Abstract

Approximately 2/3 of California’s water comes from snow in the Sierra Nevada. With better management, California’s existing water supply could go further to meeting the needs of the state’s urban and agricultural uses. Currently, California’s water reservoirs are controlled and regulated using forecasts based upon more than 75 years of historical data. In the face of global climate change, these forecasts are becoming increasingly inadequate to precisely manage water resources. We are implementing an intelligent water infrastructure system that leverages the newest frontiers of information technology. The system is based on blending real-time ground based measurements and satellite and LiDAR remote imaging. To this end we have implemented the world’s largest wireless sensor network covering the upper reaches of the 4500 km2 American River Basin. We are nearing 15 subnetworks, each covering approximately a 2 km2 area with 10 ~ 15 sensor stations and 35 sensing relay stations. We measure snow depth, temperature, relative humidity, solar radiation, soil moisture and temperature, and matric suction. Real-time data can be seen at glaser.berkeley.edu/wsn. This real-time data will be used by the Sacramento Municipal Utility District and the Placer County Water Agency to optimize their hydro-electric operations. I will present the background of wireless sensor networks, our unique hardware, new machine learning methods to pick representative sites and locate sensors, and representative data.