Unmanned Aerial Vehicle Multispectral Imagery Research Articles

Predicting canopy chlorophyll concentration in citronella crop using machine learning algorithms and spectral vegetation indices derived from UAV multispectral imagery

Unmanned Aerial Vehicle (UAV) remote sensing in precision agriculture (PA) is a promising technique for managing crop inputs. The high spatial-resolution data enables extensive examination of the crop canopy, including identifying low-chlorophyll patches for initiating prophylactic measures as early as possible. In this study DJI M-200 equipped with MicaSense Altum multispectral camera was used to acquire multispectral images of citronella fields under various nutrient treatments at different growth stages. The study assessed the relevance of Machine Learning (ML) on multispectral images to predict citronella chlorophyll concentrations. To predict the crop canopy chlorophyll concentration for citronella, we evaluated Random Forest (RF), Support Vector Machine (SVM) and Partial Least Square (PLS) machine learning models. Based on the Rsquare value of all three models, the SVM machine learning model could best predict the crop canopy chlorophyll concentration with coefficient of determination R2 (0.79), root mean square error (0.05) and mean absolute error (0.04) respectively. The correlation between predicted chlorophyll contents and selected Vegetation Indices (VIs) also demonstrated significant relationship, implying that these can serve as a valuable indicator of crop canopy chlorophyll, which in turn can be used for providing insights into crop health, vigor, and productivity. This study showed that by employing UAV multispectral images and machine learning models the spatial distributions of chlorophyll concentration in a citronella crop at different growth phases can be predicted accurately.

Quantification of species composition in grass-clover swards using RGB and multispectral UAV imagery and machine learning.

Growing grass-legume mixtures for forage production improves both yield productivity and nutritional quality, while also benefiting the environment by promoting species biodiversity and enhancing soil fertility (through nitrogen fixation). Consequently, assessing legume proportions in grass-legume mixed swards is essential for breeding and cultivation. This study introduces an approach for automated classification and mapping of species in mixed grass-clover swards using object-based image analysis (OBIA). The OBIA procedure was established for both RGB and ten band multispectral (MS) images capturedby an unmanned aerial vehicle (UAV). The workflow integrated structural (canopy heights) and spectral variables (bands, vegetation indices) along with a machine learning algorithm (Random Forest) to perform image segmentation and classification. Spatial k-fold cross-validation was employed to assess accuracy. Results demonstrated good performance, achieving an overall accuracy of approximately 70%, for both RGB and MS-based imagery, with grass and clover classes yielding similar F1 scores, exceeding 0.7 values. The effectiveness of the OBIA procedure and classification was examined by analyzing correlations between predicted clover fractions and dry matter yield (DMY) proportions. This quantification revealed a positive and strong relationship, with R2 values exceeding 0.8 for RGB and MS-based classification outcomes. This indicates the potential of estimating (relative) clover coverage, which could assist breeders but also farmers in a precision agriculture context.

Assessing radiometric calibration methods for multispectral UAV imagery and the influence of illumination, flight altitude and flight time on reflectance, vegetation index and inversion of winter wheat AGB and LAI

