A SELF-POWERED ENERGY-HARVESTING DEVICE FOR REMOTE MONITORING APPLICATIONS Natural disasters can cause severe harm to human life, infrastructure, and ecosystems. Although prediction remains challenging, early detection is vital for timely intervention and damage mitigation. Many monitoring systems rely on batteries that require regular replacement, limiting long-term reliability and increasing maintenance costs in remote environments. To help address this challenge, I explored renewable, self-powered energy technologies. I designed and built a triboelectric nanogenerator (TENG), a device that converts mechanical motion into electricity through triboelectricity and electrostatic induction. TENGs offer a lightweight, low-cost, and environmentally sustainable power source for small electronic systems. I constructed a working prototype and supporting circuit capable of storing generated energy and powering an LED. I also investigated how material combinations, surface area, operating modes, and multi-unit configurations affect electrical output and overall performance. Building this device inspired me to tackle a larger challenge in triboelectric research: identifying high-performance material combinations efficiently. I independently assembled and curated experimental datasets from published studies, then designed a graph neural network (GNN) model that captures relationships between materials and predicts promising triboelectric pairings. By combining materials science with artificial intelligence, this work aims to accelerate the development of next-generation self-powered sensors and energy-harvesting systems, and was recently accepted for presentation at an IEEE conference. See More Here: https://www.youtube.com/watch?v=Qxf3ddyxS5I