Detection and classification of tree species from remote sensing data were performed using mainly multispectral and hyperspectral images and Light Detection And Ranging (LiDAR) data. Despite the ...comparatively lower cost and higher spatial resolution, few studies focused on images captured by Red-Green-Blue (RGB) sensors. Besides, the recent years have witnessed an impressive progress of deep learning methods for object detection. Motivated by this scenario, we proposed and evaluated the usage of Convolutional Neural Network (CNN)-based methods combined with Unmanned Aerial Vehicle (UAV) high spatial resolution RGB imagery for the detection of law protected tree species. Three state-of-the-art object detection methods were evaluated: Faster Region-based Convolutional Neural Network (Faster R-CNN), YOLOv3 and RetinaNet. A dataset was built to assess the selected methods, comprising 392 RBG images captured from August 2018 to February 2019, over a forested urban area in midwest Brazil. The target object is an important tree species threatened by extinction known as
Vogel (Fabaceae). The experimental analysis delivered average precision around 92% with an associated processing times below 30 miliseconds.
In recent years, many agriculture-related problems have been evaluated with the integration of artificial intelligence techniques and remote sensing systems. Specifically, in fruit detection ...problems, several recent works were developed using Deep Learning (DL) methods applied in images acquired in different acquisition levels. However, the increasing use of anti-hail plastic net cover in commercial orchards highlights the importance of terrestrial remote sensing systems. Apples are one of the most highly-challenging fruits to be detected in images, mainly because of the target occlusion problem occurrence. Additionally, the introduction of high-density apple tree orchards makes the identification of single fruits a real challenge. To support farmers to detect apple fruits efficiently, this paper presents an approach based on the Adaptive Training Sample Selection (ATSS) deep learning method applied to close-range and low-cost terrestrial RGB images. The correct identification supports apple production forecasting and gives local producers a better idea of forthcoming management practices. The main advantage of the ATSS method is that only the center point of the objects is labeled, which is much more practicable and realistic than bounding-box annotations in heavily dense fruit orchards. Additionally, we evaluated other object detection methods such as RetinaNet, Libra Regions with Convolutional Neural Network (R-CNN), Cascade R-CNN, Faster R-CNN, Feature Selective Anchor-Free (FSAF), and High-Resolution Network (HRNet). The study area is a highly-dense apple orchard consisting of Fuji Suprema apple fruits (Malus domestica Borkh) located in a smallholder farm in the state of Santa Catarina (southern Brazil). A total of 398 terrestrial images were taken nearly perpendicularly in front of the trees by a professional camera, assuring both a good vertical coverage of the apple trees in terms of heights and overlapping between picture frames. After, the high-resolution RGB images were divided into several patches for helping the detection of small and/or occluded apples. A total of 3119, 840, and 2010 patches were used for training, validation, and testing, respectively. Moreover, the proposed method’s generalization capability was assessed by applying simulated image corruptions to the test set images with different severity levels, including noise, blurs, weather, and digital processing. Experiments were also conducted by varying the bounding box size (80, 100, 120, 140, 160, and 180 pixels) in the image original for the proposed approach. Our results showed that the ATSS-based method slightly outperformed all other deep learning methods, between 2.4% and 0.3%. Also, we verified that the best result was obtained with a bounding box size of 160 × 160 pixels. The proposed method was robust regarding most of the corruption, except for snow, frost, and fog weather conditions. Finally, a benchmark of the reported dataset is also generated and publicly available.
Competition with weeds is one of the main factors that limit the development of forest species. Some herbicides used to control these plants have a residual effect on the soil. Bioremediation is an ...alternative to decontaminate these areas. The aim of this study was to evaluate the tolerance of Aspergillus niger, Penicillium pinophilum and Trichoderma sp. and its degrading potential on residual effect herbicides. The tolerance of Bacillus subtilis, Pseudomonas sp. and Azospirillum brasilense to herbicides was also evaluated. The herbicides used in this study were indaziflam, sulfentrazone, sulfentrazone + diuron, clomazone and glyphosate + s-metolachlor. The analysis of the tolerance and degradation potential of fungi was carried out in Czapek Dox medium and the growth was evaluated by determining the biomass. Bacterial tolerance analysis was performed in Luria Bertani medium and growth monitored by optical density. The data were applied to the Gompertz model to evaluate the behavior of bacteria. Bacterial growth parameters were not influenced by the presence of herbicides. All fungi were tolerant to the herbicides tested and there was an increase in the growth of Trichoderma sp. Thus, the analysis of the degrading potential was performed only for Trichoderma sp. in the presence of herbicides that potentiated its growth. In this analysis, there was no effect of herbicides on fungal growth; the fungus was unable to use the carbon present in the herbicide to enhance its growth; and there was no significant effect of nitrogen in the presence of the herbicide. It is concluded, therefore, that the tested residual herbicides do not interfere with the development of the evaluated microorganisms.
