Tree-level yield estimation using UAV-based vegetation indices and plant physiology-informed machine learning

Abstract: The use of Unmanned Aerial Vehicles (UAVs) is becoming very common for last few years for monitoring agricultural crops efficiently. Low altitude remote sensing (UAV) provides people with high temporal and spatial resolution for non-destructive, accurate and timely estimation of biophysical parameters like Leaf Area Index (LAI), crop growth, plant biomass and final crop yield. Collection of the data by UAV helps to reduce errors and it fills the biasness on an observational scale in precision agriculture. The main objective of this study was to estimate real time LAI and yield of groundnut crop based on Normalized Difference Vegetation Index (NDVI) using low cost multispectral UAV. A field experiment was set up  with three different groundnut cultivars (V1= BARD-479, V2 = Chakwal-2011 and V3 = Chakwal-2016) with three replications. Field data collection regarding LAI was performed in 2019 at two different growth stages (2-3 leaf stage and Peg formation stage) of groundnut on PMAS-Arid Agriculture Research Farm (Knoot), Pakistan. Final yield was calculated at the time of crop maturity. In this study, low cost UAV platform was established with DJI Phantom 4 pro and Parrot Sequoia Sensor to develop a multispectral UAV system used as the survey platform. A Parrot Sequoia camera was mounted on the UAV used as the remote sensor. The sensor provided the information in five narrow bands including Red, Blue, Green, Near infrared (NIR) and Red Edge. The processing of UAV images was performed in the Python environment and NDVI images were created. Then regression model was performed to compare the NDVI data with the LAI and final yield of groundnut crop. The results indicated that the highest value of R 2 = 0.93 was found with NDVI and LAI at peg formation stage while value of R 2 = 0.59 was at 2-3 leaf stage. The strong and positive relationship was found between LAI and yield ( R 2 = 0.97). There was also a strong and positive relationship between NDVI and yield of groundnut with value of R 2 = 0.92. The study showed that low cost multispectral UAV can be effectively used for real time estimation of LAI and groundnut yield nondestructively and accurately. The study results show that this low cost multispectral UAV platform (DJI Phantom 4 Pro with Parrot Squoia) is robust in management decisions of agriculture such as effective fertilizer application, growth monitoring, and yield estimation accurately and timely based on the vegetation indices. This study also proved the low cost multispectral UAV practicability in estimating plant biophysical parameters at a small field experiment scale reliably. Keywords: vegetation indices, UAV, LAI, yield, multispectral camera, NDVI, groundnut, growth stages DOI:  10.33440/j.ijpaa.20200301.70  Citation: Tahir M N, Lan Y B, Zhang Y L, Wang Y K, Faisal N, Shah M A A, et al.  Real time estimation of leaf area index and groundnut yield using multispectral UAV.  Int J Precis Agric Aviat, 2020; 3(1): 1–6.

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.

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).

Yield estimations in a vineyard based on high-resolution spatial imagery acquired by a UAV

Understanding the relationship between leaf phenology and physiological properties has important implications for improving ecosystem models of biogeochemical cycling. However, previous studies have investigated such relationships only at the ecosystem level, limiting the biological interpretation and application of the observed relationships due to the complex vegetation structure of forest ecosystems. Additionally, studies focusing on transpiration are generally limited compared to those on photosynthesis. Thus, we investigated the relationship between stem sap flux density (SFD) and crown leaf phenology at the individual tree level using the heat dissipation method, unmanned aerial vehicle (UAV)-based observation, and ground-based visual observation across 17 species in a cool temperate forest in Japan, and assessed the potential of UAV-derived phenological metrics to track individual tree-level sap flow phenology. We computed five leaf phenological metrics (four from UAV imagery and one from ground observations) and evaluated the consistency of seasonality between the phenological metrics and SFD using Bayesian modelling. Although seasonal trajectories of the leaf phenological metrics differed markedly among the species, the daytime total SFD (SFDday) estimated by the phenological metrics was significantly correlated with the measured ones across the species, irrespective of the type of metric. Crown leaf cover derived from ground observations (CLCground) showed the highest ability to predict SFDday, suggesting that the seasonality of leaf amount rather than leaf color plays a predominant role in sap flow phenology in this ecosystem. Among the UAV metrics, Hue had a superior ability to predict SFDday compared with the other metrics because it showed seasonality similar to CLCground. However, all leaf phenological metrics showed earlier spring increases than did sap flow in more than half of the individuals. Our study revealed that UAV metrics could be used as predictors of sap flow phenology for deciduous species in cool, temperate forests. However, for a more accurate prediction, phenological metrics representing the spring development of sap flow must be explored.

