Unmanned Aerial Vehicles Research Articles

Soil moisture content estimation of drip-irrigated citrus orchard based on UAV images and machine learning algorithm in Southwest China

Soil moisture content (SMC), as a pivotal component in the energy and matter exchange processes within the soil-plant-atmosphere continuum, plays a crucial role in surface water dynamics, energy fluxes, and carbon cycling within ecosystems. The development of remote sensing technology has offered new perspectives for monitoring soil moisture at regional scales. Unmanned aerial vehicles (UAV) equip with multispectral remote sensing technology have distinct advantages for vegetation monitoring at the field scale, including rapidity and cost-effectiveness, which has superior applicability and practicality at the field scale. Therefore, in a 5a "Daya" late-maturing citrus orchard, the vegetation index (VI) and texture feature (TF) information of citrus canopy based on UAV multi-spectral images as well as soil and plant analyzer development (SPAD) of citrus physiological parameter were extracted. These different data sources were integrated into the framework of the random forest algorithm (RF) and genetic algorithm-optimized random forest (GA-RF) to evaluate the accuracy of surface SMC (SSMC) estimation in citrus orchard. The Biswas model was utilized to simulate the root zone SMC (RSMC) in citrus orchard. The spatiotemporal variations of soil moisture in citrus orchards were analyzed, and the potential of low-cost sensor-equipped drones in rapidly acquiring spatial and temporal distribution information of soil moisture at a large regional scale was explored. The results indicated that the GA-RF model outperformed the RF model in estimating citrus orchard SMC (with R2 ranging from 0.502 to 0.949 and RMSE ranging from 0.552 to 3.166% for GA-RF, compared to R2 ranging from 0.430 to 0.936 and RMSE ranging from 0.587 to 3.449% for the RF). The GA-RF model using VI+SPAD as inputs exhibited the best performance for SMC at depths of 5cm, 10cm, 20cm and 40cm (SMC5, SMC10, SMC20 and SMC40) across four citrus growth stages (R2 ranging from 0.793 to 0.949 at 5cm, R2 ranging from 0.702 to 0.938 at 10cm, R2 ranging from 0.714 to 0.927 at 20cm). In bud bust to flowering, young fruit and fruit maturation stages (stage Ⅰ, ⅠⅠ and ⅠⅤ), all models demonstrated good accuracy in estimating SMC at depth of 10cm (R2 ranging from 0.567 to 0.908 in stage Ⅰ, with R2 ranging from 0.681 to 0.916 in stage ⅠⅠ and R2 ranging from 0.579 to 0.938 in stage ⅠⅤ). In fruit expansion stage (stage III), the models performed best in predicting SMC5 (R2 ranging from 0.698 to 0.861). The Biswas model was constructed to simulate SMC40 by utilizing the inverted SMC10 and SMC20, thereby generating spatiotemporal distribution maps of SMC at different depths in citrus orchard. The SSMC was susceptible to environmental factors, exhibiting significant spatiotemporal heterogeneity. In summary, this study illustrated that the integration of multiple data sources into GA-RF model enhanced the estimation performance of SMC at different growth stages of late-maturing citrus orchards in the Southwest China. Additionally, it enabled the rapid and efficient monitoring of spatiotemporal variations in SMC, providing an effective method and practical foundation for precision irrigation and improved water use efficiency in agricultural fields.

Comparison of off-target pesticide drift in paddy fields from unmanned aerial vehicle spraying using cellulose deposition sampler

Off-target pesticide drift in paddy fields following unmanned aerial vehicle (UAV) spraying was evaluated using cellulose deposition samplers (CDSs). An analytical method for quantifying ferimzone Z and E isomers deposited on CDSs was developed using LC-MS/MS. The suitability of the CDS method was confirmed by comparing deposition patterns on CDSs with residue levels in rice plant samples. To assess pesticide deposition in paddy fields, CDSs were strategically placed at varying distances from target areas, followed by UAV spraying. The fungicide agrochemicals were applied with and without adjuvants, and wind direction affected the drift trajectory for all treatment groups. Adjuvants, particularly soy lecithin as the major component, significantly enhanced pesticide deposition within the spray pathway while reducing drift rates relatively by 47.9-68.0%. Higher wind speeds were found to exacerbate drift, but adjuvant-treated sprays showed less variability in deposition patterns under these conditions. Pesticide residues in harvested brown rice were found to be below the maximum residue limits (MRLs), ensuring safety for consumption. These findings highlight the importance of selecting appropriate adjuvants in UAV-based pesticide applications to optimize deposition efficiency and minimize environmental contamination.