Radiometric correction is essential to unmanned aerial vehicle (UAV) precision agriculture applications, especially for crop multi-period analysis and quantitative inversion of phenotypic and physiological parameters. In this study, we investigated the performance of four radiometric correction methods: “Camera only” (A), “Camera and sun irradiance” (B) and “Camera, sun irradiance and sun angle” (C) methods provided by Pix4d Mapper and an irradiance sensor-based method (D) implemented with the R software. UAV campaigns were conducted at flight altitudes of 30 m, 60 m and 90 m under clear and cloudy skies at different times over an experimental field of winter wheat. The influences of illumination, flight altitude and flight time on reflectance and vegetation indexes derived from different radiometric calibration methods were analyzed. Moreover, we further assessed the impact of reflectance and vegetation index variations on the above-ground biomass (AGB) and leaf area index (LAI) estimations of winter wheat. Results showed that method D is a promising approach for radiometric calibration, which produced consistent reflectance with method A at noon (e.g., 10:44:41 AM March 17 and 11:39:37 AM April 7) and mid-afternoon (e.g., 15:30:02 PM May 1) and more reliable reflectance in the morning (e.g., 7:15:44 AM March 17). Methods B and C seriously underestimated the reflectance at 10:44:41 AM March 17 and 11:39:37 AM April 7. This was caused by the incorrect attitude angles of the irradiance sensor and further miscalculation of the solar irradiance by Pix4d Mapper. Interestingly, these errors were eliminated in the calculation of the ratio type of vegetation indexes. Methods B and C yielded vegetation indexes that were almost the same as those of methods A and D. Under cloudy sky, when direct sunlight is not blocked by clouds, method D was effective; with cloud occlusion, results on April 24 indicated that the method failed to estimate the total sunlight and direct sunlight ratio. Reflectance and vegetation indexes obtained from different radiometric correction methods were all obviously affected by flight altitude. Furthermore, the variations of NDVI with flight altitude increasing were different with reflectance. Changes in reflectance and vegetation indexes with flight altitude had little effect on the correlation coefficients yielded with AGB, but showed a significant influence on those of LAI. Through analyzing the variation of observed solar radiation at different time intervals, caution is recommended when using the assumption that solar radiation is stable during the UAV flight. The longer the flight, the greater the variation in solar radiation, especially at sunrise and sunset. Even at noon, when the flight duration is 30 min, the change in solar radiation may exceed 10 % (e.g., 16.5 % on March 20).

Assessment of the Health Status of Old Trees of Platycladus orientalis L. Using UAV Multispectral Imagery

Assessing the health status of old trees is crucial for the effective protection and health management of old trees. In this study, we utilized an unmanned aerial vehicle (UAV) equipped with multispectral cameras to capture images for the rapid assessment of the health status of old trees. All trees were classified according to health status into three classes: healthy, declining, and severe declining trees, based on the above-ground parts of the trees. Two traditional machine learning algorithms, Support Vector Machines (SVM) and Random Forest (RF), were employed to assess their health status. Both algorithms incorporated selected variables, as well as additional variables (aspect and canopy area). The results indicated that the inclusion of these additional variables improved the overall accuracy of the models by 8.3% to 13.9%, with kappa values ranging from 0.166 and 0.233. Among the models tested, the A-RF model (RF with aspect and canopy area variables) demonstrated the highest overall accuracy (75%) and kappa (0.571), making it the optimal choice for assessing the health condition of old trees. Overall, this research presents a novel and cost-effective approach to assessing the health status of old trees.

Water Quality Inversion of a Typical Rural Small River in Southeastern China Based on UAV Multispectral Imagery: A Comparison of Multiple Machine Learning Algorithms

Remote sensing technology applications for water quality inversion in large rivers are common. However, their application to medium/small-sized water bodies within rural areas is limited due to the low spatial resolution of remote sensing images. In this work, a typical small rural river was selected, and high-resolution unmanned aerial vehicle (UAV) multispectral images and ground monitoring data of the river were obtained. Then, a comparative analysis of three univariate regression models and nine machine learning models (Ridge Regression (RR), Support Vector Regression (SVR), Grid Search Support Vector Regression (GS-SVR), Random Forest (RF), Grid Search Random Forest (GS-RF), eXtreme Gradient Boosting (XGBoost), Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), and Catboost Regression (CBR)) for their accuracy in the prediction of turbidity (TUB), total nitrogen (TN), and total phosphorus (TP) was performed. TUB can be achieved by simple statistical regression models. The CBR model exhibited the best performance for the three index inversions on the test set evaluation metrics: R2 (0.90~0.92), RMSE (7.57 × 10−3~1.59 mg/L), MAE (0.01~1.30 mg/L), RPD (3.21~3.56), and NSE (0.84~0.92). The water pollution of the study area was closely related to its land-use pattern, excessive and irrational fertilizer application, and distribution of pollutant outlets.

