Soybean Yield Preharvest Prediction Based on Bean Pods and Leaves Image Recognition Using Deep Learning Neural Network Combined With GRNN

Soybean yield is a highly complex trait determined by multiple factors such as genotype, environment, and their interactions. The earlier the prediction during the growing season the better. Accurate soybean yield prediction is important for germplasm innovation and planting environment factor improvement. But until now, soybean yield has been determined by weight measurement manually after soybean plant harvest which is time-consuming, has high cost and low precision. This paper proposed a soybean yield in-field prediction method based on bean pods and leaves image recognition using a deep learning algorithm combined with a generalized regression neural network (GRNN). A faster region-convolutional neural network (Faster R-CNN), feature pyramid network (FPN), single shot multibox detector (SSD), and You Only Look Once (YOLOv3) were employed for bean pods recognition in which recognition precision and speed were 86.2, 89.8, 80.1, 87.4%, and 13 frames per second (FPS), 7 FPS, 24 FPS, and 39 FPS, respectively. Therefore, YOLOv3 was selected considering both recognition precision and speed. For enhancing detection performance, YOLOv3 was improved by changing IoU loss function, using the anchor frame clustering algorithm, and utilizing the partial neural network structure with which recognition precision increased to 90.3%. In order to improve soybean yield prediction precision, leaves were identified and counted, moreover, pods were further classified as single, double, treble, four, and five seeds types by improved YOLOv3 because each type seed weight varies. In addition, soybean seed number prediction models of each soybean planter were built using PLSR, BP, and GRNN with the input of different type pod numbers and leaf numbers with which prediction results were 96.24, 96.97, and 97.5%, respectively. Finally, the soybean yield of each planter was obtained by accumulating the weight of all soybean pod types and the average accuracy was up to 97.43%. The results show that it is feasible to predict the soybean yield of plants in situ with high precision by fusing the number of leaves and different type soybean pods recognized by a deep neural network combined with GRNN which can speed up germplasm innovation and planting environmental factor optimization.

Growth responses of maize-soybean intercropping system and its potential for cattle feed in Bali

There had been a 2.145 ha fields transition in Bali which had a major impact on the loss of food production. However, there was raise in the population annually, therefore it disrupts local food security. Effort to raise the effectiveness and agricultural productivity areas through changing cropping system from monoculture to intercropping. This study aimed to find out the growth responses of maize and soybean crops cultivated by monoculture and intercropping planting systems and its carrying capacity for cattle feed. The study was arranged using a randomized block design with 3 treatments and 3 replications, namely: T1: Bima 20 URI VUB maize seeds in monoculture (40cm x 20cm x 80cm; 1 seed/hole or 70cm x 40cm x 100cm; 2 seeds/hole); T2: Anjasmoro, Deja 2 and Devon soybean VUB seeds in monoculture system (40cm x 20cm; 2-3 seeds/hole); T3: maize-soybean intercropping; Maize (2 rows; 40cm x 12.5; 2 seeds/hole); Soybeans (4 rows; 30cm x 10cm; 2-3 seeds/hole); both distance: 40cm. Data collected were growth performance, yield components and yield capacity of both maize and soybean crops also competition and profit value of maize and soybeans crops cultivated by intercropping planting system. The results showed that monoculture maize crops cultivated by monoculture planting system were better than it intercropped with soybean crops in terms of growth parameters. However, intercropping maize and soybean were produced greater yield components on cobs number, cobs and grains weight than monoculture (P<0.05), except grains weight per cobs. The monoculture soybean plant in growth, components and yield parameters were greater than intercropping (P>0.05). The ATER, LER, RCC, CR, and AYL values were 3.24; 1.28; -2.69; 4.58; -0.098 on maize and 2.52; 0.84; 1.82; 0.21; -0.158 on soybean. Those result was followed by carrying capacity in intercropping system by 30% usage can be used for 1.804 AU meanwhile 40% usage was sufficient for 1.353 AU. Intercropping system can be recommended to farmers to increase growth responses of maize-soybean and its potential carrying capacity for cattle feed.

The influence of mineral fertilizers and biopreparation on growth and development of soybean plants

