Variation In Leaf Shape Research Articles

PSR-LeafNet: A Deep Learning Framework for Identifying Medicinal Plant Leaves Using Support Vector Machines

In computer vision, recognizing plant pictures has emerged as a multidisciplinary area of interest. In the last several years, much research has been conducted to determine the type of plant in each image automatically. The challenges in identifying the medicinal plants are due to the changes in the effects of image light, stance, and orientation. Further, it is difficult to identify the medicinal plants due to factors like variations in leaf shape with age and changing leaf color in response to varying weather conditions. The proposed work uses machine learning techniques and deep neural networks to choose appropriate leaf features to determine if the leaf is a medicinal or non-medicinal plant. This study presents a neural network design based on PSR-LeafNet (PSR-LN). PSR-LeafNet is a single network that combines the P-Net, S-Net, and R-Net, all intended for leaf feature extraction using the minimum redundancy maximum relevance (MRMR) approach. The PSR-LN helps obtain the shape features, color features, venation of the leaf, and textural features. A support vector machine (SVM) is applied to the output achieved from the PSR network, which helps classify the name of the plant. The model design is named PSR-LN-SVM. The advantage of the designed model is that it suits more considerable dataset processing and provides better results than traditional neural network models. The methodology utilized in the work achieves an accuracy of 97.12% for the MalayaKew dataset, 98.10% for the IMP dataset, and 95.88% for the Flavia dataset. The proposed models surpass all the existing models, having an improvement in accuracy. These outcomes demonstrate that the suggested method is successful in accurately recognizing the leaves of medicinal plants, paving the way for more advanced uses in plant taxonomy and medicine.

Herbarium specimens reveal links between leaf shape of Capsella bursa-pastoris and climate.

Studies into the evolution and development of leaf shape have connected variation in plant form, function, and fitness. For species with consistent leaf margin features, patterns in leaf architecture are related to both biotic and abiotic factors. However, for species with inconsistent leaf shapes, quantifying variation in leaf shape and the effects of environmental factors on leaf shape has proven challenging. To investigate leaf shape variation in a species with inconsistently shaped leaves, we used geometric morphometric modeling and deterministic techniques to analyze approximately 500 digitized specimens of Capsella bursa-pastoris collected throughout the continental United States over 100 years. We generated a morphospace of the leaf shapes and modeled leaf shape as a function of environment and time. Leaf shape variation of C. bursa-pastoris was strongly associated with temperature over its growing season, with lobing decreasing as temperature increased. While we expected to see changes in variation over time, our results show that the level of leaf shape variation was consistent over the 100 years. Our findings showed that species with inconsistent leaf shape variation can be quantified using geometric morphometric modeling techniques and that temperature is the main environmental factor influencing leaf shape variation.

Deep learning to capture leaf shape in plant images: Validation by geometric morphometrics.

Plant leaves play a pivotal role in automated species identification using deep learning (DL). However, achieving reproducible capture of leaf variation remains challenging due to the inherent "black box" problem of DL models. To evaluate the effectiveness of DL in capturing leaf shape, we used geometric morphometrics (GM), an emerging component of eXplainable Artificial Intelligence (XAI) toolkits. We photographed Ranunculus auricomus leaves directly in situ and after herbarization. From these corresponding leaf images, we automatically extracted DL features using a neural network and digitized leaf shapes using GM. The association between the extracted DL features and GM shapes was then evaluated using dimension reduction and covariation models. DL features facilitated the clustering of leaf images by source populations in both in situ and herbarized leaf image datasets, and certain DL features were significantly associated with biological leaf shape variation as inferred by GM. DL features also enabled leaf classification into morpho-phylogenomic groups within the intricate R. auricomus species complex. We demonstrated that simple in situ leaf imaging and DL reproducibly captured leaf shape variation at the population level, while combining this approach with GM provided key insights into the shape information extracted from images by computer vision, a necessary prerequisite for reliable automated plant phenotyping.

Genetic Evidence of SpGH9A3 in Leaf Morphology Variation of Spathiphyllum 'Mojo'.

