@article{howell_haug_everman_leon_richardson_2023, title={Low carrier volume herbicide trials and UAAS support management efforts of giant salvinia (Salvinia molesta): a case study}, volume={5}, ISSN={["1939-747X"]}, url={https://doi.org/10.1017/inp.2023.16}, DOI={10.1017/inp.2023.16}, abstractNote={Abstract}, journal={INVASIVE PLANT SCIENCE AND MANAGEMENT}, author={Howell, Andrew W. and Haug, Erika J. and Everman, Wesley J. and Leon, Ramon G. and Richardson, Robert J.}, year={2023}, month={May} }
 @article{howell_leon_everman_mitasova_nelson_richardson_2023, title={Performance of unoccupied aerial application systems for aquatic weed management: Two novel case studies}, volume={5}, ISSN={["1550-2740"]}, url={https://doi.org/10.1017/wet.2023.32}, DOI={10.1017/wet.2023.32}, abstractNote={Abstract}, journal={WEED TECHNOLOGY}, author={Howell, Andrew W. and Leon, Ramon G. and Everman, Wesley J. and Mitasova, Helena and Nelson, Stacy A. C. and Richardson, Robert J.}, year={2023}, month={May} }
 @article{haug_howell_sperry_mudge_richardson_getsinger_2023, title={Simulated herbicide spray retention of commonly managed invasive emergent aquatic macrophytes}, volume={5}, ISSN={["1550-2740"]}, url={https://doi.org/10.1017/wet.2023.26}, DOI={10.1017/wet.2023.26}, abstractNote={Abstract}, journal={WEED TECHNOLOGY}, author={Haug, Erika J. and Howell, Andrew W. and Sperry, Benjamin P. and Mudge, Christopher R. and Richardson, Robert J. and Getsinger, Kurt D.}, year={2023}, month={May} }
 @article{perrin_jernigan_thayer_howell_leary_buckner_2022, title={Sensor Fusion with Deep Learning for Autonomous Classification and Management of Aquatic Invasive Plant Species}, volume={11}, ISSN={["2218-6581"]}, DOI={10.3390/robotics11040068}, abstractNote={Recent advances in deep learning, including the development of AlexNet, Residual Network (ResNet), and transfer learning, offer unprecedented classification accuracy in the field of machine vision. A developing application of deep learning is the automated identification and management of aquatic invasive plants. Classification of submersed aquatic vegetation (SAV) presents a unique challenge, namely, the lack of a single source of sensor data that can produce robust, interpretable images across a variable range of depth, turbidity, and lighting conditions. This paper focuses on the development of a multi-sensor (RGB and hydroacoustic) classification system for SAV that is robust to environmental conditions and combines the strengths of each sensing modality. The detection of invasive Hydrilla verticillata (hydrilla) is the primary goal. Over 5000 aerial RGB and hydroacoustic images were generated from two Florida lakes via an unmanned aerial vehicle and boat-mounted sonar unit, and tagged for neural network training and evaluation. Classes included “HYDR”, containing hydrilla; “NONE”, lacking SAV, and “OTHER”, containing SAV other than hydrilla. Using a transfer learning approach, deep neural networks with the ResNet architecture were individually trained on the RGB and hydroacoustic datasets. Multiple data fusion methodologies were evaluated to ensemble the outputs of these neural networks for optimal classification accuracy. A method incorporating logic and a Monte Carlo dropout approach yielded the best overall classification accuracy (84%), with recall and precision of 84.5% and 77.5%, respectively, for the hydrilla class. The training and ensembling approaches were repeated for a DenseNet model with identical training and testing datasets. The overall classification accuracy was similar between the ResNet and DenseNet models when averaged across all approaches (1.9% higher accuracy for the ResNet vs. the DenseNet).}, number={4}, journal={ROBOTICS}, author={Perrin, Jackson E. and Jernigan, Shaphan R. and Thayer, Jacob D. and Howell, Andrew W. and Leary, James K. and Buckner, Gregory D.}, year={2022}, month={Aug} }
 @article{howell_hofstra_heilman_richardson_2022, title={Susceptibility of native and invasive submersed plants in New Zealand to florpyrauxifen-benzyl in growth chamber exposure studies}, volume={15}, ISSN={["1939-747X"]}, url={https://doi.org/10.1017/inp.2022.22}, DOI={10.1017/inp.2022.22}, abstractNote={Abstract}, number={3}, journal={INVASIVE PLANT SCIENCE AND MANAGEMENT}, author={Howell, Andrew W. and Hofstra, Deborah E. and Heilman, Mark A. and Richardson, Robert J.}, year={2022}, month={Sep}, pages={133–140} }
