Nondestructive Estimation Of Leaf Area Research Articles

Leaf Area Prediction of Pennywort Plants Grown in a Plant Factory Using Image Processing and an Artificial Neural Network

The leaf is a primary part of a plant, and examining the leaf area is crucial in understanding growth and plant physiology. Accurately estimating leaf area is key to this understanding. This study proposed a methodology for the non-destructive estimation of leaf area in pennywort plants using image processing and an artificial neural network (ANN) model. The image processing method involved a series of steps, including grayscale conversion, histogram equalization, binary masking, and region filling, achieving an accuracy of around 96.6%. The ANN model, trained with 70% of a dataset, exhibited high correlations of 97.1% in training and 96.6% in testing phases, with leaf length and width significantly impacting the model output. A comparative analysis revealed the superior performance of the ANN model over the image processing method, demonstrating higher R2 values (>0.99) and lower errors. Furthermore, it showed the impact of diverse LED light combinations and nutrient levels (electrical conductivity, EC) on pennywort plant growth, indicating that the R70:B30 LED light ratio with nutrient level 2 (2.0 dS·m−1) fostered the most favorable growth for pennywort plants. The non-destructive nature, simplicity, and speed of the ANN model in estimating leaf area based on easily obtainable measurements of length and width render it an accessible and accurate tool for plant growth assessment in controlled environments. This approach offers opportunities for future studies, tracking changes in leaf areas under varied growth conditions without harming the plant, thus enhancing precision in research.

Non-destructive estimation of leaf area and leaf weight of Cinchona officinalis L. (Rubiaceae) based on linear models

Non-destructive methods that accurately estimate leaf area (LA) and leaf weight (LW) are simple and inexpensive, and represent powerful tools in the development of physiological and agronomic research. The objective of this research is to generate mathematical models for estimating the LA and LW of Cinchona officinalis leaves. A total of 220 leaves were collected from C. officinalis plants 10 months after transplantation. Each leaf was measured for length, width, weight, and leaf area. Data for 80% of leaves were used to form the training set, and data for the remaining 20% were used as the validation set. The training set was used for model fit and choice, whereas the validation set al.lowed assessment of the of the model’s predictive ability. The LA and LW were modeled using seven linear regression models based on the length (L) and width (Wi) of leaves. In addition, the models were assessed based on calculation of the following statistics: goodness of fit (R 2), root mean squared error (RMSE), Akaike’s information criterion (AIC), and the deviation between the regression line of the observed versus expected values and the reference line, determined by the area between these lines (ABL). For LA estimation, the model LA = 11.521(Wi) − 21.422 (R 2 = 0.96, RMSE = 28.16, AIC = 3.48, and ABL = 140.34) was chosen, while for LW determination, LW = 0.2419(Wi) − 0.4936 (R 2 = 0.93, RMSE = 0.56, AIC = 37.36, and ABL = 0.03) was selected. Finally, the LA and LW of C. officinalis could be estimated through linear regression involving leaf width, proving to be a simple and accurate tool.

A Machine Learning Approach for the Non-Destructive Estimation of Leaf Area in Medicinal Orchid Dendrobium nobile L.

In this study, leaf area prediction models of Dendrobium nobile, were developed through machine learning (ML) techniques including multiple linear regression (MLR), support vector regression (SVR), gradient boosting regression (GBR), and artificial neural networks (ANNs). The best model was tested using the coefficient of determination (R2), mean absolute errors (MAEs), and root mean square errors (RMSEs) and statistically confirmed through average rank (AR). Leaf images were captured through a smartphone and ImageJ was used to calculate the length (L), width (W), and leaf area (LA). Three orders of L, W, and their combinations were taken for model building. Multicollinearity status was checked using Variance Inflation Factor (VIF) and Tolerance (T). A total of 80% of the dataset and the remaining 20% were used for training and validation, respectively. KFold (K = 10) cross-validation checked the model overfit. GBR (R2, MAE and RMSE values ranged at 0.96, (0.82–0.91) and (1.10–1.11) cm2) in the testing phase was the best among the ML models. AR statistically confirms the outperformance of GBR, securing first rank and a frequency of 80% among the top ten ML models. Thus, GBR is the best model imparting its future utilization to estimate leaf area in D. nobile.