Leaves play a crucial role as ornamental organs in Spathiphyllum, exhibiting distinct differences across various Spathiphyllum varieties. Leaf development is intricately linked to processes of cell proliferation and expansion, with cell morphology often regulated by plant cell walls, primarily composed of cellulose. Alterations in cellulose content can impact cell morphology, subsequently influencing the overall shape of plant organs. Although cellulases have been shown to affect cellulose levels in plant cells, genetic evidence linking them to the regulation of leaf shape remains limited. This study took the leaves of Spathiphyllum 'Mojo' and its somatic variants as the research objects. We screened four cellulase gene family members from the transcriptome and then measured the leaf cellulose content, cellulase activity, and expression levels of cellulase-related genes. Correlation analysis pinpointed the gene SpGH9A3 as closely associated with leaf shape variations in the mutant. Green fluorescent fusion protein assays revealed that the SpGH9A3 protein was localized to the cell membrane. Notably, the expression of the SpGH9A3 gene in mutant leaves peaked during the early spread stage, resulting in smaller overall leaf size and reduced cellulose content upon overexpression in Arabidopsis.

Leaf rolling detection in maize under complex environments using an improved deep learning method

Leaf rolling is a common adaptive response that plants have evolved to counteract the detrimental effects of various environmental stresses. Gaining insight into the mechanisms underlying leaf rolling alterations presents researchers with a unique opportunity to enhance stress tolerance in crops exhibiting leaf rolling, such as maize. In order to achieve a more profound understanding of leaf rolling, it is imperative to ascertain the occurrence and extent of this phenotype. While traditional manual leaf rolling detection is slow and laborious, research into high-throughput methods for detecting leaf rolling within our investigation scope remains limited. In this study, we present an approach for detecting leaf rolling in maize using the YOLOv8 model. Our method, LRD-YOLO, integrates two significant improvements: a Convolutional Block Attention Module to augment feature extraction capabilities, and a Deformable ConvNets v2 to enhance adaptability to changes in target shape and scale. Through experiments on a dataset encompassing severe occlusion, variations in leaf scale and shape, and complex background scenarios, our approach achieves an impressive mean average precision of 81.6%, surpassing current state-of-the-art methods. Furthermore, the LRD-YOLO model demands only 8.0 G floating point operations and the parameters of 3.48 M. We have proposed an innovative method for leaf rolling detection in maize, and experimental outcomes showcase the efficacy of LRD-YOLO in precisely detecting leaf rolling in complex scenarios while maintaining real-time inference speed.

Water wisteria genome reveals environmental adaptation and heterophylly regulation in amphibious plants.

Heterophylly is a phenomenon whereby an individual plant dramatically changes leaf shape in response to the surroundings. Hygrophila difformis (Acanthaceae; water wisteria), has recently emerged as a model plant to study heterophylly because of its striking leaf shape variation in response to various environmental factors. When submerged, H. difformis often develops complex leaves, but on land it develops simple leaves. Leaf complexity is also influenced by other factors, such as light density, humidity, and temperature. Here, we sequenced and assembled the H. difformis chromosome-level genome (scaffold N50: 60.43 Mb, genome size: 871.92 Mb), which revealed 36 099 predicted protein-coding genes distributed over 15 pseudochromosomes. H. difformis diverged from its relatives during the Oligocene climate-change period and expanded gene families related to its amphibious habit. Genes related to environmental stimuli, leaf development, and other pathways were differentially expressed in submerged and terrestrial conditions, possibly modulating morphological and physiological acclimation to changing environments. We also found that auxin plays a role in H. difformis heterophylly. Finally, we discovered candidate genes that respond to different environmental conditions and elucidated the role of LATE MERISTEM IDENTITY 1 (LMI1) in heterophylly. We established H. difformis as a model for studying interconnections between environmental adaptation and morphogenesis.

A CUC1/auxin genetic module links cell polarity to patterned tissue growth and leaf shape diversity in crucifer plants

How tissue-level information encoded by fields of regulatory gene activity is translated into the patterns of cell polarity and growth that generate the diverse shapes of different species remains poorly understood. Here, we investigate this problem in the case of leaf shape differences between Arabidopsis thaliana, which has simple leaves, and its relative Cardamine hirsuta that has complex leaves divided into leaflets. We show that patterned expression of the transcription factor CUP-SHAPED COTYLEDON1 in C. hirsuta (ChCUC1) is a key determinant of leaf shape differences between the two species. Through inducible genetic perturbations, time-lapse imaging of growth, and computational modeling, we find that ChCUC1 provides instructive input into auxin-based leaf margin patterning. This input arises via transcriptional regulation of multiple auxin homeostasis components, including direct activation of WAG kinases that are known to regulate the polarity of PIN-FORMED auxin transporters. Thus, we have uncovered a mechanism that bridges biological scales by linking spatially distributed and species-specific transcription factor expression to cell-level polarity and growth, to shape diverse leaf forms.