Remote sensing monitoring of rice growth under Cnaphalocrocis medinalis (Guenée) damage by integrating satellite and UAV remote sensing data

ABSTRACT Satellite remote sensing is commonly used for large-scale agricultural monitoring, but the low spatial resolution of its imagery does not allow it to present details of crop growth. Combining satellite remote sensing and unmanned aerial vehicle (UAV) remote sensing to complement each other’s advantages may be a way to realize large-scale and precision agricultural monitoring. Therefore, to explore the effect of the fusion method of UAV remote sensing data and satellite remote sensing data on improving satellite monitoring of the growth of damaged rice and to achieve large-scale accurate monitoring of the growth characteristics of damaged rice, in this study, the research object was rice infested by Cnaphalocrocis medinalis Guenee. We selected SuperDove satellite imagery on 14 August 2022 and UAV multispectral imagery on 15 August 2022 for vegetation index calculation and fused the two by a scale transformation method. We constructed LAI monitoring models using multiple linear regression (MLR), back-propagation neural network (BPNN) and support vector machine regression (SVR) to evaluate the effect of satellite data on LAI inversion for affected rice before and after fusion. The results showed that (1) the learning ability of the machine learning model represented by BPNN and SVR was better than that of the traditional regression model represented by MLR. The SVR model had the best inversion effect on the LAI. (2) The satellite data after fusion with UAV data significantly improved the inversion accuracy of the LAI of damaged rice. Compared with the original satellite data, with the combined data, R2 increased by approximately 0.3, RMSE and MAE decreased by approximately 0.1. Moreover, the spatial details of remote sensing images were clearer, and the spatial matching degree with the UAV image inversion results was higher. This study can provide theoretical and technical support for large-scale and high-precision monitoring of affected rice.

Estimation of the Bio-Parameters of Winter Wheat by Combining Feature Selection with Machine Learning Using Multi-Temporal Unmanned Aerial Vehicle Multispectral Images

Accurate and timely monitoring of biochemical and biophysical traits associated with crop growth is essential for indicating crop growth status and yield prediction for precise field management. This study evaluated the application of three combinations of feature selection and machine learning regression techniques based on unmanned aerial vehicle (UAV) multispectral images for estimating the bio-parameters, including leaf area index (LAI), leaf chlorophyll content (LCC), and canopy chlorophyll content (CCC), at key growth stages of winter wheat. The performance of Support Vector Regression (SVR) in combination with Sequential Forward Selection (SFS) for the bio-parameters estimation was compared with that of Least Absolute Shrinkage and Selection Operator (LASSO) regression and Random Forest (RF) regression with internal feature selectors. A consumer-grade multispectral UAV was used to conduct four flight campaigns over a split-plot experimental field with various nitrogen fertilizer treatments during a growing season of winter wheat. Eighteen spectral variables were used as the input candidates for analyses against the three bio-parameters at four growth stages. Compared to LASSO and RF internal feature selectors, the SFS algorithm selects the least input variables for each crop bio-parameter model, which can reduce data redundancy while improving model efficiency. The results of the SFS-SVR method show better accuracy and robustness in predicting winter wheat bio-parameter traits during the four growth stages. The regression model developed based on SFS-SVR for LAI, LCC, and CCC, had the best predictive accuracy in terms of coefficients of determination (R2), root mean square error (RMSE) and relative predictive deviation (RPD) of 0.967, 0.225 and 4.905 at the early filling stage, 0.912, 2.711 μg/cm2 and 2.872 at the heading stage, and 0.968, 0.147 g/m2 and 5.279 at the booting stage, respectively. Furthermore, the spatial distributions in the retrieved winter wheat bio-parameter maps accurately depicted the application of the fertilization treatments across the experimental field, and further statistical analysis revealed the variations in the bio-parameters and yield under different nitrogen fertilization treatments. This study provides a reference for monitoring and estimating winter wheat bio-parameters based on UAV multispectral imagery during specific crop phenology periods.

