Feasibility of Hybrid PSO-ANN Model for Identifying Soybean Diseases

Soybean disease has become one of vital factors restricting the sustainable development of high-yield and high-quality soybean industry. A hybrid artificial neural network (ANN) model optimized via particle swarm optimization (PSO) algorithm, which is denoted as PSO-ANN, is proposed in this paper for soybean diseases identification based on categorical feature inputs. Augmentation dataset is created via Synthetic minority over-sampling technique (SMOTE) to deal with quantitative insufficiency and categorical unbalance of the dataset. PSO algorithm is used to optimize the parameters in ANN, including the activation function, the number of hidden layers, the number of neurons in each hidden layer and the optimizer. In the end, ANN model with 2 hidden layers, 63 and 61 neurons in hidden layers respectively, Relu activation function and Adam optimizer yields the best overall test accuracy of 92.00%, compared with traditional machine learning methods. PSO-ANN shows superiority on various evaluation metrics, which may have great potential in crop diseases control for modern agriculture.

The еffect of fungicides on the development of diseases and soybean yield in the Forest steppe of Ukraine

Goal. To study the effectiveness of modern fungicides against the most common diseases of soybeans during the growing season and their effect on crop productivity in the Forest-steppe of Ukraine. Methods. Field, phytopathological, statistical. The experiments were carried out in the farms of the Kyiv region, belonging to the Forest-steppe zone of Ukraine. Spraying of soybean crops was carried out twice during the growing season in the phases of budding-beginning of flowering (51—55) and the formation of beans (71—75). Determined the development of diseases, the effectiveness of fungicides, crop yield. Results. The most common diseases of soybeans in the forest-steppe zone of Ukraine have been identified: Alternaria, downy mildew, Fusarium wilting, Septoria, and bacterial blight. The species composition of diseases and the degree of their development were largely influenced by the weather conditions of the growing season. The investigated fungicides Abacus mk.e. (pyraclostrobin, 62.5 + epoxiconazole, 62.5), Amistar Extra 280 SC, (azoxystrobin, 200 + cyproconazole, 80), Acanto Plus 28 c.s. (picoxystrobin, 200 g/l + cyproconazole, 80 g/l), Coronet 300 SC (trifloxystrobin, 100 g/l + tebuconazole, 200 g/l), as well as Impact K preparations, c.s. (flutriafol, 117.5 g/l + carbendazim, 250 g/l) and Koside 2000 w. g. (copper hydroxide, 350 g/kg) at the recommended application rates effectively limited the development of most fungal pathogens. The highest protective effect of 69.8—78.9% of fungicides was shown against downy mildew of soybeans, the lowest — 31.7—42.2% against Alternaria, which had the highest development in comparison with other diseases. Fungicide Koside 2000 w. g. at the level of 67% limited the development of bacterial diseases. The use of fungicides had a positive effect on the yield of soybeans. Due to the limitation of the development of diseases, the soybean yield increased by 21.2—30.3%, depending on the variant of the experiment. Conclusions. The use of fungicides significantly affected the limitation of the development of the most common soybean diseases in the Forest-steppe of Ukraine. The effectiveness of The effectiveness of the studied modern fungicides against peronospora, fusarium wilting, septoria was at the level of 60.2—78.9%. Fungicides most effectively controlled the development of downy mildew, less effectively — the development of Alternaria. The limitation of soybean diseases when using fungicides contributed to an increase in its yield by an average of 0.7—1.0 t/ha.

High-quality genome assembly of the soybean fungal pathogen Cercospora kikuchii

Plant diseases caused by the Cercospora genus of ascomycete fungi are a major concern for commercial agricultural practices. Several Cercospora species can affect soybeans, such as C. kikuchii which causes soybean leaf blight. Speciation in Cercospora on soybean has not been adequately studied. Some cryptic groups of Cercospora also cause diseases on soybean. Moreover, it has been known C. kikuchii population genetic structure is different between countries. Consequently, further genomic information could help to elucidate the covert differentiation of Cercospora diseases in soybean. Here, we report for the first time, a chromosome-level genome assembly for C. kikuchii. The genome assembly of 9 contigs was 34.44 Mb and the N50 was 4.19 Mb. Based on ab-initio gene prediction, several pathogenicity-related genes, including 242 genes for effector candidates, 55 secondary metabolite gene clusters, and 399 carbohydrate-active enzyme genes were identified. The genome sequence and the features described in this study provide a solid foundation for comparative and evolutionary genomic analysis for Cercospora species that cause soybean diseases worldwide.

