Inversion model of soil salinity in alfalfa covered farmland based on sensitive variable selection and machine learning algorithms.

Purpose: Timely and accurate monitoring of soil salinity content (SSC) is essential for precise irrigation management of large-scale farmland. Uncrewed aerial vehicle (UAV) low-altitude remote sensing with high spatial and temporal resolution provides a scientific and effective technical means for SSC monitoring. Many existing soil salinity inversion models have only been tested by a single variable selection method or machine learning algorithm, and the influence of variable selection method combined with machine learning algorithm on the accuracy of soil salinity inversion remain further studied. Methods: Firstly, based on UAV multispectral remote sensing data, by extracting the spectral reflectance of each sampling point to construct 30 spectral indexes, and using the pearson correlation coefficient (PCC), gray relational analysis (GRA), variable projection importance (VIP), and support vector machine-recursive feature elimination (SVM-RFE) to screen spectral index and realize the selection of sensitive variables. Subsequently, screened and unscreened variables as model input independent variables, constructed 20 soil salinity inversion models based on the support vector machine regression (SVM), back propagation neural network (BPNN), extreme learning machine (ELM), and random forest (RF) machine learning algorithms, the aim is to explore the feasibility of different variable selection methods combined with machine learning algorithms in SSC inversion of crop-covered farmland. To evaluate the performance of the soil salinity inversion model, the determination coefficient (R2), root mean square error (RMSE) and performance deviation ratio (RPD) were used to evaluate the model performance, and determined the best variable selection method and soil salinity inversion model by taking alfalfa covered farmland in arid oasis irrigation areas of China as the research object. Results: The variable selection combined with machine learning algorithm can significantly improve the accuracy of remote sensing inversion of soil salinity. The performance of the models has been improved markedly using the four variable selection methods, and the applicability varied among the four methods, the GRA variable selection method is suitable for SVM, BPNN, and ELM modeling, while the PCC method is suitable for RF modeling. The GRA-SVM is the best soil salinity inversion model in alfalfa cover farmland, with Rv 2 of 0.8888, RMSEv of 0.1780, and RPD of 1.8115 based on the model verification dataset, and the spatial distribution map of soil salinity can truly reflect the degree of soil salinization in the study area. Conclusion: Based on our findings, the variable selection combined with machine learning algorithm is an effective method to improve the accuracy of soil salinity remote sensing inversion, which provides a new approach for timely and accurate acquisition of crops covered farmland soil salinity information.

Uncrewed aerial vehicle with onboard winch system for rapid, cost-effective, and safe oceanographic profiling in hazardous and inaccessible areas.

Interactions between coastal waters and marine-terminating glaciers in the Polar Regions play a significant role in global sea level rise fueled by a rapidly warming Arctic. The risk of glacier calving, and the abundance of ice, can make it impossible for surface vessels to access the waters near glacier termini. Alternative methods using manned aircraft are expensive. As a result, oceanographic measurements are limited near glacier termini. We present an uncrewed aerial vehicle (UAV) with an on-board winch system that allows oceanographic profiling in remote, hazardous areas using a commercial conductivity, temperature, and depth (CTD) sensor payload. The UAV is optimized for easy handling and deployment and is capable of high-speed and efficient cruise flight. An autopilot system provides pilot assistance and autonomous flight capabilities. The total weight of the UAV including payload is 6.5 kg with an endurance of 24 min. Testing of the system was conducted in South Greenland during winter conditions in March 2023 with successful profiles collected near a glacier terminus (<5 m) and in small openings in ice mélange (2.2 m). The system proved capable, reliable, and efficient. Further development of the system will allow other sensors for an even more flexible measurement suite.

UAV and Satellite Synergies for Mapping Grassland Aboveground Biomass in Hulunbuir Meadow Steppe.

Aboveground biomass (AGB) is an important indicator of the grassland ecosystem. It can be used to evaluate the grassland productivity and carbon stock. Satellite remote sensing technology is useful for monitoring the dynamic changes in AGB across a wide range of grasslands. However, due to the scale mismatch between satellite observations and ground surveys, significant uncertainties and biases exist in mapping grassland AGB from satellite data. This is also a common problem in low- and medium-resolution satellite remote sensing modeling that has not been effectively solved. The rapid development of uncrewed aerial vehicle (UAV) technology offers a way to solve this problem. In this study, we developed a method with UAV and satellite synergies for estimating grassland AGB that filled the gap between satellite observation and ground surveys and successfully mapped the grassland AGB in the Hulunbuir meadow steppe in the northeast of Inner Mongolia, China. First, based on the UAV hyperspectral data and ground survey data, the UAV-based AGB was estimated using a combination of typical vegetation indices (VIs) and the leaf area index (LAI), a structural parameter. Then, the UAV-based AGB was aggregated as a satellite-scale sample set and used to model satellite-based AGB estimation. At the same time, spatial information was incorporated into the LAI inversion process to minimize the scale bias between UAV and satellite data. Finally, the grassland AGB of the entire experimental area was mapped and analyzed. The results show the following: (1) random forest (RF) had the best performance compared with simple regression (SR), partial least squares regression (PLSR) and back-propagation neural network (BPNN) for UAV-based AGB estimation, with an R2 of 0.80 and an RMSE of 76.03 g/m2. (2) Grassland AGB estimation through introducing LAI achieved higher accuracy. For UAV-based AGB estimation, the R2 was improved by an average of 10% and the RMSE was reduced by an average of 9%. For satellite-based AGB estimation, the R2 was increased from 0.70 to 0.75 and the RMSE was decreased from 78.24 g/m2 to 72.36 g/m2. (3) Based on sample aggregated UAV-based AGB and an LAI map, the accuracy of satellite-based AGB estimation was significantly improved. The R2 was increased from 0.57 to 0.75, and the RMSE was decreased from 99.38 g/m2 to 72.36 g/m2. This suggests that UAVs can bridge the gap between satellite observations and field measurements by providing a sufficient training dataset for model development and AGB estimation from satellite data.

