Estimating Leaf Area Research Articles

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.

Planting Materials, Shading Effects, and Non-Destructive Estimation of Compound Leaf Area in Konjac (Amorphophallus Muelleri)

Konjac glucomannan has been commercially produced and used as functional food, food additives, food supplements, pharmaceutical and cosmetic, and biomaterials. Despite intensive and advance research at postharvest stage, knowledge on cultivation of konjac plants has been limited. This research covered current issues associated with selecting agronomically the most suitable planting material, shading effects on shoot emergence and growth characteristics, and non-destructive area estimation of the compound leaf in the konjac plants. Planting materials used were 81 true seeds, 81 bulbils and 81 cormels. Results of this study indicated that bulbil was a suitable planting material based on its early shoot emergence and size of above ground organs. Shading at 50 and 70 % exhibited a better performance in time of emergence and growth characteristics than konjac plant fully exposed to sunlight, even though the differences were not statistically significant. Total leaf blade area (LA) of the irregular konjac compound leaf can be accurately (R2 = 0.9932) and consistently estimated using the 0-intercept linear model and the multiplication product of total midrib length and average width of all leaflets (TLM×AWL) is used as predictor. The recommended formula is LA = 0.6761(TLM×AWL).
 HIGHLIGHTS
 
 Shoot emergence in konjac plant was significantly earlier if the true seed was used rather than bulbil and cormel as planting materials
 Plant grown using cormel and bulbil exhibited larger shoot and corm compared to those grown using true seed
 Shading at 50 and 70 % increased length of the pseudo-stem, total number of leaflet, and other morphological characters
 Total midrib length of all leaflets and average of all leaflet width (TLM×AWL) could be used as predictors for accurate LA estimation
 
 GRAPHICAL ABSTRACT

Comparison of artificial neural network and linear regression model for the leaf morphology of fenugreek (Trigonella foenum graecum) grown under different nitrogen fertilizer doses

Health of a plant and its growth can be assessed by the area of its leaf. The present study envisaged to develop an artificial neural network (ANN) and linear regression-based leaf area estimation model, and to compare the models in statistical terms; thereby obtaining a statistically accurate model suitable for predicting leaf area of fenugreek. Fenugreek (Trigonella foenum graecum) was grown at open field conditions at different doses (0, 50, 100, 150, 200, 250, 300, 350 and 400 kgN/ha) of nitrogenous fertilizer using a randomised block design. The morphological parameters in term of leaf area (AP, mm2), leaf width (LW, mm), leaf length (LL, mm), roundness (R), leaf perimeter (LP,mm) and eccentricity (e) using a MATLAB based graphical user interface (GUI) software. Among all the linear regression models, AP =19.66 + 00.62 (LL × LW) (R2 = 0.94, RMSE = 14.09) was found to be the best fitting for fenugreek leaf area estimation. In case of ANN model, the best results obtained when three hidden neurons were considered. The R2, RMSE and MAD values of ANN model during training (0.97, 12.55 and 8.55, respectively) as well as validation (0.97, 10.48 and 7.92, respectively) were found more accurate than the linear regression model. Thus, the proposed ANN model can be used for the estimation of leaf area of fenugreek leaves.

Estimating leaf area of basil cultivars through linear dimensions of leaves

Ocimum basilicum L. (basil) is an annual herb belonging to the Lamiaceae family that has economic importance for many regions around the world. Thus, ecophysiological studies are needed to assess this species growth and dispersal. This work aimed to obtain equations from regression models that meaningfully estimate the leaf area of ​​basil cultivars using linear dimensions of leaves. For this purpose, 300 leaves from 'Italiano Roxo' and 500 leaves from 'Folha Fina' cultivar were collected from plants cultivated in a greenhouse. Then, the length, width, and leaf area of each leaf were measured, and product of length by width were calculated. The equations were adjusted using the simple linear, linear without intercept, quadratic, cubic, power, and exponential regression models. Criteria for selecting the best equations were highest determination coefficient and Willmott's agreement index, lowest Akaike information criterion and root mean square error, and BIAS index closest to zero. All the equations fitted using the product of length by width (L.W) can estimate the leaf area of basil cultivars. Thus, basil leaf area can be estimated through a non-destructive method using linear dimensions of leaves. However, the equation ŷ = 0.8175*LW0.9307 is the most suitable for 'Italiano Roxo' and ŷ = 0.6335*LW for 'Folha Fina'.

