Using Brainwave Patterns Recorded from Plant Pathology Experts to Increase the Reliability of AI-Based Plant Disease Recognition System.

One of the most challenging problems associated with the development of accurate and reliable application of computer vision and artificial intelligence in agriculture is that, not only are massive amounts of training data usually required, but also, in most cases, the images have to be properly labeled before models can be trained. Such a labeling process tends to be time consuming, tiresome, and expensive, often making the creation of large labeled datasets impractical. This problem is largely associated with the many steps involved in the labeling process, requiring the human expert rater to perform different cognitive and motor tasks in order to correctly label each image, thus diverting brain resources that should be focused on pattern recognition itself. One possible way to tackle this challenge is by exploring the phenomena in which highly trained experts can almost reflexively recognize and accurately classify objects of interest in a fraction of a second. As techniques for recording and decoding brain activity have evolved, it has become possible to directly tap into this ability and to accurately assess the expert's level of confidence and attention during the process. As a result, the labeling time can be reduced dramatically while effectively incorporating the expert's knowledge into artificial intelligence models. This study investigates how the use of electroencephalograms from plant pathology experts can improve the accuracy and robustness of image-based artificial intelligence models dedicated to plant disease recognition. Experiments have demonstrated the viability of the approach, with accuracies improving from 96% with the baseline model to 99% using brain generated labels and active learning approach.

The recombinant pea defensin Drr230a is active against impacting soybean and cotton pathogenic fungi from the genera Fusarium, Colletotrichum and Phakopsora.

Plant defensins are antifungal peptides produced by the innate immune system plants developed to circumvent fungal infection. The defensin Drr230a, originally isolated from pea, has been previously shown to be active against various entomopathogenic and phytopathogenic fungi. In the present study, the activity of a yeast-expressed recombinant Drr230a protein (rDrr230a) was tested against impacting soybean and cotton fungi. First, the gene was subcloned into the yeast expression vector pPICZαA and expressed in Pichia pastoris. Resulting rDrr230a exhibited in vitro activity against fungal growth and spore germination of Fusarium tucumaniae, which causes soybean sudden death syndrome, and against Colletotrichum gossypii var. cephalosporioides, which causes cotton ramulosis. The rDrr230a IC50 corresponding to inhibition of fungal growth of F. tucumaniae and C. gossypii var. cephalosporioides was 7.67 and 0.84 µM, respectively, demonstrating moderate activity against F. tucumaniae and high potency against C. gossypii var. cephalosporioides. Additionally, rDrr230a at 25 ng/µl (3.83 µM) resulted in 100 % inhibition of spore germination of both fungi, demonstrating that rDrr230a affects fungal development since spore germination. Moreover, rDrr230a at 3 µg/µl (460.12 µM) inhibited 100 % of in vitro spore germination of the obligatory biotrophic fungus Phakopsora pachyrhizi, which causes Asian soybean rust. Interestingly, rDrr230a substantially decreased the severity of Asian rust, as demonstrated by in planta assay. To our knowledge, this is the first report of a plant defensin active against an obligatory biotrophic phytopathogenic fungus. Results revealed the potential of rDrr230a as a candidate to be used in plant genetic engineering to control relevant cotton and soybean fungal diseases.

Relações de causa e efeito entre condições ambientais, urediniósporos e severidade de ferrugem-asiática da soja / Relations of cause and effect among environmental conditions, airborne urediniospores and asian soybean rust severity

O objetivo deste trabalho foi estabelecer relações entre condições ambientais, o número de urediniósporos de Phakopsora pachyrhizi e a severidade da ferrugem-asiática-da-soja. Para quantificar urediniósporos de P. pachyrhizi, coletores foram instalados em campos de soja, em Itambé e Mandaguari, PR. Avaliações de severidade foram realizadas e dados climáticos foram coletados nos dois locais. As variáveis elaboradas foram: número de dias com umidade favorável (>60%), número de dias com temperatura favorável (18 a 32º C), preciptação acumulada e urediniósporos coletados. Uma variável baseada no controle químico também foi elaborada. Correlações entre as variáveis foram estimadas. A análise de trilha foi empregada para desdobrar as correlações. Cerca de 76% da variação das relações de causa e efeito entre as variáveis foi explicada pela análise de trilha. O número de dias para efetuar o controle químico teve efeito direto sob a severidade. O número de dias com temperatura favorável e as precipitações tiveram efeito indireto na severidade, atuando via manutenção de condições favoráveis de umidade.

