Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385432822> ?p ?o ?g. }
- W4385432822 abstract "Abstract Atmospheric processes involve both space and time. Thus, humans looking at atmospheric imagery can often spot important signals in an animated loop of an image sequence not apparent in an individual (static) image. Utilizing such signals with automated algorithms requires the ability to identify complex spatiotemporal patterns in image sequences. That is a very challenging task due to the endless possibilities of patterns in both space and time. Here, we review different concepts and techniques that are useful to extract spatiotemporal signals from meteorological image sequences to expand the effectiveness of AI algorithms for classification and prediction tasks. We first present two applications that motivate the need for these approaches in meteorology, namely the detection of convection from satellite imagery and solar forecasting. Then we provide an overview of concepts and techniques that are helpful for the interpretation of meteorological image sequences, such as (a) feature engineering methods using (i) meteorological knowledge, (ii) classic image processing, (iii) harmonic analysis, and (iv) topological data analysis; (b) ways to use convolutional neural networks for this purpose with emphasis on discussing different convolution filters (2D/3D/LSTM-convolution); and (c) a brief survey of several other concepts, including the concept of “attention” in neural networks and its utility for the interpretation of image sequences and strategies from self-supervised and transfer learning to reduce the need for large labeled datasets. We hope that presenting an overview of these tools—many of which are not new but underutilized in this context—will accelerate progress in this area." @default.
- W4385432822 created "2023-08-01" @default.
- W4385432822 creator A5022162451 @default.
- W4385432822 creator A5045919940 @default.
- W4385432822 creator A5082309905 @default.
- W4385432822 creator A5087017686 @default.
- W4385432822 date "2023-01-01" @default.
- W4385432822 modified "2023-10-09" @default.
- W4385432822 title "Leveraging spatiotemporal information in meteorological image sequences: From feature engineering to neural networks" @default.
- W4385432822 cites W126328138 @default.
- W4385432822 cites W1789155650 @default.
- W4385432822 cites W1985621603 @default.
- W4385432822 cites W1991339015 @default.
- W4385432822 cites W1995349031 @default.
- W4385432822 cites W1997012688 @default.
- W4385432822 cites W2020297738 @default.
- W4385432822 cites W2047243358 @default.
- W4385432822 cites W2064675550 @default.
- W4385432822 cites W2076077531 @default.
- W4385432822 cites W2079567099 @default.
- W4385432822 cites W2097336824 @default.
- W4385432822 cites W2098702616 @default.
- W4385432822 cites W2100649405 @default.
- W4385432822 cites W2103504761 @default.
- W4385432822 cites W2108598243 @default.
- W4385432822 cites W2136848157 @default.
- W4385432822 cites W2147800946 @default.
- W4385432822 cites W2176774719 @default.
- W4385432822 cites W2212330491 @default.
- W4385432822 cites W2412782625 @default.
- W4385432822 cites W2470699557 @default.
- W4385432822 cites W2510642588 @default.
- W4385432822 cites W2748715875 @default.
- W4385432822 cites W2766736793 @default.
- W4385432822 cites W2799555932 @default.
- W4385432822 cites W2885398382 @default.
- W4385432822 cites W2885645302 @default.
- W4385432822 cites W2889377359 @default.
- W4385432822 cites W2914856364 @default.
- W4385432822 cites W2915701005 @default.
- W4385432822 cites W2917445752 @default.
- W4385432822 cites W2921208939 @default.
- W4385432822 cites W2922401428 @default.
- W4385432822 cites W2945976633 @default.
- W4385432822 cites W2960560113 @default.
- W4385432822 cites W2963116731 @default.
- W4385432822 cites W2963986342 @default.
- W4385432822 cites W2969309273 @default.
- W4385432822 cites W2986661129 @default.
- W4385432822 cites W2991136643 @default.
- W4385432822 cites W2998726446 @default.
- W4385432822 cites W3006973843 @default.
- W4385432822 cites W3016253179 @default.
- W4385432822 cites W3025786591 @default.
- W4385432822 cites W3037957586 @default.
- W4385432822 cites W3082330840 @default.
- W4385432822 cites W3082499568 @default.
- W4385432822 cites W3090823604 @default.
- W4385432822 cites W3095867871 @default.
- W4385432822 cites W3096600794 @default.
- W4385432822 cites W3098773906 @default.
- W4385432822 cites W3116147763 @default.
- W4385432822 cites W3120761343 @default.
- W4385432822 cites W3126335003 @default.
- W4385432822 cites W3136985093 @default.
- W4385432822 cites W3147008637 @default.
- W4385432822 cites W3161760456 @default.
- W4385432822 cites W3174285742 @default.
- W4385432822 cites W3174465772 @default.
- W4385432822 cites W3185151088 @default.
- W4385432822 cites W3186888943 @default.
- W4385432822 cites W3202525453 @default.
- W4385432822 cites W3205440207 @default.
- W4385432822 cites W3208501207 @default.
- W4385432822 cites W3211187796 @default.
- W4385432822 cites W3217586766 @default.
- W4385432822 cites W3217596343 @default.
- W4385432822 cites W4210916416 @default.
- W4385432822 cites W4226251268 @default.
- W4385432822 cites W4226289820 @default.
- W4385432822 cites W4229494842 @default.
- W4385432822 cites W4281785683 @default.
- W4385432822 cites W4283168768 @default.
- W4385432822 cites W4283396075 @default.
- W4385432822 cites W4292451836 @default.
- W4385432822 cites W4294068833 @default.
- W4385432822 cites W4296350506 @default.
- W4385432822 cites W4297239582 @default.
- W4385432822 cites W4311875050 @default.
- W4385432822 cites W4312171485 @default.
- W4385432822 cites W4322011423 @default.
- W4385432822 cites W4322211038 @default.
- W4385432822 cites W4377101865 @default.
- W4385432822 cites W4380053006 @default.
- W4385432822 doi "https://doi.org/10.1017/eds.2023.26" @default.
- W4385432822 hasPublicationYear "2023" @default.
- W4385432822 type Work @default.
- W4385432822 citedByCount "1" @default.
- W4385432822 crossrefType "journal-article" @default.
- W4385432822 hasAuthorship W4385432822A5022162451 @default.