Real time estimation of leaf area index and groundnut yield using multispectral UAV

Accurate leaf area index estimation in sorghum using high-resolution UAV data and machine learning models

Leaf area index (LAI) is a key variable for monitoring crop growth. Compared with traditional measurement methods, unmanned aerial vehicle (UAV) remote sensing offers a cost-effective and efficient approach for rapidly obtaining crop LAI. Although there is extensive research on rice LAI estimation, many studies suffer from the limitations of models that are only applicable to specific scenarios with unclear applicability conditions. In this study, we selected commonly used RGB and multispectral (Ms) data sources, which contain three channels of color information and five multi-band information, respectively, combined with five different spatial resolutions of data at intervals of 20–100 m. We evaluated the effectiveness of models using single- and multi-feature variables for LAI estimation in rice. In addition, texture and coverage features other than spectra were introduced to further analyze their effects on the inversion accuracy of the LAI. The results show that the accuracy of the model established with multi-variables under single features is significantly higher than that of the model established with single variables under single features. The best results were obtained using the RFR (random forest regression) model, in which the model’s R2 is 0.675 and RMSE is 0.886 for multi-feature VIs at 40 m. Compared with the analysis results of Ms and RGB data at different heights, the accuracy of Ms data estimation results fluctuates slightly and is less sensitive to spatial resolution, while the accuracy of the results based on RGB data gradually decreases with the increase in height. The estimation accuracies of both Ms and RGB data were improved by adding texture features and coverage features, and their R2 improved by 9.1% and 7.3% on average. The best estimation heights (spatial resolution) of the two data sources were 40 m (2.2 cm) and 20 m (0.4 cm), with R2 of 0.724 and 0.673, and RMSE of 0.810 and 0.881. This study provides an important reference for the estimation of rice LAI based on RGB and Ms data acquired using the UAV platform.

This work explores the suitability of various deep convolutional neural network (CNN) architectures for semantic segmentation of agricultural crops such as cotton, maize etc. from multi-spectral UAV (unmanned aerial vehicle) data. Initially, the UAV data were preprocessed and training samples for each crop type were manually annotated from multiple UAV scenes. Different CNN architectures such as U-Net, SegNet and PSPNet (Pyramid Scene Parsing Network) were trained with various combinations of input spectral bands along with select band derived indices such as NDVI (Normalized Difference Vegetation Index) and EVI (Enhanced Vegetation Index) as additional features. The experimental results indicated that inclusion of NIR (near-infrared) band and NDVI in the input data yielded high segmentation accuracy of more than 90%. U-Net proved to be the best among the three architectures with 97% overall accuracy while dealing with three classes separation problem. This study demonstrated the scope of deep neural network based semantic segmentation techniques in crop classification from multi-spectral UAV data.KeywordsCrop classificationUAV (unmanned aerial vehicle)Multi-spectral dataDeep learningU-NetSegNetPSPNetImage analysis

The Leaf Area Index (LAI) strongly influences vegetation evapotranspiration and photosynthesis rates. Timely and accurately estimating the LAI is crucial for monitoring vegetation growth. The unmanned aerial vehicle (UAV) multispectral digital camera platform has been proven to be an effective tool for this purpose. Currently, most remote sensing estimations of LAIs focus on cereal crops, with limited research on economic crops such as apples. In this study, a method for estimating the LAI of an apple orchard by extracting spectral and texture information from UAV multispectral images was proposed. Specifically, field measurements were conducted to collect LAI data for 108 sample points during the final flowering (FF), fruit setting (FS), and fruit expansion (FE) stages of apple growth in 2023. Concurrently, UAV multispectral images were obtained to extract spectral and texture information (Gabor transform). The Support Vector Regression Recursive Feature Elimination (SVR-REF) was employed to select optimal features as inputs for constructing models to estimate the LAI. Finally, the optimal model was used for LAI mapping. The results indicate that integrating spectral and texture information effectively enhances the accuracy of LAI estimation, with the relative prediction deviation (RPD) for all models being greater than 2. The Categorical Boosting (CatBoost) model established for FF exhibits the highest accuracy, with a validation set R2, root mean square error (RMSE), and RPD of 0.867, 0.203, and 2.482, respectively. UAV multispectral imagery proves to be valuable in estimating apple orchard LAIs, offering real-time monitoring of apple growth and providing a scientific basis for orchard management.

