Use of UAVs in Agriculture for Monitoring and Management of Cereal Crops

Sensors for UAVs dedicated to agriculture: current scenarios and challenges

The spatial resolution of in situ unmanned aerial vehicle (UAV) multispectral images has a crucial effect on crop growth monitoring and image acquisition efficiency. However, existing studies about optimal spatial resolution for crop monitoring are mainly based on resampled images. Therefore, the resampled spatial resolution in these studies might not be applicable to in situ UAV images. In order to obtain optimal spatial resolution of in situ UAV multispectral images for crop growth monitoring, a RedEdge Micasense 3 camera was installed onto a DJI M600 UAV flying at different heights of 22, 29, 44, 88, and 176m to capture images of seedling rapeseed with ground sampling distances (GSD) of 1.35, 1.69, 2.61, 5.73, and 11.61 cm, respectively. Meanwhile, the normalized difference vegetation index (NDVI) measured by a GreenSeeker (GS-NDVI) and leaf area index (LAI) were collected to evaluate the performance of nine vegetation indices (VIs) and VI*plant height (PH) at different GSDs for rapeseed growth monitoring. The results showed that the normalized difference red edge index (NDRE) had a better performance for estimating GS-NDVI (R2 = 0.812) and LAI (R2 = 0.717), compared with other VIs. Moreover, when GSD was less than 2.61 cm, the NDRE*PH derived from in situ UAV images outperformed the NDRE for LAI estimation (R2 = 0.757). At oversized GSD (≥5.73 cm), imprecise PH information and a large heterogeneity within the pixel (revealed by semi-variogram analysis) resulted in a large random error for LAI estimation by NDRE*PH. Furthermore, the image collection and processing time at 1.35 cm GSD was about three times as long as that at 2.61 cm. The result of this study suggested that NDRE*PH from UAV multispectral images with a spatial resolution around 2.61 cm could be a preferential selection for seedling rapeseed growth monitoring, while NDRE alone might have a better performance for low spatial resolution images.

The use of unmanned aerial vehicles (UAVs) in agriculture in general, and precision agriculture in particular, is expanding significantly every year. UAVs are employed in various tasks, including sowing, monitoring crop growth and yields, field mapping, and spraying crops with plant protection products (PPP) or applying fertilizers. Precision agriculture enables the integration of geospatial data, GIS and remote sensing technologies, artificial intelligence, Big Data, the Internet of Things, and other innovative solutions. UAVs provide opportunities for rapid monitoring, analyzing field conditions and dynamics, identifying problem areas requiring managerial intervention, evaluating the effectiveness of agronomic practices, and storing photogrammetric data and high-resolution images efficiently. Modern UAVs, accessible to farmers, not only deliver current information on plant condition and growth dynamics but also allow for protective treatment of fields and perennial plantations using pesticides. UAVs can provide georeferenced data on the state of cultivated crops, significantly assisting farmers in maintaining high yields. Moreover, UAVs equipped with multispectral and RGB cameras enable the prompt storage of agricultural images in the near-infrared spectrum, facilitating monitoring of vegetation health and condition. UAV imaging offers much greater detail compared to satellite imagery, achieving resolutions down to centimeters per pixel, thanks to flight altitudes ranging from 100 to 600 meters above ground. The paper outlines the use of UAVs in precision agriculture and explores field monitoring methods using UAVs. The implementation of UAV imaging technology allows for the creation of electronic field maps and the rapid adoption of managerial decisions based on the collected data. The NDVI index obtained with UAVs provides a more comprehensive and detailed representation of current conditions on individual field sections, a level of detail that is difficult to achieve with satellite imagery. It is noted that our country has strong potential for adopting UAVs in agriculture, considering their technical, economic, and human resources.

Abstract. Sugarcane is a perennial crop that contributes to nearly 80% of the global sugar-based products. Therefore, sugarcane growers and food companies are seeking ways to address the concerns related to sugarcane crop yield and health. In this study, a spatial and spectral analysis on the peak growth stage of the sugarcane fields in Bundaberg, Queensland, Australia is performed using the Normalized Difference Vegetation Index (NDVI) and Normalized Difference Red Edge Index (NDRE) derived from high-resolution WorldView-2 (WV2) images and multispectral Unmanned Aerial Vehicle (UAV) images. Two topics are chosen for this study: 1) the difference and correlation between NDVI and NDRE that are commonly used to estimate Leaf Area Index, a common crop parameter for the assessment of crop yield and health stages; 2) the impact of spatial resolution on the systematic difference in the abovementioned two Vegetation Indices (VIs). The statistical correlation analysis between the WV2 and UAV images produced correlation coefficients of 0.68 and 0.71 for NDVI and NDRE, respectively. In addition, an overall comparison of the WV2 and UAV-derived VIs indicated that the UAV images produced a better accuracy than the WV2 images because UAV can effectively distinguish various status of vegetation owing to its high spatial resolution. The results illustrated a strong positive correlation between NDVI and NDRE, each derived from the WV2 and UAV images, and the correlation coefficients were 0.81 and 0.90, respectively, i.e. the correlation between NDVI and NDRE is higher in the UAV images than the WV2 images.