무인항공기의 적외선 기반 정밀착륙

무인항공기의 적외선 기반 정밀착륙

Detecting Denial of Service Attacks (DoS) over the Internet of Drones (IoD) Based on Machine Learning

The use of Unmanned Aerial Vehicles (UAVs) or drones has increased lately. This phenomenon is due to UAVs’ wide range of applications in fields such as agriculture, delivery, security and surveillance, and construction. In this context, the security and the continuity of UAV operations becomes a crucial issue. Spoofing, jamming, hijacking, and Denial of Service (DoS) attacks are just a few categories of attacks that threaten drones. The present paper is focused on the security of UAVs against DoS attacks. It illustrates the pros and cons of existing methods and resulting challenges. From here, we develop a novel method to detect DoS attacks in UAV environments. DoS attacks themselves have many sub-categories and can be executed using many techniques. Consequently, there is a need for robust protection and mitigation systems to shield UAVs from DoS attacks. One promising security solution is intrusion detection systems (IDSs). IDs paired with machine learning (ML) techniques provide the ability to greatly reduce the risk, as attacks can be detected before they happen. ML plays an important part in improving the performance of IDSs. The many existing ML models that detect DoS attacks on UAVs each carry their own strengths and limitations.

Multi-UAV Path Planning for Inspection of Target Points with Stable Monitoring Frequencies

In this study, we focus on the path-planning problem of unmanned aerial vehicles (UAVs) deployed for inspection missions at target points. The goal is to visit each target point, provide revisits to important target points, and ultimately meet the monitoring requirements with regular and stable monitoring frequencies. Herein, we present MTSP-R, a novel variant of the multiple traveling salesmen problem (MTSP), in which revisits to important target points are allowed. We address the path-planning problem of multi-UAV in two stages. First, we propose a nearest insertion algorithm with revisits (NIA-R) to determine the number of required UAVs and initial inspection paths. We then propose an improved genetic algorithm (IGA) with two-part chromosome encoding to further optimize the inspection paths of the UAVs. The simulation results demonstrate that the IGA can effectively overcome the shortcomings of the original genetic algorithm, providing shorter paths for multiple UAVs and more stable monitoring frequencies for the target points.

Mission Planning and Trajectory Optimization in UAV Swarm for Track Deception against Radar Network

In this article, a mission planning and trajectory optimization scheme in unmanned aerial vehicle (UAV) swarm for track deception against radar networks is proposed. The core of this scheme is to formulate the track deception problem as a model with the objective of simultaneously maximizing the number of phantom tracks while minimizing the total flight distance of the UAV swarm, subject to the constraints of UAV kinematic performance, phantom track rotation angles, and a homology test. It is shown that the formulated track deception problem is a mixed-integer programming, multivariable, and non-linear optimization model. By incorporating mission planning based on platform reuse and a particle swarm optimization (PSO) algorithm, a three-stage solution methodology is proposed to tackle the above problem. Through joint optimization for mission planning and flight trajectories of the UAV swarm, a low-speed UAV swarm is capable of generating a number of high-speed phantom tracks. Numerical results demonstrate that the proposed scheme enables a low-speed UAV swarm to generate as many high-speed phantom tracks as possible, effectively achieving track deception against radar network.

