Hasil untuk "Plant culture"

Ross M. Welch

Nurul Labib Sayeedi, Md. Faiyaz Abdullah Sayeedi, Shubhashis Roy Dipta et al.

Bangla culture is richly expressed through region, dialect, history, food, politics, media, and everyday visual life, yet it remains underrepresented in multimodal evaluation. To address this gap, we introduce BanglaVerse, a culturally grounded benchmark for evaluating multilingual vision-language models (VLMs) on Bengali culture across historically linked languages and regional dialects. Built from 1,152 manually curated images across nine domains, the benchmark supports visual question answering and captioning, and is expanded into four languages and five Bangla dialects, yielding ~32.3K artifacts. Our experiments show that evaluating only standard Bangla overestimates true model capability: performance drops under dialectal variation, especially for caption generation, while historically linked languages such as Hindi and Urdu retain some cultural meaning but remain weaker for structured reasoning. Across domains, the main bottleneck is missing cultural knowledge rather than visual grounding alone, with knowledge-intensive categories. These findings position BanglaVerse as a more realistic test bed for measuring culturally grounded multimodal understanding under linguistic variation.

T. Kakimoto

Jianping Yao, Son N. Tran

Plant leaf disease classification is an important task in smart agriculture which plays a critical role in sustainable production. Modern machine learning approaches have shown unprecedented potential in this classification task which offers an array of benefits including time saving and cost reduction. However, most recent approaches directly employ convolutional neural networks where the effect of the relationship between plant species and disease types on prediction performance is not properly studied. In this study, we proposed a new model named Multi-output Deep Supervised Classifier Chains (Mo-DsCC) which weaves the prediction of plant species and disease by chaining the output layers for the two labels. Mo-DsCC consists of three components: A modified VGG-16 network as the backbone, deep supervision training, and a stack of classification chains. To evaluate the advantages of our model, we perform intensive experiments on two benchmark datasets Plant Village and PlantDoc. Comparison to recent approaches, including multi-model, multi-label (Power-set), multi-output and multi-task, demonstrates that Mo-DsCC achieves better accuracy and F1-score. The empirical study in this paper shows that the application of Mo-DsCC could be a useful puzzle for smart agriculture to benefit farms and bring new ideas to industry and academia.

Hilda Hadan, Sabrina A. Sgandurra, Leah Zhang-Kennedy et al.

Deceptive game designs that manipulate players are increasingly common in the gaming industry, but the impact on players is not well studied. While studies have revealed player frustration, there is a gap in understanding how cultural attributes affect the impact of deceptive design in games. This paper proposes a new research direction on the connection between the representation of culture in games and player response to deceptive designs. We believe that understanding the interplay between cultural attributes and deceptive design can inform the creation of games that are ethical and entertaining for players around the globe.

I. Bailo, F. Buonora, G. Ciarfaglia et al.

The energy transition is a key theme of the last decades to determine a future of eco-sustainability, and an area of such importance cannot disregard digitization, innovation and the new technological tools available. This is the context in which the Generative Artificial Intelligence models described in this paper are positioned, developed by Engineering Ingegneria Informatica SpA in order to automate the plant structures acquisition of SNAM energy infrastructure, a leading gas transportation company in Italy and Europe. The digitization of a gas plant consists in registering all its relevant information through the interpretation of the related documentation. The aim of this work is therefore to design an effective solution based on Artificial Intelligence techniques to automate the extraction of the information necessary for the digitization of a plant, in order to streamline the daily work of MGM users. The solution received the P&ID of the plant as input, each one in pdf format, and uses OCR, Vision LLM, Object Detection, Relational Reasoning and optimization algorithms to return an output consisting of two sets of information: a structured overview of the relevant design data and the hierarchical framework of the plant. To achieve convincing results, we extend a state-of-the-art model for Scene Graph Generation introducing a brand new Transformer architecture with the aim of deepening the analysis of the complex relations between the plant's components. The synergistic use of the listed AI-based technologies allowed to overcome many obstacles arising from the high variety of data, due to the lack of standardization. An accuracy of 91\% has been achieved in the extraction of textual information relating to design data. Regarding the plants topology, 93\% of components are correctly identified and the hierarchical structure is extracted with an accuracy around 80\%.

