OBJECTIVES/GOALS: The aim of this study was to design and implement the Pharos application to map the cellular network support structure around Lake Victoria in Western Kenya. Additionally, the Pharos app was used to collect images of disease-relevant vector and plant life surrounding the study sites to train a computer vision algorithm to map disease-relevant areas. METHODS/STUDY POPULATION: Pharos was provided to a 4-person team of healthcare workers. The app was pre-loaded on both iOS and Android devices to be used during the course of normal field activity. Pharos ambiently collects network data and the team was asked to capture images of landmarks relevant to their work in schistosomiasis control. The field team traveled to 4 counties of differing schistosomiasis risk surrounding Kisumu, Kenya in autumn 2022 and will return to these areas in early spring 2023. Cell signal indicators (upload and download speed) were collected and asynchronously uploaded to a database for further analysis. Additionally, all landmark images (cell network towers, landmarks (e.g. schools, churches, public centers), plant life, vectors, and water bodies) were recorded and tagged with GPS coordinates and time stamps. RESULTS/ANTICIPATED RESULTS: Iterative development powered by small, informal, user-centered focus group discussions with the field team led to several key adaptations to the Pharos software. On the first deployment, 1,297 unique upload and download events were recorded across 3 Kenyan cell providers and 1 American provider. 1,197 data points were collected in Kenya using both Android and iOS devices using several versions of the Pharos application. 154 unique landmarks were photographed, but a distinct difference in landmark recording was observed between devices, prompting a transition to iOS-only data collection. Of the landmarks recorded, the majority (120, 77.9%) were landmarks or cell network towers, while 22.1% were water bodies, plant life, or schistosomiasis vectors. DISCUSSION/SIGNIFICANCE: For the first time, high-detail maps of cellular signal and critical schistosomiasis-related landmarks were generated. Future work on this project is focused on training computer vision algorithms using the captured images of environmental and ecological factors to isolate possible areas of human disease transmission.