Pre-trained feature aggregated deep learning-based monitoring of overshooting tops using multi-spectral channels of GeoKompsat-2A advanced meteorological imagery

Rainfall retrieval using geostationary satellites provides critical means to the monitoring of extreme rainfall events. Using the relatively new Himawari 8 meteorological satellite with three times more channels than its predecessors, the deep learning framework of “convolutional autoencoder” (CAE) was applied to the extraction of cloud and precipitation features. The CAE method was incorporated into the Convolution Neural Network version of the PERSIANN precipitation retrieval that uses GOES satellites. By applying the CAE technique with the addition of Residual Blocks and other modifications of deep learning architecture, the presented derivation of PERSIANN operated at the Central Weather Bureau of Taiwan (referred to as PERSIANN-CWB) expands four extra convolution layers to fully use Himawari 8’s infrared and water vapor channels, while preventing degradation of accuracy caused by the deeper network. The development of PERSIANN-CWB was trained over Taiwan for its diverse weather systems and localized rainfall features, and the evaluation reveals an overall improvement from its CNN counterpart and superior performance over all other rainfall retrievals analyzed. Limitation of this model was found in the derivation of typhoon rainfall, an area requiring further research.

Download Full-text

Understanding the Effects of Optimal Combination of Spectral Bands on Deep Learning Model Predictions: A Case Study Based on Permafrost Tundra Landform Mapping Using High Resolution Multispectral Satellite Imagery

Journal of Imaging ◽

10.3390/jimaging6090097 ◽

2020 ◽

Vol 6 (9) ◽

pp. 97 ◽

Cited By ~ 2

Author(s):

Md Abul Ehsan Bhuiyan ◽

Chandi Witharana ◽

Anna K. Liljedahl ◽

Benjamin M. Jones ◽

Ronald Daanen ◽

...

Keyword(s):

Deep Learning ◽

Object Detection ◽

Satellite Imagery ◽

Statistical Measures ◽

Everyday Object ◽

Model Predictions ◽

The Impact ◽

Band Combinations ◽

Spectral Channels

Deep learning (DL) convolutional neural networks (CNNs) have been rapidly adapted in very high spatial resolution (VHSR) satellite image analysis. DLCNN-based computer visions (CV) applications primarily aim for everyday object detection from standard red, green, blue (RGB) imagery, while earth science remote sensing applications focus on geo object detection and classification from multispectral (MS) imagery. MS imagery includes RGB and narrow spectral channels from near- and/or middle-infrared regions of reflectance spectra. The central objective of this exploratory study is to understand to what degree MS band statistics govern DLCNN model predictions. We scaffold our analysis on a case study that uses Arctic tundra permafrost landform features called ice-wedge polygons (IWPs) as candidate geo objects. We choose Mask RCNN as the DLCNN architecture to detect IWPs from eight-band Worldview-02 VHSR satellite imagery. A systematic experiment was designed to understand the impact on choosing the optimal three-band combination in model prediction. We tasked five cohorts of three-band combinations coupled with statistical measures to gauge the spectral variability of input MS bands. The candidate scenes produced high model detection accuracies for the F1 score, ranging between 0.89 to 0.95, for two different band combinations (coastal blue, blue, green (1,2,3) and green, yellow, red (3,4,5)). The mapping workflow discerned the IWPs by exhibiting low random and systematic error in the order of 0.17–0.19 and 0.20–0.21, respectively, for band combinations (1,2,3). Results suggest that the prediction accuracy of the Mask-RCNN model is significantly influenced by the input MS bands. Overall, our findings accentuate the importance of considering the image statistics of input MS bands and careful selection of optimal bands for DLCNN predictions when DLCNN architectures are restricted to three spectral channels.

Download Full-text

Multi-scale 3D-convolutional neural network for hyperspectral image classification

Indonesian Journal of Electrical Engineering and Computer Science ◽

10.11591/ijeecs.v25.i1.pp307-316 ◽

2022 ◽

Vol 25 (1) ◽

pp. 307

Author(s):

Murali Kanthi ◽

Thogarcheti Hitendra Sarma ◽

Chigarapalle Shoba Bindu

Keyword(s):