The soybean (Glycine max) is one of the most important food plants of the world, and seems to be growing in importance. It is an annual crop, fairly easy to grow, that produces more protein and oil per unit of land than almost any other crop. It is a versatile food plant that, used in its various forms, is capable of supplying most nutrients. It can substitute for meat and to some extent for milk. It is a crop capable of reducing protein malnutrition. In addition, soybeans are a source of high value animal feed. Nevertheless, the soybean is adapted primarily to the Temperate Zone. Each improved variety has an adaptation determined in large part by latitude. Soybean requires careful home processing to bring out its best qualities, and if not well prepared, it has an off-flavor that is seldom appreciated Soybeans need to be inoculated with a particular strain of Rhizobium fungus before planting. This fungus fixes nitrogen (i. e. takes elemental nitrogen from the air and adds it to the soil in a form that the soybean plant can use). However, if soybeans are planted in a field that contained soybeans as a previous crop, they may not require inoculation because the Rhizobium will still be in the soil. If soybeans are not grown in association with Rhizobium, they will grow more slowly, require nitrogen fertilizer, and yield less. Rhizobium inoculum must be fresh (viable) and is usually purchased with the seed. If Rhizobium inoculum is not available in a particular area, and soybeans are not now being grown, it may be difficult to produce this crop. Soybeans need fertilizer, including both the macronutrients phosphorous and potassium (P and K) and sometimes micronutrients. Nitrogen is not required if soybeans are properly inoculated. Soybeans need rather large amounts of phosphorous, calcium, magnesium, and sulfur. Minor elements are sometimes required. Soybeans cannot be recommended for unfertilized soils. For optimum soybean yield, it is necessary to use both biological N2-fixation and nitrogen uptake by soybean roots. Nitrogen fertilizer applied to soybean is based on the plant nitrogen needs during seedling development prior to nodule formation that is crucial to the growth and development of soybean As with all crops, soybean yield is the result of the net accumulation of organic compounds assimilated through photosynthesis. Research on soybean photosynthesis conducted during the 1950’s and 1960’s found that several cultivars grown at that time became light saturated. However, much of those data were collected from plants grown in a greenhouse or other artificial environment. Much of the information on the response of soybean photosynthesis to changing light levels however is dated, having been published prior to 1985, with cultivars that are no longer in production, using less portable and sophisticated instrumentation than is now available. In the article are presented results of researching peculiarities of growth development and formation of soybean photosynthetic productivity depending on weather conditions, level of mineral fertilization and different application methods of biological product on the chelate form under conditions of the Right-bank Forest-Steppe. It is established that a systematic approach to soybean nutrition, namely its cultivation on the background of optimal doses of mineral fertilizers N30P45K45 and the use of biological product Organic-Balance for seed treatment in combination with foliar feeding creates the best conditions for growth, development and preservation of maximum plants full ripeness, which is the basis for obtaining high grain yields.

Regulation of Phosphorus Supply on Nodulation and Nitrogen Fixation in Soybean Plants with Dual-Root Systems

Phosphorus (P) is an important nutrient affecting nodulation and nitrogen fixation in soybeans. To further investigate the relationship of phosphorus with soybean nodulation and nitrogen fixation, the seedling grafting technique was applied in this study to prepare dual-root soybean systems for a sand culture experiment. From the unfolded cotyledon stage to the initial flowering stage, one side of each dual-root soybean system was irrigated with nutrient solution containing 1 mg/L, 31 mg/L, or 61 mg/L of phosphorus (phosphorus-application side), and the other side was irrigated with a phosphorus-free nutrient solution (phosphorus-free side), to study the effect of local phosphorus supply on nodulation and nitrogen fixation in soybean. The results are described as follows: (1) Increasing the phosphorus supply increased the nodules weight, nitrogenase activity, ureide content, number of bacteroids, number of infected cells, and relative expression levels of nodule nitrogen fixation key genes (GmEXPB2, GmSPX5, nifH, nifD, nifK, GmALN1, GmACP1, GmUR5, GmPUR5, and GmHIUH5) in root nodules on the phosphorus-application side. Although the phosphorus-application and phosphorus-free sides demonstrated similar changing trends, the phosphorus-induced increases were more prominent on the phosphorus-application side, which indicated that phosphorus supply systematically regulates nodulation and nitrogen fixation in soybean. (2) When the level of phosphorus supply was increased from 1 mg/L to 31 mg/L, the increase on the P– side root was significant, and nodule phosphorus content increased by 57.14–85.71% and 68.75–75.00%, respectively; ARA and SNA were 218.64–383.33% and 11.41–16.11%, respectively, while ureide content was 118.18–156.44%. When the level of phosphorus supply was increased from 31mg/L to 61mg/L, the increase in the regulation ability of root and nodule phosphorus content, ARA, SNA, and ureide content were low for roots, and the value for nodules was lower than when the phosphorus level increased from 1 mg/L to 31 mg/L. (3) A high-concentration phosphorus supply on one side of a dual-root soybean plant significantly increased the phosphorus content in the aboveground tissues, as well as the roots and nodules on both sides. In the roots on the phosphorus-free side, the nodules were prioritized for receiving the phosphorus transported from the aboveground tissues to maintain their phosphorus content and functionality.

Allelopathic potential of siam weed (Chromolaena odorata L.) extract for enhancing soybean productivity

Many tropical invasive species have strong allelopathic effects. Chromolaena odorata is reported to have the best potential to act as bioherbicide against several weeds on crops. This research was conducted in May-September 2019 to evaluate the efficacy of C. odorata extract on soybean plant. This study employed Randomized Block Design (RBD) Factorial with two factors. The first factor was 4 different doses of C. odorata extracts: 0, 8, 16 and 24 tons ha−1. The second factor was 3 different times of application: 0, 7 and 14 days after planting. Variables observed were number of pods per plant, seed weight per plant, weight of 100 seeds and dry seed yield. The findings indicated that the extract did have effect on seed weight per plant, weight of 100 seeds and yield of dry seeds. The application of extract 16-24 tons ha−1 has improved the seed weight per plant, weight of 100 seeds, and yield of dry seeds. There was no interaction between siam weed extract and time of application in all variables observed.

