Using Machine Learning and RGB Images to Assess Nitrogen and Potassium Status in Sorghum (Sorghum bicolor L.) Under Field Conditions

Plants meet machines: Prospects in machine learning for plant biology

The biomass productivity and wheat grains efficiency is determined by nitrogen dose adjustment (full or fractioned), environmental conditions, and cropping system. The aim of this study was to improve the efficiency of N-fertilizer usage on wheat to maximize the biomass productivity and grain yield by adjusting the full or fractioned nitrogen dose in favorable and unfavorable year conditions, in succession systems with high and reduced N-residual release. In this study, two experiments were conducted between 2012 and 2014. One was to quantify the biomass productivity rate and another to determine grain yield. The experimental design was a complete randomized block, with four replications, in a 4 × 3 factorial scheme to N fertilizer rates (0, 30, 60 and 120 kg ha-1) and supply forms of the nutrient [full dose (100%) in the V3 phenological stage (third expanded leaf); fractioned (70 and 30%) at the V3 and V6 phenological stages (third and sixth expanded leaf, respectively) and; fractionated (70 and 30%) at the V3 and E phenological stages (third expanded leaf and early grain filling), ] respectively, in soybean/wheat and maize/wheat cultivation systems. The nitrogen supply in wheat through single dose or fraction indicates linear tendency over the productivity biomass daily rate-1 with the increase of N-fertilizer, regardless of a favorable and unfavorable year and system of a succession of the high and reduced N-residual release. However, in favorable years, the use of full dose on V3 stage is indicated. In the maize/wheat system, the full dose at V3 stage is more efficient, especially with higher doses of the nutrient. For grain yield, the N-fertilizer fractioning was adjusted in intermediate cropping years, while the full dose became suitable at the V3 stage in favorable years. However, in unfavorable years, nitrogen investments should be minimized, regardless of the supply form and succession system. Key words: Triticum aestivum L., succession system, optimization, regression.

Li, Y., Iwaasa, A. D., Wang, Y., Jin, L., Han, G. and Zhao, M. 2014. Condensed tannins concentration of selected prairie legume forages as affected by phenological stages during two consecutive growth seasons in western Canada. Can. J. Plant Sci. 94: 817–826. Studies have shown that condensed tannins (CT) at appropriate concentrations improve nutrient digestion in animals and influence ecosystem processes. However, knowledge of CT concentration in different phenological stages and different plant parts of non-conventional legumes growing in the western Canadian prairies is lacking for feed and grazing management. The research objectives were to determine the level and distribution of total CT (TCT), extractable CT (ECT) and protein-bound (PCT) or fiber-bound CT (FCT) concentrations in the whole plant of legume forages at different phenological (vegetative, flowering, seed maturity) stages and plant parts (leaves, stems, inflorescences and inflorescences+seedpods) using the Butanol-HCl procedure. Whole plant samples of purple prairie clover (Dalea purpurea Vent.), white prairie clover (D. candida Michx. ex Willd), sainfoin (Onobrychis viciifolia Scop.) and Canadian milkvetch (Astragalus canadensis L.) were collected in the 2011 and 2012 growing seasons from replicated small trial plots at vegetative, flowering and seed maturity stages. Species, phenological stages and their interactions all significantly affect the TCT, ECT, PCT and FCT concentrations in whole plant and plant parts (P<0.001). Concentrations of ECT and TCT increased for all species as they matured from vegetative to seed maturity, except for sainfoin where the vegetative stage had the highest ECT and TCT levels. The highest mean ECT and TCT concentrations for purple prairie clover and white prairie clover were found in the inflorescences part at flowering stage, while sainfoin had the highest ECT and TCT concentrations in the leaves at vegetative stage. There was little variation for PCT among different phenological stages in whole plant for species except for purple prairie clover and white prairie clover which had higher (P<0.05) PCT at seed maturity than at flowering stage. Only trace amounts of FCT were detected from either whole plant or different fractions of all plant species, except Canadian milkvetch. Condensed tannins were not observed in Canadian milkvetch except for trace amounts in the seed coat at seed maturity stage. The results demonstrate that legumes differ in their condensed tannin content which could potentially be used in pasture management.