High quality genome of potherb mustard XC (Brassica juncea var. multiceps) provides new insight into leaf shape variation1

The potherb mustard ‘Xuecai’ (XC) cultivar is a cruciferous vegetable that is popular as a fresh and a pickled vegetable. On the basis of the deep notches in the edges of leaves in mustard XC, this plant can be said to have multipinnately lobed leaves. The net photosynthesis of lobed leaves has been found to be significantly greater than that of simple leaves. However, the molecular mechanism of leaf shape variation has not been determined. Here, we used HiFi and Hi-C data to assemble the XC genome. The genome was 961.72 Mb in size, with a contig N50 value of 6.565 Mb. The XC genome was compared with four previously sequenced mustard genomes, and genomic collinearity regions, SNPs, and indels were identified. Quintuple BjRCO genes were found on Chromosome (Chr.) A10 in potherb mustard XC when the BjRCO gene locus was compared against other sequenced B. juncea genomes. Segmental duplication was found to contribute to the BjRCO gene copy number. The transcript expression of BjRCO genes was greater in multipinnately lobed leaves than in sawtooth-like leaves. Together, these findings indicate that both the copy number increase and the high expression of BjRCO genes regulate leaf shape from simple to complex in B. juncea. Gene editing of the BjRCO gene from XC changed the leaf shape from multipinnately lobed to simple. The high-quality XC genome sequence not only provides new insight into B. juncea leaf type genomics but also helps in deciphering leaf shape variation. Our study provides insight into the variation and evolution of important traits through comparative analysis of the sequenced genome.

Morphometric analysis of wild potato leaves

To catalog and promote the conservation and use of crop wild relatives, comprehensive phenotypic and genotypic information must be available. Plant genotyping has the power to resolve the phylogenetic relationships between crop wild relatives, quantify genetic diversity, and identify marker-trait associations for expedited molecular breeding. However, access to cost-effective genotyping strategies is often limited in underutilized crops and crop wild relatives. Potato landraces and wild species, distributed throughout Central and South America, exhibit remarkable phenotypic diversity and are an invaluable source of resistance to pests and pathogens. Unfortunately, very limited information is available for these germplasm resources, particularly regarding phenotypic diversity and potential use as trait donors. In this work, more than 150 accessions corresponding to 12 species of wild and cultivated potatoes, collected from different sites across the American continent, were analyzed using computer vision and morphometric methods to evaluate leaf size and shape. In total, more than 1100 leaves and leaflets were processed and analyzed for nine traits related to size, shape, and color. The results produced in this study provided a visual depiction of the extensive variability among potato wild species and enabled a precise quantification of leaf phenotypic differences, including shape, color, area, perimeter, length, width, aspect ratio, convexity, and circularity. We also discussed the application and utility of inexpensive but comprehensive morphometric approaches to catalog and study the diversity of crop wild relatives. Finally, this study provided insights for further experimental research looking into the potential role of leaf size and shape variation in plant–insect interactions, agronomic productivity, and adaptation.

A diffusible small-RNA-based Turing system dynamically coordinates organ polarity.

The formation of a flat and thin leaf presents a developmentally challenging problem, requiring intricate regulation of adaxial-abaxial (top-bottom) polarity. The patterning principles controlling the spatial arrangement of these domains during organ growth have remained unclear. Here we show that this regulation in Arabidopsis thaliana is achieved by an organ-autonomous Turing reaction-diffusion system centred on mobile small RNAs. The data illustrate how Turing dynamics transiently instructed by prepatterned information is sufficient to self-sustain properly oriented polarity in a dynamic, growing organ, presenting intriguing parallels to left-right patterning in the vertebrate embryo. Computational modelling demonstrates that this self-organizing system continuously adapts to coordinate the robust planar polarity of a flat leaf while affording flexibility to generate the tissue patterns of evolutionarily diverse organ shapes. Our findings identify a small-RNA-based Turing network as a dynamic regulator of organ polarity that accounts for leaf shape diversity at the level of the individual organ, plant or species.