Mathematical modelling of soybean var. anjasmoro plant growth

Thorough understanding of interactions between all factors involved in soybean plant cultivation process is needed to increase the yield. This study is aimed to determine which interaction has the highest correlation according to the Pearson correlation coefficient, to define a certain model for said interaction, and to confirm the identicality of all samples that were observed using destructive sampling method. After being tested using Pearson correlation coefficient, the highest r value is 0,81 which is between plant height and number of leaves, proving they are highly related. Both parameters were simulated in several different ways until it was found that number of leaves variable is best described as function of plant height variable, the equation is y1 = 0,85x1 + c1 where y1 represents number of leaves and x1 represents plant height. Identicality between all plants is not confirmed, thus destructive sampling method is not recommended to be applied for similar studies.

Extraction Methods of Oils and Phytochemicals from Seeds and Their Environmental and Economic Impacts

Over recent years, the food industry has striven to reduce waste, mostly because of rising awareness of the detrimental environmental impacts of food waste. While the edible oils market (mostly represented by soybean oil) is forecasted to reach 632 million tons by 2022, there is increasing interest to produce non-soybean, plant-based oils including, but not limited to, coconut, flaxseed and hemp seed. Expeller pressing and organic solvent extractions are common methods for oil extraction in the food industry. However, these two methods come with some concerns, such as lower yields for expeller pressing and environmental concerns for organic solvents. Meanwhile, supercritical CO2 and enzyme-assisted extractions are recognized as green alternatives, but their practicality and economic feasibility are questioned. Finding the right balance between oil extraction and phytochemical yields and environmental and economic impacts is challenging. This review explores the advantages and disadvantages of various extraction methods from an economic, environmental and practical standpoint. The novelty of this work is how it emphasizes the valorization of seed by-products, as well as the discussion on life cycle, environmental and techno-economic analyses of oil extraction methods.

The effect of organic fertilizers on growth several varieties of soybeans

This study aims to analyse the effect of three types of organic fertilizers on the vegetative growth several varieties of soybeans. This study used a factorial randomized block design with two treatment factors, namely organic fertilizers and varieties. The first factor is: organic fertilizer from 3 levels, namely: K1 (1.5 kg of compost), K2 (1.5 kg of goat manure), and K3 (1.5 kg of chicken manure). The second factor is: soybean plant varieties consist of 4 levels, namely: V1 (Dena 1), V2 (Devon 1), V3 (Anjasmoro) and V4 (Derap 1). The parameters observed were plant height, number of branches, number of leaves, amount of chlorophyll, leaf area, and flowering age. The results of our research is organic fertilizers have a significant effect and are able to increase the growth of soybean plants except for leaf area and flowering age. Types of varieties had a significant effect and were able to increase plant height, number of branches, leaf area, and flowering age, but had no significant effect on the parameters of the number of leaves and the amount of chlorophyll. Moreover, there isn't interaction effect between the two treatments for all parameters.

Spatial Associations of Key Lepidopteran Pests With Defoliation, NDVI, and Plant Height in Soybean

In soybean, Glycine max (L.) Merrill, production, losses to, and control costs for insect pests can be significant limiting factors. Although the heterogeneity of pests has typically been ignored in traditional field management practices, technological advancements have allowed for site-specific pest management systems to be developed for the precise control of pests within a field. In this study, we chose to determine how the in-field distributions of the larvae of three major lepidopteran pests [velvetbean caterpillar Anticarsia gemmatalis (Hübner) (Lepidoptera: Erebidae), soybean looper Chrysodeixis includens (Walker) (Lepidoptera: Noctuidae), and green cloverworm Hypena scabra (Lepidoptera: Erebidae) (Fabricius)] were spatially associated with defoliation, Normalized Difference Vegetation Index (NDVI), and plant height in soybean. Spatial analysis by distance indices (SADIE) of data from two South Carolina soybean fields in 2017 and 2018 revealed a limited number of spatial aggregations for insect datasets. However, 14% and 6% of paired plant–insect datasets were significantly associated or dissociated, respectively. NDVI was found to be more associated with pest distributions than soybean plant heights and defoliation estimates, and the majority of all plant–insect associations and dissociations occurred in the first 4 wk of sampling (late July–early August). If changes are to be implemented regarding how a pest is managed, critical factors explaining the spatial distribution of pests must be identified. Results from this study advocate for the relationship between early-season distributions of pests and important plant variables such as NDVI to be further investigated to better determine the strength of the correlations across years and sites.