Evaluation of canopy fraction-based vegetation indices, derived from multispectral UAV imagery, to map water status variability in a commercial vineyard

AbstractWater stress is a major factor affecting grapevine yield and quality. Standard methods for measuring water stress, such as midday stem water potential (ΨSWP), are laborious and time-consuming for intra-block variability mapping. In this study, we investigate water status variability within a 2.42-ha commercial Cabernet Sauvignon block with a standard vertical trellis system, using remote sensing (RS) tools, specifically canopy fraction-based vegetation indices (VIs) derived from multispectral unmanned aerial vehicle (UAV) imagery, as well as standard reference methods to evaluate soil and plant water status. A total of 31 target vines were monitored for ΨSWP during the whole growing season. The highest variability was at véraison when the highest atmospheric demand occurred. The ΨSWP variability present in the block was contrasted with soil water content (SWC) measurements, showing similar patterns. With spatial and temporal water stress variability confirmed for the block, the relationship between the ΨSWP measured in the field and fraction-based VIs obtained from multispectral UAV data was analysed. Four UAV flights were obtained, and five different VIs were evaluated per target vine across the vineyard. The VI correlation to ΨSWP was further evaluated by comparing VI obtained from canopy fraction (VIcanopy) versus the mean (VImean). It was found that using canopy fraction-based VIs did not significantly improve the correlation with ΨSWP (NDVIcanopyr = 0.57 and NDVImeanr = 0.53), however fractional cover (fcover) did seem to show a similar trend to plant water stress with decreasing canopy size corresponding with water stress classes. A subset of 14 target vines were further evaluated to evaluate if additional parameters (maximum temperature, relative humidity (RH), vapour pressure deficit, SWC and fractional cover) could serve as potential water stress indicators for future mapping. Results showed that the integration of NDVIcanopy and NDREmean with additional information could be used as an indicator for mapping water stress variability within a block.

Use of Drone Imagery to Predict Leaf Nitrogen Content of Sugarcane Cultivated Under Organic Fertilizer Application

This study investigated the potential of unmanned aerial vehicle (UAV) based multispectral imagery (MI) to predict the leaf nitrogen (N) content of sugarcane (Saccharum officinarum L.). MI of canopy cover of two sugarcane varieties (Co 775 and SL 96 128) applied with different doses of N (0 – 550 kg/ha) were captured at 4½ months after planting. These images were used to calculate 10 different vegetation indices (VIs). Five machine learning (ML) models were tested for their potential to predict leaf N status using the most appropriate VIs. The correlation analysis showed that DVI (Difference Vegetation Index) was the most powerful VI for the prediction of leaf N (r = 0.81), followed by the RVI (Ratio Vegetation Index) and NDVI (Normalized Difference Vegetation Index) (R2= 0.78 and 0.77, respectively). A threshold correlation (r > 0.6) was applied to select predictive variables for ML models and performance was evaluated using a validation data set of leaf N content. Individual variety testing revealed that PLSR (Partial Least Squares Regression) and SVR (Support Vector Regression) models as the best prediction models with the highest Coefficient of determination (R2>0.72) and the lowest Root Mean Square Error values (RMSE<0.11). When both variety data were pooled, RF (Random Forest) demonstrated the highest predictive performance on the validation dataset, with an R2 value of 0.66 with a RMSE value of 0.12. Generally, the prediction accuracy of models was less when data from both varieties were pooled. This study postulated the potential for the fusion of UAV MI and ML approaches to predict leaf N states and the importance of developing varietal-specific prediction models for the sugarcane vegetation.

Prediction of vertical distribution of SPAD values within maize canopy based on unmanned aerial vehicles multispectral imagery.