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.

Estimating Leaf Area Index and biomass of sugarcane based on Gaussian process regression using Landsat 8 and Sentinel 1A observations

ABSTRACT Accurate estimation of crop parameters, such as Leaf Area Index (LAI) and biomass over large areas using remote sensing techniques, is crucial for monitoring crop growth and yield prediction. In this study, a Gaussian Process Regression (GPR) method was developed to estimate LAI and biomass values of sugarcane during growth season using optical and synthetic-Aperture Radar (SAR) data fusion. Predicting LAI on an independent test data set using the GPR and the combined optical and SAR indices provided better prediction accuracies of LAI; with the GPR based on radial basis function (Root Mean Square Error [RMSE] = 0.34, Mean Absolute Error [MAE] = 0.28 and Mean Absolute Percentage Error [MAPE] = 10.5%) and polynomial function (RMSE = 0.42, MAE = 0.31 and MAPE = 12.58%), respectively. The test results of sugarcane biomass also showed that the GPR (poly) produced the highest statistical results (RMSE = 2.45 kg/m2, MAE = 1.72 kg/m2, MAPE = 8.1%) using the combined indices. The results suggest that the crop biophysical retrieval based on optical and SAR data fusion and GPR proposed in this study could improve LAI and biomass estimation that could help for effective crop growth monitoring and mapping applications.

Combining Spectral and Textural Information from UAV RGB Images for Leaf Area Index Monitoring in Kiwifruit Orchard

The use of a fast and accurate unmanned aerial vehicle (UAV) digital camera platform to estimate leaf area index (LAI) of kiwifruit orchard is of great significance for growth, yield estimation, and field management. LAI, as an ideal parameter for estimating vegetation growth, plays a significant role in reflecting crop physiological process and ecosystem function. At present, LAI estimation mainly focuses on winter wheat, corn, soybean, and other food crops; in addition, LAI on forest research is also predominant, but there are few studies on the application of orchards such as kiwifruit. Concerning this study, high-resolution UAV images of three growth stages of kiwifruit orchard were acquired from May to July 2021. The extracted significantly correlated spectral and textural parameters were used to construct univariate and multivariate regression models with LAI measured for corresponding growth stages. The optimal model was selected for LAI estimation and mapping by comparing the stepwise regression (SWR) and random forest regression (RFR). Results showed the model combining texture features was superior to that only based on spectral indices for the prediction accuracy of the modeling set, with the R2 of 0.947 and 0.765, RMSE of 0.048 and 0.102, and nRMSE of 7.99% and 16.81%, respectively. Moreover, the RFR model (R2 = 0.972, RMSE = 0.035, nRMSE = 5.80%) exhibited the best accuracy in estimating LAI, followed by the SWR model (R2 = 0.765, RMSE = 0.102, nRMSE = 16.81%) and univariate linear regression model (R2 = 0.736, RMSE = 0.108, nRMSE = 17.84%). It was concluded that the estimation method based on UAV spectral parameters combined with texture features can provide an effective method for kiwifruit growth process monitoring. It is expected to provide scientific guidance and practical methods for the kiwifruit management in the field for low-cost UAV remote sensing technology to realize large area and high-quality monitoring of kiwifruit growth, thus providing a theoretical basis for kiwifruit growth investigation.

Estimation of Leaf Area and Leaf Area Density for Design Optimization of a Recycling Tunnel Sprayer

A tunnel sprayer system is considered as one of the most economical and reasonable sprayers for protection of an orchard crop. The performance of the spraying system (spray deposition %, recycling %, and deposition % on abaxial and adaxial surface) could be improved through appropriate design. However, the morphological parameter of the orchard significantly influenced accuracy and effectiveness of the same spraying system. Therefore, this study was conducted to determine the morphological parameters of guava tree. Three techniques were used for estimation of leaf area: Grid Count Method (GCM), Image Processing Technique (IPT) and Regression Model (RM). The grid count method was used as a reference for area estimation. R2 was 0.98 and 0.94 for IP & RM compared to GCM, respectively. In the regression model, only length and width of the guava leaf were found statistically significant (P < 0.01). It was concluded that the image processing technique provided better results for leaf area estimation with mean error ± standard deviation (−0.23 ± 3.41) than regression developed model. This study ensured the accuracy of image processing technique for the leaf area estimation and allows the researchers to deal with voluminous of leafs with accurate and quick response. Leaf area density (LAD) was recorded to be in range of 0.07–2.73 m2/m3. These morphological parameters could be used for design optimization of recycling tunnel sprayer in future, which would help to improve the performance of tunnel system.