Image Recognition for Floating Waste Monitoring in a Traditional Surface Irrigation System

In the traditional surface irrigation system of Vega Baja del Segura (Spain), large amounts of floating waste accumulate at certain points of the river, irrigation channels and drainage ditches, causing malfunctioning of the irrigation network and rising social problems related to the origins of waste. This work proposes a standardized and quick methodology to characterize the floating waste to detect changes in its amount and components. A dataset was created with 477 images of floating plastic items in different environments and was used for training an algorithm based on YOLOv5s. The mean Average Precision of the trained algorithm was 96.9%, and the detection speed was 81.7 ms. Overhead photographs were taken with an unmanned aerial vehicle at strategic points of the river and channels, and its automatic count of floating objects was compared with their manual count. Both methods showed good agreement, confirming that water bottles were the most abundant (95%) type of floating waste. The automatic count reduced the required time and eliminated human bias in image analysis of the floating waste. This procedure can be used to test the reach of corrective measures implemented by local authorities to prevent floating waste in the river.

Aerodynamic Analysis and Simulation for a Z-Shaped Folding Wing UAV

The potential of folding wing unmanned aerial vehicles (UAVs) in enhancing the adaptability of complex missions is substantial. Analyzing the aerodynamic characteristics of these UAVs is vital for optimizing the design of their folding wing configuration and airfoil shape. In this study, a model of a Z-shaped folding wing UAV was established with the objective of enhancing UAV maneuverability. An integrated vortex lattice method (VLM) was employed to analyze the aerodynamic characteristics of the Z-shaped folding wing and numerical simulations were utilized to validate the obtained results, which prove the effectiveness of the integrated VLM in studying aerodynamic characteristics at a high angle of attack of the Z-shaped folding wing UAV. This is a new way to reduce computation time while maintaining accuracy to calculate such complex folding structures in high fidelity. Furthermore, the Z-shaped folding wing configuration demonstrates enhanced maneuverability at high angles of attack, and a Simulink flight simulation model based on the aerodynamic coefficients of the Z-shaped folding wing verifies this property. This analysis can properly predict the post-stall characteristics for the Z-shaped folding wing UAV to ensure the safety of the vehicle during flight.

Bridge Surface Defect Localization Based on Panoramic Image Generation and Deep Learning-Assisted Detection Method

Applying unmanned aerial vehicles (UAVs) and vision-based analysis methods to detect bridge surface damage significantly improves inspection efficiency, but the existing techniques have difficulty in accurately locating damage, making it difficult to use the results to assess a bridge’s degree of deterioration. Therefore, this study proposes a method to generate panoramic bridge surface images using multi-view images captured by UAVs, in order to automatically identify and locate damage. The main contributions are as follows: (1) We propose a UAV-based image-capturing method for various bridge sections to collect close-range, multi-angle, and overlapping images of the surface; (2) we propose a 3D reconstruction method based on multi-view images to reconstruct a textured bridge model, through which an ultra-high resolution panoramic unfolded image of the bridge surface can be obtained by projecting from multiple angles; (3) we applied the Swin Transformer to optimize the YOLOv8 network and improve the detection accuracy of small-scale damages based on the established bridge damage dataset and employed sliding window segmentation to detect damage in the ultra-high resolution panoramic image. The proposed method was applied to detect surface damage on a three-span concrete bridge. The results indicate that this method automatically generates panoramic images of the bridge bottom, deck, and sides with hundreds of millions of pixels and recognizes damage in the panoramas. In addition, the damage detection accuracy reached 98.7%, which is improved by 13.6% when compared with the original network.

An Innovative New Approach to Light Pollution Measurement by Drone

The study of light pollution is a relatively new and specific field of measurement. The current literature is dominated by articles that describe the use of ground and satellite data as a source of information on light pollution. However, there is a need to study the phenomenon on a microscale, i.e., locally within small locations such as housing estates, parks, buildings, or even inside buildings. Therefore, there is an important need to measure light pollution at a lower level, at the low level of the skyline. In this paper, the authors present a new drone design for light pollution measurement. A completely new original design for an unmanned platform for light pollution measurement is presented, which is adapted to mount custom sensors (not originally designed to be mounted on a unmanned aerial vehicles) allowing registration in the nadir and zenith directions. The application and use of traditional photometric sensors in the new configuration, such as the spectrometer and the sky quality meter (SQM), is presented. A multispectral camera for nighttime measurements, a calibrated visible-light camera, is used. The results of the unmanned aerial vehicle (UAV) are generated products that allow the visualisation of multimodal photometric data together with the presence of a geographic coordinate system. This paper also presents the results from field experiments during which the light spectrum is measured with the installed sensors. As the results show, measurements at night, especially with multispectral cameras, allow the assessment of the spectrum emitted by street lamps, while the measurement of the sky quality depends on the flight height only up to a 10 m above ground level.

