This project develops an explainable AI (XAI) model to assist in interpreting prostate cancer scans using biparametric MRI, offering faster and lower-cost imaging without contrast agents. Designed for surgeons and radiotherapists with limited radiology training, the model enhances diagnostic accuracy, consistency, and speed. With a scarcity of radiologic specialists in many parts of the Philippines, the tool strengthens cancer detection and treatment planning in both urban and rural hospitals.

This project develops a mental health chatbot built with input from professionals and real conversations to deliver culturally sensitive support anytime, anywhere. Through a user-centered approach and formal testing, the chatbot is designed to understand user needs and offer helpful responses and action plans. In areas where stigma, cost, or distance limit access to care, the chatbot can serve as a triage tool to support Filipinos and connect them to the right services more efficiently.

Arch(AI)ve uses artificial intelligence to digitize, virtually restore, and analyze Philippine artworks and cultural heritage materials from institutions such as the College of Fine Arts, the Vargas Museum, and national archives. It enhances preservation by digitally cleaning degraded paintings and architectural documents while uncovering stylistic connections among Filipino artists using global art databases. This pioneering work ensures that Filipino cultural assets are not only protected from age and environmental damage, but are also made more accessible to researchers, educators, and the public.

ENMESH introduces low-cost, locally developed multi-sensor systems for continuous biodiversity monitoring in UP campuses and Davao’s urban forests. By combining acoustic, visual, and environmental data analyzed through TinyML, it enables around-the-clock ecological tracking and big data generation. This initiative supports nature-based solutions to climate change and strengthens biodiversity protection efforts across Philippine cities.

MALAIMO equips Filipino fact-checkers with tools to combat online disinformation through LAKOM, a web-based archiving system, and PATUNAI, an AI model trained to analyze Tagalog posts. Together, they streamline detection, reduce manual workload, and support verification without replacing human judgment. In a country vulnerable to coordinated disinformation, this initiative enhances digital literacy and strengthens democratic resilience.

This project investigates the wide-reaching impacts of disruptive technologies—such as AI, virtual reality, and quantum computing—on higher education in the Philippines. Using futures research and complexity science, it explores how these innovations affect pedagogy, assessment, and institutional systems, with the UP System as a model. Through scenario-building and consensus-driven techniques, the study aims to guide strategic adaptation for Philippine universities navigating fast-moving digital disruptions.

MATIBAI develops data-driven models and AI-assisted tools to improve early diagnosis and treatment planning for TB and HIV co-infection, a growing public health concern in the Philippines. By integrating local health data, modeling disease dynamics, and identifying high-impact diagnostic indicators, the project supports more accurate, accessible, and timely screening. The work addresses major gaps in standard diagnostics and informs strategies for nationwide TB-HIV control in high-burden contexts.

The DiWA App is a virtual planning and disease surveillance platform developed by the Mindanao Center for Disease Watch and Analytics to empower local decision-makers. Building on prior work with LGUs and health agencies, the project is now scaling up to include predictive tools for more diseases, expanded infrastructure, and broader institutional partnerships. In a region with uneven health access, this app supports evidence-based interventions and lays the groundwork for long-term digital public health resilience.

ARCHAEO-VISION pioneers digital zooarchaeology in the Philippines by using AI and 3D modeling to analyze tens of thousands of vertebrate remains from sites like Callao Cave. A custom-built field-ready imaging platform helps automate sample classification, while advanced techniques like neural radiance fields and Gaussian splatting improve accuracy and speed. The project promotes heritage preservation, public engagement through citizen science, and new digital tools for archaeological and industrial applications.

This project enhances buffalo breeding in the Philippines by applying network science to optimize artificial insemination routes and using machine learning to analyze key reproductive success factors. Backed by data from the Philippine Carabao Center, it identifies how estrus type, season, and location influence calf birth outcomes. The results aim to improve food security, reduce delivery costs, and support sustainable agriculture—while also contributing to a pioneering PhD in Data Science at UP Diliman.

This project develops an AI-powered system that uses satellite imagery and machine learning to identify and allocate critical disaster resources like water, food, and shelter. Designed to be scalable nationwide, it includes crowdsourced validation, logistics optimization, and routing algorithms to guide real-time decision-making. By strengthening supply chain strategies in disaster response, the system enhances national preparedness and resilience in the Philippines.

Project DALISAI applies IoT and AI to support data-driven decision-making in durian farming by integrating real-time environmental monitoring, predictive modeling, and anomaly detection. It empowers farmers and stakeholders with actionable insights through an easy-to-use dashboard that visualizes soil and climate data critical to durian production. By enhancing operational efficiency and sustainability, the project strengthens Mindanao’s durian industry—giving local growers a competitive edge in the global export market.