Upscaling ground-based backpack gamma-ray spectrometry to spatial resolution of UAV-based gamma-ray spectrometry for system validation.

Advances in the development of gamma-ray spectrometers have resulted in devices that are ideal for use in conjunction with the increasingly reliable systems of autonomously flying uncrewed aerial vehicles (UAVs) that have recently become available on the market. Airborne gamma-ray spectrometry (GRS) measurements have many different applications. Here, the technique is applied to a former uranium mining and processing site, which is characterized by relatively low specific activities and, hence, low count rates, requiring relatively large detectors and correspondingly big size UAVs. The future acceptance of the use of such UAV-based GRS systems for radionuclide mapping depends on their ability to measure absolute specific activities of natural radionuclides such as U-238 in near-surface soil that are consistent with the results of established and proven ground-based systems. To determine absolute specific activities on the ground, the gamma radiation data from airborne detectors must be corrected for attenuation caused by the flight altitude above ground. In recent years, mathematical procedures for altitude correction have been developed, that are specifically tailored to the working range of several tens of meters typical for UAVs. However, very limited experimental validation of these theoretical approaches is available. A very large dataset consisting of about 3000 UAV-based and 19,000 backpack-based measurements was collected at a low-grade uranium ore dump in Yangiabad, Uzbekistan. We applied different geostatistical interpolation methods to compare the data from both survey techniques by upscaling backpack data to airborne data. Compared to backpack systems, UAV-based systems have lower spatial resolution, so measurements average over larger areal units (or in geostatistical terminology: "spatial support"). Taking into account the change in spatial support, we illustrate that (1) the UAV-based measurements show good agreement with the upscaled backpack measurements and that (2) UAV surveys provide good delineation of contrasts of the relatively smooth U-238 specific activity distribution typical for former uranium mining and processing sites. We are able to show that the resolution of UAV-based systems is sufficient to map extended uranium waste facilities.

The use of drones for mosquito surveillance and control.

In recent years, global health security has been threatened by the geographical expansion of vector-borne infectious diseases such as malaria, dengue, yellow fever, Zika and chikungunya. For a range of these vector-borne diseases, an increase in residual (exophagic) transmission together with ecological heterogeneity in everything from weather to local human migration and housing to mosquito species' behaviours presents many challenges to effective mosquito control. The novel use of drones (or uncrewed aerial vehicles) may play a major role in the success of mosquito surveillance and control programmes in the coming decades since the global landscape of mosquito-borne diseases and disease dynamics fluctuates frequently and there could be serious public health consequences if the issues of insecticide resistance and outdoor transmission are not adequately addressed. For controlling both aquatic and adult stages, for several years now remote sensing data have been used together with predictive modelling for risk, incidence and detection of transmission hot spots and landscape profiles in relation to mosquito-borne pathogens. The field of drone-based remote sensing is under continuous change due to new technology development, operation regulations and innovative applications. In this review we outline the opportunities and challenges for integrating drones into vector surveillance (i.e. identification of breeding sites or mapping micro-environmental composition) and control strategies (i.e. applying larval source management activities or deploying genetically modified agents) across the mosquito life-cycle. We present a five-step systematic environmental mapping strategy that we recommend be undertaken in locations where a drone is expected to be used, outline the key considerations for incorporating drone or other Earth Observation data into vector surveillance and provide two case studies of the advantages of using drones equipped with multispectral cameras. In conclusion, recent developments mean that drones can be effective for accurately conducting surveillance, assessing habitat suitability for larval and/or adult mosquitoes and implementing interventions. In addition, we briefly discuss the need to consider permissions, costs, safety/privacy perceptions and community acceptance for deploying drone activities.

Estimating fine-scale changes in turbulence using the movements of a flapping flier.

