Estimation of the Hourly Aerosol Optical Depth From GOCI Geostationary Satellite Data: Deep Neural Network, Machine Learning, and Physical Models

Spectral aerosol optical depth (AOD) estimation from satellite-measured top of atmosphere (TOA) reflectances is challenging because of the complicated TOA-AOD relationship and a nexus of land surface and atmospheric state variations. This task is usually undertaken using a physical model to provide a first estimate of the TOA reflectances which are then optimized by comparison with the satellite data. Recently developed deep neural network (DNN) models provide a powerful tool to represent the complicated relationship statistically. This study presents a methodology based on DNN to estimate AOD using Himawari-8 Advanced Himawari Imager (AHI) TOA observations. A year (2017) of AHI TOA observations over the Himawari-8 full disk collocated in space and time with Aerosol Robotic Network (AERONET) AOD data were used to derive a total of 14,154 training and validation samples. The TOA reflectance in all six AHI solar bands, three TOA reflectance ratios derived based on the dark-target assumptions, sun-sensor geometry, and auxiliary data are used as predictors to estimate AOD at 500 nm. The DNN AOD is validated by separating training and validation samples using random k-fold cross-validation and using AERONET site-specific leave-one-station-out validation, and is compared with a random forest regression estimator and Japan Meteorological Agency (JMA) AOD. The DNN AOD shows high accuracy: (1) RMSE = 0.094, R2 = 0.915 for k-fold cross-validation, and (2) RMSE = 0.172, R2 = 0.730 for leave-one-station-out validation. The k-fold cross-validation overestimates the DNN accuracy as the training and validation samples may come from the same AHI pixel location. The leave-one-station-out validation reflects the accuracy for large-area applications where there are no training samples for the pixel location to be estimated. The DNN AOD has better accuracy than the random forest AOD and JMA AOD. In addition, the contribution of the dark-target derived TOA ratio predictors is examined and confirmed, and the sensitivity to the DNN structure is discussed.

Download Full-text

Aerosol optical depth and surface reflectance retrieval over land using geostationary satellite data

2012 IEEE International Geoscience and Remote Sensing Symposium ◽

10.1109/igarss.2012.6351907 ◽

2012 ◽

Author(s):

Chi Li ◽

Yong Xue ◽

Yingjie Li ◽

Leiku Yang ◽

Tingting Hou ◽

...

Keyword(s):

Aerosol Optical Depth ◽

Optical Depth ◽

Satellite Data ◽

Geostationary Satellite ◽

Surface Reflectance ◽

Land Using

Download Full-text

An Algorithm for the Retrieval of Aerosol Optical Depth from Geostationary Satellite Data in Thailand

Journal of the Institute of Engineering ◽

10.3126/jie.v8i3.5929 ◽

1970 ◽

Vol 8 (3) ◽

pp. 32-41

Author(s):

Itsara Masiri ◽

Serm Janjai ◽

Treenuch Jantarach

Keyword(s):

Solar Radiation ◽

Aerosol Optical Depth ◽

Optical Depth ◽

Satellite Data ◽

Reasonable Agreement ◽

Surface Albedo ◽

Computer Code ◽

Geostationary Satellite ◽

Digital Data ◽

Main Input

An algorithm was developed to estimate aerosol optical depth (AOD) from geostationary satellite data. The 6S radiative transfer computer code was employed to generate a look-up table (LUT) which incorporates several combinations of satellite-derived variables including earthatmospheric reflectivity, atmospheric reflectivity and surface albedo. The parameterization of the satellite-derived atmospheric reflectivity accounted for the scattering of solar radiation by clouds, absorption of solar radiation by water vapour, ozone and gases and solar radiation depletion by aerosols. The digital data of the MTSAT-1R satellite were used as the main input of the algorithm. For the validation, the values of AOD derived from this algorithm were compared with those obtained from four sites of Aerosol Robotic Network (AERONET) in Thailand, and a reasonable agreement was found. DOI: http://dx.doi.org/10.3126/jie.v8i3.5929 JIE 2011; 8(3): 32-41

Download Full-text

Spatial Assessment of Solar Radiation by Machine Learning and Deep Neural Network Models Using Data Provided by the COMS MI Geostationary Satellite: A Case Study in South Korea

