Search Constraints
Filtering by:
Discipline
Engineering
Remove constraint Discipline: Engineering
Discipline
Science
Remove constraint Discipline: Science
« Previous |
1 - 10 of 66
|
Next »
Number of results to display per page
View results as:
Search Results
-
- Creator:
- Shah, Bhavarth
- Description:
- The three approaches used three distinct datasets named as follows: Historicalwater_levels.csv, Historical_Precipitation.csv, and Bayesian Statistical dataset.csv. These files are accessible using Microsoft Office or similar software. The machine learning models are developed in Jupyter Notebook (.ipynb) files, named according to the datasets they utilize. However, for the third approach, the models are named Random Forest, LSTM Model Base, and Multivariate LSTM Models. More details are available on the Shah_Bhavarth_Readme.txt. These notebooks can be accessed through Python, Project Jupyter, or Google Colab, and dependencies include libraries such as Pandas, NumPy, Matplotlib, Scikit-learn, Keras, and TensorFlow. The supplementary material also includes Excel files for stage-curve calculations and diversions, named Water_levels_Stage_Curve_Calculations1970-2018.xlsx and Diversions_calculation.xlsx, respectively.
- Keyword:
- Machine learning, Forecasting, Water levels, Mono lake, and Hydrology
- Citation to related publication:
- Shah, Bhavarth. 2024. "Mono Lake Water Levels Forecasting Using Machine Learning." Master’s thesis, University of Michigan, School for Environment and Sustainability. ORCID iD: 0000-0002-2391-8610. https://dx.doi.org/10.7302/22659
- Discipline:
- Science and Engineering
-
- Creator:
- Hong, Yi, Fry, Lauren M., Orendorf, Sophie, Ward, Jamie L., Mroczka, Bryan, Wright, David, and Gronewold, Andrew
- Description:
- Accurate estimation of hydro-meteorological variables is essential for adaptive water management in the North American Laurentian Great Lakes. However, only a limited number of monthly datasets are available nowadays that encompass all components of net basin supply (NBS), such as over-lake precipitation (P), evaporation (E), and total runoff (R). To address this gap, we developed a daily hydro-meteorological dataset covering an extended period from 1979 to 2022 for each of the Great Lakes. The daily P and E were derived from six global gridded reanalysis climate datasets (GGRCD) that include both P and E estimates, and R was calculated from National Water Model (NWM) simulations. Ensemble mean values of the difference between P and E (P – E) and NBS were obtained by analyzing daily P, E, and R. Monthly averaged values derived from our new daily dataset were validated against existing monthly datasets. This daily hydro-meteorological dataset has the potential to serve as a validation resource for current data and analysis of individual NBS components. Additionally, it could offer a comprehensive depiction of weather and hydrological processes in the Great Lakes region, including the ability to record extreme events, facilitate enhanced seasonal analysis, and support hydrologic model development and calibration. The source code and data representation/analysis figures are also made available in the data repository.
- Keyword:
- Great Lakes, Hydrometeorological, National Water Model, Daily, Overlake precipitation, Overlake evaporation, Total runoff, Net Basin Supply, and Water Balance
- Discipline:
- Science and Engineering
-
- Creator:
- Agnit Mukhopadhyay, Sanja Panovska, Raven Garvey, Michael Liemohn, Natalia Ganjushkina, Austin Brenner, Ilya Usoskin, Michael Balikhin, and Daniel Welling
- Description:
- In the recent geological past, Earth’s magnetic field reduced to 4% of the modern values and the magnetic poles moved severely apart from the geographic poles causing the Laschamps geomagnetic excursion, which happened about 41 millennia ago. The excursion lasted for about two millennia, with the peak strength reduction and dipole tilting lasting for a shorter period of 300 years. During this period, the geomagnetic field exhibited significant differences from the modern nearly-aligned dipolar field, causing non-dipole variables to mimic a magnetic field akin to the outer planets while displaying a significantly reduced magnetic strength. However, the precise magnetospheric configuration and their electrodynamic coupling with the atmosphere have remained critically understudied. This dataset contains the first space plasma investigation of the exact geomagnetic conditions in the near-Earth space environment during the excursion. The study contains a full 3D reconstruction and analysis of the geospace system including the intrinsic geomagnetic field, magnetospheric system and the upper atmosphere, linked in sequence using feedback channels for distinct temporal epochs. The reconstruction was conducted using the LSMOD.2 model, Block Adaptive Tree Solar wind-Roe-Upwind Scheme (BATS-R-US) Model and the MAGnetosphere-Ionosphere-Thermosphere (MAGNIT) Auroral Precipitation Model, all of which are publicly-available models. The dataset contains the raw data from each of these models, in addition to the images/post-processing results generated using these models. Paleomagnetic data produced by LSMOD.2 can be visualized using a combination of linear plotting and contour plotting tools available commonly in visualization software like Python (e.g. Python/Matplotlib) or MATLAB. Standard tools to read and visualize BATS-R-US and MAGNIT output are already publicly available using IDL and Python (see SpacePy/PyBats - https://spacepy.github.io/pybats.html). For information and details about the post-processed data, visualization and analysis, please contact the authors for details. The anthropological dataset can be visualized using a shape file reader (e.g. Python/GeoPandas) and a linear plotting tool (e.g. Python/Matplotlib).