Display omitted
•Plant growth-promoting bacteria and fungi were tolerant to herbicides.•Herbicides indaziflam, sulfentrazone, and clomazone were tested.•Mixtures diuron + sulfentrazone and glyphosate + s-metolachlor were also tested.
ABSTRACT Sweet potato is a promising crop in Brazil due to its potential for bioenergy production. However, little information on adequate chemical weed control is found for this crop. Thus, the ...objective of this work was to evaluate the effect of clomazone on 20 genotypes of sweet potato and the sensitivity of these materials to weed interference. A field experiment was conducted using an experimental design with four blocks arranged in split-plots. The sweet potato genotypes Brazlândia-Branca, Cariru-Vermelha, Princesa, Tomba-Carro-1 and UFVJM (01, 05, 06, 07, 08, 10, 14, 23, 26, 30, 35, 42, 43, 46, 48 and 49) were grown for 180 days under three weed managements (soils treated with clomazone, mechanically weeded and with no weed control). The plots consisted of the weed control methods and the subplots consisted of the sweet potato genotypes. Phytotoxicity, branch growth and yield were evaluated. Plants grown with no weed interference had larger branch length. The highest yields were found in clomazone-treated soils. Weed interference reduced 81 to 99.7% of the yield. The less susceptible genotypes to weed interference were UFVJM07, UFVJM10 and UFVJM35, and the most sensitive were Princesa and UFVJM01. The root yield of plants under chemical weed control was similar to or greater than those with mechanical weed control in 17 of the 20 genotypes evaluated.
RESUMO O cultivo de batata-doce é promissor no Brasil em função do seu potencial para produção de bioenergia. Porém, são escassas informações acerca da adequacão do controle químico de plantas daninhas na cultura. Objetivou-se avaliar o uso de clomazone no cultivo de 20 genótipos de batata-doce e a sensibilidade dos materiais à interferência de plantas daninhas. Para isso, em condições de campo, foi delineado um experimento em quatro blocos e esquematizado em parcelas subdivididas. Os genótipos Brazlândia Branca, Cariru Vermelha, Princesa, Tomba Carro1 e UFVJM (01, 05, 06 , 07, 08, 10, 14, 23, 26, 30, 35, 42, 43, 46, 48 e 49) foram cultivados por 180 dias em solo tratado com clomazone, capinado mecanicamente ou sem o controle de plantas daninhas. As formas de controle compunham as parcelas, e os genótipos foram alocados nas subparcelas. Foi avaliada a fitointoxicação, o crescimento de ramas e a produtividade. Foi observado maior comprimento de ramas quando as plantas cresceram sem a interferencia das plantas daninhas. As maiores produtividades foram conseguidas em solo tratado com clomazone e a interferência de plantas daninhas provocou reduções de 81 a 99,7% na produtividade. Os genótipos menos sensíveis à interferência de plantas daninhas foram UFVJM07, UFVJM10 e UFVJM35, enquanto os mais sensíveis foram Princesa e UFVJM01. O controle químico proporcionou produtividade de raízes semelhante ou superior ao controle mecânico para 17 dos 20 genótipos estudados.
Celiac disease (CD) is a chronic illness characterized by an inflammatory process triggered by gluten protein intake. Recent evidence has suggested that the lower relative abundance of bifidobacteria ...in the intestinal lumen may be associated with CD. Herein, we assessed the effect of the Bifidobacterium species Bifidobacterium bifidum, Bifidobacterium longum, Bembidion breve, Bifidobacterium animalis alone, and also a Bifidobacterium consortium on the digestion of intact gluten proteins (gliadins and glutenins) and the associated immunomodulatory responses elicited by the resulting peptides. The cytotoxicity and proinflammatory responses were evaluated through the activation of NF-kB p65 and the expression of cytokines TNF-α and IL-1β in Caco-2 cell cultures exposed to gluten-derived peptides. The peptides induced a clear reduction in cytotoxic responses and proinflammatory marker levels compared to the gluten fragments generated during noninoculated gastrointestinal digestion. These results highlight the possible use of probiotics based on bifidobacteria as a prospective treatment for CD.
