U-Net Inspired Deep Neural Network-Based Smoke Plume Detection in Satellite Images

Industrial activities, through the human-induced release of Green House Gas (GHG) emissions, have beenidentified as the primary cause of global warming. Accurate and quantitative monitoring of these emissions isessential for a comprehensive understanding of their impact on the Earth’s climate and for effectively enforcingemission regulations at a large scale. This work examines the feasibility of detecting and quantifying industrialsmoke plumes using freely accessible geo-satellite imagery. The existing systemhas so many lagging factors such aslimitations in accuracy, robustness, and efficiency and these factors hinder the effectiveness in supporting timelyresponse to industrial fires. In this work, the utilization of grayscale images is done instead of traditional colorimages for smoke plume detection. The dataset was trained through a ResNet-50 model for classification and aU-Net model for segmentation. The dataset consists of images gathered by European Space Agency’s Sentinel-2 satellite constellation from a selection of industrial sites. The acquired images predominantly capture scenesof industrial locations, some of which exhibit active smoke plume emissions. The performance of the abovementionedtechniques and models is represented by their accuracy and IOU (Intersection-over-Union) metric.The images are first trained on the basic RGB images where their respective classification using the ResNet-50model results in an accuracy of 94.4% and segmentation using the U-Net Model with an IOU metric of 0.5 andaccuracy of 94% which leads to the detection of exact patches where the smoke plume has occurred. This work hastrained the classification model on grayscale images achieving a good increase in accuracy of 96.4%.

GEO Satellite Thruster Configuration and Optimization

A thruster configuration and optimization method for GEO satellite is proposed in this paper.All thrusters are installed on the back panel of satellite,which is not only compatible with the design of satellite subdivision structure,but also able to provide a large installation room for the payloads and components carried by the satellite.Chemical thruster and electric thruster were selected because they have complementary advantages and can effectively reduce propellant consumption.The working mode and tasks of the thruster were analyzed in detail for thruster configuration,which was optimized in order to minimize propellant consumption.Lastly,a GEO satellite thruster was configured and optimized using this method,with results showing that the method is feasible and effective,and consequently has value for engineering applications.

A GEO Satellite Position and Beam Features Estimation Method Based on Beam Edge Positions

Constrained by orbital configuration and spectrum sharing,non-geostationary orbit(NGEO)satellites may be interfered when they are in the beam range of geostationary orbit(GEO)satellite.However,it is difficult for NGEO operators to determine the signal source.Herein,we propose a method to locate the GEO signal source and estimate beam features,including beam pointing azimuth,elevation,and beamwidth,by the beam edge positions.We transform this estimation problem into two optimization problems by minimizing the estimation error,and solve both of them through a multi-variable joint iteration method with acceptable computation complexity.Numerical results show that when NGEO satellites pass through the beam twice,the longitude estimation error is about 0.01 degree,and the estimation results will be more and more accurate as the number of passing times increases.Besides,the proposed method is also effective when there are kilometer-level errors in beam edge positions.