- Discipline:
- Engineering and Science
-
- Creator:
- Brenner, Austin M
- Description:
- Results of computer simulation of near Earth space is looked at in a new way to understand how energy moves around the global system. It is found that in addition to a pathway of energy from the outside into the system and back again there is an internal loop which recirculates energy. These new methods will greatly improve our understanding how the whole magnetosphere system evolves and will help address evolution of processes that have space weather impacts.
- Keyword:
- Energy flux, geospace, magnetopause, magnetosphere, poynting flux, and reconnection
- Citation to related publication:
- Austin Brenner, Tuija I. Pulkkinen, Qusai Al Shidi, et al. Dissecting Earth’s Magnetosphere: 3D Energy Transport in a Simulation of a Real Storm Event. ESS Open Archive . August 04, 2023.
- Discipline:
- Science and Engineering
-
- Creator:
- Wallace, Dylan M, Benyamini, Miri, Nason-Tomaszewski, Samuel R, Costello, Joseph T, Cubillos, Luis H, Mender, Matthew J, Temmar, Hisham, Willsey, Matthew S, Patil, Parag P, Chestek, Cynthia A, and Zacksenhouse, Miriam
- Description:
- This is data from Wallace, Benyamini et al., 2023, Journal of Neural Engineering. There are two sets of data included: 1. Neural features and error labels used to train error classifiers for each day used in the study 2. Trial data from an example experiment day (Monkey N, Day 6), with runs for offline calibration, online brain control, error monitoring, and error correction. The purpose of this study was to investigate the use of error signals in motor cortex to improve brain-machine interface (BMI) performance for control of two finger groups. All data is contained in .mat files, which can be opened using MATLAB or the Python SciPy library.
- Keyword:
- Brain-machine interface (BMI), Error detection, and Neural recording
- Citation to related publication:
- Wallace, D. M., Benyamini, M., Nason-Tomaszewski, S. R., Costello, J. T., Cubillos, L. H., Mender, M. J., Temmar, H., Willsey, M. S., Patil, P. G., Chestek, C. A., & Zacksenhouse, M. (2023). Error detection and correction in intracortical brain–machine interfaces controlling two finger groups. Journal of Neural Engineering, 20(4), 046037. https://doi.org/10.1088/1741-2552/acef95
- Discipline:
- Engineering, Science, and Health Sciences
-
- Creator:
- Brian, Chen
- Description:
- The procedure followed while creating this data is summarized in Section II of Chen, Brian, et al. "Behavioral cloning in atari games using a combined variational autoencoder and predictor model." 2021 IEEE Congress on Evolutionary Computation (CEC). IEEE, 2021. This data is not a result of a research but an intermediate product that is used in research. This dataset is generated to train a behavioral cloning framework from gameplay screen captures and keystrokes of an "expert" player. The RL agent that is trained using "RL Baselines Zoo package" acts as the "expert" player, whose decision making process we desire to learn. In addition to behavioral cloning experiments, this dataset is further used to demonstrate the efficacy of a novel incremental tensor decomposition algorithm on image-based data streams.
- Keyword:
- Imitation Learning, Behavioral Cloning, Reinforcement Learning, Machine Learning, and Gameplay Data
- Citation to related publication:
- Chen, Brian, et al. "Behavioral cloning in atari games using a combined variational autoencoder and predictor model." 2021 IEEE Congress on Evolutionary Computation (CEC). IEEE, 2021., Aksoy, Doruk, et al. "An Incremental Tensor Train Decomposition Algorithm." arXiv preprint arXiv:2211.12487 (2022)., and Chen, Brian, et al. "Low-Rank Tensor-Network Encodings for Video-to-Action Behavioral Cloning", forthcoming
- Discipline:
- Engineering and Science
-
- Creator:
- Elvati, Paolo, Luyet, Chloe, Wang, Yichun, Liu, Changjiang, VanEpps, J. Scott, Kotov, Nicholas A., and Violi, Angela
- Description:
- Amyloid nanofibers are abundant in microorganisms and are integral components of many biofilms, serving various purposes, from virulent to structural. Nonetheless, the precise characterization of bacterial amyloid nanofibers has been elusive, with incomplete and contradicting results. The present work focuses on the molecular details and characteristics of PSMa1-derived functional amyloids present in Staphylococcus aureus biofilms, using a combination of computational and experimental techniques, to develop a model that can aid the design of compounds to control amyloid formation. Results from molecular dynamics simulations, guided and supported by spectroscopy and microscopy, show that PSMa1 amyloid nanofibers present a helical structure formed by two protofilaments, have an average diameter of about 12 nm, and adopt a left-handed helicity with a periodicity of approximately 72 nm. The chirality of the self-assembled nanofibers, an intrinsic geometric property of its constituent peptides, is central to determining the fibers' lateral growth.
