Abstract: Described herein is a chemical sensing system that can be deployed in an environment and automatically monitor the environment. The chemical sensing system includes one or more chemical sensing units with sensing elements that sense chemicals in the environment. The chemical sensing system analyzes measured values output by the sensing elements to identify patterns indicative of events. After identifying an event, the chemical sensing system may generate an inference about the environment using measured values output by the sensing elements during the event.

Abstract: Described herein is a chemical sensing system that can be deployed in an environment and automatically monitor the environment. The chemical sensing system includes one or more chemical sensing units with sensing elements that sense chemicals in the environment. The chemical sensing system analyzes measured values output by the sensing elements to identify patterns indicative of events. After identifying an event, the chemical sensing system may generate an inference about the environment using measured values output by the sensing elements during the event.

Abstract: Systems and methods for training models across multiple sensing units in a chemical sensing system are described. The chemical sensing system comprises at least one computer processor and at least one computer readable medium including instructions that, when executed by the at least one computer processor, cause the chemical sensing system to perform a training process. The training process comprises accessing a training dataset including first values representing first signals output from a first chemical sensing unit of multiple chemical sensing units, and second values representing second signals output from a second chemical sensing unit of the multiple chemical sensing units, and training a set of models to relate the first values and the second values to a mutual latent representation using the training dataset.

Abstract: Systems and methods for training models across multiple sensing units in a chemical sensing system are described. The chemical sensing system comprises at least one computer processor and at least one computer readable medium including instructions that, when executed by the at least one computer processor, cause the chemical sensing system to perform a training process. The training process comprises accessing a training dataset including first values representing first signals output from a first chemical sensing unit of multiple chemical sensing units, and second values representing second signals output from a second chemical sensing unit of the multiple chemical sensing units, and training a set of models to relate the first values and the second values to a mutual latent representation using the training dataset.