Li, Y., Iwaasa, A. D., Wang, Y., Jin, L., Han, G. and Zhao, M. 2014. Condensed tannins concentration of selected prairie legume forages as affected by phenological stages during two consecutive growth seasons in western Canada. Can. J. Plant Sci. 94: 817-826. Studies have shown that condensed tannins (CT) at appropriate concentrations improve nutrient digestion in animals and influence ecosystem processes. However, knowledge of CT concentration in different phenological stages and different plant parts of non-conventional legumes growing in the western Canadian prairies is lacking for feed and grazing management. The research objectives were to determine the level and distribution of total CT (TCT), extractable CT (ECT) and protein-bound (PCT) or fiber-bound CT (FCT) concentrations in the whole plant of legume forages at different phenological (vegetative, flowering, seed maturity) stages and plant parts (leaves, stems, inflorescences and inflorescences seedpods) using the Butanol-HCl procedure. Whole plant samples of purple prairie clover (Dalea purpurea Vent.), white prairie clover (D. candida Michx. ex Willd), sainfoin (Onobrychis viciifolia Scop.) and Canadian milkvetch (Astragalus canadensis L.) were collected in the 2011 and 2012 growing seasons from replicated small trial plots at vegetative, flowering and seed maturity stages. Species, phenological stages and their interactions all significantly affect the TCT, ECT, PCT and FCT concentrations in whole plant and plant parts (P<0.001). Concentrations of ECT and TCT increased for all species as they matured from vegetative to seed maturity, except for sainfoin where the vegetative stage had the highest ECT and TCT levels. The highest mean ECT and TCT concentrations for purple prairie clover and white prairie clover were found in the inflorescences part at flowering stage, while sainfoin had the highest ECT and TCT concentrations in the leaves at vegetative stage. There was little variation for PCT among different phenological stages in whole plant for species except for purple prairie clover and white prairie clover which had higher (P<0.05) PCT at seed maturity than at flowering stage. Only trace amounts of FCT were detected from either whole plant or different fractions of all plant species, except Canadian milkvetch. Condensed tannins were not observed in Canadian milkvetch except for trace amounts in the seed coat at seed maturity stage. The results demonstrate that legumes differ in their condensed tannin content which could potentially be used in pasture management.

Determining the phenological growth stages is crucial for estimating crop growth and development. Stage-specific crop coefficient (K c ) values, derived from phenological stages, are essential for optimizing irrigation scheduling in lily cultivation. This study quantified the crop water requirements (CWR) of lilies by estimating evapotranspiration (ET) at different growth stages. Using a modified Biologische Bundesanstalt, Bundessortenamt und CHemische Industrie (BBCH) scale, six principal stages were defined: germination/sprouting (stage 0), stem elongation and leaf development (stage 1), inflorescence emergence (stage 5), flowering (stage 6), bulb development (stage 7), and senescence (stage 9). Growing degree days (GDD) consistently predicted bud visible and flowering stages across different conditions. Changes in bulb dry weight and size illustrated the source-sink transition throughout the growth cycle of lilies. Reference evapotranspiration (ET o ) was estimated using the FAO-56 Penman–Monteith equation, a widely used method for estimating ET o , and calibrated for an experimental greenhouse to improve accuracy. Crop evapotranspiration (ET c ), defined as the actual evapotranspiration of the lily crop, varied across growth stages, with daily means of 0.93, 1.95, 2.11, 1.88, and 1.80 mm·d⁻¹ in stages 0, 1, 5, 6, and 7–9, respectively. These values indicate that water minimal water use at germination, peak consumption during inflorescence emergence and flowering, and a decline during bulb development and senescence. The corresponding mean K c values were 0.7, 1.0, 1.1, 1.1, and 0.8. These findings highlight the distinct water use pattern of lilies and provide an approach for optimizing irrigation efficiency in greenhouse cultivation by integrating phenology-based K c values into scheduling.

