earlier dates of the predictions. • Soybean yield can be forecasted with MAE of 0.42 Mg ha−1 ~70 days before harvesting. Soybean yield predictions in Brazil are of great interest for market behavior, to drive governmental policies and to increase global food security. In Brazil soybean yield data generally demand various revisions through the following months after harvest suggesting that there is space for improving the accuracy and the time of yield predictions. This study presents a novel model to perform in-season ("near real-time") soybean yield forecasts in southern Brazil using Long-Short Term Memory (LSTM), Neural Networks, satellite imagery and weather data. The objectives of this study were to: (i) compare the performance of three different algorithms (multivariate OLS linear regression, random forest and LSTM neural networks) for forecasting soybean yield using NDVI, EVI, land surface temperature and precipitation as independent variables, and (ii) evaluate how early (during the soybean growing season) this method is able to forecast yield with reasonable accuracy. Satellite and weather data were masked using a non-crop-specific layer with field boundaries obtained from the Rural Environment Registry that is mandatory for all farmers in Brazil. Main outcomes from this study were: (i) soybean yield forecasts at municipality-scale with a mean absolute error (MAE) of 0.24 Mg ha−1 at DOY 64 (march 5) (ii) a superior performance of the LSTM neural networks relative to the other algorithms for all the forecast dates except DOY 16 where multivariate OLS linear regression provided the best performance, and (iii) model performance (e.g., MAE) for yield forecast decreased when predictions were performed earlier in the season, with MAE increasing from 0.24 Mg ha−1 to 0.42 Mg ha−1 (last values from OLS regression) when forecast timing changed from DOY 64 (March 5) to DOY 16 (January 6). This research portrays the benefits of integrating statistical techniques, remote sensing, weather to field survey data in order to perform more reliable in-season soybean yield forecasts. [ABSTRACT FROM AUTHOR]

• Data fusion offered new opportunities for agricultural monitoring. • Spatial data patterns affected model performance in regions with high variability. • Aggregating crop year data presented high accuracy in transfer learning. • Early crop classification resulted in similar overall accuracy to full length time-series. • Crop classification and mapping were produced for Rio Grande do Sul state, Brazil. Field-scale crop monitoring is essential for agricultural management and policy making for food security and sustainability. Automating crop classification process while elaborating a workflow is a key step for reliable and precise crop mapping. This study aims to develop an approach for crop classification in the state of Rio Grande do Sul, Brazil, following the specific goals of i) evaluating spatial satellite-based features to guide crop data collection; ii) testing transfer learning model with subsequent growing season data; iii) examining accuracy in early-season prediction model; and lastly, iv) developing a crop classification model for estimating large scale crop area. As main data inputs, Sentinel-2, Sentinel-1, and Shuttle Radar Topographic Mission (SRTM) Digital Elevation data were used to extract features to input in the Random Forest classifier. Spatial variability of satellite features was evaluated using Moran's I Index and cluster k-means. Crop area prediction data were obtained at municipality level to compare with census data (standard method). A crop summer map layer was generated for three major crops: soybeans (Glycine max L.), corn (Zea mays L.), and rice (Oryza sativa L.) in the state of Rio Grande do Sul, Brazil. The crop classification model achieved an overall accuracy of 0.95. Model performance was influenced by sample size and spatial variability of the samples. The random forest model was transferred to the next growing season with 0.89 and 0.91 overall accuracy for 250 and 750 samples, respectively. However, overall accuracy increased from 0.93 to 0.95 when 50 to 250 samples of same-year data was aggregated to the model. Similar accuracy was obtained for predictions done with data until March relative to when the entire season was considered, until May. When data for more growing seasons were aggregated, the model produced more accurate early season predictions (January and February). Soybean prediction area obtained the highest performance (R2 = 0.94), relative to rice (R2 = 0.90) and corn (R2 = 0.37). The rice prediction area presented a high precision, but the crop area was overestimated due to errors with wetland target relative to other class. Lastly, this study presents the first crop map layer of the three major field crops for the state of Rio Grande do Sul, Brazil, serving as a foundation for the creation of crop type maps for other states in the country and around the globe. [ABSTRACT FROM AUTHOR]