Development of a Simple Empirical Yield Predition Model Based on Dry Matter Production in Sweet Pepper

Abstract The development of models for yield prediction in greenhouse sweet peppers may help improve yield and labour productivity. We aimed to monitor the growth and yield of hydroponically grown sweet pepper plants without destructive sampling. First, we constructed a prediction model and validated it in a cultivation experiment. In the developed model, daily node appearance and light use efficiency were predicted from daily mean air temperature and daytime carbon dioxide (CO2) concentration. The daily light interception was obtained by non-destructive leaf area estimation. Second, we validated the model through the cultivation experiment. The predicted total dry matter production at 200 days after transplanting (DAT), 1,379 g/m2, fell within the range of the observed value, 1,353 ± 46 g/m2 (mean ± SE). The predicted and observed yields at 200 DAT were 7.90 kg/m2 and 7.73 ± 0.82 kg/m2, respectively. We approximately predicted node appearance, total dry matter production, and fruit yield, while partially succeeding in predicting leaf area index and dry matter partitioning to fruit. Our non-destructive prediction model can be an effective tool for growers and to improve the yield of sweet pepper production.

A research on Non-Destructive Leaf Area Estimation Modeling for some Apple Cultivars

A research on Non-Destructive Leaf Area Estimation Modeling for some Apple Cultivars

Non-destructive estimation of leaf area of Citrus varieties of the Kotra Germplasm Bank

Non-destructive estimation of leaf area of Citrus varieties of the Kotra Germplasm Bank

Effect of the Cultivation Systems and Split Fertilizer Applications on the Growth and Yields of Tatsoi (Brassica rapa subsp. narinosa)

Tatsoi [Brassica rapa subsp. narinosa (L.H.Bailey) Hanelt] is a leafy vegetable with potential for cultivation in a riparian wetland ecosystem. The floating culture system has the advantage of ensuring a sufficient water supply in the growing substrate due to the continuous upward water movement caused by capillarity force. This study evaluated the responses of the tatsoi plant to split fertilizer applications under conventional cultivation and floating culture systems. The fertilizer treatments consisted of control (F0), single (F1), split into 2 (F2), split into 3 (F3) or split into 4 applications (F4). The results showed that early growth of tatsoi was better using floating culture than the conventional system. However, tatsoi adapted well to conventional and floating culture systems as long as sufficient nutrients were available. A single application of 6 g NPK fertilizer (16:16:16 v/v/v) at transplanting provided sufficient nutrients, as indicated by the number of leaves, total leaf area, canopy area, stem dry weight, and leaf dry weight at harvest. The leaf SPAD values in the tatsoi plants were higher in the floating culture system than in the conventional system at 14 and 20 DAT fertilized with a 4-split application. Transplanting occurred 14 days after seed planting (DAP), and harvest occurred 49 days later. A quadratic regression model using leaf length (L), leaf width (W), or L×W as predictors was reliable for non-destructive leaf area estimation in the tatsoi plant. It is recommended for farmers to apply a single NPK fertilizer at the rate of 6 g/plant to achieve an optimum yield in tatsoi cultivated using a conventional or floating culture system.
 HIGHLIGHTS
 
 Tatsoi plant grew well under conventional and floating culture systems as long as sufficient nutrients were available
 Splitting fertilizer into several times of application did not significantly better than single application of NPK fertilizer at time of transplanting
 SPAD values in the tatsoi leaves were higher in the floating culture than in the conventional system
 Length and width of leaves were reliable predictors for non-destructive accurate leaf area estimation in the tatsoi plant
 
 GRAPHICAL ABSTRACT

Non-destructive leaf area estimation of Fig (Ficus carica L.) cv. Iraqi grown in different root zone spatial limitation and controlled porosity level under greenhouse condition