Precise and timely leaf area index (LAI) estimation for winter wheat is crucial for precision agriculture. The emergence of high-resolution unmanned aerial vehicle (UAV) data and machine learning techniques offers a revolutionary approach for fine-scale estimation of wheat LAI at the low cost. While machine learning has proven valuable for LAI estimation, there are still model limitations and variations that impede accurate and efficient LAI inversion. This study explores the potential of classical machine learning models and deep learning model for estimating winter wheat LAI using multispectral images acquired by drones. Initially, the texture features and vegetation indices served as inputs for the partial least squares regression (PLSR) model and random forest (RF) model. Then, the ground-measured LAI data were combined to invert winter wheat LAI. In contrast, this study also employed a convolutional neural network (CNN) model that solely utilizes the cropped original image for LAI estimation. The results show that vegetation indices outperform the texture features in terms of correlation analysis with LAI and estimation accuracy. However, the highest accuracy is achieved by combining both vegetation indices and texture features to invert LAI in both conventional machine learning methods. Among the three models, the CNN approach yielded the highest LAI estimation accuracy (R 2 = 0.83), followed by the RF model (R 2 = 0.82), with the PLSR model exhibited the lowest accuracy (R 2 = 0.78). The spatial distribution and values of the estimated results for the RF and CNN models are similar, whereas the PLSR model differs significantly from the first two models. This study achieves rapid and accurate winter wheat LAI estimation using classical machine learning and deep learning methods. The findings can serve as a reference for real-time wheat growth monitoring and field management practices.

ABSTRACTThe normalized difference vegetation index (NDVI) is a commonly used index for monitoring crop growth status. Previous studies have shown that the leaf area index (LAI) estimation based on NDVI is limited by saturation that occurs under conditions of relatively dense canopies (LAI > 2 m2 m–2). To reduce the saturation effect, we suggested new spectral indices through the spectral indices approach. The results suggested that the two-band normalized difference spectral index (NDSI = ((ρ940 – ρ730) /(ρ940 + ρ730))) resulted from the two-band spectral indices approach and the three-band modified normalized difference spectral index (mNDSI = ((ρ940 – 0.8 × ρ950) – ρ730) /((ρ940 – 0.8 × ρ950) + ρ730)) resulted from the three-band spectral indices approach, and they were able to mitigate saturation and improve the LAI prediction with a determination coefficient (R2) of 0.77 and 0.78, respectively. In the validation based on data from independent experiments, these new indices exhibited an accuracy with relative root mean square error (RRMSE) lower than 23.38% and bias higher than –0.40. These accuracies were significantly higher than those obtained with some existing indices with good performance in LAI estimation, such as the enhanced vegetation index (EVI) (RRMSE = 30.19%, bias = –0.34) and the modified triangular vegetation index 2 (MTVI2) (RRMSE = 29.30%, bias = –0.28), and the indices with the ability to mitigate the saturation, such as the wide dynamic range vegetation index (WDRVI) (RRMSE = 31.37%, bias = –0.54), the red-edge wide dynamic range vegetation index (red-edge WDRVI) (RRMSE = 26.34%, bias = –0.54), and the normalized difference red-edge index (NDRE) (RRMSE = 28.41%, bias = –0.56). Additionally, these new indices were more sensitive under moderate to high LAI conditions (between 2 and 8 m2 m–2). Between these two new developed spectral indices, there was no significant difference in the accuracy and sensitivity assessments. Considering the index structure and convenience in application, we demonstrated that the two-band spectral index NDSI((ρ940 – ρ730) /(ρ940 + ρ730)) is efficient in mitigating saturation and has considerable potential for estimating the LAI of canopies throughout the entire growing season of wheat (Triticum aestivum L.), whereas the three-band spectral index contributes lesser in the saturation mitigation provided the red-edge band has been contained.

