Particulate matter (PM2.5 and PM10) generation map using MODIS Level-1 satellite images and deep neural network

2021 ◽  
Vol 281 ◽  
pp. 111888
Author(s):  
Maryam Imani
Keyword(s):  
Neural Network ◽  
Particulate Matter ◽  
Deep Neural Network ◽  
Satellite Images ◽  
Level 1 ◽  
Pm2.5 And Pm10

scholarly journals Direct Short-Term Forecast of Photovoltaic Power through a Comparative Study between COMS and Himawari-8 Meteorological Satellite Images in a Deep Neural Network

2020 ◽  
Vol 12 (15) ◽  
pp. 2357
Author(s):  
Minho Kim ◽  
Hunsoo Song ◽  
Yongil Kim
Keyword(s):  
Neural Network ◽  
Comparative Study ◽  
Deep Neural Network ◽  
Satellite Images ◽  
Solar Irradiation ◽  
Next Generation ◽  
Short Term ◽  
Input Dataset ◽  
One Year ◽  
Meteorological Satellite

Meteorological satellite images provide crucial information on solar irradiation and weather conditions at spatial and temporal resolutions which are ideal for short-term photovoltaic (PV) power forecasts. Following the introduction of next-generation meteorological satellites, investigating their application on PV forecasts has become imminent. In this study, Communications, Oceans, and Meteorological Satellite (COMS) and Himawari-8 (H8) satellite images were inputted in a deep neural network (DNN) model for 2 hour (h)- and 1 h-ahead PV forecasts. A one-year PV power dataset acquired from two solar power test sites in Korea was used to directly forecast PV power. H8 was used as a proxy for GEO-KOMPSAT-2A (GK2A), the next-generation satellite after COMS, considering their similar resolutions, overlapping geographic coverage, and data availability. In addition, two different data sampling setups were designed to implement the input dataset. The first setup sampled chronologically ordered data using a relatively more inclusive time frame (6 a.m. to 8 p.m. in local time) to create a two-month test dataset, whereas the second setup randomly sampled 25% of data from each month from the one-year input dataset. Regardless of the setup, the DNN model generated superior forecast performance, as indicated by the lowest normalized mean absolute error (NMAE) and normalized root mean squared error (NRMSE) results in comparison to that of the support vector machine (SVM) and artificial neural network (ANN) models. The first setup results revealed that the visible (VIS) band yielded lower NMAE and NRMSE values, while COMS was found to be more influential for 1 h-ahead forecasts. For the second setup, however, the difference in NMAE results between COMS and H8 was not significant enough to distinguish a clear edge in performance. Nevertheless, this marginal difference and similarity of the results suggest that both satellite datasets can be used effectively for direct short-term PV forecasts. Ultimately, the comparative study between satellite datasets as well as spectral bands, time frames, forecast horizons, and forecast models confirms the superiority of the DNN and offers insights on the potential of transitioning to applying GK2A for future PV forecasts.

‘This is a House’: Large Image Collections and Their Platform Embeddings

2021 ◽  
pp. 135485652110520
Author(s):  
Adrian Mackenzie
Keyword(s):  
Neural Network ◽  
Predictive Model ◽  
Deep Neural Network ◽  
Satellite Images ◽  
Predictive Modelling ◽  
Active Role ◽  
Human Settlement ◽  
The World

This paper analyses the active role of image collections in supporting platforms and their operations. Large image collections are increasingly present on media, scientific and other platforms. A case study of Facebook’s predictive modelling of satellite images of human settlement exemplifies how image collections are changing. The treatment of images in a predictive model – a deep neural network – constructs a condensed indexical field, a field that allows the platform to generate referential statements about the world. Under platform conditions, image collections function less as archives or records and more as densely woven indexical fields that orient, position and embed the platform. In describing the transformation of image collections, the paper points to important changes in how platforms use images to position themselves in the world.

scholarly journals Semantic Segmentation of Satellite Images: A Deep Learning Approach Integrated with Geospatial Hash Codes

2021 ◽  
Vol 13 (14) ◽  
pp. 2723
Author(s):  
Naisen Yang ◽  
Hong Tang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Deep Neural Network ◽  
Satellite Images ◽  
Spatial Information ◽  
Semantic Segmentation ◽  
Binary Codes ◽  
Underlying Assumption ◽  
Hash Codes

Satellite images are always partitioned into regular patches with smaller sizes and then individually fed into deep neural networks (DNNs) for semantic segmentation. The underlying assumption is that these images are independent of one another in terms of geographic spatial information. However, it is well known that many land-cover or land-use categories share common regional characteristics within a certain spatial scale. For example, the style of buildings may change from one city or country to another. In this paper, we explore some deep learning approaches integrated with geospatial hash codes to improve the semantic segmentation results of satellite images. Specifically, the geographic coordinates of satellite images are encoded into a string of binary codes using the geohash method. Then, the binary codes of the geographic coordinates are fed into the deep neural network using three different methods in order to enhance the semantic segmentation ability of the deep neural network for satellite images. Experiments on three datasets demonstrate the effectiveness of embedding geographic coordinates into the neural networks. Our method yields a significant improvement over previous methods that do not use geospatial information.

Multitemporal distribution analysis of Dodonaea viscosa (L.) Jacq. by remote sensing in Durango, Mexico

2020 ◽  
Vol 13 (8) ◽  
Author(s):  
Marco, A. Márquez-Linares ◽  
Jonathan G. Escobar--Flores ◽  
Sarahi Sandoval- Espinosa ◽  
Gustavo Pérez-Verdín
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Design Methodology ◽  
Supervised Classification ◽  
Satellite Images ◽  
Ground Cover ◽  
Distribution Analysis ◽  
Dodonaea Viscosa ◽  
Artificial Neural ◽  
Landsat Satellite

Objective: to determine the distribution of D. viscosa in the vicinity of the Guadalupe Victoria Dam in Durango, Mexico, for the years 1990, 2010 and 2017.Design/Methodology/Approach: Landsat satellite images were processed in order to carry out supervised classifications using an artificial neural network. Images from the years 1990, 2010 and 2017 were used to estimate ground cover of D. viscosa, pastures, crops, shrubs, and oak forest. This data was used to calculate the expansion of D. viscosa in the study area.Results/Study Limitations/Implications: the supervised classification with the artificial neural network was optimal after 400 iterations, obtaining the best overall precision of 84.5 % for 2017. This contrasted with the year 1990, when overall accuracy was low at 45 % due to less training sites (fewer than 100) recorded for each of the land cover classes.Findings/Conclusions: in 1990, D. viscosa was found on only five hectares, while by 2017 it had increased to 147 hectares. If the disturbance caused by overgrazing continues, and based on the distribution of D. viscosa, it is likely that in a few years it will have the ability to invade half the study area, occupying agricultural, forested, and shrub areas

Deep Neural Network Classification of I-123 Ioflupane SPECT

2020 ◽  
Author(s):  
David T. Wang ◽  
Brady Williamson ◽  
Thomas Eluvathingal ◽  
Bruce Mahoney ◽  
Jennifer Scheler
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Neural Network Classification
Sign in / Sign up

Export Citation Format

Share Document