- Keyword:
- molecular self-assembly, computational nanotechnology, nanobiotechnology, and structural properties
- Citation to related publication:
- Paolo Elvati, Chloe Luyet, Yichun Wang, Changjiang Liu, J. Scott VanEpps, Nicholas A. Kotov, and Angela Violi ACS Applied Nano Materials 2023 6 (8), 6594-6604 DOI: 10.1021/acsanm.3c00174
- Discipline:
- Engineering and Science
-
- Creator:
- Thompson, Ellen P. and Ellis, Brian R.
- Description:
- Accurate prediction of physical alterations in carbonate reservoirs under dissolution is critical for development of subsurface energy technologies. The impact of mineral dissolution on flow characteristics depends on the connectivity and tortuosity of the pore network. Persistent homology is a tool from algebraic topology that describes the size and connectivity of topological features. When applied to 3D X-ray computed tomography (XCT) imagery of rock cores, it provides a novel metric of pore network heterogeneity. Prior works have demonstrated the efficacy of persistent homology in predicting flow properties in numerical simulations of flow through porous media. Its ability to combine size, spatial distribution, and connectivity information make it a promising tool for understanding reactive transport in complex pore networks, yet limited work has been done to apply persistence analysis to experimental studies on natural rocks. In this study, three limestone cores were imaged by XCT before and after acid-driven dissolution flow through experiments. Each XCT scan was analyzed using persistent homology. In all three rocks, permeability increase was driven by the growth of large, connected pore bodies. The two most homogenous samples saw an increased effect nearer to the flow inlet, suggesting emerging preferential flow paths as the reaction front progresses. The most heterogeneous sample showed an increase in along-core homogeneity during reaction. Variability of persistence showed moderate positive correlation with pore body size increase. Persistence heterogeneity analysis could be used to anticipate where greatest pore size evolution may occur in a reservoir targeted for subsurface development, improving confidence in project viability.
- Keyword:
- Carbonate dissolution, X-ray computed tomography, Porous media, Topology, and Persistent homology
- Citation to related publication:
- Thompson, E.P.; Ellis, B.R. (2023) Persistent Homology as a Heterogeneity Metric for Predicting Pore Size Change in Dissolving Carbonates. In Review.
- Discipline:
- Science and Engineering
-
Resources for Training Machine Learning Algorithms Using CAM6 Simple Physics Packages
User Collection- Creator:
- Limon, Garrett
- Description:
- The collection contains the code and the data used to train machine learning algorithms to emulate simplified physical parameterizations within the Community Atmosphere Model (CAM6). CAM6 is the atmospheric general circulation model (GCM) within the Community Earth System Model (CESM) framework, developed by the National Center for Atmospheric Research (NCAR). GCMs are made up of a dynamical core, responsible for the geophysical fluid flow calculations, and physical parameterization schemes, which estimate various unresolved processes. Simple physics schemes were used to train both random forests and neural networks in the interest of exploring the feasibility of machine learning techniques being used in conjunction with the dynamical core for improved efficiency of future climate and weather models. The results of the research show that various physical forcing tendencies and precipitation rates can be effectively emulated by the machine learning models.
- Keyword:
- Machine Learning, Climate Modeling, and Physics Emulators
- Discipline:
- Science and Engineering
2Works -
- Creator:
- Limon, Garrett C.
- Description:
- The work guides the processing of CAM6 data for use in machine learning applications. We also provide workflow scripts for training both random forests and neural networks to emulate physic s schemes from the data, as well as analysis scripts written in both Python and NCL in order to process our results.
- Keyword:
- Machine Learning, Climate Modeling, and Physics Emulation
- Citation to related publication:
- Limon, G. C., Jablonowski, C. (2022) Probing the Skill of Random Forest Emulators for Physical Parameterizations via a Hierarchy of Simple CAM6 Configurations [Pre Print]. ESSOAr. https://10.1002/essoar.10512353.1
- Discipline:
- Engineering and Science