Normalized difference vegetation index (NDVI) and normalized difference red-edge index (NDRE) are vegetation indices commonly used in agriculture to provide information on crop’s growth and health. Here, we investigated the sensitivity of both indices to management practices in lowbush blueberry fields. Images of the experimental plots were collected with a multispectral camera installed on an unmanned aerial vehicle. Both NDVI and NDRE values were significantly higher in fertilized plots than in controls (0.88 ± 0.03 vs. 0.79 ± 0.03 for NDVI, and 0.37 ± 0.01 vs. 0.33 ± 0.01 for NDRE) due to fertilization effect on vegetative growth. The increase was higher under mineral than organic fertilization during the two first phases of the cropping system (by ∼0.3 and ∼0.2 for NDVI and NDRE, respectively). NDRE was not affected by thermal pruning and fungicide application but was negatively correlated with Septoria infection level. NDVI was more strongly correlated with stem length than NDRE, but unlike NDRE, NDVI was not impacted by the development of reproductive shoots during the harvest phases. Overall, the results indicate that although both index values are correlated, their sensitivity to changes in canopy characteristics differs depending on the cropping phase. Further research must be conducted to relate these indices to blueberry’s nutrient status.

Unmanned aerial vehicles (UAVs) equipped with multispectral sensors present an opportunity to monitor vegetation with on-demand high spatial and temporal resolution. In this study we use multispectral imagery from quadcopter UAVs to monitor the progression of a water manipulation experiment on a common shrub, Baccharis pilularis (coyote brush) at the Blue Oak Ranch Reserve (BORR) ~20 km east of San Jose, California. We recorded multispectral imagery at several altitudes with nearly hourly intervals to explore the relationship between two common spectral indices, NDVI (normalized difference vegetation index) and NDRE (normalized difference red edge index), leaf water content and water potential as physiological metrics of plant water status, across a gradient of water deficit. An examination of the spatial and temporal thresholds at which water limitations were most detectable revealed that the best separation between levels of water deficit were at higher resolution (lower flying height), and in the morning (NDVI) and early morning (NDRE). We found that both measures were able to identify moisture deficit across treatments; however, NDVI was better able to distinguish between treatments than NDRE and was more positively correlated with field measurements of leaf water content. Finally, we explored how relationships between spectral indices and water status changed when the imagery was scaled to courser resolutions provided by satellite-based imagery (PlanetScope).We found that PlanetScope data was able to capture the overall trend in treatments but unable to capture subtle changes in water content. These kinds of experiments that evaluate the relationship between direct field measurements and UAV camera sensitivity are needed to enable translation of field-based physiology measurements to landscape or regional scales.

Unmanned aerial vehicles (UAVs) equipped with multi-sensors are one of the most innovative technologies for measuring plant health and predicting final yield in field conditions, especially in the water deficit situation in rain-deprived regions. The objective of this investigation was to evaluate the individual plant and canopy-level measurements using UAV imageries in three different genotypes, Suwan4452 (drought-tolerant), Pac339, and S7328 (drought-sensitive) of maize (Zea mays L.) at vegetative and reproductive stages under WW (well-watered) and WD (water deficit) conditions. At the vegetative stage, only CWSI (crop water stress index) ofPac339 and S7328 under WD increased significantly by 1.86- and 1.69-fold over WW, whereas the vegetation indices (EVI2 (Enhanced Vegetation Index 2), OSAVI (Optimized Soil-Adjusted Vegetation Index), GNDVI (Green Normalized Difference Vegetation Index), NDRE (Normalized Difference Red Edge Index), and NDVI (Normalized Difference Vegetation Index)) derived from UAV multi-sensors did not vary. At the reproductive stage, CWSI in drought-sensitive genotype (S7328) under WD increased by 1.92-fold over WW. All the vegetation indices (EVI2, OSAVI, GNDVI, NDRE, and NDVI) of Pac339 and S7328 under WD decreased when compared with those of Suwan4452. NDVI derived from GreenSeeker® handheld and NDVI from UAV data was closely related (R2 = 0.5924). An increase in leaf temperature (Tleaf) and reduction in NDVI of WD stressed maize plants was observed (R2 = 0.5829) leading to yield loss (R2 = 0.5198). In summary, a close correlation was observed between the physiological data of individual plants and vegetation indices of canopy level (collected using a UAV platform) in drought-sensitive genotypes of maize crops under WD conditions, thus indicating its effectiveness in the classification of drought-tolerant genotypes.