Leaf area (LA) is associated with many agronomic and physiological processes including growth, photosynthesis, transpiration, photon interception, energy balance and yield potential of the plant. Accurate, rapid and non-destructive leaf area estimation is a useful subject of study for the fields of applied plant science especially with potted plants. However, till date there is lack of information available on Fig (Ficus carica L.) cv. Iraqi grown in containers under different root zone spatial limitation and controlled porosity level. Thus, this study aims to determine the effect of both factors on leaf area of the crop. Determining the individual LA of F. carica cv. Iraqi involves measurements of leaf parameters such as length (L) and width (W), or some combinations of these parameters. The widest part of the foliage was taken as leaf width (W) and leaf length (L) was defined as the distance between the two furthest points (from lamina tip to the point of petiole intersection along the midrib) of the foliage. The length (L) and width (W) of each leaf will be measured by using a leaf area meter having a sensor and read-out unit which calibrated to 0.01 cm 2. There is significant interaction was observed for each treatment. It can be concluded that application of the right root zone and porosity level gave positive effect on leaf area of F. carica cv. Iraqi grown under greenhouse condition.

Nondestructive estimation of leaf area for 15 species of vines with different leaf shapes.

The nondestructive measurement of leaf area is important for expediting data acquisition in the field. The Montgomery equation (ME) assumes that leaf area (A) is a proportional function of the product of leaf length (L) and width (W), i.e., A = cLW, where c is called the Montgomery parameter. The ME has been successfully applied to calculate the surface area of many broad-leaved species with simple leaf shapes. However, whether this equation is valid for more complex leaf shapes has not been verified. Leaf A, L, and W were measured directly for each of 5601 leaves of 15 vine species, and ME and three other models were used to fit the data. All four models were compared based on their root mean square errors (RMSEs) to determine whether ME provided the best fit. The ME was a reliable method for estimating the A of all 15 species. In addition, the numerical values of 13 of the 15 values of c fell within a previously predicted numerical range (i.e., between 1/2 and π/4). The data show that the numerical values of c are largely affected by the value of W/L, the concavity of the leaf base, and the number of lobes on the lamina. The Montgomery parameter can reflect the influence of leaf shape on leaf-area calculations and can serve as an important tool for nondestructive measurements of leaf area for many broad-leaved species and for the investigation of leaf morphology.

Non-Destructive Leaf Area Estimation Model for Overall Growth Performances in Relation to Yield Attributes of Cassava (Manihot esculenta Cranz) under Water Deficit Conditions

Cassava is a tropical storage root crop, a source of carbohydrate and alternative energy. It has been classified as “drought tolerant plant” for the whole life cycle, except during the root initiation stage (120-150 DAP). Leaf area index (LAI) is one of the most parameters representing the overall growth and yield prediction in cassava. The aim of this investigation was to validate the physiological and growth performance of cassava in responses to water deficit stress in the field trial as well as to investigate the leaf area index as an important factor to cassava growth and storage root bulking. Leaf relative water content in cassava declined significantly upon a long period of water withholding, and regulated non-photochemical quenching (NPQ), leading to chlorophyll degradation, reduced number of leaves and limited leaf area index (LAI) and loss of storage root yield when compared with well-irrigated plants. Non-destructive leaf area estimation model under water deficit stress condition using spectral reflectance to determine the LAI and VIs was validated. The Ratio Vegetation Index (RVI) was suitable model with high coefficient of determination (R2 = 0.89). However, the RVI as LAI at 150 DAP (120 d water withholding) could be considered as the critical point to indicate cassava growth and yield performance. Based on the results, cassava growth, biomass and yield in the different environments may further be investigated, taking into consideration the genotypic variation and using remote sensing technology for rapid monitoring and accurate and cost-effective data assessment.
 
 *********
 In press - Online First. Article has been peer reviewed, accepted for publication and published online without pagination. It will receive pagination when the issue will be ready for publishing as a complete number (Volume 47, Issue 3, 2019). The article is searchable and citable by Digital Object Identifier (DOI). DOI link will become active after the article will be included in the complete issue.
 *********

Leaf shape simulation of castor bean and its application in nondestructive leaf area estimation

Leaf shape simulation of castor bean and its application in nondestructive leaf area estimation

Non-destructive estimation of leaf area in passion fruit (Passiflora edulis L.)

Non-destructive estimation of leaf area in passion fruit (Passiflora edulis L.)