All animals that operate within the atmospheric boundary layer need to respond to aerial turbulence. Yet little is known about how flying animals do this because evaluating turbulence at fine scales (tens to approx. 300 m) is exceedingly difficult. Recently, data from animal-borne sensors have been used to assess wind and updraft strength, providing a new possibility for sensing the physical environment. We tested whether highly resolved changes in altitude and body acceleration measured onboard solo-flying pigeons (as model flapping fliers) can be used as qualitative proxies for turbulence. A range of pressure and acceleration proxies performed well when tested against independent turbulence measurements from a tri-axial anemometer mounted onboard an ultralight flying the same route, with stronger turbulence causing increasing vertical displacement. The best proxy for turbulence also varied with estimates of both convective velocity and wind shear. The approximately linear relationship between most proxies and turbulence levels suggests this approach should be widely applicable, providing insight into how turbulence changes in space and time. Furthermore, pigeons were able to fly in levels of turbulence that were unsafe for the ultralight, paving the way for the study of how freestream turbulence affects the costs and kinematics of animal flight.

Comparison of drone and vessel-based collection of microbiological water samples in marine environments.

Many water quality metrics cannot be measured in situ and require collection of a physical sample for laboratory analysis. This includes microbiological samples for detection of fecal coliform bacteria in marine and freshwater systems which are a critical component of food safety programs for human consumption of bivalve shellfish worldwide. Water sample collection programs are typically vessel-based which can be time and resource intensive. In Canada, the Canadian Shellfish Sanitation Program aims to avoid consumption of contaminated molluscan bivalves by monitoring fecal coliform bacteria through vessel-based water sample collection. Uncrewed aerial vehicles or drones are becoming more commonly used for water sample collection given their relatively low cost but are rarely used to support microbiological analyses. A prerequisite for the acceptance of a new collection method for a regulatory program is to determine if the method of sample collection affects results. To assess this potential, we designed, developed, and tested a sampling device attached to the underside of a drone to collect water samples for bacteriological analysis. Drone and vessel-based samples were collected in the same location, at the same 20-cm depth, within a minute apart, at ten different geographic locations in coastal Nova Scotia waters to compare fecal coliform counts. Bacterial count estimates obtained from drone-collected samples were not significantly different than estimates obtained from vessel-collected samples (p < 0.5). Results from this study suggest novel water sampling techniques using drones could supplement or replace traditional vessel-based sampling methods.

Development and Testing of a UAV Laser Scanner and Multispectral Camera System for Eco-Geomorphic Applications.

While Uncrewed Aerial Vehicle (UAV) systems and camera sensors are routinely deployed in conjunction with Structure from Motion (SfM) techniques to derive 3D models of fluvial systems, in the presence of vegetation these techniques are subject to large errors. This is because of the high structural complexity of vegetation and inability of processing techniques to identify bare earth points in vegetated areas. Furthermore, for eco-geomorphic applications where characterization of the vegetation is an important aim when collecting fluvial survey data, the issues are compounded, and an alternative survey method is required. Laser Scanning techniques have been shown to be a suitable technique for discretizing both bare earth and vegetation, owing to the high spatial density of collected data and the ability of some systems to deliver dual (e.g., first and last) returns. Herein we detail the development and testing of a UAV mounted LiDAR and Multispectral camera system and processing workflow, with application to a specific river field location and reference to eco-hydraulic research generally. We show that the system and data processing workflow has the ability to detect bare earth, vegetation structure and NDVI type outputs which are superior to SfM outputs alone, and which are shown to be more accurate and repeatable, with a level of detection of under 0.1 m. These characteristics of the developed sensor package and workflows offer great potential for future eco-geomorphic research.

Comparison of Droplet Size, Coverage, and Drift Potential from UAV Application Methods and Ground Application Methods on Row Crops.

Worldwide, the use of uncrewed aerial vehicles (UAVs) for pesticide application has grown tremendously in the past decade. Their adoption has been slower for Midwestern row crops. This study compared droplet size, coverage, and drift potential of sprays from UAV application methods to those from ground (implement) sprayer methods on corn in the Midwest. Droplet sizes measured during UAV spray trials [geometric mean diameters of 179 and 112 µm for UAV (boom) and UAV (no boom), respectively] were substantially smaller than those deposited during implement spray trials [mean diameters of 303 and 423 µm for implement (regular) and implement (pulse)]. Droplet coverage was high and localized in the middle swath of the field for the UAV with boom (10 to 30 droplets cm-2) and with no boom (60 droplets cm-2). Droplet coverage was broader, covering the entire field width for the implement methods (10 to 40 droplets cm-2). Vertical coverage of droplets was more uniform for UAV methods than implement methods. Although the UAVs produced smaller droplets than the implement methods, we still observed greater potential for downwind pesticide drift during the implement spray trials. Because localized application may be beneficial for pest control and drift reduction, the findings indicate a strong potential for "spot" or "band" spray coverage using UAV methods. This is likely due to the smaller size, reduced spray volumes, and increased agility of UAVs as compared to more conventional methods.