Neural Network ◽

Deep Learning ◽

Convolutional Neural Network ◽

Classification Accuracy ◽

Hyperspectral Image ◽

State Of The Art ◽

Spatial Dimension ◽

Multi Scale ◽

Proposed Model ◽

Spectral Channels

Deep Learning methods are state-of-the-art approaches for pixel-based hyperspectral images (HSI) classification. High classification accuracy has been achieved by extracting deep features from both spatial-spectral channels. However, the efficiency of such spatial-spectral approaches depends on the spatial dimension of each patch and there is no theoretically valid approach to find the optimum spatial dimension to be considered. It is more valid to extract spatial features by considering varying neighborhood scales in spatial dimensions. In this regard, this article proposes a deep convolutional neural network (CNN) model wherein three different multi-scale spatial-spectral patches are used to extract the features in both the spatial and spectral channels. In order to extract these potential features, the proposed deep learning architecture takes three patches various scales in spatial dimension. 3D convolution is performed on each selected patch and the process runs through entire image. The proposed is named as multi-scale three-dimensional convolutional neural network (MS-3DCNN). The efficiency of the proposed model is being verified through the experimental studies on three publicly available benchmark datasets including Pavia University, Indian Pines, and Salinas. It is empirically proved that the classification accuracy of the proposed model is improved when compared with the remaining state-of-the-art methods.

Download Full-text

Southern Hemisphere Seti Survey: Five Years of Project Meta II

International Astronomical Union Colloquium ◽

10.1017/s0252921100015153 ◽

1997 ◽

Vol 161 ◽

pp. 611-621

Author(s):

Guillermo A. Lemarchand ◽

Fernando R. Colomb ◽

E. Eduardo Hurrell ◽

Juan Carlos Olalde

Keyword(s):

Southern Hemisphere ◽

Scattering Theory ◽

Galactic Plane ◽

Narrow Band ◽

Neutral Hydrogen ◽

Sky Survey ◽

Inertial Frames ◽

Interstellar Scattering ◽

Extraterrestrial Origin ◽

Spectral Channels

AbstractProject META II, a full sky survey for artificial narrow-band signals, has been conducted from one of the two 30-m radiotelescopes of the Instituto Argentino de Radioastronomía (IAR). The search was performed near the 1420 Mhz line of neutral hydrogen, using a 8.4 million channels Fourier spectrometer of 0.05 Hz resolution and 400 kHz instantaneous bandwidth. The observing frequency was corrected both for motions with respect to three astronomical inertial frames, and for the effect of Earths rotation, which provides a characteristic changing signature for narrow-band signals of extraterrestrial origin. Among the 2 × 1013spectral channels analyzed, 29 extra-statistical narrow-band events were found, exceeding the average threshold of 1.7 × 10−23Wm−2. The strongest signals that survive culling for terrestrial interference lie in or near the galactic plane. A description of the project META II observing scheme and results is made as well as the possible interpretation of the results using the Cordes-Lazio-Sagan model based in interstellar scattering theory.

Download Full-text

Deep Learning

10.1017/cbo9780511780295 ◽

2009 ◽

Cited By ~ 94

Author(s):

Stellan Ohlsson

Keyword(s):

Deep Learning

Download Full-text

Intelligence artificielle : le futur de l’Orthodontie ?

Revue d Orthopédie Dento-Faciale ◽

10.1051/odf/2019026 ◽

2019 ◽

Vol 53 (3) ◽

pp. 281-294

Author(s):

Jean-Michel Foucart ◽

Augustin Chavanne ◽

Jérôme Bourriau

Keyword(s):

Big Data ◽

Deep Learning ◽

Intelligence Artificielle ◽

Set Up

Nombreux sont les apports envisagés de l’Intelligence Artificielle (IA) en médecine. En orthodontie, plusieurs solutions automatisées sont disponibles depuis quelques années en imagerie par rayons X (analyse céphalométrique automatisée, analyse automatisée des voies aériennes) ou depuis quelques mois (analyse automatique des modèles numériques, set-up automatisé; CS Model +, Carestream Dental™). L’objectif de cette étude, en deux parties, est d’évaluer la fiabilité de l’analyse automatisée des modèles tant au niveau de leur numérisation que de leur segmentation. La comparaison des résultats d’analyse des modèles obtenus automatiquement et par l’intermédiaire de plusieurs orthodontistes démontre la fiabilité de l’analyse automatique; l’erreur de mesure oscillant, in fine, entre 0,08 et 1,04 mm, ce qui est non significatif et comparable avec les erreurs de mesures inter-observateurs rapportées dans la littérature. Ces résultats ouvrent ainsi de nouvelles perspectives quand à l’apport de l’IA en Orthodontie qui, basée sur le deep learning et le big data, devrait permettre, à moyen terme, d’évoluer vers une orthodontie plus préventive et plus prédictive.

Download Full-text