Real-time monitoring of canopy chlorophyll content is significant in understanding crop growth status and guiding precision agricultural management. Remote sensing methods have demonstrated great potential in this regard. However, the spatiotemporal heterogeneity of chlorophyll content within crop canopies poses challenges to the accuracy and stability of remote sensing estimation models. Hence, this study aimed to develop a novel method for estimating canopy chlorophyll content (represented by SPAD values) in maize (Zea mays L.) canopies. Firstly, we investigated the spatiotemporal distribution patterns of maize canopy SPAD values under varying nitrogen application rates and different growth stages. The results revealed a non-uniform, "bell-shaped" curve distribution of maize canopy SPAD values in the vertical direction. Nitrogen application significantly influenced the distribution structure of SPAD values within the canopy. Secondly, we achieved satisfactory results by fitting the Lorentz peak distribution function to the SPAD values of different leaf positions in maize. The fitting performance, evaluated using R2 and RMSE, ranged from 0.69 to 0.98 and 0.45 to 3.59, respectively, for the year 2021, and from 0.69 to 0.77 and 2.38 to 6.51, respectively, for the year 2022.Finally, based on the correlation between canopy SPAD values and vegetation indices (VIs) at different growth stages, we identified the sensitive leaf positions for the selected CCCI (Canopy Chlorophyll Index) in each growth stage. The 6th (r = 0.662), 4th (r = 0.816), 12th (r = 0.722), and 12th (r = 0.874) leaf positions exhibited the highest correlations. Compared to the estimation model using canopy wide SPAD values, the model based on sensitive leaf positions showed improved accuracy, with increases of 34%, 3%, 20%, and 3% for each growth stage, respectively. In conclusion, the findings of this study contribute to the enhancement of chlorophyll content estimation models in crop canopies and provide valuable insights for the integration of crop growth models with remote sensing methods.

Using Remote and Proximal Sensing Data and Vine Vigor Parameters for Non-Destructive and Rapid Prediction of Grape Quality

The traditional method for determining wine grape total soluble solid (TSS) is destructive laboratory analysis, which is time consuming and expensive. In this study, we explore the potential of using different predictor variables from various advanced techniques to predict the grape TSS in a non-destructive and rapid way. Calculating Pearson’s correlation coefficient between the vegetation indices (VIs) obtained from UAV multispectral imagery and grape TSS resulted in a strong correlation between OSAVI and grape TSS with a coefficient of 0.64. Additionally, seven machine learning models including ridge regression and lasso regression, k-Nearest neighbor (KNN), support vector regression (SVR), random forest regression (RFR), extreme gradient boosting (XGBoost), and artificial neural network (ANN) are used to build the prediction models. The predictor variables include the unmanned aerial vehicles (UAV) derived VIs, and other ancillary variables including normalized difference vegetation index (NDVI_proximal) and soil electrical conductivity (ECa) measured by proximal sensors, elevation, slope, trunk circumference, and day of the year for each sampling date. When using 23 VIs and other ancillary variables as input variables, the results show that ensemble learning models (RFR, and XGBoost) outperform other regression models when predicting grape TSS, with the average of root mean square error (RMSE) of 1.19 and 1.2 °Brix, and coefficient of determination (R2) of 0.52 and 0.52, respectively, during the 20 times testing process. In addition, this study examines the prediction performance of using optimized soil adjusted vegetation index (OSAVI) or normalized green-blue difference index (NGBDI) as the main input for different machine learning models with other ancillary variables. When using OSAVI-based models, the best prediction model is RFR with an average R2 of 0.51 and RMSE of 1.19 °Brix, respectively. For NGBDI-based model, the RFR model showed the best average result of predicting TSS were a R2 of 0.54 and a RMSE of 1.16 °Brix, respectively. The approach proposed in this study provides an opportunity to grape growers to estimate the whole vineyard grape TSS in a non-destructive way.

The potential of UAV and very high-resolution satellite imagery for yellow and stem rust detection and phenotyping in Ethiopia

Very high (spatial and temporal) resolution satellite (VHRS) and high-resolution unmanned aerial vehicle (UAV) imagery provides the opportunity to develop new crop disease detection methods at early growth stages with utility for early warning systems. The capability of multispectral UAV, SkySat and Pleiades imagery as a high throughput phenotyping (HTP) and rapid disease detection tool for wheat rusts is assessed. In a randomized trial with and without fungicide control, six bread wheat varieties with differing rust resistance were monitored using UAV and VHRS. In total, 18 spectral features served as predictors for stem and yellow rust disease progression and associated yield loss. Several spectral features demonstrated strong predictive power for the detection of combined wheat rust diseases and the estimation of varieties’ response to disease stress and grain yield. Visible spectral (VIS) bands (Green, Red) were more useful at booting, shifting to VIS–NIR (near-infrared) vegetation indices (e.g., NDVI, RVI) at heading. The top-performing spectral features for disease progression and grain yield were the Red band and UAV-derived RVI and NDVI. Our findings provide valuable insight into the upscaling capability of multispectral sensors for disease detection, demonstrating the possibility of upscaling disease detection from plot to regional scales at early growth stages.