Soybean yield loss estimates due to diseases in the United States and Ontario, Canada from 2015-2019

Soybean [Glycine max (L.) Merrill] yield losses as a result of plant diseases were estimated by university and government plant pathologists in 29 soybean-producing states in the United States and in Ontario, Canada, from 2015 through 2019. In general, the estimated losses that resulted from each of 28 plant diseases or pathogens varied by state or province as well as year. Soybean cyst nematode (SCN) (Heterodera glycines Ichinohe) caused more than twice as much loss than any other disease during the survey period. Seedling diseases (caused by various pathogens), Sclerotinia stem rot (white mold) (caused by Sclerotinia sclerotiorum [Lib.] de Bary), and sudden death syndrome (caused by Fusarium virguliforme O'Donnell & T. Aoki) caused the next greatest yield losses, in descending order. Following SCN, the most damaging diseases in the northern U.S. and Ontario differed from those in the southern U.S. The estimated mean economic loss from all soybean diseases, averaged across the U.S. and Ontario, Canada was $45 U.S. dollars per acre ($111 per hectare). The outcome from the current survey will provide pertinent information regarding the important soybean diseases and their overall severity in the soybean crop and help guide future research and Extension efforts on managing soybean diseases.

Botanical fungicides in the control of soybean leaf diseases / Fungicidas botânicos no controle de doenças foliares na soja

The soybean cultivation (Glycine max (L.) Merrill) is responsible for the highest pesticides use in agriculture in Brazil. There is an environmental and social need to reduce the use of these substances in crops. The alternative products applied in agriculture such as plant extracts and essential oils, becomes necessary and indispensable, mainly in disease control. Among the plants studied, the Noni (Morinda citrifolia L.), has stood out in some studies, where relevant fungitoxic results have been demonstrated, however, there are still few works that prove its viability in the diseases management in field. Thus, this work aimed to evaluate the soybean diseases alternative control through the aqueous extracts and noni essential oil application, in plantings high and low disease pressure. Two field experiments were implemented, with soybean culture, evaluating leaf, fruit aqueous extract and noni essential oil as a fungicidal action. Foliar application of noni extracts and essential oil did not differ from fungicide in Asian Rust and Anthracnose control, in the 2016/17 crop, in both experiments. Soybean productivity was similar in treatments that received leaf extract (1748,8 Kg ha-1), essential oil (1762,5 Kg ha-1) and fungicides (2031,7 Kg ha-1). Where there was no large disease pressure all agronomic characteristics were equivalent, regardless of treatment.

Robotic agricultural instrument for automated extraction of nematode cysts and eggs from soil to improve integrated pest management

Soybeans are an important crop for global food security. Every year, soybean yields are reduced by numerous soybean diseases, particularly the soybean cyst nematode (SCN). It is difficult to visually identify the presence of SCN in the field, let alone its population densities or numbers, as there are no obvious aboveground disease symptoms. The only definitive way to assess SCN population densities is to directly extract the SCN cysts from soil and then extract the eggs from cysts and count them. Extraction is typically conducted in commercial soil analysis laboratories and university plant diagnostic clinics and involves repeated steps of sieving, washing, collecting, grinding, and cleaning. Here we present a robotic instrument to reproduce and automate the functions of the conventional methods to extract nematode cysts from soil and subsequently extract eggs from the recovered nematode cysts. We incorporated mechanisms to actuate the stage system, manipulate positions of individual sieves using the gripper, recover cysts and cyst-sized objects from soil suspended in water, and grind the cysts to release their eggs. All system functions are controlled and operated by a touchscreen interface software. The performance of the robotic instrument is evaluated using soil samples infested with SCN from two farms at different locations and results were comparable to the conventional technique. Our new technology brings the benefits of automation to SCN soil diagnostics, a step towards long-term integrated pest management of this serious soybean pest.

Identification of Sources of Resistance and Yield Loss Assessment for Aerial Blight and Anthracnose/Pod Blight Diseases in Soybean

Background: Aerial blight (Rhizoctonia solani Kuhn) and Anthracnose/pod blight (Colletotrichum truncatum) are important soybean diseases, affect most of the present varieties with varying intensity, in India. There are also few reports of resistance against both the diseases. Methods: To identify resistance, a set of 121 diverse soybean genotypes including six susceptible checks i.e. JS 93-05, JS 335, JS 72-280, Punjab 1, RKS 18 and VLS 58 were evaluated under high disease pressure field conditions during 2017, 2018 and 2019. Moreover, assessment of yield losses due to these diseases were also worked out in highly infected plants of susceptible checks.Result: It was observed that aerial blight (0.0-46.8 per cent) and anthracnose/pod blight (0.0-56.2 per cent) were affected soybean genotypes from R1 to R7 and V3 to R7 stages, respectively. The genotypes responded differently and showed absolute resistance to susceptible reaction. Out of 121 genotypes, only five genotypes i.e. JS 20-57, JSM 222, MACS 1407, PS 1611 and Cat 2126 B were found to be highly resistant against both the diseases. Per cent pod and yield losses were significantly correlated with varying severity of aerial blight (0.966** and 0.995**) and anthracnose/pod blight (0.957** and 0.995**), respectively. However, the highest yield loss of 41.0 and 64.8 per cent were recorded on 55.6 and 75.2 per cent disease index (at 90 days) of aerial blight and anthracnose/pod blight, respectively.