مطالعه با هدف شناسایی برخی شاخص‌های فیزیولوژیک و زراعی مناسب برای گزینش ژنوتیپ‌های متحمل به خشکی کلزای بهاره اجرا گردید. آزمایش به‌صورت کرت‌های خرد شده بر پایه بلوک‌های کامل تصادفی با سه تکرار در ایستگاه خسروشاه مرکز تحقیقات و آموزش کشاورزی و منابع طبیعی آذربایجان شرقی طی دو سال زراعی 1394 و 1395 اجرا گردید. فاکتور اصلی تنش کمبود آب با سطوح: بدون تنش، تنش از زمان گل‌دهی و از خورجین‌دهی تا رسیدگی و فاکتور فرعی ژنوتیپ شامل: RGS003، ظفر، ساری گل، زرفام و دلگان بودند. نتایج نشان دادند بروز خشکی از مراحل گل‌دهی و خورجین‌دهی باعث افزایش معنی‌دار دمای برگ و کاهش معنی‌دار مقدار نسبی آب برگ (RWC)، هدایت روزنه، شاخص کلروفیل برگ، تعداد خورجین در بوته، تعداد دانه در خورجین، وزن هزار دانه، درصد روغن، عملکرد دانه و روغن گردید ولی بیشترین تأثیرپذیری به هنگام وقوع تنش از مرحله گل‌دهی بود. بنابراین تأمین آب در این مرحله اولویت بیشتری خواهد داشت. کمبود آب با اثر کاهشی روی همه اجزای عملکرد باعث افت عملکرد دانه گردید. همبستگی‌های معنی‌داری بین دمای برگ، RWC ، شاخص کلروفیل برگ و هدایت روزنه با همدیگر و با عملکرد دانه و روغن و اجزای عملکرد دانه دیده شد. شاخص‌های مذکور از کارایی قابل قبولی در شناسایی اثرات کمبود آب روی ژنوتیپ‌های بهاره کلزا برخوردار بودند. ژنوتیپ RGS003 با کسب بیشترین مقدار نسبی آب برگ، هدایت روزنه و شاخص کلروفیل برگ، همواره بیشترین عملکرد دانه و روغن را به خود اختصاص داد و برای کشت در شرایط مواجه با کمبود آب قابل توصیه است.

Productivity and production components of safflower genotypes affected by irrigation at phenological stages

This study was aimed at determining the nutrient composition and in vitro ruminal digestion values of Plantago lanceolata herbage in different phenological stages. The plant samples were gathered in the vegetative, flowering and early seed stages of the plant. The crude protein, diethyl ether extract, ash, non-fibre carbohydrates, and proanthocyanidins levels of the vegetative and flowering stages were higher than those of the early seed stage (P &amp;lt; 0.001). Structural carbohydrate levels (P &amp;lt; 0.05) were determined to have a higher value in the early seed stage. Glucose, fructose, Ca, K, Mg, P, Fe and Cu concentrations decreased as the plant matured (P &amp;lt; 0.001), but Na, Zn, and Mn concentrations increased (P &amp;lt; 0.05). The asymptote gas production, gas production rate (P &amp;lt; 0.001), total gas production at 24 h (P = 0.002), metabolic energy, net energy lactation and organic matter digestibility values and the number of Entodinium (P &amp;lt; 0.001) and total bacteria count (P = 0.026) of the flowering and vegetative stages were higher than those of the early seed stage. Methane produced by 0.2 g dry matter was similar in the three phenological stages (P = 0.078). The bound condensed tannins and saponin contents of plants and ammoniacal-N, number of total protozoa and pH value of rumen fluid were similar in the three different phenological stages (P &amp;gt; 0.05). The present study indicates that P. lanceolata in the vegetative and flowering stages has, owing to its chemical composition, energy content and digestibility, the potential to be used as a forage source for ruminants in areas affected by drought.