Seyed Hamidreza Nabaei, Ryan Lenfant, Viswajith Govinda Rajan et al.

In the era of growing interest in healthy buildings and smart homes, the importance of sustainable, health conscious indoor environments is paramount. Smart tools, especially VOC sensors, are crucial for monitoring indoor air quality, yet interpreting signals from various VOC sources remains challenging. A promising approach involves understanding how indoor plants respond to environmental conditions. Plants produce terpenes, a type of VOC, when exposed to abiotic and biotic stressors - including pathogens, predators, light, and temperature - offering a novel pathway for monitoring indoor air quality. While prior work often relies on specialized laboratory sensors, our research leverages readily available commercial sensors to detect and classify plant emitted VOCs that signify changes in indoor conditions. We quantified the sensitivity of these sensors by measuring 16 terpenes in controlled experiments, then identified and tested the most promising terpenes in realistic environments. We also examined physics based models to map VOC responses but found them lacking for real world complexity. Consequently, we trained machine learning models to classify terpenes using commercial sensors and identified optimal sensor placement. To validate this approach, we analyzed emissions from a living basil plant, successfully detecting terpene output. Our findings establish a foundation for overcoming challenges in plant VOC detection, paving the way for advanced plant based sensors to enhance indoor environmental quality in future smart buildings.

Margarita Velandia, Carlos Trejo-Pech, David Butler et al.

Alley cropping is an agroforestry practice that involves the planting of trees or shrubs alongside herbaceous crops within the same production system. Potential benefits of alley cropping include crop diversification, enhanced productivity of annual crops, reduced soil erosion, improved pollinators and wildlife habitat, decreased incidence of pests and diseases, carbon sequestration, and reduced nitrogen leaching. Despite these potential benefits, the adoption of alley cropping remains low. In Tennessee, specifically, only about 2% of the farms have used agroforestry practices, including alley cropping. We surveyed Tennessee fruit and vegetable farmers to assess their willingness to adopt alley cropping and the differences in characteristics of those willing and not willing to use this production practice. In general, those respondents who are willing to adopt alley cropping are more familiar with this production system and are facing or have faced production challenges that could be alleviated by adopting this production practice, such as low organic matter and crop heat stress. Our results also suggest that the type of trees or shrubs incorporated in this system and adequate payment for adoption that covers investment and maintenance costs could affect Tennessee fruit and vegetable farmers’ willingness to use this system.

Gan Kunfa, Chen Meng, Liang Tingting et al.

Panax notoginseng, a valuable plant used in traditional Chinese medicine, is often difficult to cultivate because of its susceptibility to various diseases, including root rot. In this study, an antagonistic bacterium (Pn1), which was identified as Bacillus subtilis, effectively controlled P. notoginseng root rot. The underlying mechanism in B. subtilis Pn1 was analyzed. The Pn1 culture supernatant had inhibitory effects on the root rot pathogen Fusarium solani and down-regulated the expression of pathogenicity-related genes. A liquid chromatography-tandem mass spectrometry analysis indicated that Pn1 produces many antifungal metabolites effective against F. solani. Additionally, proteins extracted from the Pn1 culture supernatant adversely affected F. solani mycelial growth and spore germination. Moreover, a proteomic analysis identified several antifungal proteins and antibiotic-related synthases. Furthermore, transcriptome and metabolome analyses of P. notoginseng suggested that B. subtilis Pn1 may protect against root rot through a mechanism involving the activation of phytohormone and phenylpropanoid/flavonoid biosynthesis pathways. This study reports, for the first time, the in-depth and multifaceted mechanisms on the application of B. subtilis in controlling P. notoginseng root rot. The study findings may lead to the application of B. subtilis Pn1 to enhance P. notoginseng root rot resistance, with potential implications for the development of more advanced disease control methods.

Xinpeng Liu, Hiroaki Santo, Yosuke Toda et al.