Harnessing UAVs and deep learning for accurate grass weed detection in wheat fields: a study on biomass and yield implications

Weeds are undesired plants competing with crops for light, nutrients, and water, negatively impacting crop growth. Identifying weeds in wheat fields accurately is important for precise pesticide spraying and targeted weed control. Grass weeds in their early growth stages look very similar to wheat seedlings, making them difficult to identify. In this study, we focused on wheat fields with varying levels of grass weed infestation and used unmanned aerial vehicles (UAVs) to obtain images. By utilizing deep learning algorithms and spectral analysis technology, the weeds were identified and extracted accurately from wheat fields. Our results showed that the precision of weed detection in scattered wheat fields was 91.27% and 87.51% in drilled wheat fields. Compared to areas without weeds, the increase in weed density led to a decrease in wheat biomass, with the maximum biomass decreasing by 71%. The effect of weed density on yield was similar, with the maximum yield decreasing by 4320 kg·ha− 1, a drop of 60%. In this study, a method for monitoring weed occurrence in wheat fields was established, and the effects of weeds on wheat growth in different growth periods and weed densities were studied by accurately extracting weeds from wheat fields. The results can provide a reference for weed control and hazard assessment research.

The Optimal Strategies of Maneuver Decision in Air Combat of UCAV Based on the Improved TD3 Algorithm

Nowadays, unmanned aerial vehicles (UAVs) pose a significant challenge to air defense systems. Unmanned combat aerial vehicles (UCAVs) have been proven to be an effective method to counter the threat of UAVs in application. Therefore, maneuver decision-making has become the crucial technology to achieve autonomous air combat for UCAVs. In order to solve the problem of maneuver decision-making, an autonomous model of UCAVs based on the deep reinforcement learning method was proposed in this paper. Firstly, the six-degree-of-freedom (DoF) dynamic model was built in three-dimensional space, and the continuous actions of tangential overload, normal overload, and roll angle were selected as the maneuver inputs. Secondly, to improve the convergence speed for the deep reinforcement learning method, the idea of “scenario-transfer training” was introduced into the twin delayed deep deterministic (TD3) policy gradient algorithm, the results showing that the improved algorithm could cut off about 60% of the training time. Thirdly, for the “nose-to-nose turns”, which is one of the classical maneuvers for experienced pilots, the optimal maneuver generated by the proposed method was analyzed. The results showed that the maneuver strategy obtained by the proposed method was highly consistent with that made by experienced fighter pilots. This is also the first time in a public article that compared the maneuver decisions made by the deep reinforcement learning method with experienced fighter pilots. This research can provide some meaningful references to generate autonomous decision-making strategies for UCAVs.

Digital Construction Preservation Techniques of Endangered Heritage Architecture: A Detailed Reconstruction Process of the Dong Ethnicity Drum Tower (China)

This study suggests a pioneering conservation framework that significantly enhances the preservation, renovation, and restoration of heritage architecture through the integration of contemporary digital technologies. Focusing on the endangered drum towers of the Dong ethnic group in Southwestern China, the research employs a meticulous data collection process that combines manual measurements with precise 2D imaging and oblique unmanned aerial vehicle (UAV) photography, enabling comprehensive documentation of tower interiors and exteriors. Collaboration with local experts in drum tower construction not only enriches the data gathered but also provides profound insights into the architectural nuances of these structures. An accurate building information modeling (BIM) simulation illuminates the internal engineering details, deepening the understanding of their complex design. Furthermore, UAV-obtained point cloud data facilitate a 3D reconstruction of the tower’s exterior. This innovative approach to heritage preservation not only advances the documentation and comprehension of heritage structures but also presents a scalable, replicable model for cultural conservation globally, paving the way for future research in the field.