• Remote-sensing based crop type maps and available datasets enable rotation mapping. • Continuous soybean was the most common crop rotation in Rio Grande do Sul, Brazil. • Crop rotation in lowlands showed an increase in soybean area in rotation with rice. • Crop rotation had more benefits for soybean yields according to different regions. • The study showed an end-to-end approach for crop rotation analyses at large-scale. Crop monitoring is a key process for agricultural management and policy making linked to food security and sustainability. The spatio-temporal assessment of crop-specific management is essential for mapping crop rotation at field-scale. The aims of this study were to generate a satellite-based data fusion approach for mapping crop rotation at field-scale and generating analyses of crop rotation patterns among different mesoregions, examining the impact of environmental factors on crop yields, within the Rio Grande do Sul, southern Brazil. Within this geographical region, soybeans (Glycine max (L.) Merr.), corn (Zea mays L.), and rice (Oryza sativa L.) are the major grain crops of the state. We have utilized a satellite-based data fusion crop type classification and mapping to extract spatial crop features during four growing seasons (2017–2021), associated to field boundary delineation to generate the crop rotation database. This database showed current crop rotation practices within the study region, highlighting continuous soybean (monocrop), and three soybeans with one corn year rotation as the most frequent in the state. Midwestern and Northwest mesoregions presented the highest mean municipality values of continuous crop with 76% and 61%, respectively. Crop rotation patterns in Porto Alegre metropolitan, Southwest, and Southern mesoregions showed soybean-rice rotation, but with a trend of increases in soybean area in detriment to rice in lowlands. Crop rotation effects on yield for soybeans varied from 20 up to 65% depending on the regions and years of crop rotation. Other crop rotation effects in the crop yields were not significant at the municipality level. Crop rotation showed more significant benefits for soybean yields in warm and wet climate, with higher bulk density and lower soil organic carbon. Lastly, this study presents the first crop rotation map layer for the entire state of Rio Grande do Sul, southern Brazil, serving as a foundation for the creation of similar database for other states in the country and around the globe. [ABSTRACT FROM AUTHOR]

• Similar harmonic regression coefficients were derived from modeling and imagery. • Random forest model, MapBiomas and Environmental Rural Register were field masks. • Crop modeling as input for supervised crop classification model had high accuracy. • Crop modeling aggregated with ground data increased model performance. • Spatial variability was treated with crop modeling aggregated with ground data. Crop type mapping is essential for agricultural monitoring, but lack of terrestrial labels (herein termed as ground truth data) limit these models around the globe. In this study, we tested different methods for creating crop type maps for soybean (Glycine max L.) and corn (Zea mays L.), with aims of i) compare ground truth data related to crop modeling; ii) evaluate agricultural field masks generated by Environmental Rural Register, MapBiomas product, and random forest model; iii) evaluate models of a) unsupervised classification, b) supervised classification with ground truth data of 1 year, c) with ground truth data of 2 years, d) supervised classification with crop modeling only, e) with the combination of crop modeling and ground truth data of 1 year, and f) with ground truth data of 2 years; iv) test sample size for training the model utilizing ground truth data and crop modeling in transfer learning approach; and v) examine spatial remote sensing features to guide crop data collection. The APSIM-NG crop model was utilized for generate crop modeling simulations to compare with satellite images harmonic regression of ground truth data. We found similarity of harmonic regression coefficients derived from crop modeling and satellite imagery of Sentinel-2 of the labeled ground truth data for both soybean and corn crops. Agricultural masks showed efficiency for crop area estimation for soybean, with highest accuracy with random forest model. Crop modeling aggregated with growing season data as input for supervised learning presented the greater model performance with overall accuracy of 0.94. Crop area prediction was most accurate for soybean [R2 = 0.93, and mean absolute error (MAE) = 2,052 ha] for the model with the combination of crop modeling and ground truth data of 2 years, and least for corn, [R2 = 0.18, and MAE = 1,146 ha] when only using crop modeling. Model performance was influenced by sample size, with greater accuracy (0.93) for aggregating crop modeling (150 samples) and year data (100 samples). In addition, considering spatial field data variability as model input increased overall accuracy from 0.84 to 0.93, with higher impact when only ground truth data was utilized for input in the model. Our results suggest that these methods offer options for crop type classification when less adequate ground truth data is available and with unsupervised learning. On the other hand, supervised learning utilizing crop modeling with presence of field data did improve model performance overall. [ABSTRACT FROM AUTHOR]

