Changes

Sapling-1's structure comprised four anodized aluminum rails with slots on the interior that support the avionics. The rails were held together by the side panels, which contained the solar panels and GPS modules. The Z+ side panel (pointing upwards in the photo on the right) contained the tape spring radio antennas tuned for the 433 MHz radio.

Sapling-1's structure comprised four anodized aluminum rails with slots on the interior that support the avionics. The rails were held together by the side panels, which contained the solar panels and GPS modules. The Z+ side panel (pointing upwards in the photo on the right) contained the tape spring radio antennas tuned for the 433 MHz radio.

=== Sequoia: 2019–2020 ===

=== Sequoia: 2018–2020 ===

Sequoia was a planned 3U CubeSat that would demonstrate on-board image classification and processing with updateable machine learning models. The goal of the project was to obtain a high volume of scientifically important imagery for ecological and climatology research. Researchers many times have no need of images saturated with clouds or uninteresting areas—so why not filter them out with a convolutional neural network? Sequoia’s deep learning with images taken by the satellite would be retained, with improvements implemented on-orbit. SSI worked on developing deep learning models for forest fire risk assessment and detection and a number of other applications. The mission architecture was user definable with the operator specifying desirable image locations or types and resolutions, and the satellite planned to maximize delivery of fully open-source images.  

Sequoia was a planned 3U CubeSat that would demonstrate on-board image classification and processing with updateable machine learning models. The goal of the project was to obtain a high volume of scientifically important imagery for ecological and climatology research. Researchers many times have no need of images saturated with clouds or uninteresting areas—so why not filter them out with a convolutional neural network? Sequoia’s deep learning with images taken by the satellite would be retained, with improvements implemented on-orbit. SSI worked on developing deep learning models for forest fire risk assessment and detection and a number of other applications. The mission architecture was user definable with the operator specifying desirable image locations or types and resolutions, and the satellite planned to maximize delivery of fully open-source images.  

Project materials can be found in the [https://github.com/stanford-ssi/Sequoia Sequoia GitHub].

Project materials can be found in the [https://github.com/stanford-ssi/Sequoia Sequoia GitHub].

=== POINTR: [year]–2018 ===

=== POINTR: 2016–2018 ===

The Satellites team developed various [[Optical Communications]] technologies, culminating in the launch of [[POINTR]]. This was a 1U segment of a 3U CubeSat launched in 2018, but it unfortunately never connected with ground control due to improper orbital insertion from the launch provider.  

The Satellites team developed various [[Optical Communications]] technologies, culminating in the launch of [[POINTR]]. This was a 1U segment of a 3U CubeSat launched in 2018, but it unfortunately never connected with ground control due to improper orbital insertion from the launch provider.