Abstract
Capstone Technical Report Abstract
My internship at the Naval Surface Warfare Center Dahlgren Division was centered around designing a scalable, user-friendly graphical user interface (GUI) to provide a solution to a mission-critical problem. Addressing the need for robust software in high-stakes environments, like in wartime, I employed a Model-View-Controller (MVC) architectural framework using the software language Python. The GUI integrated real-time dashboards, input validation, and encrypted data management via SQLite, aligning with defense-grade security standards.
The solution successfully met stakeholder requirements, earning management approval. I was able to achieve many of my goals, including streamlining data synchronization, providing dynamic user feedback to those using the system, and using a responsive design optimized for high-risk and high-pressure scenarios. Some of the stakeholder feedback emphasized the GUI’s potential as a foundation for future work, such as peer-to-peer synchronization and API integrations. On the other hand, areas that stakeholders highlighted that could be improved were the presence of some scalability and refinement issues.
This project highlighted the critical role that software engineering principles—such as algorithm design, object-oriented programming, and system analysis—have in national defense. The importance of teamwork, iterative development, and stakeholder engagement in delivering impactful solutions was also underscored. I learned many soft skills throughout my internship experience, such as the ability to put together and deliver a presentation to stakeholders and colleagues more senior than I. Future work will focus on expanding the GUI’s ability to analyze larger datasets, advanced dashboard customization, and simulated environment testing to ensure long-term usefulness. By successfully bridging academic knowledge and my love of learning with real-world application, this internship deepened my love for computer science and demonstrated how structured, user-centered software solutions can help bring security into the future.
STS Project Abstract
My Science, Technology, and Society (STS) paper explores the integration of artificial intelligence (AI) to enhance extinction forecasting and conservation strategies for animals in Africa, with a focus on the critically endangered black rhinoceroses (Diceros bicornis). Focusing on 11 countries, namely Chad, Côte d'Ivoire, Kenya, Tanzania, Zambia, Malawi, Mozambique, Zimbabwe, Botswana, Namibia, and South Africa, with historical black rhino populations, my research uses machine learning models—including random forests, logistic regression, and predictive forecasting—to analyze a self-compiled dataset of poaching incidents, habitat loss, agricultural expansion, and climate variables from 1980 to 2021.
The results of the machine learning analysis identified habitat destruction and agricultural land use with a correlation of 0.59 and poaching with a correlation of 0.53 as primary drivers of population decline, with climate factors playing a minimal role. AI models demonstrated the potential to predict extinction risks and prioritize proactive interventions, such as targeted anti-poaching measures.
My study highlights ethical and political challenges present in this topic, including data ownership disparities and biases stemming from political instability in regions like Zimbabwe and Mozambique, which have a detrimental effect on conservation efforts. I emphasize the importance of collaborative frameworks that bring together local stakeholders, AI developers, and policymakers to minimize inequalities within the field. While the dataset was limited to publicly available data, my findings highlight AI’s ability to complement traditional methods by offering real-time, data-driven insights. Future work includes expanding the dataset with satellite imagery and genetic data, broadening the scope of this research to other endangered species, and addressing the socio-economic impacts on local communities involved. By bridging computer science and ecology, my research contributes to scalable, ethical conservation tools, emphasizing the need for interdisciplinary collaboration to mitigate biodiversity loss globally.
Bridge Between Technical and STS Project
Both my technical project and STS project—developing a GUI for defense operations and applying AI to black rhino conservation—although very different, both demonstrate a cohesive interdisciplinary approach to solving complex, high-stakes challenges through technology while balancing ethical and political considerations. Both projects emphasize the critical role of structured software design and data-driven decision-making. Throughout my internship, my use of the MVC framework ensured my GUI was modular and scalable and enabled secure, real-time data management to operate well for high-risk missions. Likewise, my conservation research leveraged machine learning models to analyze a self-compiled dataset, identifying key factors driving extinction risk in black rhinos. Both technical parts of my research highlight the importance of reliability and adaptability, whether that is in optimizing defense workflows or predicting biodiversity threats.
The projects are further bridged because of their ethical and collaborative considerations. My GUI prioritized user-centered design and stakeholder feedback to enhance operational efficiency, mirroring my conservation study’s focus on equitable data practices and partnerships with local communities. Also, my GUI’s future plans to handle large datasets align with my AI project’s future plans of integrating satellite imagery and genetic data to better predictive models. Together, both of these projects illustrate how software engineering and AI can bridge disparate fields—national security and ecology—by transforming raw data into actionable insights, fostering resilience in both human and natural systems through innovation, collaboration, and ethical foresight.