Estimating mangrove leaf area index based on red-edge vegetation indices: A comparison among UAV, WorldView-2 and Sentinel-2 imagery

Precision agriculture (PA) technologies, such as GPS-guided tractors and unmanned aerial vehicles (UAVs), have increased farming efficiency, allowing precise input application and reducing waste. Precision agriculture enhances crop yield and quality, balancing economic and environmental interests. Simultaneously, hay production in agriculture, crucial for livestock during scarce pasture periods, benefits from these advancements. Its harvesting process, aimed at preserving nutritional value and preventing spoilage, enables large-scale storage for consistent livestock feeding. Additionally, hay production, adaptable to various climatic conditions and incorporating diverse grass and legume species, enhances soil health and aligns with sustainable agriculture principles. Previous research on using proximal and remote sensing for hay yield estimation has shown promise but faces several limitations. These include low accuracy in mixed species or low-density crops and in heterogeneous field conditions. Challenges also arise in selecting optimal data collection dates and dealing with ambient conditions like wind and dirt, which affect the accuracy of both proximal and remote sensing technologies. These limitations highlight the need for improved methods in hay yield estimation. This study aims to develop and evaluate hay yield estimation systems using remote and proximal sensing as an improvement over the conventional bale weight method. The focus is on enhancing spatial resolution for site-specific management, involving the use of LiDAR, ultrasonic sensors, and UAV-based remote sensing. It includes detailed analysis, data processing methodologies, predictive model evaluation, and key variable identification. The study is structured into chapters, each addressing a specific aspect of yield estimation, including preliminary remote sensing tests, machine learning applications using UAV imagery, and comparative analysis of proximal sensing technologies. All studies were conducted in a 35-ha field near Centralia, Missouri, involving the collection of ground-truth biomass data in a hay field having a mixture of timothy grass and red clover, proximal sensing data by ground based ultrasonic and LiDAR, and UAV-based remote sensing data. Ground-truth data was collected in 1-m2 quadrats and multiple descriptive statistics such as median, mean and quantile 90 percent were extracted for calibration and validation for all studies. The first study utilized various multispectral image vegetation indices (VIs) and regression models for biomass estimation. It evaluated the use of multispectral imaging systems, along with data collection and processing approaches. A multiple linear regression model was developed, using independent variables selected from candidate VIs and texture features, to predict hay biomass. Model performance was evaluated using measures like R2 and RMSE, and models including VIs and texture features provided R2 values from 0.31 to 0.68. Significant findings included correlations between VIs and dry mass and the effectiveness of texture features in improving model accuracy. While standard VIs showed substantial correlation with biomass, challenges like variable image resolution impacted accuracy. The second study used UAV-based remote sensing systems and machine learning models to estimate and map hay yield, employing a red-green-blue (RGB) camera for image acquisition. A random forest (RF) model was applied to estimate yield, after selecting predictive variables from VIs, texture features, color features, moisture content, and proportion of grass through recursive feature elimination (RFE). The highest accuracy model achieved R2 = 0.59, RMSE = 331 g/m^2, and MAE = 277 g/m^2 for wet hay mass estimation. This research provided insights into the selection of appropriate analysis methods for hay estimation using UAV imagery and showed the prospects for future research to apply these models to whole-field imagery for creating hay yield maps. Finally, the last study focused on comparing the effectiveness of ultrasonic and LiDAR sensors for estimating hay yield. The use of these sensors to measure plant height when mounted on a boom in front of a hay mower was evaluated, correlating these measurements with hay biomass. Data from the ultrasonic sensor, collected over a 3 m range and analyzed with machine learning models, provided the most accurate biomass estimates, with R2 values ranging from 0.31 to 0.52. Decision tree models were the most effective for use with data collected by these sensors. Results indicated that higher sensor data collection frequencies might improve prediction results.