Unsteady aerodynamic interaction in regulated two-stage radial turbine at pulsating conditions

Regulated multi-stage turbocharging is an indispensable technology to achieve high boosting pressure and hence power recovery for High-Altitude Long-Endurance Unmanned Aerial Vehicle (HALE UAV). Inevitably, unsteady interstage coupling has become a key factor restricting the pursuit of higher aerodynamic performance in multi-stage turbochargers. This study is to investigate the unsteady gasdynamic behavior of two-stage radial turbines and aimed to obtained the knowledge of unsteady aerodynamic interaction at pulsating conditions. Results reveal an obvious difference in the performance discrepancy mechanisms of high-pressure turbine (HPT) and low-pressure turbine (LPT). HPT shows more unsteady than that of LPT according to the discussion on mass accumulation and local temporal gradient. Furthermore, this unsteadiness is drastically enhanced when the valve is open. For HPT with open valve, a sharp reduction of up to 10.7% in the cycle-averaged efficiency is observed. Both the volute and the rotor are the main components causing the deterioration of efficiency. Swirling flow precession leads to a dramatically loss generation in the volute. Leading-edge separation and tip leakage flow are the dominated factors in rotor. The former is primarily attributed to inlet swirling flow and the latter is predominantly attributed to the pulsating effect. For LPT, the performance is not sensitive to the valve state, with no more than 3% discrepancy on efficiency. At specific velocity ratio, the negative swirling flow tends to exert a positive effect to the rotor efficiency, whereas the positive swirling flow leads to a higher entropy generation in rotor passage.

Effects of Spray Adjuvants on Droplet Deposition Characteristics in Litchi Trees under UAV Spraying Operations

In the last decade, unmanned aerial vehicles (UAVs) for plant protection have rapidly developed worldwide as a new method for pesticide application, especially in China and other Asian countries. To improve the deposition quality in UAV applications, adding appropriate types of spray adjuvants into pesticide solutions is one of the most effective ways to facilitate droplet deposition and control efficacy. At present, research on spray adjuvants for UAVs are mainly based on droplet drift and laboratory tests. Few studies have been conducted on the physicochemical properties of spray adjuvants and the effects of droplet deposition characteristics. To explore the properties of four different kinds of spray adjuvants (Mai Fei, Bei Datong, G-2801, and Agrospred 910) and the deposition characteristics of spray adjuvants on litchi leaves, an automatic surface tension meter, a contact angle measuring device, an ultraviolet visible spectrophotometer, and a DJI AGRAS T30 plant protection UAV was used to measure the surface tension, contact angle, and droplet deposition characteristics on litchi under UAV spraying operations. The results showed that the addition of spray adjuvants could significantly reduce the surface tension of the solution. The surface tension value of the solution after adding the spray additives was reduced by 53.1–68.9% compared with the control solution. Among them, the Agrospred 910 spray adjuvant had the best effect on reducing the surface tension of the solution. The contact angle of the control solution on the litchi leaves varied from 80.15° to 72.76°. With the increase in time, the contact angle of the spray adjuvant solution gradually decreased, the Agrospred 910 spray adjuvant had the best effect, and the contact angle decreased from 40.44° to 20.23° after the droplets fell on the litchi leaves for 60 s. The adjuvant solutions increased the droplet size, but the uniformity of the droplet size decreased. The Dv0.5 of different spray solutions ranged from 97.3 to 117.8 μm, which belonged to the fine or very fine droplets, and the Dv0.5 of adjuvants solutions were significantly greater than that of the control solution. The RSs of adjuvant solutions were very similar and ranged from 0.92 to 0.96, all of which were significantly greater than the result of the control solution (0.57). Compared with the deposition of the control solution, the Mai Fei, Bei Datong, and G-2801 solutions clearly increased spray deposition, with total depositions of 0.776, 0.705, and 0.721 μL/cm2, which are all greater than the total deposition of the control solution of 0.645 μL/cm2. The addition of tank-mixed adjuvants could effectively increase the uniformity of the spray deposition, and all the average CVs of adjuvant solutions were lower than 96.86%. On the whole, Mai Fei performed best in increasing the spray deposition and promoting penetration, followed by Bei Datong and G-2801. Meanwhile, the test can also provide a reference for improving the utilization rate of UAV pesticide applications.