Evolution of larval gregariousness is associated with host plant specialisation, but not host morphology, in Heliconiini butterflies.

Insect herbivores, such as lepidopteran larvae, often have close evolutionary relationships with their host plants, with which they may be locked in an evolutionary arms race. Larval grouping behaviour may be one behavioural adaptation that improves host plant feeding, but aggregation also comes with costs, such as higher competition and limited resource access. Here, we use the Heliconiini butterfly tribe to explore the impact of host plant traits on the evolution of larval gregariousness. Heliconiini almost exclusively utilise species from the Passifloraceae as larval host plants. Passifloraceae display incredible diversity in leaf shape and a range of anti-herbivore defences, suggesting they are responding to, and influencing, the evolution of Heliconiini larvae. By analysing larval social behaviour as both a binary (solitary or gregarious) and categorical (increasing larval group size) trait, we revisit the multiple origins of larval gregariousness across Heliconiini. We investigate whether host habitat, leaf defences and leaf size are important drivers of, or constraints on, larval gregariousness. Whereas our data do not reveal links between larval gregariousness and the host plant traits included in this study, we do find an interaction between host plant specialisation and larval behaviour, revealing gregarious larvae to be more likely to feed on a narrower range of host plant species than solitary larvae. We also find evidence that this increased specialisation typically precedes the evolutionary transition to gregarious behaviour. The comparatively greater host specialisation of gregarious larvae suggests that there are specific morphological and/or ecological features of their host plants that favour this behaviour.

FAMeLeS: A multispecies and fully automated method to measure morphological leaf traits

Abstract Leaf shape parameters are of key importance to explain the role of energy balance and water economy in plant species distribution, plant productivity and, more generally, in plant–environment interactions. Yet, leaf shape measurements based on image processing are still challenging due to the high diversity of leaf shapes, colours and sizes leading to the development of time‐consuming methods with a narrow field of applicability, sometimes species‐specific or often limited to a few species. We developed a fully automated method for measuring multiple leaf shape parameters (area, perimeter, length, width, circularity and solidity) based on a large image sampling of leaf diversity (including litter) belonging to 587 species and spread over 232 countries worldwide. To evaluate the accuracy of the method to detect small objects, the sampling particularly targeted Mediterranean ecosystems (32 species and 25,205 leaves), in which small leaves often represent methodological challenges. We compared our approach and found that its mean error in leaf area measurement (+0.46%) was 1.7–148 times lower than four existing methods. It was also the only one capable of detecting and measuring all leaves in the test data set, even variegated and small leaves (less than 1 mm2). Its reliability was extensively checked on the largest and most diversified data set ever used. Our method, accessible to the broader scientific community, was simple, rapid and effective on multiple image file types and on a high diversity of leaf size, shape and colour. As such, our approach allows measurement not only on fresh leaves but also on dry leaves, such as leaf litter or leaves from herbaria. This tolerance to leaf characteristics is crucial to increase large‐scale sampling efforts and paves the way for a standardized multispecies approach to measuring leaf morphological traits for ecological and agricultural studies.

Foliar Morphological and Micromorphological Variation of Dioscorea Species in Terengganu, Malaysia

Dioscorea species are recognised for their production of tuberous roots and are referred to as "ubi" by the local population in Malaysia. The tubers of Dioscorea are commonly consumed by individuals residing in the East Coast region of Peninsular Malaysia as their primary food source. These tuberous roots are particularly abundant during the monsoon season, typically observed in local markets from October to December. Due to the availability and potential of this Dioscorea species, a study about the variation in morphological and micromorphological study of the leaves of three species of Dioscorea in Terengganu was conducted in order to identify the variation in their morphological and micromorphological characteristics. The selected species are D. esculenta (ubi itik), D. alata (ubi besar), and D. hispida (ubi gadong). The collection has been done in the Kuala Berang Terengganu area. The leaves morphological characteristics such as leaf colour, leaf type, leaf shape, leaf size, leaf margin and hairiness of adaxial and abaxial surface and shape of leaves and petiole were recorded. The morphological descriptors were suggested by the International Plant Genetic Resources Institute (IPGRI) / International Institute of Tropical Agriculture (IITA). The foliar anatomical studies of selected Dioscorea were followed by the standard tissue sectioning procedures and the observation was done by using light microscopy. The morphological study shows the variations in leaf shape, leaf base, and leaf size but they have the similarity in term of leaf margin shape and leaf attachment which is all species are petiolate. The micromorphological study shows the presence of non-glandular and uniseriate trichomes which is only obtained in the D. esculenta and D. hispida. Hence, this study contributes to the information on these species, especially for classification and identification of Dioscorea species.Keywords: Dioscorea, morphology, foliar anatomy

Chromosome-level genome of the transformable northern wattle, Acacia crassicarpa.

