Description: NeuraLightning is a Neural Network based framework to generate regions of interest for lightning storm clusters from the lightning event stream (i.e., L1b data generated by the real time event processor) that can be used to adjust the sensor/satellite attitude and as input to the CIS. NeuraLightning will use nowcasting to predict future lighting event frames from recent aggregated LIS/GLM/LXM data output using a Convolutional LSTM (C-LSTM). Lightning storms in each predicted frame will then be detected using a "one shot" CNN based object detection model (e.g., YOLO). The chosen NN architectures will also be optimized to execute efficiently on a space qualified hardware. A fundamental constraint is that the autonomous processing of lightning event data must be performed on the processing hardware available on a space-borne satellite, which must satisfy multiple constraints such as weight, power, radiation hardness etc. Since the achievable throughput for the various algorithmic components/options on appropriate space-borne hardware are not known a priori, our approach will be to develop a family of algorithmic variants that represent a trade-off between achievable throughput and model accuracy. Once hardware platform choices are identified, the achieved throughput for the various variants can be evaluated and the version with highest accuracy and sufficient throughput can be selected.

Benefits: NASA uses space based lightning sensors aboard GOES-R, TRMM, and ISS, and is the primary developer and for space based sensing in the US. The next generation lightning sensor is being developed for the upcoming GEO-XO. Other NASA Science Mission Directorate Earth Science missions that may include LIS sensors include the Atmosphere Observing System (AOS) and Earth Venture Mission Investigation of Convective Updrafts (INCUS). Further, the NASA Earth Science Technology Office is exploring the development of a 3D lightning mapper through an Instrument Incubator Project. All of these programs have the potential to use NeuraLightning Pipeline to detect and track lightning storms autonomously.Therefore, NASA is the primary customer for NeuraLightning Pipeline. The "go to market" strategy will be to commercialize and tech transition NeuraLightning Pipeline to these customers, by collaborating with the chosen software vendor on a "co-designed" software/hardware implementation. Further, NeuraLightning Pipeline and its variants can be used to aboard autonomous swarm satellite system such as Starling. Developing next generation autonomous control for additional, non-lightning platforms will be a secondary market.Satellite lightning data is becoming an increasingly used component in producing weather products. As such, \NeuraLightning will be a component in the sensors used by a wide range of international government space and weather agencies. Other countries are also including Lightning mappers in the space-based sensing products, including Rocosmos (e.g., Electro-M satellites), and the European Union's Leonardo Lightning Imager aboard the MTG satellite missions.