Advancements in UAV Path Planning: A Deep Reinforcement Learning Approach with Soft Actor-Critic for Enhanced Navigation

This paper tackles the intricate challenge of autonomous navigation for Unmanned Aerial Vehicles (UAVs) through dynamically changing environments. We focus on a sophisticated Deep Reinforcement Learning (DRL) approach using the Soft Actor-Critic (SAC) algorithm, optimized for UAV path planning within a continuous action space. This methodology leverages environmental image data to enhance the precision of flight maneuvers and effective obstacle avoidance. Our approach, validated through extensive simulations in Gazebo and field tests, demonstrates the algorithm’s efficacy in enabling UAVs to adeptly navigate obstacles using depth maps. The study further explores the robustness of the SAC algorithm by comparing it with traditional DRL methods, emphasizing its superior performance in real-world applications. This research contributes significantly to advancing UAV technology, particularly in autonomous motion planning, by integrating cutting-edge machine learning techniques. The video link is: https://www.youtube.com/watch?v=Nd_aMzejNXY .

G-YOLO: A Lightweight Infrared Aerial Remote Sensing Target Detection Model for UAVs Based on YOLOv8

A lightweight infrared target detection model, G-YOLO, based on an unmanned aerial vehicle (UAV) is proposed to address the issues of low accuracy in target detection of UAV aerial images in complex ground scenarios and large network models that are difficult to apply to mobile or embedded platforms. Firstly, the YOLOv8 backbone feature extraction network is improved and designed based on the lightweight network, GhostBottleneckV2, and the remaining part of the backbone network adopts the depth-separable convolution, DWConv, to replace part of the standard convolution, which effectively retains the detection effect of the model while greatly reducing the number of model parameters and calculations. Secondly, the neck structure is improved by the ODConv module, which adopts an adaptive convolutional structure to adaptively adjust the convolutional kernel size and step size, which allows for more effective feature extraction and detection based on targets at different scales. At the same time, the neck structure is further optimized using the attention mechanism, SEAttention, to improve the model’s ability to learn global information of input feature maps, which is then applied to each channel of each feature map to enhance the useful information in a specific channel and improve the model’s detection performance. Finally, the introduction of the SlideLoss loss function enables the model to calculate the differences between predicted and actual truth bounding boxes during the training process, and adjust the model parameters based on these differences to improve the accuracy and efficiency of object detection. The experimental results show that compared with YOLOv8n, the G-YOLO reduces the missed and false detection rates of infrared small target detection in complex backgrounds. The number of model parameters is reduced by 74.2%, the number of computational floats is reduced by 54.3%, the FPS is improved by 71, which improves the detection efficiency of the model, and the average accuracy (mAP) reaches 91.4%, which verifies the validity of the model for UAV-based infrared small target detection. Furthermore, the FPS of the model reaches 556, and it will be suitable for wider and more complex detection task such as small targets, long-distance targets, and other complex scenes.

Use of different vegetation indices for the evaluation of the kinetics of the cherry tomato (Solanum lycopersicum var. cerasiforme) growth based on multispectral images by UAV

Abstract This study evaluated seven vegetation indices for the monitoring of a cherry tomato crop using an unmanned aerial vehicle with a multispectral camera that measures in the green, red, and near-infrared spectral bands. A photogrammetric flight plan was designed to capture the spectral images every 2 weeks in two agricultural parcels identified as Treatment 1 ( T 1 {T}_{1} ) and Treatment 2 ( T 2 {T}_{2} ). The corresponding orthophotographs were obtained using digital photogrammetry techniques. Subsequently, vegetation indices were calculated for these orthophotographs. The mean and standard deviation of these indices were extracted, and a statistical analysis was performed to compare the vegetation indices and to analyze their behavior over time. Analysis of variance showed that the ratio vegetation index (RVI), green vegetation index (GVI), normalized difference vegetation index (NDVI), infrared percentage vegetation index (IPVI), green normalized difference vegetation index (GNDVI), and optimized soil-adjusted vegetation index (OSAVI) indices showed significant variation (P-value <0.05) over time. No statistically significant differences between the two treatments were found. IPVI, NDVI, and OSAVI showed less variation in pixel values. RVI, GVI, NDVI, IPVI, GNDVI, and OSAVI proved to be valuable tools for monitoring field crops since these indices responded to the crop growth kinetics.