The genus Acacia is a large group of woody legumes containing an enormous amount of morphological diversity in leaf shape. This diversity is at least in part the result of an innovation in leaf development where many Acacia species are capable of developing leaves of both bifacial and unifacial morphologies. While not unique in the plant kingdom, unifaciality is most commonly associated with monocots, and its developmental genetic mechanisms have yet to be explored beyond this group. In this study, we identify an accession of Acacia crassicarpa with high regeneration rates and isolate a clone for genome sequencing. We generate a chromosome-level assembly of this readily transformable clone, and using comparative analyses, confirm a whole-genome duplication unique to Caesalpinoid legumes. This resource will be important for future work examining genome evolution in legumes and the unique developmental genetic mechanisms underlying unifacial morphogenesis in Acacia.

The Competing Endogenous RNAs Regulatory Genes Network Mediates Leaf Shape Variation and Main Effector Gene Function in Mulberry Plant (Morus alba)

Mulberry plants (Morus alba) have leaf shapes, ranging from unlobed to lobed, which are crucial for yield, growth, and adaptability, indicating their ability to adapt to their environment. Competing endogenous RNAs (ceRNAs) constitute a web of RNAs within the organism’s transcriptional regulatory system, including protein-coding genes (mRNAs), microRNAs (miRNAs), long non-coding RNAs (lncRNAs), circular RNAs (circRNAs), and others. In this study, samples for ceRNA sequencing were categorized into two groups: whole leaves and lobed leaves, each group with three replicates. In addition, we isolated, cloned, and characterized the precursor miRNA (miR156x) from the leaves of M. alba. miR156x precursor had a length of 107 base pairs and a minimum folding free energy of 50.27 kcal/mol. We constructed a pCAMBIA-35S-GUS-miR156x dual overexpression vector and established a transient transformation system for mulberry. At an optimal transformation solution (OD600 = 0.7), the GUS gene showed a higher expression in the leaves of transiently transformed mulberry with miR156x overexpression, four days after transformation, while the target genes of miR156x had decreased expression in the same leaves. Investigations into the transgenic mulberry plants uncovered various modifications to physio-chemical parameters including POD, SOD, PRO, MDA, soluble proteins and sugars, and chlorophyl content. miRNAs in the plants were found to act as negative regulators of gene expression in response to changes in leaf shape regulation, which was confirmed in vitro using dual-luciferase reporter assays. Subsequently, we cloned Maspl3 in vitro and conducted GST-Pull down assays, obtaining multiple proteins that interacted with the Maspl3 gene. This indicates that the miR156x/Maspl3/MSTRG.25812.1 regulatory module contributes to the differences in mulberry leaf shape.

S 2 CL-Leaf Net : Recognizing Leaf Images Like Human Botanists

Automatically classifying plant leaves is a challenging fine-grained classification task because of the diversity in leaf morphology, including size, texture, shape, and venation. Although powerful deep learning-based methods have achieved great improvement in leaf classification, these methods still require a large number of well-labeled samples for supervised training, which is difficult to get. In contrast, relying on the specific coarse-to-fine classification strategy, human botanists only require a small number of samples for accurate leaf recognition. Inspired by the classification strategy of human botanists, we propose a novel S 2 CL-Leaf Net , which exploits multi-granularity clues with a hierarchical attention mechanism and boosts the learning ability with the supervised sampling contrastive learning with limited training samples to classify plant leaves as human botanists do. Specifically, to fully explore and exploit the subtle details of the leaves, a novel sampling transformation mechanism is combined with the supervised contrastive learning to enhance the network’s perception of details by amplifying the discriminative regions with a weighted sampling of different regions. Furthermore, we construct the hierarchical attention mechanism to produce attention maps of different granularity, which helps to discover details in leaves that are important for classification. Experiments are conducted on the open-access leaf datasets, including Flavia, Swedish, and LeafSnap, which prove the effectiveness of the proposed S 2 CL-Leaf Net .