Phenomic selection in slash pine multi-temporally using UAV-multispectral imagery.

Genomic selection (GS) is an option for plant domestication that offers high efficiency in improving genetics. However, GS is often not feasible for long-lived tree species with large and complex genomes. In this paper, we investigated UAV multispectral imagery in time series to evaluate genetic variation in tree growth and developed a new predictive approach that is independent of sequencing or pedigrees based on multispectral imagery plus vegetation indices (VIs) for slash pine. Results show that temporal factors have a strong influence on the h2 of tree growth traits. High genetic correlations were found in most months, and genetic gain also showed a slight influence on the time series. Using a consistent ranking of family breeding values, optimal slash pine families were selected, obtaining a promising and reliable predictive ability based on multispectral+VIs (MV) alone or on the combination of pedigree and MV. The highest predictive value, ranging from 0.52 to 0.56, was found in July. The methods described in this paper provide new approaches for phenotypic selection (PS) using high-throughput multispectral unmanned aerial vehicle (UAV) technology, which could potentially be used to reduce the generation time for conifer species and increase the genetic granularity independent of sequencing or pedigrees.

Irrigation Scheduling for Small-Scale Crops Based on Crop Water Content Patterns Derived from UAV Multispectral Imagery

A timely irrigation schedule for small-scale farms is imperative for ensuring optimum crop production in the wake of drought and climate change. Owing to the large number of irrigated small-scale farms that grow different crops across all seasons in the Mutale River catchment, this study sought to develop irrigation scheduling for these crops for sustainable water utilization without compromising crop yields. Unmanned aerial vehicle (UAV) images were utilized as the base from which crop water content patterns were derived. A total of four (4) spectral vegetation indices, viz, the Greenness Normalized Difference Vegetation Index (GNDVI), Normalized Difference Vegetation Index (NDVI), Normalized Difference Red-Edge Index (NDRE), and Optimized Soil-Adjusted Vegetation Index (OSAVI), were generated to characterize crop types and water content in this study. Crop water content data, in the form of the relative water content (RWC), were measured in the field for each type of crop. Crop water content was modelled based on the empirical relationships between spectral indices and field-measured RWC. The linear regression analysis revealed a significant association between the GNDVI and the water content of sweet potato, maize, sugar beans, and Florida broadleaf mustard, with r2 values of 0.948, 0.995, 0.978, and 0.953, respectively. The NDVI revealed a strong association with the water content of Solanum retroflexum, pepper, and cabbage, with r2 values of 0.949, 0.956, and 0.995, respectively. The NDRE, on the other hand, revealed a strong relationship with water content in peas and green beans, with r2 values of 0.961 and 0.974, respectively. The crop water content patterns simulation revealed that Solanum retroflexum, sweet potato, maize, sugar beans, and Florida broadleaf mustard reached their respective wilting points on day four after irrigation, implying that irrigation of these crops should be scheduled after every four (4) days. Peas, green beans, pepper, and cabbage reached their respective wilting points on day five after irrigation, implying that irrigation of these crops should be scheduled after every five days. The results of this study highlight the significance of considering crop water content derived from spectral bands of UAV imagery in scheduling irrigation for various types of crops. This study also emphasized the on-going significance of remote sensing technology in addressing agricultural issues that impede hunger alleviation and food security goals.

Tree Height and Crown Extraction From UAV-Based Multispectral Imagery

Conventional methods in measuring tree height and crown diameter are time consuming compared to the advanced technology of unmanned aerial vehicle (UAV) multispectral imagery. UAV multispectral imagery is widely used in vegetation analysis such as crop analysis, vegetation monitoring, precise farming and vegetation health assessment. Thus, the purpose of this research is to extract the individual tree height and crown diameter from UAV- based multispectral imagery using the integration of geospatial techniques. Altogether, the total of 395 individual trees were extracted from the study area of Section U11, Shah Alam using the Support Vector Machine (SVM) classifier. Tree height values were extracted from normalized digital surface model (nDSM) using the zonal statistics tool with the tree height range between 1.568m to 27.850m. The range for derived crown diameters is between 0.919m to 24.506m. The final map shows the distribution of tree height and tree crown extraction from the UAV-based multispectral imagery. The spatial distribution data of tree height and crown diameter are beneficial especially in landscaping and identifying the potential of tree hazard in the urban area.

