Yield and Quality Prediction of Winter Rapeseed—Artificial Neural Network and Random Forest Models

As one of the greatest agricultural challenges, yield prediction is an important issue for producers, stakeholders, and the global trade market. Most of the variation in yield is attributed to environmental factors such as climate conditions, soil type and cultivation practices. Artificial neural networks (ANNs) and random forest regression (RFR) are machine learning tools that are used unambiguously for crop yield prediction. There is limited research regarding the application of these mathematical models for the prediction of rapeseed yield and quality. A four-year study (2015–2018) was carried out in the Republic of Serbia with 40 winter rapeseed genotypes. The field trial was designed as a randomized complete block design in three replications. ANN, based on the Broyden–Fletcher–Goldfarb–Shanno iterative algorithm, and RFR models were used for prediction of seed yield, oil and protein yield, oil and protein content, and 1000 seed weight, based on the year of production and genotype. The best production year for rapeseed cultivation was 2016, when the highest seed and oil yield were achieved, 2994 kg/ha and 1402 kg/ha, respectively. The RFR model showed better prediction capabilities compared to the ANN model (the r2 values for prediction of output variables were 0.944, 0.935, 0.912, 0.886, 0.936 and 0.900, for oil and protein content, seed yield, 1000 seed weight, oil and protein yield, respectively).

The results of preliminary trial experimental hybrids of winter rapeseed bred at VNIIMK by economically valuable traits

The purpose of the research was a preliminary estimation of ten experimental hybrids of winter rapeseed (Brassica napus L.) bred in the V.S. Pustovoit All-Russian Research Institute of Oil Crops by the primary economically valuable traits. The research was conducted in the central zone of the Krasnodar region in 2019–2020. The results of the research are presented for the first time. On average for two years, nine of ten the best experimental hybrids increased by seeds yield by 0.32–0.76 t per ha both the standard cultivar Loris and the foreign hybrid Mercure. Middle seed yield of the studied hybrids varied significantly, variance range was from 4.99 t per ha (VN-3 × ОРK-10) to 5.62 t per ha (VN-4 × ОРK-20). Maximal values of seed and oil yields per a unit area were fixed for a hybrid combination VN-4 × ОРK-20. Except that, the hybrid is characterized with high weight of 1000 seeds (4.5 g). A hybrid combination VN-13 × ОРK-10 demonstrated high average by years seeds yield (5.33 t per ha) and oil yield (2.25 t per ha).Oil content in seeds and weight of 1000 seeds of this combination were at the level of the standard cultivar and the foreign hybrid. This hybrid shows the lowest glucosinolate content in seeds – 16.7 µmol/g, that is less that the foreign hybrid Mercure has by 2.3 µmol/g. The preliminary conclusion based on our researches is: the selected hybrids after confirmation of the competitive trial results can be of a great interest for production.

Breeding of winter rapeseed in VNIIMK: history and new results (review)

Breeding of winter rapeseed in the V.S. Pustovoit All-Russian Research Institute of Oil Crops was started at the end of 60th of previous century with a selection of perspective winter forms from hybrids of spring brown mustard and winter rapeseed. Heterosis in intraspecific hybrids was studied. The best intraspecific hybrids exceeded the parental forms by 20–36% by seed yield, by 20–27% by green mass yield. A possibility to create intervarietal hybrids based on heterostyly was studied. Conditions for plants acclimation to increase cold resistance of winter rapeseed were studied; methods of selection for cold resistance were developed. In 1982, the development of rapeseed and turnip rape cultivars of ‘00’ type began. To create diversity of breeding germplasm, a great amount of samples from European counties that actively deals with rapeseed breeding were included into the work. In the V.S. Pustovoit All-Russian Research Institute of Oil Crops, the methods of estimation of oil and fodder protein quality were perfected, cultivars of rapeseed and turnip rape of ‘00’ type (e.g. erucic acid free and with low glucosinolate content) were developed. As a result of breeding for oil quality, high oleic cultivars were developed, that not only improve upon the oil nutritive efficiency but open new possibilities of its technical uses due to increasing oxi- and thermostability. The first Russian high oleic winter rapeseed cultivar Olivin was developed in the V.S. Pustovoit AllRussian Research Institute of Oil Crops and introduced in the State Variety Commission in 2019. The linear cultivars of winter rapeseed were developed by inbreeding, the first interlinear hybrids – using a CMS Ogura system. One of them named Debyut was introduced in the State variety trials 2020.