Comprehensive Study for Breast Cancer Using Deep Learning and Traditional Machine Learning

This paper presents a comparison of conventional and modern machine (deep) learning within the framework of anomaly detection in self-organizing networks. While deep learning has gained significant traction, especially in application scenarios where large volumes of data can be collected and processed, conventional methods may yet offer strong statistical alternatives, especially when using proper learning representations. For instance, support vector machines have previously demonstrated state-of-the-art potential in many binary classification applications and can be further exploited with different representations, such as one-class learning and data augmentation. We demonstrate for the first time, on a previously published and publicly available dataset, that conventional machine learning can outperform the previous state-of-the-art using deep learning by 15% on average across four different application scenarios. Our results further indicate that with nearly two orders of magnitude improvement in computational speed and an order of magnitude reduction in trainable parameters, conventional machine learning provides a robust alternative for 5G self-organizing networks especially when the execution and detection times are critical.

Physiology of yield determination of mung bean ( Vigna radiata (L.) Wilczek) under various irrigation regimes in the dry and intermediate zones of Sri Lanka

Harnessing deep reinforcement learning algorithms for image categorization: A multi algorithm approach

Machine learning and deep learning are currently widely used in various fields, including remote sensing for food security. However, there is no research that specifically examines the interests, developments, and trends of this research in the future. This study aims to examine the development of machine and deep learning research for mapping food crops through a bibliometric approach with computational mapping analysis using VOSviewer. Article data was obtained from the Google Scholar database using the publish or perish reference manager application. The title and abstract of the article were used to guide the search process by referring to the keyword “Machine and Deep Learning Mapping Food Crops”. 114 relevant articles were discovered. Google Scholar-indexed articles over the last ten years, from 2014 to 2023, were used as study material. The results show that machine research and deep learning for mapping food crops can be separated into three terms: machine learning, deep learning, and plant mapping. The term “Crop Mapping” has 57 links for a total of 199 links. The term "machine learning" has 41 links for a total of 79 links, and the term "deep learning" has 26 links for a total of 41 links. The results of the analysis of machine development and deep learning publications for mapping food crops in the last 10 years show a constant increase. The peak of the increase occurred in 2021 and 2022, namely 25 articles published per year, respectively. This means that this research topic is still relatively new in terms of interest and exploration, therefore there is still room further research. We examine numerous articles that have been published on machine and deep learning for crop mapping and their relation to the field studied with VOSviewer. This review can serve as a starting point for further research in different domains

Nutritional deficiencies and muscle loss in adults with type 2 diabetes using GLP-1 receptor agonists: A retrospective observational study

Salinity and drought are two major abiotic stresses challenging global crop production and food security. In this study, the effects of individual and combined effects of drought (at different phenological stages) and salt stresses on growth, morphology, and physiology of triticale were evaluated. For this purpose, a 3 x 4 factorial design in three blocks experiment was conducted. The stress treatments included three levels of salinity (0, 50, and 100 mM NaCl) and four levels of drought (regular irrigation as well as irrigation disruption at heading, flowering, and kernel extension stages). The stresses, individual as well as combined, caused a significant decrease in chlorophyll contents, total dry matter, leaf area index, relative water content, and grain yield of triticale. In this regard, the highest reduction was recorded under combined stresses of 100 mM NaCl and drought stress at flowering. However, an increase in soluble sugars, leaf free proline, carotenoid contents, and electrolyte leakage was noted under stress conditions compared to the control. In this regard, the highest increase in leaf free proline, soluble sugars, and carotenoid contents were noted under the combination of severe salinity and drought stress imposed at the flowering stage. Investigating the growth indices in severe salinity and water deficit stress in different phenological stages shows the predominance of ionic stress over osmotic stress under severe salinity. The highest grain yield was observed under non-saline well-watered conditions whereas the lowest grain yield was recorded under severe salinity and drought stress imposed at the flowering stage. In conclusion, the flowering stage was more sensitive than the heading and kernel extension stages in terms of water deficit. The impact of salinity and water deficit was more pronounced on soluble sugars and leaf free proline; so, these criteria can be used as physiological indicators for drought and salinity tolerance in triticale.