The objective of this work was to study the relationships among environmental conditions, airborne urediniospores of P. pachyrhizi and the Asian soybean rust (ASR) severity. To quantify airbone urediniospores, collectors were installed in soybean fields in Itambé and Mandaguari, PR. Severity assessments were conducted and climatic data were collected in the two locations. The variables elaborated were: number of days with favorable humidity (<60%), number of days with favorable temperature (18-32ºC), rainfall accumulated and urediniospores collected. A variable based on the chemical control was also created. Correlations between variables were estimated. Path analysis was performed for correlations. Path analysis explained about 76% of the relations of cause and effect among the variables. Number of days to the chemical control had direct effect on severity. Number of days with favorable temperature and rainfall had indirect effect on severity. This two variables provided favorable humidity conditions for ASR development.

Genetic control of soybean (Glycine max) yield in the absence and presence of the Asian rust fungus (Phakopsora pachyrhizi)

Soybean is one of the most important crops in Brazil and continuously generates demands for production technologies, such as cultivars resistant to diseases. In recent years, the Asian rust fungus (Phakopsora pachyrhizi Syd. & P. Syd 1914) has caused severe yield losses and the development of resistant cultivars is the best means of control. Understanding the genetic control and estimating parameters associated with soybean (Glycine max) resistance to P. pachyrhizi will provide essential information for cultivar selection. We investigated quantitative genetic control of P. pachyrhizi and estimated parameters associated to soybean yield in the absence and presence of this phytopathogen. Six cultivars and their 15 diallel derived F2 and F3 generations were assessed in experiments carried out in the absence and presence of P. pachyrhizi. The results indicated that soybean yield in the presence and absence of P. pachyrhizi is controlled by polygenes expressing predominantly additive effects that can be selected to develop new cultivars resistant or tolerant to P. pachyrhizi. These cultivars may prove to be a useful and more durable alternative than cultivars carrying major resistance genes.

Relação entre medidas de refletância e área foliar sadia, severidade da ferrugem asiática e produtividade da cultura da soja / Relationships between measures of reflectance and health leaf area, soybean rust severity and soybean yield

O objetivo do trabalho foi verificar se as medidas de refletância detectavam variações na área foliar sadia a fim de serem utilizadas como parâmetros para estimar danos na produção decorrentes da ferrugem asiática, bem como determinar a influência da doença na eficiência fotossintética das plantas em condições de campo. O experimento foi conduzido na área experimental pertencente à Embrapa Soja, no município de Londrina, PR, utilizou-se a cultivar de soja BRS 154. O delineamento experimental utilizado foi de blocos ao acaso, com oito tratamentos (diferentes estádios de início da aplicação do fungicida) comquatro repetições O produto utilizado foi azoxistrobin + ciproconazole (60+24 g i.a./ha) + óleo mineral (0,5%). As leituras de refletância foram feitas em oito comprimentos de onda, de 460 a 810 nm, em intervalos de 50 nm. Calculou-se o Índice Vegetativo de Diferença Normalizada (NDVI), onde NDVI=(810- 660)/(810+660). A produção apresentou incremento linear (P<0,01) com a Duração da Área Foliar Sadia (HAD) (r2=37,7%), com a Absorção da Radiação Solar pela Área Foliar Sadia (HAA) (r2=21,6%), com aÁrea Abaixo da Curva de Progresso da Doença (AUDPC) (r2=25,4%) e com a Integral da Diferença Normalizada (AURNDVI) (r2=54,8%). Verificou-se diferença significativa (P<0,05) na Eficiência Fotossintética (RUE) entre a testemunha e o tratamento que recebeu três aplicações de fungicida (primeira em R4), sendo esse também o único tratamento que diferiu significativamente (P<0,05) da testemunha em produtividade. Apesar dos baixos valores para os coeficientes de determinação, a sensibilidade dasmedidas de NDVI e RUE apresentaram potencial para captar variações entre os tratamentos. Sugerem-se novos estudos para verificar e eliminar possíveis interferências decorrentes da calibração do radiômetro e dos demais parâmetros antes dessas medidas poderem ser utilizadas no processo de tomada de decisão para controle da ferrugem asiática.