Hormone-like herbicides, used for large crops, can contaminate non-target areas with their waste. The objective of this study was to evaluate the tolerance of Mabea fistulifera and Zeyheria ...tuberculosa to 2,4-D + picloram herbicides by means of morphological and anatomical evaluations. The experiment was performed in a greenhouse in a 4 × 2 factorial scheme. The first factor was the control (without herbicide) and three doses (0.166; 0.333, and 0.666 L ha
−1
) of the herbicide Tordon
®
(402 g L
−1
2,4-D + 103.6 g L
−1
picloram) and the second factor, the species Mabea fistulifera and Zeyheria tuberculosa. The number of M. fistulifera leaves was lower after treatment with the highest dose of the 2,4-D + picloram mixture. The herbicide rates did not influence the number of Z. tuberculosa leaves. The higher dose of 2,4-D + picloram caused a more than 50% reduction in leaf area. Toxicity increased linearly as a function of the doses of the 2,4-D + picloram mixture. Changes in the leaf anatomy of the two species treated with herbicides were observed; however, the roots did not show any changes. Mabea fistulifera and Zeyheria tuberculosa can be recommended for phytoremediation programs in areas contaminated by the herbicides 2,4-D + picloram.
Phytoremediation of soils contaminated with herbicides is a recent and viable tool for environmental decontamination and for the protection of water resources. Mabea fistulifera and Zeyheria tuberculosa can be used to compose riparian forests and retain the arrival of herbicides in the water. Plant anatomy and morphological characteristics are viable tools to assess the tolerance and phytoremediation potential of plant species. Mabea fistulifera and Zeyheria tuberculosa are tolerant to the presence of hormonal herbicides. In this way, they can be used to recover natural areas close to the cultivation areas where the herbicides 2,4-D and picloram are used.
etically modified organisms (GMOs) are widespread in Brazil, especially those related to resistance to herbicides and insects. This work aimed to evaluate herbicides' effect on the emergence of maize ...weevil Sitophilus zeamais (Coleoptera: Curculionidae) in different maize genotypes. The experimental design was a 3 × 5 factorial experiment in a randomized complete block design with four replications. Genotypes of transgenic maize, Herculex® (TC1507) and PowerCore® (MON89034 × TC1507 × NK603) and an Isohybrid (non-transgenic) were used. The herbicides were Atrazine, Atrazine + Nicosulfuron, Ammonium Glufosinate, Nicosulfuron and a control treatment without herbicide application. The emergence of S. zeamais was observed in grains from each plot for 100 days, with 300 grams of maize grains. The Isohybrid was the most attractive to S. zeamais when no herbicide was applied. The application of Ammonium Glufosinate increased S. zeamais preference for Herculex® and Nicosulfuron for PowerCore®. The insertion of an exogenous gene and the application of herbicides in maize plants can alter components of the insect-plant interaction, changing the attractiveness to S. zeamais.
Abstract Trees occurring on the margins of agricultural areas can mitigate damage from residual herbicides. Rhizospheric microbial activity associated with trees is one of the main remedial capacity ...indicators. The objective of this study was to evaluate the rhizospheric microbiological activity in tree species subjected to the herbicides atrazine and sulfentrazone via the rhizosphere. The experiment was designed in four blocks and a 6 × 3 factorial scheme. The first factor consisted of six tree species from Brazil and the second of atrazine, sulfentrazone, and water solutions. Four herbicide applications were performed via irrigation. The total dry mass of the plants, mycorrhizal colonization, number of spores, basal respiration of the rhizospheric soil, and survival rate of bioindicator plants after phytoremediation were determined. Trichilia hirta had higher biomass when treated with atrazine and sulfentrazone. Herbicides decreased the microbial activity in Triplaris americana and did not affect the microbiological indicators of Myrsine gardneriana, Schizolobium parahyba, and Toona ciliata. Fewer bioindicator plants survived in soil with Triplaris americana and sulfentrazone. Microbiological indicators were influenced in different ways between species by the presence of herbicides in the rhizosphere.
Resumo As árvores que ocorrem nas margens das áreas agrícolas podem mitigar os danos dos herbicidas residuais. A atividade microbiana rizosférica associada às árvores é um dos principais indicadores de capacidade corretiva. O objetivo deste trabalho foi avaliar a atividade microbiológica rizosférica em espécies arbóreas submetidas aos herbicidas atrazina e sulfentrazone via rizosfera. O experimento foi estruturado em quatro blocos e esquema fatorial 6 × 3. O primeiro fator consistiu em seis espécies de árvores do Brasil e o segundo em soluções de atrazine, sulfentrazone e água. Quatro aplicações de herbicidas foram realizadas via irrigação. Foram determinados a massa seca total das plantas, colonização micorrízica, número de esporos, respiração basal do solo rizosférico e taxa de sobrevivência de plantas bioindicadoras após fitorremediação. Trichilia hirta apresentou maior biomassa quando tratada com atrazina e sulfentrazone. Os herbicidas diminuíram a atividade microbiana em Triplaris americana e não afetaram os indicadores microbiológicos de Myrsine gardneriana, Schizolobium parahyba e Toona ciliata. Menos plantas bioindicadoras sobreviveram no solo com Triplaris americana e sulfentrazone. Os indicadores microbiológicos foram influenciados de formas distintas entre as espécies pela presença dos herbicidas na rizosfera.
