Abstract: Environment information such as precipitation, temperature, solar radiation, soil and ambient humidity is fundamental to identify the climate change patterns across a country. For example, the monthly and daily records of these meteorological variables are important to locate regions that present water deficit (droughts) or excess (floods). By, monitoring, analysing, and evaluating this data, it is not only possible to take effective actions to prevent any hard climate variation but also to improve the planning of superficial and underground hydrological resources in a region. The present paper describes the development process of a low-cost IoT system for automatic recording, monitoring, prediction of rainfall in urban and rural regions in Bolivia, using Arduino, sensors, GSM/GPRS communication, and Machine Learning. Additionally, the project considers the integration and processing of public data sources such as the System of Meteorological Information SISMET, which increased the accuracy of the project’s visualizations and predictions across Bolivia.