Precision estimation of winter wheat crop height and above-ground biomass using unmanned aerial vehicle imagery and oblique photoghraphy point cloud data

IntroductionCrop height and above-ground biomass (AGB) serve as crucial indicators for monitoring crop growth and estimating grain yield. Timely and accurate acquisition of wheat crop height and AGB data is paramount for guiding agricultural production. However, traditional data acquisition methods suffer from drawbacks such as time-consuming, laborious and destructive sampling.MethodsThe current approach to estimating AGB using unmanned aerial vehicles (UAVs) remote sensing relies solely on spectral data, resulting in low accuracy in estimation. This method fails to address the ill-posed inverse problem of mapping from two-dimensional to three-dimensional and issues related to spectral saturation. To overcome these challenges, RGB and multispectral sensors mounted on UAVs were employed to acquire spectral image data. The five-directional oblique photography technique was utilized to construct the three-dimensional point cloud for extracting crop height.Results and DiscussionThis study comparatively analyzed the potential of the mean method and the Accumulated Incremental Height (AIH) method in crop height extraction. Utilizing Vegetation Indices (VIs), AIH and their feature combinations, models including Random Forest Regression (RFR), eXtreme Gradient Boosting (XGBoost), Gradient Boosting Regression Trees (GBRT), Support Vector Regression (SVR) and Ridge Regression (RR) were constructed to estimate winter wheat AGB. The research results indicated that the AIH method performed well in crop height extraction, with minimal differences between 95% AIH and measured crop height values were observed across various growth stages of wheat, yielding R2 ranging from 0.768 to 0.784. Compared to individual features, the combination of multiple features significantly improved the model’s estimate accuracy. The incorporation of AIH features helps alleviate the effects of spectral saturation. Coupling VIs with AIH features, the model’s R2 increases from 0.694-0.885 with only VIs features to 0.728-0.925. In comparing the performance of five machine learning algorithms, it was discovered that models constructed based on decision trees were superior to other machine learning algorithms. Among them, the RFR algorithm performed optimally, with R2 ranging from 0.9 to 0.93.ConclusionIn conclusion, leveraging multi-source remote sensing data from UAVs with machine learning algorithms overcomes the limitations of traditional crop monitoring methods, offering a technological reference for precision agriculture management and decision-making.

UAV or satellites? How to find the balance between efficiency and accuracy in above ground biomass estimation of artificial young coniferous forest?

The accurate estimation of Above Ground Biomass (AGB) is the basis for plantation forest carbon trading. This study focused on Picea crassifolia artificial plantations, extracting individual tree crown diameters and heights using Unmanned Aerial Vehicles (UAV) data and calculating the individual tree biomass using allometric growth equations. These results were then used to train a satellite image AGB prediction model. In additional, satellite images were resampled to different resolutions to assess the impact of satellite image resolution on model the accuracy. Finally, the model with the highest accuracy among the deep learning algorithms was selected to predicts the AGB within the P. crassifolia plantation forest. The results indicated that the accuracy of single tree crown diameters extracted from P. crassifolia point clouds significantly surpassed those extracted from general point clouds and Crown Height Model (CHM), while the accuracy of the heights extracted from all three sources was similar; RepLKNet outperformed GoogLeNet and ResNet in identifying plantation forest; random forest slightly outperformed XGBoost in the capability of AGB prediction, while the accuracy of the AGB prediction models initially increasd and then decreasd with satellite image resolution, reaching the highest accuracy at a resolution of 50 m. This indicates that the optimal satellite image resolution for estimating the AGB in the study area was affected by scale effects of 50 m. Compared with the combination of satellite data and manual field measurements, the concurrent use of UAVs and satellites offers significant advantages in terms of efficiency and accuracy. UAVs can replace manual sampling for carbon sequestration transactions for plantations.