Even though research has shown that the spectral parameters of yellow-edge, red-edge and NIR (near-infrared) shoulder wavelength regions are able to estimate green cover and leaf area index (LAI), a large amount of dead materials in grasslands challenges the accuracy of their estimation using hyperspectral remote sensing. However, the exact impact of dead vegetation cover on these spectral parameters remains unclear. Therefore, we evaluated the influences of dead materials on the spectral parameters in the wavelength regions of yellow-edge, red-edge and NIR shoulder by comparing normalized difference vegetation indices (NDVI) including the common red valley at 670 nm and NDVI using the red valley extracted by a new statistical method. This method, based on the concept of segmented linear regression, was developed to extract the spectral parameters and calculate NDVI automatically from the hyper-spectra. To fully understand the impact of dead cover on the spectral parameters (i.e., consider full coverage combinations of green vegetation, dead materials and bare soil), both in situ measured and simulated hyper-spectra were analyzed. The impact of dead cover on LAI estimation by those spectral parameters and NDVI were also evaluated. The results show that: (i) without considering the influence of bare soil, dead materials decreases the slope of red-edge, the slope of NIR shoulder and NDVI, while dead materials increases the slope of yellow-edge; (ii) the spectral characteristics of red valley disappear when dead cover exceeds 67%; (iii) large amount of dead materials also result in a blue shift of the red-edge position; (iv) accurate extraction of the red valley position enhances LAI estimation and reduces the influences of dead materials using hyperspectral NDVI; (v) the accuracy of LAI estimation using the slope of yellow-edge, the slope of red-edge, red-edge position and NDVI significantly drops when dead cover exceeds 72.3–74.5% (variation among indices).

Comparative analysis of IKONOS, SPOT, and ETM+ data for leaf area index estimation in temperate coniferous and deciduous forest stands

The estimation of leaf area index (LAI) from optical remotely sensed data based on vegetation indices (VIs) is a quick and practical approach to acquire LAI over vast areas. Reflectance in the red-edge bands is sensitive to vegetation status, and its information is thought to be useful in agricultural applications. Based on three red-edge band observations (represented as RE1, RE2, and RE3 for bands 5-7) from the Multispectral Instrument (MSI) onboard the Sentinel-2 satellite, this article aims to investigate the feasibility and performance of using red-edge bands for LAI estimates with the VI method and ground-measured LAI data sets. Sensitivity analysis from PROSAIL simulations revealed that RE1 is mainly affected by the influence of the leaf chlorophyll content, and this uncertainty should not be ignored during LAI estimation. For the normalized difference vegetation index (NDVI), modified simple ratio (MSR), chlorophyll index (CI), and wide dynamic range vegetation index (WDRVI), the optimal combination of Sentinel-2 bands for LAI estimation was RE2 and RE3, with a minimum root-mean-square error (RMSE) of 0.75. Four 3-band red-edge VIs were proposed to exploit the full content of the red-edge bands of Sentinel-2, and their performance in LAI estimation improved slightly. However, both 2-band red-edge VIs and 3-band red-edge VIs remained slightly saturated at high LAI levels; therefore, a segmental estimation with a threshold was suggested for large LAIs. The results indicate that the optimal 2-band red-edge VIs and proposed 3-band red-edge VIs are effective tools for crop LAI estimation in multiple-growth stages with Sentinel-2 MSI images.

Leaf Area Index (LAI) is an important biophysical parameter necessary to infer vegetation vigour, seasonal vegetation variability and different physiological and biochemical processes of vegetation. Gap fraction analysis has been carried out to estimate plot‐wise LAI. Tropical dry deciduous forests of the study area can be categorized into two prominent phases—growing and senescent phases. Efforts have been made to observe the relationship between ground based LAI values and satellite derived parameters, such as radiance values and also different vegetation indices, namely the Normalized Difference Vegetation Index (NDVI), maximum, minimum, amplitude, sum and radiance NDVI values for both the phases. Multi‐temporal IRS 1C WiFS data have been used. WiFS provides information in two bands: red (0.62–0.68 µm) and near‐infrared (0.77–0.86 µm). All the images from the representative months have been corrected radiometrically and geometrically. NDVI values have been derived for all the representative months. Among various parameters maximum NDVI values showed better relationships with LAI for both the phases. For the growing phase R 2 (coefficient of determination) was 0.79, whereas for the senescent phase it was 0.48. These empirical relationships have been used to estimate LAI at a regional level. The LAI estimate for growing and senescent phases ranged from <1 to 4.25.