Non-destructive estimation of leaf area of durian (Durio zibethinus) – An artificial neural network approach

Non destructive estimation of leaf area is necessary for taking successive observations on the same leaf. Usually, a common method for developing leaf area estimation models was to execute regression analysis by taking leaf area as dependant variable and leaf parameters as independent variables. However, the regression analysis applicable only when there is a relation between dependent and independent variables. Therefore, the objective of this work was to develop an artificial neural network (ANN) model including leaf length and leaf width as inputs and to make comparison with regression models. Leaf area (LA) of Durain (Durio zibethinus) was estimated by ANN and regression models. Among the linear regression models (LRM), the equation LA=0.888 (L*W)−4.961 (R2=0.91, MSE=5.17) was found to be the best fitting for durian. In ANN modelling best fitting results were obtained with two input nodes (leaf length and leaf width), one hidden layer, and one output layer (leaf area) as 2-1-1. Based on the values of root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE) and coefficient determination (R2), ANN model was found to be more accurate both in terms of training (R2=0.96, RMSE=3.77, MAE=2.41 and MAPE=7.77) and testing phases (R2=0.94, RMSE=4.81, MAE=2.91 and MAPE=0.05) than the best fitting regression model. Hence ANN method may be used as an alternative or supportive model in the estimation of leaf area of durian.

Comparación de métodos directos e indirectos para la estimación del área foliar en duraznero (<i>Prunus persica</i>) y ciruelo (<i>Prunus salicina</i>)

El área foliar es un parámetro ampliamente usado en estudios de ecofisiología de cultivos, debido a que la relación existente entre el área foliar y la producción de fruta es bastante estrecha. Para su determinación se utilizan diferentes métodos ya sean destructivos, no destructivos o indirectos. La estimación del área foliar es una importante observación biométrica que debe hacerse con el propósito de comparar el comportamiento de los vegetales en función de diferentes tratamientos. El objetivo del estudio fue la determinación y validación de las funciones de regresión más acertadas para la estimación no destructiva del área foliar en algunos cultivares de duraznero y ciruelo. En este trabajo se calcularon funciones matemáticas para estimar el área foliar en los cultivares Gold Fruly, Ecuatoriano, Methley y Horvin, de ciruelo, y en los cultivares Dorado, Rubidoux, Diamante y Rey Negro, de duraznero. Las hojas se colectaron de árboles cultivados en Paipa, Colombia. Se seleccionó una función de regresión para cada cultivar y se realizó su validación comparando datos de área foliar estimados con las funciones matemáticas y datos medidos con el medidor de área foliar. Se tomó como variable independiente (X) de la función, el producto del largo por el ancho de la hoja. En todos los casos el coeficiente de correlación de Pearson presentó valores superiores a 0,9, señalando la estrecha relación entre los datos estimados y los observados. Con el uso de estas funciones, es posible estimar de manera no destructiva, el área foliar en los cultivares de duraznero y ciruelo involucrados en el estudio.

A simple linear model for leaf area estimation in Persian walnut (Juglans regia L.)

Accurate non-destructive leaf area estimation is a useful subject of study for the fields of applied plant science, physiology and plant genetic engineering. The relationship between leaf area and fruit is very important in fruit crops. It determines the nut size and nut filling potential. The aim of this paper is to produce a statistical model based on linear measurements such as leaflet length and width in combination with other simple parameters. Measurements of leaf length, width and surface area of the leaflets were achieved using digital photography. Digital images of Persian walnut (Juglans regia L.) leaves were prepared in August 2011 for 14 genotypes and in 2012 for one genotype under open field conditions. Results of regression analysis indicated several models are suitable to estimate leaf area of Persian walnut. The linear model with LW as an independent variable (LA=1.11+0.69LW) with accurate estimation (maximum R2=0.99 and lowest MSE=10.09) was the best model. To determine the leaf area, the earliest measurements to take would be the length and width of leaflets. Total area of the leaflets is then reported as leaf area. In conclusion, in walnut, number of leaflets and leaflet area should be involved in the estimation of leaf area.