Unleashing the potential of IoT, Artificial Intelligence, and UAVs in contemporary agriculture: A comprehensive review

The information on biophysical parameters—such as height, crown area, and vegetation indices such as the normalized difference vegetation index (NDVI) and normalized difference red edge index (NDRE)—are useful to monitor health conditions and the growth of oil palm trees in precision agriculture practices. The use of multispectral sensors mounted on unmanned aerial vehicles (UAV) provides high spatio-temporal resolution data to study plant health. However, the influence of UAV altitude when extracting biophysical parameters of oil palm from a multispectral sensor has not yet been well explored. Therefore, this study utilized the MicaSense RedEdge sensor mounted on a DJI Phantom–4 UAV platform for aerial photogrammetry. Three different close-range multispectral aerial images were acquired at a flight altitude of 20 m, 60 m, and 80 m above ground level (AGL) over the young oil palm plantation area in Malaysia. The images were processed using the structure from motion (SfM) technique in Pix4DMapper software and produced multispectral orthomosaic aerial images, digital surface model (DSM), and point clouds. Meanwhile, canopy height models (CHM) were generated by subtracting DSM and digital elevation models (DEM). Oil palm tree heights and crown projected area (CPA) were extracted from CHM and the orthomosaic. NDVI and NDRE were calculated using the red, red-edge, and near-infrared spectral bands of orthomosaic data. The accuracy of the extracted height and CPA were evaluated by assessing accuracy from a different altitude of UAV data with ground measured CPA and height. Correlations, root mean square deviation (RMSD), and central tendency were used to compare UAV extracted biophysical parameters with ground data. Based on our results, flying at an altitude of 60 m is the best and optimal flight altitude for estimating biophysical parameters followed by 80 m altitude. The 20 m UAV altitude showed a tendency of overestimation in biophysical parameters of young oil palm and is less consistent when extracting parameters among the others. The methodology and results are a step toward precision agriculture in the oil palm plantation area.

NDVI/NDRE prediction from standard RGB aerial imagery using deep learning

Rapid growth of mechanization of all agricultural work cannot completely reduce human participation, so agricultural automation is extremely important. In terms of automation, this study highlights crucial role of UAVs in accurate and intelligent agriculture. In the article, possibilities of using unmanned aerial vehicles (UAVs) in agriculture are conisred. Advantages of using UAVs in comparison with traditional methods are described, as well as prospects for the development of this direction in the agricultural sector are highlighted. Of course, using of unmanned aerial vehicles is widespread in many countries of the world, and results of research in this direction, despite short period of implementation of this technology, are presented in numerous scientific publications. The volume of the global market for Unmanned Aircraft Systems is constantly increasing, and Ukraine, given high development of the aircraft industry, can become one of the leading manufacturers of integrated solutions and services to meet the ever-growing needs of this market. Ukraine has potential to use unmanned aerial vehicles in agriculture in terms of technical, economic and human resources. UAVs can provide clear, high-resolution images for commercial use, including agriculture. However, at present, the area of increasing the activity of multi-rotor UAVs for agricultural needs is not sufficiently studied. Many scientific works of domestic and foreign authors are devoted to the use of UAVs in agriculture. Nevertheless, today, the full list of works that can be performed with the help of UAVs, in particular in agriculture (agronomy), has not yet been determined. Using unmanned aerial vehicles in agriculture is the innovation for Ukraine, since UAVs were primarily used for military needs and only after military tests began to be widely used in agriculture. An important section of research on ways to improve the functionality of UAVs in the agricultural sector is to improve ways to control UAVs when using these advanced technologies as machine learning and the Internet of things. The analysis of the most effective ways to increase the activity of UAVs in agriculture is carried out and it is stated that evelopment of UAVs with new capabilities and improvement of their sensor base are the main ways of their modernization. It is noted that addition of new sensors that provide more accurate information about the state of crops will allow farmers to monitor and care for plants as efficiently as possible.

