Engineering topics

Chi, Yuechen

Publications and source records attributed to Chi, Yuechen.

5 records

NASA NTRS2005

Automated Wildfire Detection Through Artificial Neural Networks

Wildfires have a profound impact upon the biosphere and our society in general. They cause loss of life, destruction of personal property and natural resources and alter the chemistry of the atmosphere. In response to the concern over the consequences of wildland fire and to support the fire management community, the National Oceanic and Atmospheric Administration (NOAA), National Environmental Satellite, Data and Information Service (NESDIS) located in Camp Springs, Maryland gradually developed an operational system to routinely monitor wildland fire by satellite observations. The Hazard Mapping System, as it is known today, allows a team of trained fire analysts to examine and integrate, on a daily basis, remote sensing data from Geostationary Operational Environmental Satellite (GOES), Advanced Very High Resolution Radiometer (AVHRR) and Moderate Resolution Imaging Spectroradiometer (MODIS) satellite sensors and generate a 24 hour fire product for the conterminous United States. Although assisted by automated fire detection algorithms, N O M has not been able to eliminate the human element from their fire detection procedures. As a consequence, the manually intensive effort has prevented NOAA from transitioning to a global fire product as urged particularly by climate modelers. NASA at Goddard Space Flight Center in Greenbelt, Maryland is helping N O M more fully automate the Hazard Mapping System by training neural networks to mimic the decision-making process of the frre analyst team as well as the automated algorithms.

Miller, Jerry↗

NASA NTRS2005

Automated Wildfire Detection Through Artificial Neural Networks

We have tested and deployed Artificial Neural Network (ANN) data mining techniques to analyze remotely sensed multi-channel imaging data from MODIS, GOES, and AVHRR. The goal is to train the ANN to learn the signatures of wildfires in remotely sensed data in order to automate the detection process. We train the ANN using the set of human-detected wildfires in the U.S., which are provided by the Hazard Mapping System (HMS) wildfire detection group at NOAA/NESDIS. The ANN is trained to mimic the behavior of fire detection algorithms and the subjective decision- making by N O M HMS Fire Analysts. We use a local extremum search in order to isolate fire pixels, and then we extract a 7x7 pixel array around that location in 3 spectral channels. The corresponding 147 pixel values are used to populate a 147-dimensional input vector that is fed into the ANN. The ANN accuracy is tested and overfitting is avoided by using a subset of the training data that is set aside as a test data set. We have achieved an automated fire detection accuracy of 80-92%, depending on a variety of ANN parameters and for different instrument channels among the 3 satellites. We believe that this system can be deployed worldwide or for any region to detect wildfires automatically in satellite imagery of those regions. These detections can ultimately be used to provide thermal inputs to climate models.

Miller, Jerry↗

NASA NTRS1993

Satellite observation and mapping of wintertime ozone variability in the lower stratosphere

Comparison is made between 30 mbar ozone fields that are generated by a transport chemistry model utilizing the winds from the Goddard Space Flight Center stratospheric data assimilation system (STRATAN), observations from the LIMS instrument on Nimbus-7, and the ozone fields that result from 'flying' a mathematical simulation of LIMS observations through the transport chemistry model ozone fields. The modeled ozone fields were found to resemble the LIMS observations, but the model fields show much more temporal and spatial structure than do the LIMS observations. The 'satellite mapped' model results resemble the LIMS observations much more closely. These results are very consistent with the earlier discussions of satellite space-time sampling by Salby.

Geller, M. A.↗

NASA NTRS1992

Satellite observation and mapping of wintertime ozone variability in the lower stratosphere

Comparison is made between 30 mbar ozone fields that are generated by a transport chemistry model utilizing the winds from the Goddard Space Flight Center stratospheric data assimilation system (STRATAN), observations from the LIMS instrument on Nimbus-7, and the ozone fields that result from 'flying a mathematical simulation of LIMS observations through the transport chemistry model ozone fields. The modeled ozone fields were found to resemble the LIMS observations, but the model fields show much more temporal and spatial structure than do the LIMS observations. The 'satellite mapped' model results resemble the LIMS observations much more closely. These results are very consistent with the earlier discussions of satellite space-time sampling by Salby.

Geller, Marvin A.↗

NASA NTRS1991

Three-dimensional simulations of wintertime ozone variability in the lower stratosphere

The evolution of ozone has been calculated for the winters of 1979 and 1989 using winds derived from the stratospheric data assimilation system STRATAN. The ozone fields calculated using this technique are found to compare well with satellite-measured fields for simulations of 2-3 months. This paper presents comparisons of model fields with both satellite and sonde measurements to verify that stratospheric transport processes are properly represented by this modeling technique. Attention is focused on the Northern Hemisphere middle and high latitudes at the 10-hPa level and below, where transport processes are most important to the ozone distribution. First-order quantities and derived budgets from both the model and satellite data are presented. By sampling the model with a limb-viewing satellite and then Kalman filtering the 'observations' of the model, it is shown that transient subplanetary-scale features that are essential to the ozone budget are missed by the satellite system.

Rood, Richard B.↗