Accurate estimation of plant skeletal structure (e.g., branching structure) from images is essential for smart agriculture and plant science. Unlike human skeletons with fixed topology, plant skeleton estimation presents a unique challenge, i.e., estimating arbitrary tree graphs from images. While recent graph generation methods successfully infer thin structures from images, it is challenging to constrain the output graph strictly to a tree structure. To this problem, we present TreeFormer, a plant skeleton estimator via tree-constrained graph generation. Our approach combines learning-based graph generation with traditional graph algorithms to impose the constraints during the training loop. Specifically, our method projects an unconstrained graph onto a minimum spanning tree (MST) during the training loop and incorporates this prior knowledge into the gradient descent optimization by suppressing unwanted feature values. Experiments show that our method accurately estimates target plant skeletal structures for multiple domains: Synthetic tree patterns, real botanical roots, and grapevine branches. Our implementations are available at https://github.com/huntorochi/TreeFormer/.

Andrew L. Thomas, George E. Rottinghaus, Matheus Dela Libera Tres et al.

A long-term horticultural experiment was conducted at two geographically distinct sites in southern Missouri in 2011–15 to study the response of American elderberry [Sambucus nigra (L.) subsp. canadensis (L.) Bolli] to various soil nitrogen (N) fertilizer levels. Three commercially available elderberry cultivars (‘Adams II’, ‘Bob Gordon’, and ‘Wyldewood’) were used. The three cultivars were each assigned to 16 of 48 four-plant plots in a completely randomized manner at each site. Four replications of four N fertilizer treatments (0, 56, 112, 169 kg⋅ha−1 N) were randomly assigned to each cultivar’s plots and applied for 4 years (2012–15). Fruit yields, plant growth, phenology, and pest incidence were determined each year. Fruit quality was assessed by analyzing basic juice characteristics as well as organic acids, carbohydrates, anthocyanins, and polyphenols from 2012–14 samples. Leaf tissue analysis determined the plants’ mineral contents in 2012–14. Most factors evaluated were significantly affected by site, year, and cultivar, whereas the effects of N fertilizer treatment were less definitive. Fruit yields and plant growth increased with increasing N levels. For example, plants fertilized with 0, 56, 112, and 169 kg⋅ha−1 N produced 123, 137, 155, and 161 fruiting cymes per plot (5.8 m2), respectively. The eriophyid mite incidence was higher on fertilized plants, but other pests were not influenced by the N treatment. Basic fruit juice characteristics (soluble solids, pH, titratable acidity, polyphenols) were not influenced by the N treatment, whereas total anthocyanins were statistically higher in unfertilized plants. Levels of organic acids and carbohydrates in juice varied statistically among N treatments, but patterns were difficult to discern. Leaf N concentrations were correlated with N fertilizer levels—2.75% N with the highest fertilizer level compared with 2.55% N in unfertilized plants. Leaf levels of most other macronutrients varied, but consistent patterns did not emerge, and none of the micronutrients was different among N treatments. Although elderberry plants responded positively to increased N fertilizer levels in terms of plant growth and fruit yield, genetics (cultivar) and environment (site, year) were more influential on most other experimental factors evaluated.

A. S. Abdulrhman, Sh. M. M. Al-Atrushy

This investigation was aimed to study the effect of soil application of Bio health and foliar application with Tecamin max and Benzyl adenine on growth characteristic of sweet orange (Citrus sinensis L.) seedlings during two successive seasons (2020 and 2021). Bio health was added with three concentrations (0, 6 and 12 g.L-1) to the soil and foliar application of Tecamin max with three concentration (0, 5 and 10 ml.L-1), Benzyl adenine with three concentration (0, 100 and 200 mg. L-1) on the sweet orange seedlings which were brought from private nursery in Duhok city and have two- years old and nearly uniform in growth vigor. The results proved that all parameters such as increases in plant high, stem diameter, branch numbers, single leaf area, total chlorophyll as soon as leaves carbohydrate and leaves dry weight  in both seasons were increased significantly as compared with control, accept  Tecamin max had no significant effect on leaves carbohydrates and leaves dry weight, Benzyl adenine no significant effect on leaves dry weight on both seasons, Furthermore, combination among high concentration of Bio health, Tecamin max and Benzyl adenine  improved all parameters in comparison with the control.

Sudisha Jogaiah, M. Abdelrahman, L. Tran et al.

G. Neumann, V. Römheld

I. Pickering, R. Prince, Martin J George et al.

Yinhao Tong, Zhaocheng Wang, Duxin Gong et al.