Recently Unmanned Aerial Vehicle (UAV) technology offers new opportunities for assessing crop growth condition using UAV imagery. The objective of this study was to select optimal vegetation indices and regression model for estimating of rice growth using UAV images. This study was conducted using a fixed- wing UAV (Model : Ebee) with Cannon S110 and Cannon IXUS camera during farming season in 2016 on the experiment field of National Institute of Crop Science. Before heading stage of rice, there were strong relationships between rice growth parameters (plant height, dry weight and LAI (Leaf Area Index)) and NDVI (Normalized Difference Vegetation Index) using natural exponential function (R≥0.97). After heading stage, there were strong relationships between rice dry weight and NDVI, gNDVI (green NDVI), RVI (Ratio Vegetation Index), CI-G (Chlorophyll Index-Green) using quadratic function (R≤-0.98). There were no apparent relationships between rice growth parameters and vegetation indices using only Red-Green-Blue band images. RVI (Ratio vegetation index), NDVI (Normalized difference vegetation index), CVI (Chlorophyll vegetation index), gNDVI (Greent normalized difference vegetation index, CI-G (Chlorophyll Index- Geen), NGRDI (Normalized green red difference index), GLI (Green leaf index), VARI (Visible atmospherically resistant index). Relationship between vegetation indices and rice growth parameter (LAI).

Estimating the yield of trees is important to improve orchard management and production. Usually, farmers need to estimate the yield of trees at the early growing stage for field management. However, methods to predict the yield at the individual tree level are currently not available because of the complexity and variability of each tree. Thus, in this article, the authors evaluated the performance of an unmanned aerial vehicle (UAV)-based remote sensing system and machine learning (ML) approaches for yield estimation. A multispectral camera was mounted on the UAV platform to acquire high-resolution images. Eight features were extracted from the UAV imagery, including normalized difference vegetation index (NDVI), green normalized vegetation index (GNDVI), red-edge normalized difference vegetation index (NDVIre), red-edge triangulated vegetation index (RTVIcore), individual tree canopy size, the modified triangular vegetation index (MTVI2), the chlorophyll index-green (CIg), and the chlorophyll index-rededge (CIre). Then, plant physiology-informed machine learning (PPIML) algorithms were applied with the extracted features to predict the yield at the individual tree level. Results showed that the decision tree classifier had the best prediction performance, with an accuracy of 85%.

Unmanned Aerial Vehicle (UAV) imagery are being assessed for analyzing within field spatial variability for agricultural precision management, because unmanned aerial vehicle imagery may be acquired quickly during critical periods of rapid crop growth. The objective of this study was to evaluate the use of unmanned aerial vehicle for the monitoring barley growth. Unmanned aerial vehicle imagery obtained from middle February to late June in Wanju, Jeollabuk-do. Unmanned aerial vehicle imagery corrected geometrically and atmospherically to calculate normalized difference vegetation index (NDVI). We analyzed the relationships between NDVI UAV of barley and biophysical measurements such as plant height, number of tiller and shoot dry weight over an entire barley growth period. The similar trend between NDVI UAV and growth parameters was shown. Correlation analysis between NDVI UAV and barley growth parameters revealed that NDVI UAV was highly correlated with shoot dry weight (r=0.932) and plant height (r=0.879). According to the relationship among growth parameters and NDVI UAV , the temporal variation of NDVIUAV was significant to interpret barley growth. The spatial distribution map of barley growth was in strong agreement with the field measurements in terms of geographical variation and relative numerical values when NDVI UAV was applied to power function. From these results, NDVI UAV can be used as a new tool for monitoring barley growth.

Subtropical region tea tree LAI estimation integrating vegetation indices and texture features derived from UAV multispectral images

Improving estimation of maize leaf area index by combining of UAV-based multispectral and thermal infrared data: The potential of new texture index