A double-layer model for improving the estimation of wheat canopy nitrogen content from unmanned aerial vehicle multispectral imagery

The accurate and rapid estimation of canopy nitrogen content (CNC) in crops is the key to optimizing in-season nitrogen fertilizer application in precision agriculture. However, the determination of CNC from field sampling data for leaf area index (LAI), canopy photosynthetic pigments (CPP; including chlorophyll a, chlorophyll b and carotenoids) and leaf nitrogen concentration (LNC) can be time-consuming and costly. Here we evaluated the use of high-precision unmanned aerial vehicle (UAV) multispectral imagery for estimating the LAI, CPP and CNC of winter wheat over the whole growth period. A total of 23 spectral features (SFs; five original spectrum bands, 17 vegetation indices and the gray scale of the RGB image) and eight texture features (TFs; contrast, entropy, variance, mean, homogeneity, dissimilarity, second moment, and correlation) were selected as inputs for the models. Six machine learning methods, i.e., multiple stepwise regression (MSR), support vector regression (SVR), gradient boosting decision tree (GBDT), Gaussian process regression (GPR), back propagation neural network (BPNN) and radial basis function neural network (RBFNN), were compared for the retrieval of winter wheat LAI, CPP and CNC values, and a double-layer model was proposed for estimating CNC based on LAI and CPP. The results showed that the inversion of winter wheat LAI, CPP and CNC by the combination of SFs+TFs greatly improved the estimation accuracy compared with that by using only the SFs. The RBFNN and BPNN models outperformed the other machine learning models in estimating winter wheat LAI, CPP and CNC. The proposed double-layer models (R2=0.67–0.89, RMSE=13.63–23.71 mg g–1, MAE=10.75–17.59 mg g–1) performed better than the direct inversion models (R2=0.61–0.80, RMSE=18.01–25.12 mg g–1, MAE=12.96–18.88 mg g–1) in estimating winter wheat CNC. The best winter wheat CNC accuracy was obtained by the double-layer RBFNN model with SFs+TFs as inputs (R2=0.89, RMSE=13.63 mg g–1, MAE=10.75 mg g–1). The results of this study can provide guidance for the accurate and rapid determination of winter wheat canopy nitrogen content in the field.

Monitoring of Wheat Fusarium Head Blight on Spectral and Textural Analysis of UAV Multispectral Imagery

Crop disease identification and monitoring is an important research topic in smart agriculture. In particular, it is a prerequisite for disease detection and the mapping of infected areas. Wheat fusarium head blight (FHB) is a serious threat to the quality and yield of wheat, so the rapid monitoring of wheat FHB is important. This study proposed a method based on unmanned aerial vehicle (UAV) low-altitude remote sensing and multispectral imaging technology combined with spectral and textural analysis to monitor FHB. First, the multispectral imagery of the wheat population was collected by UAV. Second, 10 vegetation indices (VIs)were extracted from multispectral imagery. In addition, three types of textural indices (TIs), including the normalized difference texture index (NDTI), difference texture index (DTI), and ratio texture index (RTI) were extracted for subsequent analysis and modeling. Finally, VIs, TIs, and VIs and TIs integrated as the input features, combined with k-nearest neighbor (KNN), the particle swarm optimization support vector machine (PSO-SVM), and XGBoost were used to construct wheat FHB monitoring models. The results showed that the XGBoost algorithm with the fusion of VIs and TIs as the input features has the highest performance with the accuracy and F1 score of the test set being 93.63% and 92.93%, respectively. This study provides a new approach and technology for the rapid and nondestructive monitoring of wheat FHB.