Unsupervised leaf segmentation in complex backgrounds using mutual information minimization

Leaf segmentation is crucial for plant recognition, especially for tree species identification. In natural environments, leaf segmentation can be very challenging due to the lack of prior information about leaves and the variability of backgrounds. In typical applications, supervised algorithms often require pixel-level annotation of regions, which can be labour-intensive and limited to identifying plant species using pre-labelled samples. On the other hand, traditional unsupervised image segmentation algorithms require specialised parameter tuning for leaf images to achieve optimal results. Therefore, this paper proposes an unsupervised leaf segmentation method that combines mutual information with neural networks to better generalise to unknown samples and adapt to variations in leaf shape and appearance to distinguish and identify different tree species. First, a model combining a Variational Autoencoder (VAE) and a segmentation network is used as a pre-segmenter to obtain dynamic masks. Secondly, the dynamic masks are combined with the segmentation masks generated by the mask generator module to construct the initial mask. Then, the patcher module uses the Mutual Information Minimum (MIM) loss as an optimisation objective to reconstruct independent regions based on this initial mask. The process of obtaining dynamic masks through pre-segmentation is unsupervised, and the entire experimental process does not involve any label information. The experimental method was performed on tree leaf images with a naturally complex background using the publicly available Pl@ntLeaves dataset. The results of the experiment showed that compared to existing excellent methods on this dataset, the IoU (Intersection over Union) index increased by 3.9%.

Fine genetic mapping confers a major gene controlling leaf shape variation in watermelon

Fine genetic mapping confers a major gene controlling leaf shape variation in watermelon

Patterns of host plant use do not explain mushroom body expansion in Heliconiini butterflies.

The selective pressures leading to the elaboration of downstream, integrative processing centres, such as the mammalian neocortex or insect mushroom bodies, are often unclear. In Heliconius butterflies, the mushroom bodies are two to four times larger than those of their Heliconiini relatives, and the largest known in Lepidoptera. Heliconiini lay almost exclusively on Passiflora, which exhibit a remarkable diversity of leaf shape, and it has been suggested that the mushroom body expansion of Heliconius may have been driven by the cognitive demands of recognizing and learning leaf shapes of local host plants. We test this hypothesis using two complementary methods: (i) phylogenetic comparative analyses to test whether variation in mushroom body size is associated with the morphological diversity of host plants exploited across the Heliconiini; and (ii) shape-learning experiments using six Heliconiini species. We found that variation in the range of leaf morphologies used by Heliconiini was not associated with mushroom body volume. Similarly, we find interspecific differences in shape-learning ability, but Heliconius are not overall better shape learners than other Heliconiini. Together these results suggest that the visual recognition and learning of host plants was not a main factor driving the diversity of mushroom body size in this tribe.

Assessment of halophyte plant phenotypic responses under heavy metals pollution. Implications for monitoring and phytoremediation

While phytoremediation is a highly valued practice to address local pollution problems, the use of early biomarkers of stress is useful for monitoring environments since they allow us to take measures before deleterious effects are irreversible. In this framework the goals are: to evaluate the pattern of leaf shape variation of Limonium brasiliense plants related to a metal soil gradient in the San Antonio salt marsh; to assess whether seeds from sites with different pollution levels show the same pattern of leaf shape variations under optimal growing conditions; and to compare the growth, the Pb accumulation pattern, and the leaf shape variation pattern of plants germinated from seeds originated in sites with different pollution levels in response to an experimental Pb rise. The results obtained from leaves collected in the field showed that the leaf shape changed depending on the soil metal levels. Plants germinated from seeds collected at the different sites expressed all the variation in leaf shape independently of the origin site, and the mean shape of each site was close to the consensus. Instead, when looking for the leaf shape components that maximize the differences between the sites from a growth experiment exposed to an increase in Pb in the irrigation solution, the pattern of variation found in the field disappeared. That is, only plants from the polluted site did not show variations in leaf shape in response to Pb additions. Finally, Pb accumulation in the roots was highest in plants germinated from seeds from the site where the soil pollution is greater. That suggests that seeds of L. brasiliense from polluted sites are better to use in phytoremediation practices, specifically to stabilize Pb in its roots whilst plants from the non-polluted site are better to detect pollutant soils using the leaf shape as an early biomarker.