Automatic Dust Storm Detection Based on Supervised Classification of Multispectral Data

Rivas, Pablo; Rosiles, Jose Gerardo; Murguía, Mario Ignacio Chacón; Tilton, James C.

doi:10.1007/978-3-642-15111-8_27

Cited by 14 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The machine learning algorithms are inter-compared. Rivas-Perea et al (2010b) indicated improved classification performance of PNN than ML classifier. Shahrisvand and Akhoondzadeh (2013) stated that SVM performed better than decision tree and ANN.…”

Section: Machine Learning-based Algorithmsmentioning

confidence: 94%

“…As for training algorithms, several machine learnings used for classification and regression are applicable for dust storm detection. Generally, the Maximum Likelihood classifier (ML), Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Artificial Neural Network (ANN) and Probabilistic Neural Network (PNN), have been applied for dust storm detection (Rivas-Perea et al, 2010a;Rivas-Perea et al, 2013;Rivas-Perea et al, 2010b;Shahrisvand and Akhoondzadeh, 2013;Shi et al, 2019;Shi et al, 2018;Souri and Vajedian, 2015). The machine learning algorithms are inter-compared.…”

Section: Machine Learning-based Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Review of dust storm detection algorithms for multispectral satellite sensors

Wong

Lee

et al. 2021

Atmospheric Research

View full text Add to dashboard Cite

Section: Machine Learning-based Algorithmsmentioning

confidence: 94%

Section: Machine Learning-based Algorithmsmentioning

confidence: 99%

Review of dust storm detection algorithms for multispectral satellite sensors

Wong

Lee

et al. 2021

Atmospheric Research

View full text Add to dashboard Cite

“…This LUT-based NN technique was used for aerosol retrieval from reflectances at two ADEOS/OCTS bands (0.67 and 0.865 μm) (Okada, Mukai, and Sano, 2001). Automatic dust storm detection was available by using NN for the MODIS images (Rivas-Perea et al, 2010;El-ossta, Qahwaji, and Ipson, 2013) and for AOT retrieval from the Atmospheric Infrared Sounder (AIRS) (Han and Sohn, 2013). More recently, simultaneous dust storm detection and retrieval of AOT based on the multilayer perceptron (MLP) NN model with a back-propagation (BP) learning algorithm (hereafter MLP-BP) for the geostationary satellite images were introduced (Xiao et al, 2015).…”

Section: Aerosol Retrieval Using An Artificial Neural Network Techniquementioning

confidence: 99%

Remote Sensing of Atmospheric Aerosol

Kokhanovsky

Tomasi

Petkov

et al. 2016

Atmospheric Aerosols

View full text Add to dashboard Cite

“…Little work has been done on the statistical-based dust detection approaches. Rivas-Perea et al (2010) developed a Maximum Likelihood Classifier (MLC) and a Probabilistic Neural Network (PNN) to automate dust storm detection process. Their results indicated that PNN provided improved classification performance with reference to MLC.…”

Section: Introductionmentioning

confidence: 99%

Dust storm detection using random forests and physical-based approaches over the Middle East

Souri

Vajedian

2015

J Earth Syst Sci

View full text Add to dashboard Cite

Dust storms are important phenomena over large regions of the arid and semi-arid areas of the Middle East. Due to the influences of dust aerosols on climate and human daily activities, dust detection plays a crucial role in environmental and climatic studies. Detection of dust storms is critical to accurately understand dust, their properties and distribution. Currently, remotely sensed data such as MODIS (Moderate Resolution Imaging Spectroradiometer) with appropriate temporal and spectral resolutions have been widely used for this purpose. This paper investigates the capability of two physical-based methods, and random forests (RF) classifier, for the first time, to detect dust storms using MODIS imagery. Since the physical-based approaches are empirical, they suffer from certain drawbacks such as high variability of thresholds depending on the underlying surface. Therefore, classification-based approaches could be deployed as an alternative. In this paper, the most relevant bands are chosen based on the physical effects of the major classes, particularly dust, cloud and snow, on both emissive infrared and reflective bands. In order to verify the capability of the methods, OMAERUV AAOD (aerosol absorption optical depth) product from OMI (Ozone Monitoring Instrument) sensor is exploited. In addition, some small regions are selected manually to be considered as ground truth for measuring the probability of false detection (POFD) and probability of missing detection (POMD). The dust class generated by RF is consistent qualitatively with the location and extent of dust observed in OMERAUV and MODIS true colour images. Quantitatively, the dust classes generated for eight dust outbreaks in the Middle East are found to be accurate from 7% and 6% of POFD and POMD respectively. Moreover, results demonstrate the sound capability of RF in classifying dust plumes over both water and land simultaneously. The performance of the physical-based approaches is found weaker than RF due to empirical thresholds that are not always true.

show abstract

Automatic Dust Storm Detection Based on Supervised Classification of Multispectral Data

Cited by 14 publications

References 9 publications

Review of dust storm detection algorithms for multispectral satellite sensors

Review of dust storm detection algorithms for multispectral satellite sensors

Remote Sensing of Atmospheric Aerosol

Dust storm detection using random forests and physical-based approaches over the Middle East

Contact Info

Product

Resources

About