A5047771767- Water Quality Monitoring and Analysis
- Marine and coastal ecosystems
- Water Quality Monitoring Technologies
- Aquatic Ecosystems and Phytoplankton Dynamics
- Hydrology and Watershed Management Studies
- Atmospheric and Environmental Gas Dynamics
- Remote Sensing in Agriculture
- Geographic Information Systems Studies
- Water Quality and Pollution Assessment
- Data Stream Mining Techniques
- Advanced Computational Techniques and Applications
- Environmental Monitoring and Data Management
- Geochemistry and Geologic Mapping
- Environmental Changes in China
- Spectroscopy and Chemometric Analyses
- Oil Spill Detection and Mitigation
- Advanced Research in Systems and Signal Processing
- Flood Risk Assessment and Management
- Reinforcement Learning in Robotics
- Hydrology and Sediment Transport Processes
- Satellite Image Processing and Photogrammetry
- Opinion Dynamics and Social Influence
- Robotic Path Planning Algorithms
- Infrared Target Detection Methodologies
- Fish Ecology and Management Studies
Michigan Technological University
2017-2024
Water quality issues continue to impact recreational and resource use of waterways in the Great Lakes across smaller inland water bodies their watersheds. With advancements small unmanned aerial systems (sUAS) sensor production, sUAS offer flexibility overcome several shortcomings satellite airborne systems, complement measurements this environment. In study, we deployed two different low-cost, boat launchable configurations instrumented with Ocean Optics STS hyperspectral Vis-NIR...
Harmful algal blooms (HABs) have become a major health and environmental concern in the Great Lakes. In 2014, severe HABs prompted State of Ohio to request NASA Glenn Research Center (GRC) assist with monitoring Lake Erie. The most notable species HAB is Microcystis aeruginosa, hepatotoxin producing cyanobacteria that responsible for liver complications humans other fauna come contact these blooms. GRC conducts semiweekly flights order gather up-to-date imagery regarding blooms' spatial...
The hyperspectral imaging system (HSI) developed by the NASA Glenn Research Center was used from 2015 to 2017 collect high spatial resolution data over Lake Erie and Ohio River. Paired with a vicarious correction approach implemented Michigan Tech Institute, radiance collected HSI can be converted quality reflectance which generate near-real time (within 24 h) products for monitoring of harmful algal blooms using existing algorithms. method relies on spectrally constant target normalize...
Озеро Мичиган относится к олиготрофному типу водоемов. Сильнее всего это проявляется в прибрежной зоне, где гидрологический режим вод формируется под действием различных природных и антропогенных факторов, протекающих на водосборной территории. Влияние дна достаточно сильно искажает регистрируемый спутником сигнал, препятствуя выполнению дистанционного зондирования параметров качества воды этой части озера. Для извлечения из спутниковых снимков оптически мелких районах озера был разработан...
Topological maps are a common framework for enabling autonomous robotic navigation. To be effective exploration the must able to generated quickly and compact enough store on lightweight hardware. Here we propose novel 3D topological map called Sphere-Graph which has adaptive edge lengths, can generated, used semantically identify hallways rooms produce representation of complex environments. We give examples large urban cave
We explore the generality of Reinforcement Learning (RL) agents on unseen environment configurations by analyzing behavior an agent tasked with traversing a graph based from starting position to goal position. find that training single task is likely result in inflexible policies do not respond well change. Instead, wide variety scenarios offers best chance developing flexible policy, at expense increased difficulty.
The development of automated opponents in video games has been part game since the very beginning field. advent modern AI approaches such as reinforcement learning opened door to a wide variety flexible and adaptive opponents. However, challenges producing realistic persist, namely scalability generalizability. Scalability is particular importance when many individual are required act cohesively over long distances, but this makes more difficult. This paper presents novel architecture...
With the exception of a few areas, Lake Michigan (LM) is an oligotrophic clear water body. It predominantly in its littoral zone where ecology-relevant processes unfold due to variety natural and anthropogenic forcings arising from watershed. However, bottom influence there strong enough contaminate at-satellite signal, thus impeding remote sensing quality parameters within coastal zone. A new bio-optical retrieval algorithm, based on forward radiation transfer model, LM specific...