Integration of Sentinel-3 and MODIS Vegetation Indices with ERA-5 Agro-meteorological Indicators for Operational Crop Yield Forecasting

Timely crop yield forecasts at national level are substantial to support food policies, to assess agricultural production and to subsidize regions affected by food shortage. This study presents an operational crop yield forecasting system for Poland that employs freely available satellite and agro-meteorological products provided by the Copernicus programme. The crop yield predictors consist of: (1) vegetation condition indicators provided daily by Sentinel-3 OLCI (optical) and SLSTR (thermal) imagery, (2) a backward extension of Sentinel-3 data (before 2018) derived from cross-calibrated MODIS data, (3) air temperature, total precipitation, surface radiation, and soil moisture derived from ERA-5 climate reanalysis generated by the European Centre for Medium-Range Weather Forecasts. The crop yield forecasting algorithm is based on thermal time (growing degree days derived from ERA-5 data) to better follow the crop development stage. The recursive feature elimination is used to derive an optimal set of predictors for each administrative unit, which are ultimately employed by the Extreme Gradient Boosting regressor to forecast yields using official yield statistics as a reference. According to intensive leave-one-year-out cross validation for 2000–2019 period, the relative RMSE for NUTS-2 units are: 8% for winter wheat, and 13% for winter rapeseed and maize. Respectively, for the LAU units it equals 14% for winter wheat, 19% for winter rapeseed, and 27% for maize. The system is designed to be easily applicable in other regions and to be easily adaptable to cloud computing environments (such as DIAS or Amazon AWS), where data sets from the Copernicus programme are directly accessible.

iTRAQ-based quantitative proteome analysis insights into cold stress of Winter Rapeseed (Brassica rapa L.) grown in the field

Winter rapeseed (Brassica rapa L.) is a major oilseed crop in Northern China, where its production was severely affected by chilling and freezing stress. However, not much is known about the role of differentially accumulated proteins (DAPs) during the chilling and freezing stress. In this study, isobaric tag for relative and absolute quantification (iTRAQ) technology was performed to identify DAPs under freezing stress. To explore the molecular mechanisms of cold stress tolerance at the cellular and protein levels, the morphological and physiological differences in the shoot apical meristem (SAM) of two winter rapeseed varieties, Longyou 7 (cold-tolerant) and Lenox (cold-sensitive), were explored in field-grown plants. Compared to Lenox, Longyou 7 had a lower SAM height and higher collar diameter. The level of malondialdehyde (MDA) and indole-3-acetic acid (IAA) content was also decreased. Simultaneously, the soluble sugars (SS) content, superoxide dismutase (SOD) activity, peroxidase (POD) activity, soluble protein (SP) content, and collar diameter were increased in Longyou 7 as compared to Lenox. A total of 6330 proteins were identified. Among this, 98, 107, 183 and 111 DAPs were expressed in L7 CK/Le CK, L7 d/Le d, Le d/Le CK and L7 d/L7 CK, respectively. Quantitative real-time PCR (RT-qPCR) analysis of the coding genes for seventeen randomly selected DAPs was performed for validation. These DAPs were identified based on gene ontology enrichment analysis, which revealed that glutathione transferase activity, carbohydrate-binding, glutathione binding, metabolic process, and IAA response were closely associated with the cold stress response. In addition, some cold-induced proteins, such as glutathione S-transferase phi 2(GSTF2), might play an essential role during cold acclimation in the SAM of Brassica rapa. The present study provides valuable information on the involvement of DAPs during cold stress responses in Brassica rapa L, and hence could be used for breeding experiments.