Hyperspectral imagery from an Unmanned Aerial Vehicle (UAV) has been used to predict soil organic carbon (SOC) content. This study compared UAV hyperspectral imagery with Sentinel-2A multispectral imagery and soil spectra in the laboratory to predict the SOC content in Suaeda salsa (S. salsa) coastal wetland. Characteristic variables were determined through correlation analysis comparing observed SOC with constructed spectral indices of SOC, index variables, and spectral bands. Predict Models of SOC were constructed by multilayer perceptron (MLP), the prediction accuracy was evaluated and the spatial maps of SOC were produced. The results showed that estimating SOC using UAV, Sentinel imagery, and laboratory spectra has great potential when using MLP algorithm. The SOC content can be accurately predicted by the laboratory spectra without spatial map. The accuracy of SOC estimation was better when based on Sentinel-2A imagery than UAV imagery, with the model determination coefficients (R 2) of 0.838 and 0.638, the root mean square error (RMSE) of 0.398 and 0.596 g kg−1, ratio of performance to deviations (RPD) of 2.485 and 1.660, and bias of − 0.028 and 0.085 g kg−1, respectively. The SOC estimation model using Sentinel-2A imagery demonstrated better stability than that using UAV imagery, with the mean uncertainty standard deviations (SD) of 0.226 and 0.291 g kg−1, respectively. The spatial SOC maps generated from both UAV and Sentinel-2A imagery presented more subtle variation information when compared with the spatial interpolation results. Although the prediction accuracy of SOC from UAV was lower than that from Sentinel-2A, UAV imagery could disclose more fine distribution information of SOC at the local level. The UAV imagery can be used to estimate SOC in coastal wetlands but with a higher cost than freely available Sentinel images. We recommend using sentinel imagery to predict SOC at regional, national, or even global levels.

Key messageHeritable variation in phenotypes extracted from multi-spectral images (MSIs) and strong genetic correlations with end-of-season traits indicates the value of MSIs for crop improvement and modeling of plant growth curve.Vegetation indices (VIs) derived from multi-spectral imaging (MSI) platforms can be used to study properties of crop canopy, providing non-destructive phenotypes that could be used to better understand growth curves throughout the growing season. To investigate the amount of variation present in several VIs and their relationship with important end-of-season traits, genetic and residual (co)variances for VIs, grain yield and moisture were estimated using data collected from maize hybrid trials. The VIs considered were Normalized Difference Vegetation Index (NDVI), Green NDVI, Red Edge NDVI, Soil-Adjusted Vegetation Index, Enhanced Vegetation Index and simple Ratio of Near Infrared to Red (Red) reflectance. Genetic correlations of VIs with grain yield and moisture were used to fit multi-trait models for prediction of end-of-season traits and evaluated using within site/year cross-validation. To explore alternatives to fitting multiple phenotypes from MSI, random regression models with linear splines were fit using data collected in 2016 and 2017. Heritability estimates ranging from (0.10 to 0.82) were observed, indicating that there exists considerable amount of genetic variation in these VIs. Furthermore, strong genetic and residual correlations of the VIs, NDVI and NDRE, with grain yield and moisture were found. Considerable increases in prediction accuracy were observed from the multi-trait model when using NDVI and NDRE as a secondary trait. Finally, random regression with a linear spline function shows potential to be used as an alternative to mixed models to fit VIs from multiple time points.