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

LEAF AREA OF Erythrina velutina Willd. (FABACEAE) THROUGH ALLOMETRIC EQUATIONS

Leaf area estimation is of fundamental importance to evaluate growth, development, and propagation of plants. This work aimed to adjust and identify regression models to estimate leaf area of Erythrina velutina from linear dimensions of the central leaflet of leaves. Two hundred simple leaves were collected from E. velutina mother plants in forest fragments in the municipality of Mossoró, Rio Grande do Norte state, Northeast Brazil. The equation for estimating leaf area of E. velutina was adjusted from linear, linear without intercept (0.0), quadratic, cubic, power, and exponential regression models. The best equations were those with the highest determination coefficient (R²), Pearson's correlation coefficient (r), Willmott's index ( d ) and CS index (CS), and with the lowest Akaike information criterion (AIC), mean absolute error (MAE), root mean square error (RMSE), and BIAS index closest to zero (BIAS). The equations fitted using the product of length by width (LW) showed the best criteria for estimating leaf area, thus best fitting the regression models used. Therefore, the equation ŷ = 1.4755*LW adjusted using the linear model without intercept is the most suitable for estimating leaf area of E. velutina (R² = 0.9906; r = 0.9860; d = 0.9929; CS = 0.9790; AIC = 1402.7; MAE = 5.34; RMSE = 7.90; BIAS = 0.019).

Understanding of Rice Growing Environment Based on Leaf Area Estimation Using UAV Aerial Imagery

Understanding of Rice Growing Environment Based on Leaf Area Estimation Using UAV Aerial Imagery

Adjusting line quantum sensing to improve leaf area index measurements and estimations in forests

Rapid and reliable estimation of leaf area index (LAI), a crucial parameter in process-based models of vegetation cover response, is important in ecological studies. The Beer-Lambert law is widely used to calculate forest LAI, but data collection methods are time-consuming and calculations are often inaccurate. Our objective was to improve the accuracy of Beer-Lambert law–based LAI estimation by employing indirect data collection and location-specific light extinction coefficients (K). Canopy transmittance and LAI of two 100 m2 temperate forest stands in southwestern Germany, one managed and one protected, was estimated using line quantum sensing (LQS) at 45,000 points per stand. The Beer-Lambert law was then inverted to estimate LAI using the measured transmittance with a K of 0.53–0.54. Hemispherical reference photographs were used as independent validation data to determine ideal K values. Experimental data demonstrated that LAI values estimated using LQS with adjusted K values were more accurate than those calculated using the basic application of the Beer-Lambert law. LQS results correlated with those determined using hemispherical photography for both the managed (R² = 0.80) and protected (R² = 0.81) stands. Overall, these findings show that adjusting K values for individual forest systems improves the accuracy of LAI estimation.•The modified method is more accurate than that using fixed K ranges.•The modified method accounts for individual ecosystems, with different K values for different environments.•The method can accurately reflect the dynamic changes of forest canopy structure, allowing integration of additional environmental measurements.

Digital image processing methods for estimating leaf area of cucumber plants

Increasingly &lt;span&gt;emerging technologies in agriculture such as computer vision, artificial intelligence technology, not only make it possible to increase production. To minimize the negative impact on climate and the environment but also to conserve resources. A key task of these technologies is to monitor the growth of plants online with a high accuracy rate and in non-destructive manners. It is known that leaf area (LA) is one of the most important growth indexes in plant growth monitoring system. Unfortunately, to estimate the LA in natural outdoor scenes (the presence of occlusion or overlap area) with a high accuracy rate is not easy and it still remains a big challenge in eco-physiological studies. In this paper, two accurate and non-destructive approaches for estimating the LA were proposed with top-view and side-view images, respectively. The proposed approaches successfully extract the skeleton of cucumber plants in red, green, and blue (RGB) images and estimate the LA of cucumber plants with high precision. The results were validated by comparing with manual measurements. The experimental results of our proposed algorithms achieve 97.64% accuracy in leaf segmentation, and the relative error in LA estimation varies from 3.76% to 13.00%, which could meet the requirements of plant growth monitoring &lt;/span&gt;systems.