Optimization of soil background removal to improve the prediction of wheat traits with UAV imagery

Smart agriculture is gaining a lot of attention recently, owing to technological advancement and promotion of sustainable habits. Unmanned aerial vehicles (UAVs) play a crucial role in smart agriculture by aiding in different phases of agriculture. The contribution of UAVs to sustainable and precision agriculture is a critical and challenging issue to be taken into account, particularly for smallholder farmers in order to save time and money, and improve their agricultural skills. Thence, this study targets to propose an integrated group decision-making framework to determine the best agricultural UAV. Previous studies on UAV evaluation, (i) could not model uncertainty effectively, (ii) weights of experts are not methodically determined; (iii) importance of experts and criteria types are not considered during criteria weight calculation, and (iv) personalized ranking of UAVs is lacking along with consideration to dual weight entities. Herein, nine critical selection criteria are identified, drawing upon the relevant literature and experts’ opinions, and five extant UAVs are considered for evaluation. To circumvent the gaps, in this work, a new integrated framework is developed considering q-rung orthopair fuzzy numbers (q-ROFNs) for apt UAV selection. Specifically, methodical estimation of experts’ weights is achieved by presenting the regret measure. Further, weighted logarithmic percentage change-driven objective weighting (LOPCOW) technique is formulated for criteria weight calculation, and an algorithm for personalized ranking of UAVs is presented with visekriterijumska optimizacija i kompromisno resenje (VIKOR) approach combined with Copeland strategy. The findings show that the foremost criteria in agricultural UAV selection are “camera,” “power system,” and “radar system,” respectively. Further, it is inferred that the most promising UAV is the DJ AGRAS T30. Since the applicability of UAV in agriculture will get inevitable, the developed framework can be an effective decision support system for farmers, managers, policymakers, and other stakeholders.

Accurate estimation of the leaf area index (LAI) is essential for crop growth simulations and agricultural management. This study conducted a field experiment with rice and measured the LAI in different rice growth periods. The multispectral bands (B) including red edge (RE, 730 nm ± 16 nm), near-infrared (NIR, 840 nm ± 26 nm), green (560 nm ± 16 nm), red (650 nm ± 16 nm), blue (450 nm ± 16 nm), and visible light (RGB) were also obtained by an unmanned aerial vehicle (UAV) with multispectral sensors (DJI-P4M, SZ DJI Technology Co., Ltd.). Based on the bands, five vegetation indexes (VI) including Green Normalized Difference Vegetation Index (GNDVI), Leaf Chlorophyll Index (LCI), Normalized Difference Red Edge Index (NDRE), Normalized Difference Vegetation Index (NDVI), and Optimization Soil-Adjusted Vegetation Index (OSAVI) were calculated. The semi-empirical model (SEM), the random forest model (RF), and the Extreme Gradient Boosting model (XGBoost) were used to estimate rice LAI based on multispectral bands, VIs, and their combinations, respectively. The results indicated that the GNDVI had the highest accuracy in the SEM (R2 = 0.78, RMSE = 0.77). For the single band, NIR had the highest accuracy in both RF (R2 = 0.73, RMSE = 0.98) and XGBoost (R2 = 0.77, RMSE = 0.88). Band combination of NIR + red improved the estimation accuracy in both RF (R2 = 0.87, RMSE = 0.65) and XGBoost (R2 = 0.88, RMSE = 0.63). NDRE and LCI were the first two single VIs for LAI estimation using both RF and XGBoost. However, putting more than one VI together could only increase the LAI estimation accuracy slightly. Meanwhile, the bands + VIs combinations could improve the accuracy in both RF and XGBoost. Our study recommended estimating rice LAI by a combination of red + NIR + OSAVI + NDVI + GNDVI + LCI + NDRE (2B + 5V) with XGBoost to obtain high accuracy and overcome the potential over-fitting issue (R2 = 0.91, RMSE = 0.54).

The monitoring and determination of peanut maturity are fundamental to reducing losses during digging operation. However, the methods currently used are laborious and subjective. To solve this problem, we developed models to access peanut maturity using images from unmanned aerial vehicles (UAV) and satellites. We evaluated an area of approximately 8 hectares in which a regular grid of 30 points was determined with weekly evaluations starting at 90 days after sowing. Two Artificial Neural Networking (ANN) were used with Radial Basis Function (RBF) and Multilayer Perceptron (MLP) to predict the Peanut Maturity Index (PMI) with the spectral bands available from each sensor. Several vegetation indices were used as input to the ANN, with the data being split 80/20 for training and validation, respectively. The vegetation index, Normalized Difference Red Edge Index (NDRE), was the most precise coefficient of determination (R2 = 0.88) and accurate mean absolute error (MAE = 0.06) for estimating PMI, regardless of the type of ANN used. The satellite with Normalized Difference Vegetation Index (NDVI) could also determine PMI with better accuracy (MAE = 0.05) than the NDRE. The performance evaluation indicates that the RBF and MLP networks are similar in predicting peanut maturity. We concluded that satellite and UAV images can predict the maturity index with good accuracy and precision.