Sensors ◽

10.3390/s19092082 ◽

2019 ◽

Vol 19 (9) ◽

pp. 2082 ◽

Cited By ~ 9

Author(s):

Jong-Min Yeom ◽

Seonyoung Park ◽

Taebyeong Chae ◽

Jin-Young Kim ◽

Chang Suk Lee

Keyword(s):

Neural Network ◽

Machine Learning ◽

Solar Radiation ◽

South Korea ◽

Physical Model ◽

Deep Neural Network ◽

Geostationary Satellite ◽

Data Driven ◽

Support Vector ◽

Neural Network Models

Although data-driven methods including deep neural network (DNN) were introduced, there was not enough assessment about spatial characteristics when using limited ground observation as reference. This work aimed to interpret the feasibility of several machine learning approaches to assess the spatial distribution of solar radiation on Earth based on the Communication, Ocean, and Meteorological Satellite (COMS) Meteorological Imager (MI) geostationary satellite. Four data-driven models were selected (artificial neural network (ANN), random forest (RF), support vector regression (SVR), and DNN), to compare their accuracy and spatial estimating performance. Moreover, we used a physical model to probe the ability of data-driven methods, implementing hold-out and k-fold cross-validation approaches based on pyranometers located in South Korea. The results of analysis showed the RF had the highest accuracy in predicting performance, although the difference between RF and the second-best technique (DNN) was insignificant. Temporal variations in root mean square error (RMSE) were dependent on the number of data samples, while the physical model showed relatively less sensitivity. Nevertheless, DNN and RF showed less variability in RMSE than the others. To examine spatial estimation performance, we mapped solar radiation over South Korea for each model. The data-driven models accurately simulated the observed cloud pattern spatially, whereas the physical model failed to do because of cloud mask errors. These exhibited different spatial retrieval performances according to their own training approaches. Overall analysis showed that deeper layers of networks approaches (RF and DNN), could best simulate the challenging spatial pattern of thin clouds when using satellite multispectral data.

Download Full-text

Burst Pressure Prediction of API 5L X-Grade Dented Pipelines Using Deep Neural Network

Journal of Marine Science and Engineering ◽

10.3390/jmse8100766 ◽

2020 ◽

Vol 8 (10) ◽

pp. 766

Author(s):

Dohan Oh ◽

Julia Race ◽

Selda Oterkus ◽

Bonguk Koo

Keyword(s):

Neural Network ◽

Machine Learning ◽

Artificial Neural Network ◽

Network Model ◽

Neural Network Model ◽

Deep Neural Network ◽

Machine Learning Techniques ◽

Burst Pressure ◽

Comparison Results ◽

Artificial Neural

Mechanical damage is recognized as a problem that reduces the performance of oil and gas pipelines and has been the subject of continuous research. The artificial neural network in the spotlight recently is expected to be another solution to solve the problems relating to the pipelines. The deep neural network, which is on the basis of artificial neural network algorithm and is a method amongst various machine learning methods, is applied in this study. The applicability of machine learning techniques such as deep neural network for the prediction of burst pressure has been investigated for dented API 5L X-grade pipelines. To this end, supervised learning is employed, and the deep neural network model has four layers with three hidden layers, and the neural network uses the fully connected layer. The burst pressure computed by deep neural network model has been compared with the results of finite element analysis based parametric study, and the burst pressure calculated by the experimental results. According to the comparison results, it showed good agreement. Therefore, it is concluded that deep neural networks can be another solution for predicting the burst pressure of API 5L X-grade dented pipelines.

Download Full-text

A deep neural network model for packing density predictions and its application in the study of 1.5 million organic molecules

Chemical Science ◽

10.1039/c9sc02677k ◽

2019 ◽

Vol 10 (36) ◽

pp. 8374-8383 ◽

Cited By ~ 1

Author(s):

Mohammad Atif Faiz Afzal ◽

Aditya Sonpal ◽

Mojtaba Haghighatlari ◽

Andrew J. Schultz ◽

Johannes Hachmann

Keyword(s):

Neural Network ◽

Machine Learning ◽

Refractive Index ◽

High Throughput ◽

Neural Network Model ◽

High Throughput Screening ◽

Deep Neural Network ◽

Organic Molecules ◽

High Refractive Index ◽

Computational Pipeline

Computational pipeline for the accelerated discovery of organic materials with high refractive index via high-throughput screening and machine learning.

Download Full-text