Soy is Brazil’s main commodity, and due to its importance, farmers have adopted several technological innovations, such as light supplementation, to increase grain productivity and quality. However, ...the use of artificial light can interfere with weed dynamics and herbicide efficiency. The objective of this work was to evaluate the effect of herbicides on weed control and qualitative and quantitative attributes of soybeans grown under light supplementation. A field experiment was set up in the city of Monte Carmelo, MG, Brazil. The treatments were distributed in plots mounted under a central pivot in two environments: with light supplementation (LED panels) and without light supplementation. The treatments were distributed across four blocks, and plots were subdivided in space. The herbicides used were glyphosate, diclosulam and glyphosate, s-metolachlor and glyphosate, fomesafen + clethodim, flumioxazin + clethodim. The variables analyzed were the number of weeds, biomass, and control; chlorophyll levels; initial fluorescence; ratio of variable fluorescence to maximum fluorescence; and soybean electron transport rate—indicators of soybean yield. Light supplementation increases the density and biomass of weeds and impairs the effectiveness of herbicides. However, light supplementation with LED panels installed on the central irrigation pivot promotes increased productivity and improvements in the quantitative and qualitative parameters of soybeans. Due to these benefits, light supplementation can be considered advantageous for irrigated soybean production.
ABSTRACT Mycorrhizae provide several benefits to coffee plants. This study evaluated whether these benefits influence the damage caused by the Bidens pilosa competition with coffee seedlings. A ...randomized blocks design was used, with treatments established in a 2 x 3 factorial scheme (presence and absence of B. pilosa interference in non-inoculated control or plants inoculated with either Claroideoglomus etunicatum or Dentiscutata heterogama). Coffee seedlings were inoculated with fungi spores and developed for 120 days. Then, they were subjected to the interference of B. pilosa for more 120 days, when data were collected for growth traits, mycorrhizal colonization, dry matter and foliar nutrient concentrations in coffee plants. Dry matter and nutrient contents in B. pilosa plants were also evaluated. Inoculation provided better growth and nutrition of coffee plants. The competition with B. pilosa reduced mycorrhizal colonization, height, leaf area, leaf and stem dry mass, root dry weight, number of reproductive branches and levels of P and Fe in the coffee plants. However, the harmful effect of the interference was lower in inoculated coffee plants. The dry mass of B. pilosa decreased under the interference of inoculated coffee plants. The inoculation of C. etunicatum and D. heterogama in Arabica coffee seedlings increases the competitiveness of the crop against B. pilosa interference.
RESUMO As micorrizas proporcionam diversos benefícios às plantas de cafeeiro. Avaliou-se se esses benefícios influenciam nos danos causados pela competição de Bidens pilosa com plantas jovens de café. Utilizou-se delineamento em blocos casualizados, com tratamentos estabelecidos pelo fatorial 2 x 3 (presença e ausência da interferência de B. pilosa em plantas inoculadas com Claroideoglomus etunicatum ou Dentiscutata heterogama e não inoculadas). Plântulas de café foram inoculadas com esporos dos fungos e se desenvolveram por 120 dias. Em seguida, foram submetidas à interferência de B. pilosa por mais 120 dias, quando foram coletados dados de crescimento, colonização micorrízica, massa seca e teores foliares de nutrientes no cafeeiro. Também foram avaliados a massa seca e os teores de nutrientes em plantas de B. pilosa. A inoculação proporcionou melhor crescimento e nutrição das plantas de café. A competição com B. pilosa reduziu a colonização micorrízica, altura, área foliar, massa seca de folhas e de caule, massa seca de raízes, número de ramos plagiotrópicos e teores de P e Fe das plantas de café, porém, esse efeito foi menor nas plantas inoculadas. A massa seca de B. pilosa diminuiu sob a interferência de plantas de café inoculadas. A inoculação de C. etunicatum e D. heterogama, em mudas de café arábica, aumenta a capacidade competitiva da cultura frente à interferência de B. pilosa.
PDF