Soybeans (Glycine max L.) are a crucial crop for global food security, and the state of Rio Grande do Sul (RS), Brazil, plays a significant role. However, climate instability, particularly water stress (WS), is a major concern in this region, causing large interannual yield variability. This study aims to address this issue using an in-silico approach to: i) characterize WS and spatial patterns and their frequency within ENSO events; and ii) explore climate-adaptative management strategies such as planting dates and maturity groups to mitigate the risk of crop failure and maximize seed yield and profits. Crop growth simulations were performed testing three soybean maturity groups (MG, 5.0, 5.8, and 6.4) and eight planting dates (from October 5th to January 20th) over 30 years at 187 locations in RS, Brazil, using APSIM Next Generation. Failure risk was calculated as the percentage of simulations that yielded less than the economic break-even soybean yield in a given scenario. The simulated yields were clustered into four regions: Northeast, North, Central, and Southwest. Four WS seasonal patterns were then defined (no stress, early stress, late stress, and whole season stress). On average, WS reduced yields up to 2 Mg ha-1 (∼50 % relative to the maximum). WS varied among regions, with the SW experiencing more frequent and severe stress (up to 50 % of whole season stress during La Nina). ENSO events influenced WS frequency, with El Niño events associated with reduced stress and La Niña events to increased stress. The MG 5.0 resulted in a higher probability of failure risk in all regions. Early planting dates resulted in the highest yield variability (up to 5 Mg ha-1). Climate-adaptative management strategies, such as optimizing planting dates and maturity groups, resulted in a 15 % reduction in crop failure. Our findings provide valuable insights for developing targeted approaches to enhance soybean yield stability, thereby increasing the resilience of agriculture in the face of future climate uncertainties. [Display omitted] • Soybean maturity groups 5.0, 5.8, and 6.4 coefficients were calibrated. • On average, water stress reduces soybean yields up to 2 Mg ha−1. • The Northeast region of Southern Brazil is minimally influenced by ENSO. • The maturity group 5.0 (short) reported a higher failure risk across all regions. • Early planting dates resulted in the highest yield variability (up to 5 Mg ha−1). [ABSTRACT FROM AUTHOR]

• Relative abundance of ureides (RAU) reveals changes in soybean N sources. • The accurate dry tissue RAU estimation relies on the soybean plant fraction. • Basal stem RAU reflects values from the entire main stem. • Upper leaflets and upper petiole RAU poorly correlate with main stem RAU. The present study aims to compare the relative abundance of ureides (RAU) among soybean Glycine max (L.) Merr.] plant fractions in contrasting trial settings and under three nitrogen (N) rates, designed to create variability on symbiotic N fixation. A greenhouse and a field experiment evaluated the RAU in plant fractions (base of the main stem, petiole and leaflets of the uppermost fully developed leaf) at varying growth stages and under absent, intermediate, or high N fertilization rates. The RAU was determined by measuring dry tissue nitrate and ureides and considered the entire main stem as benchmarking plant fraction, previously calibrated based on 15N isotope methods. The main outcomes of this study were: 1) RAU in the base of the stem accurately reflected the one obtained in the main stem; 2) upper leaflets RAU poorly correlate with the main stem values; and 3) the RAU from the upper petiole presented similar trends as the base of the stem but did not provide as reliable RAU estimation. The base of the stem is a reliable fraction to quantify soybean RAU while simplifying dry mass collection. The upper petiole fraction did not estimate RAU accurately, but it could differentiate contrasting N fixation levels. [ABSTRACT FROM AUTHOR]