Allometric models for non-destructive leaf area estimation of Jatropha curcas

We evaluated the current used allometric models and proposed a reliable and accurate model using non-destructive measurements of leaf length (L) and/or width (W) for estimating the leaf area of the Jatropha plant ( Jatropha curcas L.). For model construction, a total of 1200 leaves were randomly selected from different levels of the tree canopies and encompassed the full spectrum of measurable leaf sizes (0.19–367 cm 2 ). Power models better fit the Jatropha leaf area (LA) compared to linear models; however, when the LW was used, the intercept was removed from the linear model to precisely estimate LA. To validate these models, two independent data sets of 300 leaves were used. We demonstrate that the currently used models are biased and underestimate the area of Jatropha leaves. We developed an unbiased, single power model (Y = x β1 ) based on two leaf dimensions [LA = (LW) 0.9660 ] with high precision and accuracy as well as a random dispersion pattern of the residuals. The model may be simplified by using only one leaf dimension (Y = x β1 ), LA = L 1.9644 or LA = W 1.8929 . However, when either W or L alone was used as the single leaf dimension, the power model predicted the LA with good accuracy at the expense heteroscedastic residual dispersion behavior. ► A rapid and simple model was developed to predict the leaf area for the purging nut. ► The models are simple and able to produce accurate results without expensive equipment. ► Researchers can accurately estimate large quantities leaf areas of purging nut plants. ► The current model to estimate leaf area of the jatropha underestimate LA.

A simple model for nondestructive leaf area estimation in bedding plants

Measurement of leaf area is commonly used in many horticultural research experiments, but it is generally destructive, requiring leaves to be removed for measurement. Determining the individual leaf area (LA) of bedding plants like pot marigold (Calendula officinalis L.), dahlia (Dahlia pinnata), sweet William (Dianthus barbatus L.), geranium (Pelargonium × hortorum), petunia (Petunia × hybrida), and pansy (Viola wittrockiana) involves measurements of leaf parameters such as length (L) and width (W) or some combinations of these parameters. Two experiments were carried out during spring 2010 (on two pot marigold, four dahlia, three sweet William, four geranium, three petunia, and three pansy cultivars) and summer 2010 (on one cultivar per species) under greenhouse conditions to test whether a model could be developed to estimate LA of bedding plants across cultivars. Regression analysis of LA versus L and W revealed several models that could be used for estimating the area of individual bedding plants leaves. A linear model having LW as the independent variable provided the most accurate estimate (highest R 2, smallest mean square error, and the smallest predicted residual error sum of squares) of LA in all bedding plants. Validation of the model having LW of leaves measured in the summer 2010 experiment coming from other cultivars of bedding plants showed that the correlation between calculated and measured bedding plants leaf areas was very high. Therefore, these allometric models could be considered simple and useful tools in many experimental comparisons without the use of any expensive instruments.

Nondestructive leaf-area estimation and validation for green pepper (Capsicum annuum L.) grown under different stress conditions

Leaf area of a plant is essential to understand the interaction between plant growth and environment. This useful variable can be determined by using direct (some expensive instruments) and indirect (prediction models) methods. Leaf area of a plant can be predicted by accurate and simple leaf area models without damaging the plant, thus, provide researchers with many advantages in horticultural experiments. Several leaf-area prediction models have been produced for some plant species in optimum conditions, but not for a plant grown under stress conditions. This study was conducted to develop leaf area estimation models by using linear measurements such as lamina length and width by multiple regression analysis for green pepper grown under different stress conditions. For this purpose, two experiments were conducted in a greenhouse. The first experiment focused to determine leaf area of green pepper grown under six different levels of irrigation water salinity (0.65, 2.0, 3.0, 4.0, 5.0, and 7.0 dS m−1) and the other under four different irrigation regime (amount of applied water was 1.43, 1.0, 0.75, and 0.50 times of required water). In addition to general models for each experiment, prediction models of green pepper for each treatment of irrigation water salinity and of irrigation regime experiments were obtained. Validations of the models for both experiments were realized by using the measurements belong to leaf samples allocated for validation purposes. As a result, the determined equations can simply and readily be used in prediction of leaf area of green pepper grown under salinity and water stress conditions. The use of such models enable researchers to measure leaf area on the same plants during the plant growth period and, at the same time, may reduce variability in experiments.

Non-destructive Estimation of Leaf Area in Tea (Camelia sinensis)*

Non-destructive Estimation of Leaf Area in Tea (Camelia sinensis)*

Non-destructive Estimation of Leaf Area in Tea (Camelia sinensis)

Non-destructive Estimation of Leaf Area in Tea (Camelia sinensis)