Non-destructive models for estimating leaf area of guava cultivars

Non-destructive models for estimating leaf area of guava cultivars

Allometric equations to estimate the leaf area of Psychotria colorata (Willd. Ex Schult.) Müll.Arg.

Estimating leaf area using non-destructive methods from regression equations has become a more efficient, quick, and accurate way. Thus, this study aimed to propose an equation that significantly estimates the leaf area of Psychotria colorata (Rubiaceae) through linear leaf dimensions. For this purpose, 200 leaves of different shapes were collected, and length (L), width (W), product of length by width (L.W), and real leaf area (LA) of each leaf blade were determined. Then, equations were adjusted for predicting leaf area using simple linear, linear (0.0), quadratic, cubic, power, and exponential regression models. The proposed equation was selected according to the coefficient of determination (R²), Willmott's agreement index (d), Akaike's information criterion (AIC), mean absolute error (MAE), mean squared error (RMSE) and BIAS index. It was noted that the equations adjusted using L.W met the best criteria for estimating leaf area, but the equation LA = 0.59 * L.W from linear regression without intercept was the most suitable. This equation predicts that 59% of leaf area is explained by L.W. Concluding, the leaf area of P. colorata can be estimated using an allometric equation that uses linear leaf blade dimensions.

Exploring the utility of Sentinel-2 for estimating maize chlorophyll content and leaf area index across different growth stages

ABSTRACT This study investigated the utility of Sentinel-2 spectral data for estimating leaf area index (LAI), leaf and canopy chlorophyll content of maize at different growth stages. Vegetation indices based on the visible-near infrared and red-edge regions of the spectrum were computed from Sentinel-2 imagery acquired within one or two days of field data collection. Results showed that green chlorophyll index (CIgreen) and red-edge chlorophyll index (CIred-edge), using the red-edge variant centred at 705 nm, consistently showed higher relationship to maize LAI with r 2 of 0.65 and 0.63 during the early stages of growth, respectively, and an r 2 of 0.79 and 0.81 during tassel stage, respectively. Regarding canopy chlorophyll content the results indicated the spectral advantage of the Sentinel-2 sensor with the presence of two red-edge bands for continuous monitoring of maize chlorophyll content. Overall, the results indicated that maize biophysical variables can be monitored at satellite level using Sentinel-2 data.

Three-dimensional estimation of deciduous forest canopy structure and leaf area using multi-directional, leaf-on and leaf-off airborne lidar data

Airborne laser scanning (ALS) has been widely used to map gap probability and leaf area index (LAI) distribution at plot and landscape scales. As an indirect measurement, most ALS methods to estimate LAI combine waveform or point density information with supporting field measurements such as the leaf angle distribution, gap probability, or direct LAI measures. The development of a more independent estimation approach would facilitate more widespread use of existing ALS data to investigate patterns of forest structure and build realistic 3-D vegetation scenes to simulate remote sensing imagery and energy balance. Here, we develop a data processing workflow (named PVlad) using ALS point cloud apparent reflectance to estimate LAI and voxel-based leaf area density (LAD), aiming to reduce the need for associated field measurements such as the gap probability. The adaptation of the path volume (PV) concept derived from apparent reflectance integrates information from multi-directional ALS pulses, and quantifies the percentage exploration of each voxel for classification and occlusion correction, such that rigorous volumetric sampling approaches can be developed to derive LAI and LAD. The PVlad workflow was applied to discrete-return lidar data (Riegl VQ480i) acquired by NASA Goddard's LiDAR, Hyperspectral and Thermal Imager (G-LiHT) Airborne Imager during leaf-on (summer) and leaf-off (spring) conditions at the Smithsonian Environmental Research Center (SERC). The estimates of LAI and LAD captured structural differences between mature, logged, and intermediate-aged stands over eight deciduous forest plots. The derived LAI values were compared to field litter collection measurements, and the derived LAD vertical distribution was compared to the output of the VoxLAD model using terrestrial laser scan (TLS) field survey data. Using voxel sizes ranging from 0.5 m to 5 m, overall LAI estimation showed linear fitting coefficient bias <0.035 and RMSE<0.5m2/m2 for 1 and 2 m voxel sizes, and vertical LAD distribution showed strong correlation with R≈0.9 and RMSE≈0.028m2/m3 for 0.5 and 1m voxel sizes. For every forest stand, upper-canopy LAD had a low variance for voxel sizes of ≤ 2m. Application of PVlad to the G-LiHT and other similar ALS data archives enables the development of fine-resolution LAI map products, including voxelization of LAD for ecosystem science and radiative transfer simulations of remote sensing imagery or surface energy balance.

