The recent developments of new deep learning architectures create opportunities to accurately classify high-resolution unoccupied aerial system (UAS) images of natural coastal systems and mandate continuous evaluation of algorithm performance. We evaluated the performance of the U-Net and DeepLabv3 deep convolutional network architectures and two traditional machine learning techniques (support vector machine (SVM) and random forest (RF)) applied to seventeen coastal land cover types in west Florida using UAS multispectral aerial imagery and canopy height models (CHM). Twelve combinations of spectral bands and CHMs were used. Our results using the spectral bands showed that the U-Net (83.80–85.27% overall accuracy) and the DeepLabV3 (75.20–83.50% overall accuracy) deep learning techniques outperformed the SVM (60.50–71.10% overall accuracy) and the RF (57.40–71.0%) machine learning algorithms. The addition of the CHM to the spectral bands slightly increased the overall accuracy as a whole in the deep learning models, while the addition of a CHM notably improved the SVM and RF results. Similarly, using bands outside the three spectral bands, namely, near-infrared and red edge, increased the performance of the machine learning classifiers but had minimal impact on the deep learning classification results. The difference in the overall accuracies produced by using UAS-based lidar and SfM point clouds, as supplementary geometrical information, in the classification process was minimal across all classification techniques. Our results highlight the advantage of using deep learning networks to classify high-resolution UAS images in highly diverse coastal landscapes. We also found that low-cost, three-visible-band imagery produces results comparable to multispectral imagery that do not risk a significant reduction in classification accuracy when adopting deep learning models.

Lidar from small unoccupied aerial systems (UAS) is a viable method for collecting geospatial data associated with a wide variety of applications. Point clouds from UAS lidar require a means for accuracy assessment, calibration, and adjustment. In order to carry out these procedures, specific locations within the point cloud must be precisely found. To do this, artificial targets may be used for rural settings, or anywhere there is a lack of identifiable and measurable features in the scene. This paper presents the design of lidar targets for precise location based on geometric structure. The targets and associated mensuration algorithm were tested in two scenarios to investigate their performance under different point densities, and different levels of algorithmic rigor. The results show that the targets can be accurately located within point clouds from typical scanning parameters to <2 cm $\sigma ,$ and that including observation weights in the algorithm based on propagated point position uncertainty leads to more accurate results.

Emerging infectious diseases of wildlife have markedly increased in the last few decades. Unsustainable, continuous, and rapid alterations within and between coupled human and natural systems have significantly disrupted wildlife disease dynamics. Direct and indirect anthropogenic effects, such as climate change, pollution, encroachment, urbanization, travel, and trade, can promote outbreaks of infectious diseases in wildlife. We constructed a coupled human and natural systems framework identifying three main wildlife disease risk factors behind these anthropogenic effects: (i) immune suppression, (ii) viral spillover, and (iii) disease propagation. Through complex and convoluted dynamics, each of the anthropogenic effects and activities listed in our framework can lead, to some extent, to one or more of the identified risk factors accelerating disease outbreaks in wildlife. In this review, we present a novel framework to study anthropogenic effects within coupled human and natural systems that facilitate the emergence of infectious disease involving wildlife. We demonstrate the utility of the framework by applying it to Fibropapillomatosis disease of marine turtles. We aim to articulate the intricate and complex nature of anthropogenically exacerbated wildlife infectious diseases as multifactorial. This paper supports the adoption of a One Health approach and invites the integration of multiple disciplines for the achievement of effective and long-lasting conservation and the mitigation of wildlife emerging diseases.

A unique drone-based system for underwater mapping (bathymetry) was developed at the University of Florida. The system, called the “Bathy-drone”, comprises a drone that drags, via a tether, a small vessel on the water surface in a raster pattern. The vessel is equipped with a recreational commercial off-the-shelf (COTS) sonar unit that has down-scan, side-scan, and chirp capabilities and logs GPS-referenced sonar data onboard or transmitted in real time with a telemetry link. Data can then be retrieved post mission and plotted in various ways. The system provides both isobaths and contours of bottom hardness. Extensive testing of the system was conducted on a 5 acre pond located at the University of Florida Plant Science and Education Unit in Citra, FL. Prior to performing scans of the pond, ground-truth data were acquired with an RTK GNSS unit on a pole to precisely measure the location of the bottom at over 300 locations. An assessment of the accuracy and resolution of the system was performed by comparison to the ground-truth data. The pond ground truth had an average depth of 2.30 m while the Bathy-drone measured an average 21.6 cm deeper than the ground truth, repeatable to within 2.6 cm. The results justify integration of RTK and IMU corrections. During testing, it was found that there are numerous advantages of the Bathy-drone system compared to conventional methods including ease of implementation and the ability to initiate surveys from the land by flying the system to the water or placing the platform in the water. The system is also inexpensive, lightweight, and low-volume, thus making transport convenient. The Bathy-drone can collect data at speeds of 0–24 km/h (0–15 mph) and, thus, can be used in waters with swift currents. Additionally, there are no propellers or control surfaces underwater; hence, the vessel does not tend to snag on floating vegetation and can be dragged over sandbars. An area of more than 10 acres was surveyed using the Bathy-drone in one battery charge and in less than 25 min.

Fibropapillomatosis (FP) is a neoplastic disease most often found in green turtles (Chelonia mydas). Afflicted turtles are burdened with potentially debilitating tumors concentrated externally on the soft tissues, plastron, and eyes and internally on the lungs, kidneys, and the heart. Clinical signs occur at various levels, ranging from mild disease to severe debilitation. Tumors can both progress and regress in affected turtles, with outcomes ranging from death due to the disease to complete regression. Since its official description in the scientific literature in 1938, tumor growth rates have been rarely documented. In addition, FP tumors come in two very different morphologies; yet, to our knowledge, there have been no quantified differences in growth rates between tumor types. FP tumors are often rugose in texture, with a polypoid to papillomatous morphology, and may or may not be pedunculated. In other cases, tumors are smooth, with a skin-like surface texture and little to no papillose structures. In our study, we assessed growth-rate differences between rugose and smooth tumor morphologies in a rehabilitation setting. We measured average biweekly tumor growth over time in green turtles undergoing rehabilitation at the University of Florida Whitney Laboratory Sea Turtle Hospital in St. Augustine, Florida, and compared growth between rugose and smooth tumors. Our results demonstrate that both rugose and smooth tumors follow a similar active growth progression pattern, but rugose tumors grew at significantly faster rates (p = 0.013) than smooth ones. We also documented regression across several examined tumors, ranging from −0.19% up to −10.8% average biweekly negative growth. Our study offers a first-ever assessment of differential growth between tumor morphologies and an additional diagnostic feature that may lead to a more comprehensive understanding and treatment of the disease. We support the importance of tumor morphological categorization (rugose versus smooth) being documented in future FP hospital- and field-based health assessments.