Unmanned Aerial Vehicles (UAVs) have become increasingly popular in recent years for agricultural research. High spatial and temporal resolution images obtained with UAVs are ideal for many applications in agriculture. The objective of this study was to evaluate the performance of vegetation indices (VIs) derived from UAV images for quantification of plant nitrogen (N) concentration of spring wheat, a major cereal crop worldwide. This study was conducted at three locations in Idaho, United States. A quadcopter UAV equipped with a red edge multispectral sensor was used to collect images during the 2016 growing season. Flight missions were successfully carried out at Feekes 5 and Feekes 10 growth stages of spring wheat. Plant samples were collected on the same days as UAV image data acquisition and were transferred to lab for N concentration analysis. Different VIs including Normalized Difference Vegetative Index (NDVI), Red Edge Normalized Difference Vegetation Index (NDVIred edge), Enhanced Vegetation Index 2 (EVI2), Red Edge Simple Ratio (SRred edge), Green Chlorophyll Index (CIgreen), Red Edge Chlorophyll Index (CIred edge), Medium Resolution Imaging Spectrometer (MERIS) Terrestrial Chlorophyll Index (MTCI) and Red Edge Triangular Vegetation Index (core only) (RTVIcore) were calculated for each flight event. At Feekes 5 growth stage, red edge and green based VIs showed higher correlation with plant N concentration compare to the red based VIs. At Feekes 10 growth stage, all calculated VIs showed high correlation with plant N concentration. Empirical relationships between VIs and plant N concentration were cross validated using test data sets for each growth stage. At Feekes 5, the plant N concentration estimated based on NDVIred edge showed one to one correlation with measured N concentration. At Feekes 10, the estimated and measured N concentration were highly correlated for all empirical models, but the model based on CIgreen was the only model that had a one to one correlation between estimated and measured plant N concentration. The observed high correlations between VIs derived from UAV and the plant N concentration suggests the significance of VIs deriving from UAVs for within-season N concentration monitoring of agricultural crops such as spring wheat.

Unmanned aerial vehicle (UAV) imagery is considered the best approach to acquire high-resolution data over a large area in a short time, such as in the case of coastal wetlands comprising small-sized patches of perennial plants. However, to the best of our knowledge, no previous studies have used UAV imagery to quantitatively estimate blue carbon in coastal wetlands. Therefore, this study aimed to estimate the area-wide carbon stocks accumulated in halophyte habitats through the case studies of the southern coastal wetlands in South Korea using UAV imagery. Accordingly, object-based image analysis was used to identify the spatial distribution of major halophytes based on the spectral reflectance derived from multispectral UAV images. Elemental analysis (EA) was performed to estimate the content of organic carbon accumulated in individual halophytes, and the halophyte communities identified in the case study area were confirmed to have accumulated 20.80 MgC of blue carbon. These results demonstrate that applying EA to UAV images can be an innovative method to solve the spatial uncertainty encountered in the monitoring of blue carbon in existing field-based surveys and traditional remote sensing.

In this study, we investigated the variation in vegetation index in Hwado, South Korea, from 2022 to 2025.The analysis utilized time-series data collected from multiple sensors mounted on drones.The primary vegetation indices used for the analysis included the normalized difference vegetation index (NDVI) (V1), red-edge NDVI (RENDVI) (V2), normalized difference water index (NDWI) (V3), and photochemical reflectance index (PRI) (V4).These indices were specifically applied to assess vegetation health across various periods (A, B, C, and D).Notably, the indices V1 and V2 during Period A demonstrated a higher vitality than the other periods and indices.To overcome the limitations of single vegetation indices, we analyzed 44 unique combinations of multiple vegetation indices, together referred to as the composite vegetation index (CVI).In this study, we aimed to evaluate and assess areas of healthy vegetation both quantitatively and qualitatively.The results showed that combinations (1), ( 7), and (11) during Period A had the highest vegetation vitality, with more than 80% of the area covered by healthy vegetation.During all periods, combinations (1) and ( 7), each consisting of V1 and V2, consistently demonstrated a high percentage of healthy area.As a result, Combination (7) in Period A was identified as the optimal composite vegetation index (Optimal CVI) in this study.The proposed CVI accurately measures vegetation vitality by effectively reflecting the specific characteristics of the study area and integrating multisensor information.It can be utilized for health analysis in various types of forest.

