Designing SkyMate: A Smart Weather System for Personalized Lifestyle

This work set out to tackle a common problem: weather apps show data, but people still have to work out what to do with it. The solution proposed here is SkyMate, a single mobile application that combines real-time weather, air quality, and location data with an AI recommendation layer, explaining conditions in plain language and turning them into suggestions on clothing, food, hydration, activity, sleep, travel, and health, while a Sky Moments feature connects weather with sky observation, photography, and astronomical-event awareness.   Survey data guided the core design decisions. A large majority of respondents (78.8%) said they would like an AI assistant that explains the weather in simple language, and simple explanation was the most-wanted AI feature (63.8%). Current apps averaged only 3.60 out of 5. Beyond that, the survey pointed to specific needs — rain and temperature at a glance, personalized alerts, travel and health guidance, and accurate, location-specific information — all of which shaped the requirements.   On the technical side, SkyMate was built with React Native and Expo for the mobile front end, Node.js and Express.js for the API, MongoDB Atlas for storage, Firebase Cloud Messaging for notifications, and Google Maps for location features. What has been built so far covers a dashboard, an AI weather assistant, lifestyle and health advisors, an air quality center, a travel planner, alerts, and Sky Moments.   It is worth being clear that this is a working first version, not a finished product. Regional-language support, farming advice, longer-range outlooks, and wearable integration are still on the roadmap, and the app still needs thorough usability, performance, and user-acceptance testing before its real-world effectiveness can be confirmed. In short, this project shows what a requirements-driven approach to a weather assistant can look like — combining forecasts, air quality, and personalized advice in one place lays useful groundwork for helping people act on the weather, not just read it.

[1]     P. Bauer, A. Thorpe, and G. Brunet, “The quiet revolution of numerical weather prediction,” Nature, vol. 525, no. 7567, pp. 47–55, 2015, doi: 10.1038/nature14956.   [2]     R. Lam et al., “Learning skillful medium-range global weather forecasting,” Science, vol. 382, no.  6677,  pp.  1416–1421,  2023,  doi: 10.1126/science.adi2336.   [3]     S. Ravuri et al., “Skilful precipitation nowcasting using deep generative models of radar,” Nature, vol. 597, no. 7878, pp. 672–677, 2021, doi: 10.1038/s41586-021-03854-z.   [4]     World Meteorological Organization (WMO), “Early Warnings for All: Executive Action Plan 2023–2027,” WMO, Geneva, Switzerland, 2022.   [5]     World Health Organization (WHO), WHO Global Air Quality Guidelines: Particulate Matter (PM2.5 and PM10), Ozone, Nitrogen Dioxide, Sulfur Dioxide and Carbon Monoxide. Geneva, Switzerland: WHO, 2021.   [6]     G. Adomavicius and A. Tuzhilin, “Context-aware recommender systems,” in Recommender Systems Handbook, F. Ricci, L. Rokach, B. Shapira, and P. B. Kantor, Eds. Boston, MA, USA: Springer, 2011, pp. 217–253, doi: 10.1007/978-0-387-85820-3_7.   [7]     Meta Platforms, “React Native Documentation,” React Native. [Online]. Available: https://reactnative.dev/docs/getting-started   [8]     OpenJS Foundation, “Node.js Documentation,” Node.js.[Online].   Available: https://nodejs.org/docs/latest/api/   [9]     OpenJS Foundation, “Express – Node.js Web Application Framework,” Express.js Documentation. [Online]. Available: https://expressjs.com/   [10]MongoDB, Inc., “MongoDB Atlas Documentation,” MongoDB Documentation. [Online].     Available: https://www.mongodb.com/docs/atlas/