Hestia Project quantifies, simulates and visualizes greenhouse gases such as carbon dioxide emitted in urban regions. Los Angeles basin activity is provided at the 1 km grid spatial resolution, and at temporal resolutions of hourly or annually. Hestia-LA urban CO2 emissions inventory builds upon work conducted at the national scale (Vulcan Project) that includes various sectorial attributions. Hestia's high spatial and temporal resolution datasets are currently available for 2010 to 2015, in UTC or local time.

Hestia Project quantifies, simulates and visualizes greenhouse gases such as carbon dioxide emitted in urban regions. Indianapolis data is provided at the county level (200 m grid resolution), and at hourly and yearly time frames. It builds upon work conducted at the national scale by the Vulcan Project. These high spatial and temporal resolution datasets are available from 2010 to 2015.

Hestia Project quantifies, simulates and visualizes greenhouse gases such as carbon dioxide emitted in urban regions. Baltimore, Maryland activity is provided at the county level (200 m grid resolution), and at hourly and yearly time frames. It builds upon work conducted at the national scale by the Vulcan Project. These high spatial and temporal resolution datasets are available from 2010.

Hestia Project quantifies, simulates and visualizes greenhouse gases such as carbon dioxide emitted in urban regions. Salt Lake City, Utah activity is provided at the county level (0.002 degree grid resolution), and at hourly and yearly time frames. It builds upon work conducted at the national scale by the Vulcan Project. These high spatial and temporal resolution datasets are available for 2002, 2010, 2011, and 2012.

These data from the laboratory tests of a prototype residential liquid-to-air ground-source air conditioner (GSAC) using CO2 as the refrigerant. The data collection and processing methods are described in detail in this report:

Report Title: "Laboratory Tests of a Prototype Carbon Dioxide Ground-Source Air Conditioner", NIST Technical Note 2068
Publication Date: October 2019
DOI: https://doi.org/10.6028/NIST.TN.2068
Authors: Harrison Skye, Wei Wu

Round 1 Test DatasetThe data being generated and disseminated is the test data used to evaluate trojan detection software solutions. This data, generated at NIST, consists of human level AIs trained to perform a variety of tasks (image classification, natural language processing, etc.). A known percentage of these trained AI models have been poisoned with a known trigger which induces incorrect behavior. This data will be used to develop software solutions for detecting which trained AI models have been poisoned via embedded triggers.

Data files for the publication "High Accuracy Near-infrared Carbon Dioxide Intensity Measurements to Support Remote Sensing" in Geophysical Research Letters

Round 1 Training DatasetThe data being generated and disseminated is the training data used to construct trojan detection software solutions. This data, generated at NIST, consists of human level AIs trained to perform a variety of tasks (image classification, natural language processing, etc.). A known percentage of these trained AI models have been poisoned with a known trigger which induces incorrect behavior. This data will be used to develop software solutions for detecting which trained AI models have been poisoned via embedded triggers.

Round1 Holdout DatasetThe data being generated and disseminated is the holdout data used to evaluate trojan detection software solutions. This data, generated at NIST, consists of human level AIs trained to perform a variety of tasks (image classification, natural language processing, etc.). A known percentage of these trained AI models have been poisoned with a known trigger which induces incorrect behavior. This data will be used to develop software solutions for detecting which trained AI models have been poisoned via embedded triggers.

Round 2 Training DatasetThe data being generated and disseminated is the training data used to construct trojan detection software solutions. This data, generated at NIST, consists of human level AIs trained to perform image classification. A known percentage of these trained AI models have been poisoned with a known trigger which induces incorrect behavior. This data will be used to develop software solutions for detecting which trained AI models have been poisoned via embedded triggers.