Machine Learning & Environmental Data Summer Internship

Job Description

NIWC Pacific provides development, basic and applied science, test and evaluation, system engineering and integration, installation, and support of fielded Information Warfare systems from seabed to space. (Informally: NIWC provides the Navy with experts on software/cloud, sensors, signal analysis, data science, machine learning, and uncrewed vehicles).

Project: UUV Adaptive Sensing Leveraging Machine Learning and Environmental Data

The operational relevance is that Current UUV operations are ‘flying blind’, executing planned transects, maneuvers, and sensing regardless of environmental conditions. The goal is to predict UUV performance and data quality before and during missions to ultimately speed UUV operational timelines and reduce costs, and to potentially improve accuracy. The MK-18 UUV is outfitted with active sonar and is deployed to detect mine-like objects on the seabed, and will be used to validate our intuition regarding the utility of environmental data.

What will I be doing?

You will investigate one or both of the following research questions. The first hypothesis to test is “Can using environmental metadata from other instruments produce more accurate machine learning classification of the plankton images?”. This hypotheses requires the following experimental setup: A control result where networks are trained using conventional best practices, and a treatment where networks are trained using the described experimental methods, and then the results are compared. This will require using a standard deep learning library (we are currently using pytorch), but writing/using custom data loaders and neural network layers. The second research question is “Does the density and type of ‘marine snow’ and suspended sediment impact data quality &/or algorithm performance?”. The UVP-6 collects images of marine snow and sediment, but in most applications, this data is discarded by the biological oceanographer who is only interested in analyzing living ecosystem participants. Machine Learning will be used to classify particles as plankton vs. marine snow, and traditional image processing techniques, such as segmentation, will be used to further quantify the size and potentially orientation of the particles.

Under the guidance of a mentor, you will gain familiarity with the instrumentation used. Read about the CTD, Transmissometer, Flourometer, and UVP-6 (plankton camera), obtain familiarity with the datasets (e.g. review images/labels), obtain familiarity with pytorch on well-known data sets, create an outline of novel code required to conduct the assessments, write a custom code and validate code by using small subsets of the data and tiny networks, analyze initial results (e.g. write scripts, create figures), create additional trials/replicates, and draft and finalize research presentation (including updating any figures/percentages).

Why should I apply?

This fellowship provides the opportunity to independently utilize your skills and engage with experts in innovative ideas to move the proposed research forward.

Where will I be located? San Diego, California

What is the anticipated start date? June 2023

Exact start dates will be determined at the time of selection and in coordination with the selected candidate.

What is the appointment length?

This appointment is a ten week summer research appointment. Appointments may be extended depending on funding availability, project assignment, program rules, and availability of the participant.

What are the benefits?

You will receive a stipend to be determined by the sponsor. Stipends are typically based on a participant’s academic standing, discipline, experience, and research facility location. Other benefits may include the following:
• Health Insurance Supplement (Participants are eligible to purchase health insurance through ORISE)
• Relocation Allowance
• Training and Travel Allowance

About ORISE

This program, administered by Oak Ridge Associated Universities (ORAU) through its contract with the U.S. Department of Energy (DOE) to manage the Oak Ridge Institute for Science and Education (ORISE), was established through an interagency agreement between DOE and DoD. Participants do not enter into an employee/employer relationship with ORISE, ORAU, DoD or any other office or agency. Instead, you will be affiliated with ORISE for the administration of the appointment through the ORISE appointment letter and Terms of Appointment. Proof of health insurance is required for participation in this program. Health insurance can be obtained through ORISE. For more information, visit the ORISE Research Participation Program at the U.S. Department of Defense.