Detection and monitoring are the first essential step for effective management of sheath blight (ShB), a major disease in rice worldwide. Unmanned aerial systems have a high potential of being utilized to improve this detection process since they can reduce the time needed for scouting for the disease at a field scale, and are affordable and user-friendly in operation. In this study, a commercialized quadrotor unmanned aerial vehicle (UAV), equipped with digital and multispectral cameras, was used to capture imagery data of research plots with 67 rice cultivars and elite lines. Collected imagery data were then processed and analyzed to characterize the development of ShB and quantify different levels of the disease in the field. Through color features extraction and color space transformation of images, it was found that the color transformation could qualitatively detect the infected areas of ShB in the field plots. However, it was less effective to detect different levels of the disease. Five vegetation indices were then calculated from the multispectral images, and ground truths of disease severity and GreenSeeker measured NDVI (Normalized Difference Vegetation Index) were collected. The results of relationship analyses indicate that there was a strong correlation between ground-measured NDVIs and image-extracted NDVIs with the R2 of 0.907 and the root mean square error (RMSE) of 0.0854, and a good correlation between image-extracted NDVIs and disease severity with the R2 of 0.627 and the RMSE of 0.0852. Use of image-based NDVIs extracted from multispectral images could quantify different levels of ShB in the field plots with an accuracy of 63%. These results demonstrate that a customer-grade UAV integrated with digital and multispectral cameras can be an effective tool to detect the ShB disease at a field scale.

Data on forest parameters defining the structure, health and condition of a forest stand is essential for forest management and conservation. The increasing frequency of forest changes, such as those caused by climate change-related drought and heat events, highlight the importance of having a forest database with high spatial and temporal resolution. Automated forest parameter extraction based on unmanned aerial vehicle (UAV) imagery is a cost-effective way to address the need for accurate and up-to-date forest data.The aim of this project is to develop user-friendly tools based on optical data from UAVs that can be applied to accurately and efficiently conduct digital forest inventories. We are using spectral and geometric information from UAV data to create methods for automated derivation of forest parameters such as diameter at breast height (DBH), tree stem positions, individual tree crown delineation, and coarse wood debris. These methods are being designed with the practical needs of potential users from the forestry sector in mind. Different flight configurations, such as nadir and oblique camera angles, as well as different acquisition times, were combined to generate structure from motion (SfM) data products (dense 3D point clouds, orthomosaics and height models) containing both ground and canopy information. For a study site within the Hainich National Park, Germany, we analyzed how leaf-off and leaf-on data can be combined to improve the derivation of stand parameters, such as tree stem positions and individual tree crowns, using point- and raster-based algorithms. Additionally, DBH on an individual tree basis was derived for the same study site using the cast shadows of tree trunks. To do so, a deep learning model was trained to identify stem shadows based on an orthomosaic of only ground points acquired during sunny and leaf-off conditions.

Making agricultural production compatible with the conservation of biological diversity is a priority in areas in which human–wildlife conflicts arise. The threatened Western Swamphen (Porphyrio porphyrio) feeds on rice, inducing crop damage and leading to decreases in rice production. Due to the Swamphen protection status, economic compensation policies have been put in place to compensate farmers for these damages, thus requiring an accurate, quantitative, and cost-effective evaluation of rice crop losses over large territories. We used information captured from a UAV (Unmanned Aerial Vehicle) equipped with a multispectral Parrot SEQUOIA camera as ground-truth information to calibrate Sentinel-2 imagery to quantify damages in the region of Ebro Delta, western Mediterranean. UAV vegetation index NDVI (Normalized Difference Vegetation Index) allowed estimation of damages in rice crops at 10 cm pixel resolution by discriminating no-green vegetation pixels. Once co-registered with Sentinel grid, we predicted the UAV damage proportion at a 10 m resolution as a function of Sentinel-2 NDVI, and then we extrapolated the fitted model to the whole Sentinel-2 Ebro Delta image. Finally, the damage predicted with Sentinel-2 data was quantified at the agricultural plot level and validated with field information compiled on the ground by Rangers Service. We found that Sentinel2-NDVI data explained up to 57% of damage reported with UAV. The final validation with Rangers Service data pointed out some limitations in our procedure that leads the way to improving future development. Sentinel2 imagery calibrated with UAV information proved to be a viable and cost-efficient alternative to quantify damages in rice crops at large scales.