Performance Evaluation of the WOFOST Model for Estimating Evapotranspiration, Soil Water Content, Grain Yield and Total Above-Ground Biomass of Winter Wheat in Tensift Al Haouz (Morocco): Application to Yield Gap Estimation

The main goal of this investigation was to evaluate the potential of the WOFOST model for estimating leaf area index (LAI), actual evapotranspiration (ETa), soil moisture content (SM), above-ground biomass levels (TAGP) and grain yield (TWSO) of winter wheat in the semi-arid region of Tensift Al Haouz, Marrakech (central Morocco). An application for the estimation of the Yield Gap is also provided. The model was firstly calibrated based on three fields data during the 2002–2003 and 2003–2004 growing seasons, by using the WOFOST implementation in the Python Crop simulation Environment (PCSE) to optimize the different parameters that provide the minimum difference between the measured and simulated LAI, TAGP, TWSO, SM and ETa. Then, the model validation was performed based on the data from five other wheat fields. The results obtained showed a good performance of the WOFOST model for the estimation of LAI during both growing seasons on all validation fields. The average R2, RSME and NRMSE were 91.4%, 0.57 m2/m2, and 41.4%, respectively. The simulated ETa dynamics also showed a good agreement with the observations by eddy covariance systems. Values of 60% and 72% for R2, 0.8 mm and 0.7 mm for RMSE, 54% and 31% for NRMSE are found for the two validation fields, respectively. The model’s ability to predict soil moisture content was also found to be satisfactory; the two validation fields gave R2 values equal to 48% and 49%, RMSE values equal to 0.03 cm3/cm3 and 0.05 cm3/cm3, NRMSE values equal to 11% and 19%. The calibrated model had a medium performance with respect to the simulation of TWSO (R2 = 42%, RSME = 512 kg/ha, NRMSE = 19%) and TAGP (R2 = 34% and RSME = 936 kg/ha, NRMSE = 16%). After accurate calibration and validation of the WOFOST model, it was used for analyzing the gap yield since this model is able to estimate the potential yield. The WOFOST model allowed a good simulation of the potential yield (7.75 t/ha) which is close to the optimum value of 6.270 t/ha in the region. Yield gap analysis reveals a difference of 5.35 t/ha on average between the observed yields and the potential yields calculated by WOFOST. Such difference is ascribable to many factors such as the crop cycle management, agricultural practices such as water and fertilization supply levels, etc. The various simulations (irrigation scenarios) showed that early sowing is more adequate than late sowing in saving water and obtaining adequate grain yield. Based on various simulations, it has been shown that the early sowing (mid to late December) is more adequate than late sowing with a total amount of water supply of about 430 mm and 322 kg (140 kg of N, 80 kg of P and 102 kg of K) of fertilization to achieve the potential yield. Consequently, the WOFOST model can be considered as a suitable tool for quantitative monitoring of winter wheat growth in the arid and semi-arid regions.

Estimating Leaf Area Index with Dynamic Leaf Optical Properties

Leaf area index (LAI) plays an important role in models of climate, hydrology, and ecosystem productivity. The physical model-based inversion method is a practical approach for large-scale LAI inversion. However, the ill-posed inversion problem, due to the limited constraint of inaccurate input parameters, is the dominant source of inversion errors. For instance, variables related to leaf optical properties are always set as constants or have large ranges, instead of the actual leaf reflectance of pixel vegetation in the current model-based inversions. This paper proposes to estimate LAI with the actual leaf optical property of pixels, calculated from the leaf chlorophyll content (Chlleaf) product, using a three-dimensional stochastic radiative transfer model (3D-RTM)-based, look-up table method. The parameter characterizing leaf optical properties in the 3D-RTM-based LAI inversion algorithm, single scattering albedo (SSA), is calculated with the Chlleaf product, instead of setting fixed values across a growing season. An algorithm to invert LAI with the dynamic SSA of the red band (SSAred) is proposed. The retrieval index (RI) increases from less than 42% to 100%, and the RMSE decreases to less than 0.28 in the simulations. The validation results show that the RMSE of the dynamic SSA decreases from 1.338 to 0.511, compared with the existing 3D-RTM-based LUT algorithm. The overestimation problem under high LAI conditions is reduced.

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