Agricultural LCA for Food Oil of Winter Rapeseed, Sunflower, and Hemp, Based on Czech Standard Cultivation Practices

The demand for food vegetable oil is rising and this trend is reflected in the agricultural sector of the Czech Republic. The traditional oil crops of the Czech Republic are winter rapeseed and sunflower. These oil crops have high demands on energy inputs, for example, in the form of land preparation and chemical protection. At the same time, they are characterized by high food oil production and oiliness. Moreover, marginal oils crops, such as hemp, are also gaining prominence. This work aimed to evaluate the environmental impacts associated with the cultivation of winter rapeseed and sunflowers based on standard cultivation practices typical of the conditions of the Czech Republic. For comparison, an intensive cultivation strategy for hemp was modelled, also corresponding to the conditions of the Czech Republic. This study assessed the environmental impact of traditional oil crops from the agricultural Life Cycle Assessment (LCA) perspective. The system boundaries included all the processes from the cradle to the farm gate. Mass-based (volume of food oil) and area-based (land demand for generating the same volume of food oil) functional units were employed. The results cover nine impact categories related to the agricultural LCA. ReCiPe Midpoint (H) characterization and normalization models were used for the data expression. Hemp is a plant with generally low demands on the inputs of the growing cycle but generally has a low oil production, which affects the character of the results relating to the goal and scope definition of the study. Hemp food oil thus generated a higher environmental impact per unit of production and area compared to sunflower and rapeseed food oil.

Parameters of the optimal plant density of winter rape for successful overwintering in the Non-Chernozem zone

To obtain high yields of winter rapeseed seeds in the Non-Chernozem zone, it is necessary to provide conditions for good wintering. The studies were carried out in order to establish the optimal plant density of the zoned variety Severyanin. It was found that when sowing in rows with a row spacing of 25 cm, winter rape plants develop better, form a rosette of leaves with a lower location of the growing point, form a smaller amount of aboveground mass per unit of roots, which increases the safety of plants in winter by 2.5-4.3%. period under extreme conditions. The study of the dynamics of the plant density of winter rapeseed at different seeding rates showed that during the growing season, self-thinning of cenosis occurs. On average, over the years of research, plants overwintered better in variants with a lower stand density. With an increase in the seeding rate, the completeness of seedlings, the safety of plants in the autumn period, overwintering and the safety of plants in the year of harvesting for seeds decreased. The most optimal conditions for the preservation of plants for harvesting are provided at low seeding rates: with a row sowing with a row spacing of 25 cm with a seeding rate of 0.7-1.0 million pieces / ha, with an inter-row sowing (row spacing of 25 cm) - 0.5 million pcs / ha of germinating seeds: With the over-row sowing, the safety of plants for harvesting was higher than with the row method by 9-25%.

Integration of Transcriptome and Proteome Analysis Reveals the Mechanism of Freezing Tolerance in Winter Rapeseed

Winter rapeseed seedlings are susceptible to low temperature during overwintering in Northwest China, leading to reduced crops production. Freezing stress is one of the utmost environmental stresses in Northwest China from late autumn to early spring, which are eventful for overwinter survival rate of winter rapeseed. However, the molecular mechanism of freezing tolerance formation is still very backward in winter rapeseed. In this study, using a pair of freezing-sensitive and freezing-resistant cultivars NQF24 and NTS57, the exhaustive effects of freezing stress on freezing tolerance formation were evaluated by analyzing leaf at the levels of transcriptome, proteome, physiology and ultrastructure. There were 8497 differentially expressed genes (DEGs) and 418 differentially abundant proteins (DAPs) specifically identified in leaf of NQF24 under freezing stress, while 7358 DEGs and 573 DAPs were specifically identified in leaf of NTS57. Function enrichment analysis showed that most of the enriched DEGs and DAPs were associated with plant hormones signal transduction, fatty acid metabolism, ribosome, plant-pathogen interaction and secondary metabolites biosynthesis. Freezing tolerance is formed by enhanced signals transduction, increased the biosynthesis of protein and secondary metabolites, higher reactive oxygen species (ROS) scavenging, more osmolytes, lower lipid peroxidation, and stronger ultrastructure. These results can be taken as selection indicators in freezing tolerance breeding program in rapeseed.