A neural network approach to cloud classification

Lee, J.; Weger, R. C.; Sengupta, S. K.; Welch, Ronald M.

doi:10.1109/36.58972

Cited by 234 publications

(103 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The comparison of statistical classification methods and NNs has shown that NNs can achieve more accurate results (Benediktsson et al, 1990(Benediktsson et al, , 1993Chini et al, 2008). In the field of atmospheric investigations the NNs have been successfully used to address different problems such as: humidity profiles retrieval (CabreraMercader and Staelin, 1995;Blackwell, 2005), height resolved ozone retrievals (Del Frate and Schiavon, 1999;Del Frate et al, 2002;Müller et al, 2003;Sellitto et al, 2011a, b), cloud classification (Lee et al, 1990;Bankert, 1994), temperature parameter esteems (Butler et al, 1996) and retrieval of temperature profiles (Churnside et al, 1994). For a further reading about NNs for the solution of atmospheric inverse problems that involve complex physical behaviors see Gardner and Dorling (1998) and Hsieh and Tang (1998).…”

Section: Introductionmentioning

confidence: 99%

Volcanic ash detection and retrievals using MODIS data by means of neural networks

et al. 2011

View full text Add to dashboard Cite

Abstract. Volcanic ash clouds detection and retrieval represent a key issue for aviation safety due to the harming effects on aircraft. A lesson learned from the recent Eyjafjallajokull eruption is the need to obtain accurate and reliable retrievals on a real time basis.In this work we have developed a fast and accurate Neural Network (NN) approach to detect and retrieve volcanic ash cloud properties from the Moderate Resolution Imaging Spectroradiometer (MODIS) data in the Thermal InfraRed (TIR) spectral range. Some measurements collected during the 2001, 2002 and 2006 Mt. Etna volcano eruptions have been considered as test cases.The ash detection and retrievals obtained from the Brightness Temperature Difference (BTD) algorithm are used as training for the NN procedure that consists in two separate steps: ash detection and ash mass retrieval. The ash detection is reduced to a classification problem by identifying two classes: "ashy" and "non-ashy" pixels in the MODIS images. Then the ash mass is estimated by means of the NN, replicating the BTD-based model performances. A segmentation procedure has also been tested to remove the false ash pixels detection induced by the presence of high meteorological clouds. The segmentation procedure shows a clear advantage in terms of classification accuracy: the main drawback is the loss of information on ash clouds distal part.The results obtained are very encouraging; indeed the ash detection accuracy is greater than 90 %, while a mean RMSE Correspondence to: M. Picchiani (picchian@disp.uniroma2.it) equal to 0.365 t km −2 has been obtained for the ash mass retrieval. Moreover, the NN quickness in results delivering makes the procedure extremely attractive in all the cases when the rapid response time of the system is a mandatory requirement.

show abstract

Section: Introductionmentioning

confidence: 99%

Volcanic ash detection and retrievals using MODIS data by means of neural networks

et al. 2011

View full text Add to dashboard Cite

show abstract

“…Dominant color extraction and artificial neural networks are able to establish such relations. Details of these methods can be found elsewhere [6][7][8][9][10]. Through this method, users can achieve the input of sky type by taking a photo of the sky overhead.…”

Section: Rapid Inputmentioning

confidence: 99%

A rapid method of estimating the solar irradiance spectra with potential lighting applications

Gao

Dong

Isabella

et al. 2016

2016 13th China International Forum on Solid State Lighting (SSLChina)

View full text Add to dashboard Cite

Measurements by spectrophotometers are able to achieve accurate real-time data with high resolution, but at high expense. While in some engineering applications, the requirements on accuracy and resolution are much lower than that in a typical scientific research. Therefore, a rapid method of estimating the solar spectrum is proposed based on an available spectral model in this paper. In order to achieve fast estimation, we simplify the input parameters of this model into five key inputs, including latitude and longitude, altitude, date and time, sky and ground type. The first three parameters are easy to obtain from GPS and the internet. Sky and ground types include common types of sky and ground, which can be input manually or processed automatically by analyzing a digital image of target sky or ground. The automatic input is realized through dominant color extraction or by training an artificial neural network. Results show that the proposed rapid method can generate different spectral power distributions based on distinct input conditions. Two device frameworks are also proposed to implement the rapid method, which is applicable to many fields. LED lighting is one of the most prominent applications. Users can easily share local sunlight with each other through an APP in mobile phones.

show abstract

“…Minnis et al, predicted clear-sky brightness temperature values using ambient temperature and humidity and then excised pixels outside those intervals [32]. Texture cues can be utilized to recognize clouds by their high spatial heterogeneity [33]. Martins et al, demonstrated that a simple spatial analysis, i.e., the standard deviation of VNIR isotropic reflectances in a 3 × 3 pixel window, reliably discriminated clouds from aerosol plumes over ocean scenes [34].…”

Section: Introductionmentioning

confidence: 99%

Onboard Spectral and Spatial Cloud Detection for Hyperspectral Remote Sensing Images

Zheng

Han

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

Abstract:The accurate onboard detection of clouds in hyperspectral images before lossless compression is beneficial. However, conventional onboard cloud detection methods are not applicable all the time, especially for shadowed clouds or darkened snow-covered surfaces that are not identified in normalized difference snow index (NDSI) tests. In this paper, we propose a new spectral-spatial classification strategy to enhance the performance of an orbiting cloud screen obtained on hyperspectral images by integrating a threshold exponential spectral angle map (TESAM), adaptive Markov random field (aMRF) and dynamic stochastic resonance (DSR). TESAM is applied to roughly classify cloud pixels based on spectral information. Then aMRF is used to do optimal process by using spatial information, which improved the classification performance significantly. Nevertheless, misclassifications occur due to noisy data in the onboard environments, and DSR is employed to eliminate noise data produced by aMRF in binary labeled images. We used level 0.5 data from Hyperion as a dataset, and the average tested accuracy of the proposed algorithm was 96.28% by test. This method can provide cloud mask for the on-going EO-1 and related satellites with the same spectral settings without manual intervention. Experiments indicate that the proposed method has better performance than the conventional onboard cloud detection methods or current state-of-the-art hyperspectral classification methods.

show abstract

A neural network approach to cloud classification

Cited by 234 publications

References 25 publications

Volcanic ash detection and retrievals using MODIS data by means of neural networks

Volcanic ash detection and retrievals using MODIS data by means of neural networks

A rapid method of estimating the solar irradiance spectra with potential lighting applications

Onboard Spectral and Spatial Cloud Detection for Hyperspectral Remote Sensing Images

Contact Info

Product

Resources

About