 @article{howell_richardson_2019, title={Correlation of consumer grade hydroacoustic signature to submersed plant biomass}, volume={155}, ISSN={["1879-1522"]}, DOI={10.1016/j.aquabot.2019.02.001}, abstractNote={Invasive macrophytes, such as non-native Hydrilla verticillata, negatively affect lentic systems of the Southeastern United States by impeding recreational activities and power generation as well as disrupting intrinsic ecological function. Expenditures associated with aquatic weed management include costs accompanied with monitoring, mapping, and implementing control measures. Traditional biomass sampling techniques have been widely utilized to assess the extent and abundance of submersed aquatic vegetation (SAV) incursions, but often require significant labor inputs which limits repeatability, the scale of sampling, and the rapidness of processing. Advances in consumer available hydroacoustic technology and data post-processing platforms offer the opportunity to estimate SAV biomass at scale with reduced labor and economic requirements. Research was conducted at two North Carolina reservoirs to compare acoustically derived cloud-based biovolume estimations from an over-the-counter echosounder, to in situ hydrilla biomass measurements. Temporal patterns, spatial developments, and hydrilla biomass prediction models are presented. Biomass and biovolume measurements were positively correlated at both the Shearon Harris and Roanoke Rapids study locations. The most robust predictive equation employed generalized additive models (GAMs) from the Shearon Harris dataset which, described environmental parameters with the lowest error and greatest agreement compared to other verified models. Each biovolume to biomass relationship supported the initial hypothesis that as biovolume increases, SAV biomass increases in a positive, non-linear trend. Implications from this study may prove useful for comparing seasonal growth patterns, littoral occupancy, and herbicide treatment effects on a spatiotemporal level.}, journal={AQUATIC BOTANY}, author={Howell, Andrew W. and Richardson, Robert J.}, year={2019}, month={Apr}, pages={45–51} }
 @article{howell_richardson_2019, title={Estimating standing biomass of exotic macrophytes using sUAS}, volume={11008}, ISSN={["1996-756X"]}, DOI={10.1117/12.2519199}, abstractNote={With the advent of sUAS, research scientists and plant managers are capable of obtaining unique, fast, and low-cost quantitative data, which delivers many repeatable survey options. Benefits of autonomous sUAS platforms include minimal training, reduced human safety concerns, and creation of graphic outputs which may be readily viewed by any stakeholder who was not actively involved in the survey or management activity. Research conducted in the Wellington Region, New Zealand was used to evaluate consumer-grade sUAS technologies to map and estimate standing biomass of Manchurian Wild Rice (MWR), an exotic semi-aquatic grass which promotes flooding, and displacement of native flora and fauna. The goal of this research was to improve the speed and resolution of current survey strategies used to assess MWR among a lowland pasture site using unmanned systems and photogrammetry techniques. Image collection and data processing was conducted in a manner to provide a theoretic biomass estimation of remaining MWR following seasonal growth and herbicide applications. Post-processing methods and theories discussed attempt to identify and quantify MWR biomass using supervised imaging analysis, plant height modeling, and biomass collected in situ. The use of unmanned systems to map, monitor, and manage MWR is encouraged for future applications.}, journal={AUTONOMOUS AIR AND GROUND SENSING SYSTEMS FOR AGRICULTURAL OPTIMIZATION AND PHENOTYPING IV}, author={Howell, Andrew W. and Richardson, Robert J.}, year={2019} }
 @article{valdez_drake_burke_peterson_serenari_howell_2019, title={Predicting development preferences for fishing sites among diverse anglers}, volume={22}, ISSN={1083-8155 1573-1642}, url={http://dx.doi.org/10.1007/S11252-018-0800-8}, DOI={10.1007/s11252-018-0800-8}, number={1}, journal={Urban Ecosystems}, publisher={Springer Science and Business Media LLC}, author={Valdez, Rene X. and Drake, Michael D. and Burke, Conner R. and Peterson, M. Nils and Serenari, Christopher and Howell, Andrew}, year={2019}, month={Feb}, pages={127–135} }