The NASA Time History of Events and Macroscale Interactions during Substorms (THEMIS) project is intended to investigate magnetospheric substorm phenomena, which are the manifestations of a basic instability of the magnetosphere and a dominant mechanism of plasma transport and explosive energy release. The major controversy in substorm science is the uncertainty as to whether the instability is initiated near the Earth, or in the more distant > 20 Re magnetic tail. THEMIS will discriminate between the two possibilities by using five in-situ satellites and ground-based all-sky imagers and magnetometers, and inferring the propagation direction by timing the observation of the substorm initiation at multiple locations in the magnetosphere. An array of stations, consisting of 20 all-sky imagers (ASIs) and 30-plus magnetometers, has been developed and deployed in the North American continent, from Alaska to Labrador, for the broad coverage of the nightside magnetosphere. Each ground-based observatory (GBO) contains a white light imager that takes auroral images at a 3-second repetition rate ("cadence") and a magnetometer that records the 3 axis variation of the magnetic field at 2 Hz frequency. The stations return compressed images, "thumbnails," to two central databases: one located at UC Berkeley and the other at the University of Calgary, Canada. The full images are recorded at each station on hard drives, and these devices are physically returned to the two data centers for data copying. All data are made available for public use by scientists in "browse products," accessible by using internet browsers or in the form of downloadable CDF data files (the "browse products" are described in detail in a later section). Twenty all-sky imager stations are installed and running at the time of this publication. An example of a substorm was observed on the 23rd of December 2006, and from the THEMIS GBO data, we found that the substorm onset brightening of the equatorward arc was a gradual process (> 27 seconds), with minimal morphology changes until the arc breaks up. The breakup was timed to the nearest frame (< 3 s) and located to the nearest latitude degree at about +/- 3(o)E in longitude. The data also showed that a similar breakup occurred in Alaska similar to 10 minutes later, highlighting the need for an array to distinguish prime onset.