The aim of this research was to verify if some measures of reflectance could detect variations in the healthy leaf area which could be used as parameter to estimate damages in the production due to soybean rust, and to determine the influence of the disease on photosinthetic efficiency of plants underfield conditions. The experiment was lead in the experimental area of Embrapa, in Londrina, PR. The experimental design was randomly blocks, with eight treatments (different fungicide application times) with four replications. The fungicide used was azoxistrobin + ciproconazole (60+24 g i.a./ha) + mineral oil (0.5%). The reflectance readings were made at eight wave lengths, between 460 and 810 nm, with intervals of 50 nm. It was estimated the Normalized Difference Vegetation Index (NDVI), where NDVI=(810-660)/ (810+660). The yield presented linear increments (P<0.01) with Healthy Leaf Area Duration (HAD)(r2=37.7%), with Healthy Area Absorption (HAA) (r2=21.6%), with Area Under Disease Progress Curve(AUDPC) (r2=25.4%) and with Integral of Normalized Difference (AURNDVI) (r2=54.8%). Significant difference in Photosynthetic Efficiency (RUE) (P<0.05) was observed between the control plot and the treatment with three fungicide applications (first at R4), which was the only treatment that differed significantly (P<0.05) in production from untreated control. The sensitivity of the measures NDVI andRUE presented a potential to detect variations among the treatments. However additional studies are still needed to verify and eliminate some possible interferences, such as the calibration of the radiometer and other parameters before it can be used for taking of decisions.

Influência da severidade de mancha angular na eficiência fotossintética da área foliar sadia de feijoeiro, sob condições de campo / Photosynthetic efficiency of healthy leaf area influenced by angular leaf spot severity in bean field

O objetivo do trabalho foi demonstrar, em parcelas experimentais sob condições de campo, a relação entre área foliar sadia, severidade de mancha angular e produção em feijoeiro indicando influência desta relação na eficiência fotossintética do tecido foliar remanescentes nas plantas. Area foliar e severidade de mancha angular (phaeoisariopsis griseola(Sacc.) Ferraris) de feijoeiro foram avaliadas semanalmente, iniciando-se aos 30 dias após a emergência (DAE). Obtiveram-se diferentes níveis de severidade variando-se a data de início de aplicação da mistura fungicida (fentin hydroxide 0,10 por cento + tebuconazole 0,04por cento). Variações na quantidade de área foliar foram obtidas em função da variação inerente entre plantas e das diferenças de condições físico-químicas encontradas no solo das parcelas. A relação entre duração de área foliar sadia (HAD) e a àrea sob a curva de progresso da doença (AUDPC) e a produção (gm-2) apresentou r2=74,8 por cento e entre absorção da área foliar sadia (HAA), AUDPC e a produção (gm-2) apresentou r2=74,7 por cento. Os resultados indicaram que houve redução na produção em parcelas com valores altos de AUDDPC, mesmo naquelas com mesmo nível de área foliar sadia (HAD), ou seja, a doença influenciou a eficiência fotossintética da área foliar sadia das plantas, além de impedir que a área doente necrosada produzisse.