This study focused on 6-year-old ‘Pawnee’ pecan trees to elucidate the differential responses of physicochemical properties of orchard soil and pecan fruit quality when combining chemical and organic fertilizers. The aim was to unveil the mechanisms that underlie the effects of different fertilization treatments on soil fertility, soil enzyme activities, and pecan fruit quality. Four treatments were established: sole chemical fertilizer (CF; N:P₂O₅:K₂O is 15:15:15), chemical fertilizer combined with cake fertilizer (CF+CC), chemical fertilizer combined with manure fertilizer (CF+M), and chemical fertilizer combined with cake and manure fertilizer (CF+CC+M). Measurements were taken to assess the soil nutrient content, soil enzyme activities, and fruit growth quality in some orchards under different fertilization treatments. The results revealed that the combined application could increase yield and enhance pecan quality. Among these, the CF+M+CC treatment demonstrated the most favorable outcomes, with the pecan kernel oil and unsaturated fatty acid contents reaching 72.33% and 97.54%, respectively. The combined fertilization treatments had no significant impacts on soil trace elements such as Mg, Cu, and Mn; however, it significantly increased the Available Phosphorus (AP), Total Nitrogen (TN), Soil Organic Matter (SOM) and S-ACP (soil acid phosphatase) activities. In summary, the combined application of chemical and organic fertilizers can significantly increase the soil nutrient content and enzyme activities in pecan orchards, to promote the enhancement of fruit quality and economic aspects.

Yan Ren, Jin-Rong Gao, Shou-Meng Cai et al.

In vitro regeneration was studied to protect the rare Chinese medicinal orchid Liparis nervosa (Thunb.) Lindl. The mixtures of protocorm and seeding and the stem tip were used as explants. The results revealed that the best essential medium for L. nervosa growth was 1/3 MS medium with 25 g · L–1 sucrose, 50 g · L–1 banana puree, 40 g · L–1 mashed potato, and 1.0 g · L–1 AC (MS1); MS1 medium with 0.5 mg · L–1 BA, 0.05 mg · L–1 2,4-D, and 1.5 mg · L–1 NAA was optimal for proliferation. When stem tips were cultured in a proliferation medium, four types of proliferation occurred: basal stem cluster bud (occurring at the basal node), tiller bud (occurring at the root), protocorm-like body (occurring at the plant’s base incision), and high-position bud (occurring on plant stem nodes other than the basal nodes). Four methods produced 10.12 proliferation coefficients. In the MS1 medium with 0.5 mg · L−1 NAA, the plantlets rooted 100%, and the rooted plantlets survived 100% after domestication and transplantation.

Dželetović Željko, D. Gordana, G. Đorđe et al.

A. Suman, Ajar Nath Yadav, P. Verma

Hugh Lachlan Kennedy

Two ways of designing low-order discrete-time (i.e. digital) controls for low-order plant (i.e. process) models are considered in this tutorial. The first polynomial method finds the controller coefficients that place the poles of the closed-loop feedback system at specified positions for adroit controls, i.e. for a rapid and compressed transient response, when the plant model is known precisely. The poles and zeros of the resulting controller are unconstrainted, although an integrator may be included in the controller structure as a special case to drive steady-state errors towards zero. The second frequency method ensures that the feedback system has the desired phase-margin at a specified gain cross-over frequency (for the desired bandwidth) yielding robust stability with respect to plant model uncertainty. The poles of the controller are at specified positions, e.g. for a standard Proportional-Integral (PI), Proportional-Derivative (PD), Proportional-Integral-Derivative (PID), structure or other more general configurations if necessary, and the problem is solved for the controller zeros. The poles and zeros of the resulting closed-loop feedback system are unconstrained. These complementary design procedures allow simple and effective controls to be derived analytically from a plant model, using a matrix inverse operation to solve a small set of linear simultaneous equations, as an alternative to more heuristic (e.g. trial-and-error) or empirical PID-tuning approaches. An azimuth controller for a pan-tilt-zoom camera mount is used as an illustrative example. The ways in which both procedures may be used to design controls with the desired balance between adroitness and robustness are discussed.