GEOBIA and Vegetation Indices in Extracting Olive Tree Canopies Based on Very High-Resolution UAV Multispectral Imagery

In recent decades, precision agriculture and geospatial technologies have made it possible to ensure sustainability in an olive-growing sector. The main goal of this study is the extraction of olive tree canopies by comparing two approaches, the first of which is related to geographic object-based analysis (GEOBIA), while the second one is based on the use of vegetation indices (VIs). The research area is a micro-location within the Lun olives garden, on the island of Pag. The unmanned aerial vehicle (UAV) with a multispectral (MS) sensor was used for generating a very high-resolution (VHR) UAVMS model, while another mission was performed to create a VHR digital orthophoto (DOP). When implementing the GEOBIA approach in the extraction of the olive canopy, user-defined parameters and classification algorithms support vector machine (SVM), maximum likelihood classifier (MLC), and random trees classifier (RTC) were evaluated. The RTC algorithm achieved the highest overall accuracy (OA) of 0.7565 and kappa coefficient (KC) of 0.4615. The second approach included five different VIs models (NDVI, NDRE, GNDVI, MCARI2, and RDVI2) which are optimized using the proposed VITO (VI Threshold Optimizer) tool. The NDRE index model was selected as the most accurate one, according to the ROC accuracy measure with a result of 0.888 for the area under curve (AUC).

SPSI: A Novel Composite Index for Estimating Panicle Number in Winter Wheat before Heading from UAV Multispectral Imagery.

Rapid and accurate estimation of panicle number per unit ground area (PNPA) in winter wheat before heading is crucial to evaluate yield potential and regulate crop growth for increasing the final yield. The accuracies of existing methods were low for estimating PNPA with remotely sensed data acquired before heading since the spectral saturation and background effects were ignored. This study proposed a spectral-textural PNPA sensitive index (SPSI) from unmanned aerial vehicle (UAV) multispectral imagery for reducing the spectral saturation and improving PNPA estimation in winter wheat before heading. The effect of background materials on PNPA estimated by textural indices (TIs) was examined, and the composite index SPSI was constructed by integrating the optimal spectral index (SI) and TI. Subsequently, the performance of SPSI was evaluated in comparison with other indices (SI and TIs). The results demonstrated that green-pixel TIs yielded better performances than all-pixel TIs apart from TI[HOM], TI[ENT], and TI[SEM] among all indices from 8 types of textural features. SPSI, which was calculated by the formula DATT[850,730,675] + NDTICOR[850,730], exhibited the highest overall accuracies for any date in any dataset in comparison with DATT[850,730,675], TINDRE[MEA], and NDTICOR[850,730]. For the unified models assembling 2 experimental datasets, the RV2 values of SPSI increased by 0.11 to 0.23, and both RMSE and RRMSE decreased by 16.43% to 38.79% as compared to the suboptimal index on each date. These findings indicated that the SPSI is valuable in reducing the spectral saturation and has great potential to better estimate PNPA using high-resolution satellite imagery.

Peanut yield prediction with UAV multispectral imagery using a cooperative machine learning approach

<abstract> <p>The unmanned aerial vehicle (UAV), as a remote sensing platform, has attracted many researchers in precision agriculture because of its operational flexibility and capability of producing high spatial and temporal resolution images of agricultural fields. This study proposed machine learning (ML) models and their ensembles for peanut yield prediction using UAV multispectral data. We utilized five bands (red, green, blue, near-infra-red (NIR) and red-edge) multispectral images acquired at various growth stages of peanuts using UAV. The correlation between spectral bands and yield was analyzed for each growth stage, which showed that the maturity stages had a significant correlation between peanut yield and spectral bands: red, green, NIR and red edge (REDE). Using these four bands spectral data, we assessed the potential for peanut yield prediction using multiple linear regression and seven non-linear ML models whose hyperparameters were optimized using simulated annealing (SA). The best three ML models, random forest (RF), support vector machine (SVM) and XGBoost, were then selected to construct a cooperative yield prediction framework with both the best ML model and the ensemble scheme from the best three as comparable recommendations to the farmers.</p> </abstract>