Filters








232 Hits in 9.7 sec

Tropical cyclone event sequence similarity search via dimensionality reduction and metric learning

Shen-Shyang Ho, Wenqing Tang, W. Timothy Liu
2010 Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '10  
We describe a novel Longest Common Subsequence (LCSS) parameter learning approach driven by nonlinear dimensionality reduction and distance metric learning.  ...  Experimental results using a combination of synthetic and real tropical cyclone event data sequences are presented to demonstrate the feasibility of our parameter learning approach and its robustness to  ...  Acknowledgments This research was carried out at the Jet Propulsion Laboratory, California Institute of Technology, under a contract with the National Aeronautics and Space Adminstration.  ... 
doi:10.1145/1835804.1835824 dblp:conf/kdd/HoTL10 fatcat:fwldjkj3vrc3vb3aklcqqt5qja

Non-Linear Dimensionality Reduction with a Variational Autoencoder Decoder to Understand Convective Processes in Climate Models [article]

Gunnar Behrens, Tom Beucler, Pierre Gentine, Fernando Iglesias-Suarez, Michael Pritchard, Veronika Eyring
2022 arXiv   pre-print
Here, we use Variational AutoEncoder (VAE) decoder structures, a non-linear dimensionality reduction technique, to learn and understand convective processes in an aquaplanet superparameterized climate  ...  We show that similar to previous deep learning studies based on feed-forward neural nets, the VAE is capable of learning and accurately reproducing convective processes.  ...  tropical deep convection regime of Frenkel et al. (2015) were characterized by similar heating profiles.  ... 
arXiv:2204.08708v1 fatcat:pq5efj3hfjedpazpyq5gnbcthm

Intelligent Evidence-Based Management for Data Collection and Decision-Making Using Algorithmic Randomness and Active Learning

Harry Wechsler, Shen-Shyang Ho
2011 Intelligent Information Management  
learning and transduction, in particular.  ...  The set-based similarity scores, driven by algorithmic randomness and Kolmogorov complexity, employ strangeness/typicality and p-values.  ...  The L p similarity measures are metric, but they assume fixed length data sequences and do not support local time shifting; the elastic similarity can be used to compare arbitrary length data sequences  ... 
doi:10.4236/iim.2011.34018 fatcat:k36vb7cu4vcmbegzkgx7tk7ite

Mining scientific data [chapter]

Naren Ramakrishnan, Ananth Y. Grama
2002 Advances in Computers  
We discuss algorithms, techniques, and methodologies for their effective application and present application studies that summarize the stateof-the-art in this emerging field.  ...  Coupled with the availability of massive storage systems and fast networking technology to manage and assimilate data, these have given a significant impetus to data mining in the scientific domain.  ...  The outcome of an automated cyclone detection technique is a one-dimensional track in three dimensional space consisting of two space coordinates and one time coordinate.  ... 
doi:10.1016/s0065-2458(01)80028-0 fatcat:sbp5xai2yva2pcx3lj2sq64yma

2020 Index IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Vol. 13

2020 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
., +, JSTARS 2020 4934-4946 Deepti: Deep-Learning-Based Tropical Cyclone Intensity Estimation Sys- tem.  ...  Xi, B., +, JSTARS 2020 3683-3700 Deepti: Deep-Learning-Based Tropical Cyclone Intensity Estimation System.  ...  A New Deep-Learning-Based Approach for Earthquake-Triggered Landslide Detection From Single-Temporal RapidEye Satellite Imagery. Yi, Y., +, JSTARS 2020  ... 
doi:10.1109/jstars.2021.3050695 fatcat:ycd5qt66xrgqfewcr6ygsqcl2y

Nonlinear Dimensionality Reduction Methods in Climate Data Analysis [article]

Ian Ross
2009 arXiv   pre-print
I use these three methods to examine El Nino variability in the different data sets and assess the suitability of these nonlinear dimensionality reduction approaches for climate data analysis.  ...  Linear dimensionality reduction techniques, notably principal component analysis, are widely used in climate data analysis as a means to aid in the interpretation of datasets of high dimensionality.  ...  and via the chain maps relating the different simplicial complexes in the sequence.  ... 
arXiv:0901.0537v1 fatcat:2ethc7ddtjdyxkbqzmtg64upwi

Big Data for Social Sciences: Measuring patterns of human behavior through large-scale mobile phone data [article]

Pål Sundsøy
2017 arXiv   pre-print
Results show that by including social patterns and machine learning techniques in a large-scale marketing experiment in Asia, the adoption rate is increased by 13 times compared to the approach used by  ...  A data-driven and scientific approach to marketing, through more tailored campaigns, contributes to less irrelevant offers for the customers, and better cost efficiency for the companies.  ...  The next two clusters coincided with Mahasen, which made landfall on 15 and 16 May, and a cold front, which flooded the southern coast between 30 May and 1 June.  ... 
arXiv:1702.08349v1 fatcat:q73dimeqtvdkbpsjjzwed57zqu

Data mining in soft computing framework: a survey

S. Mitra, S.K. Pal, P. Mitra
2002 IEEE Transactions on Neural Networks  
Neural networks are non-parametric, robust, and exhibit good learning and generalization capabilities in data-rich environments.  ...  Genetic algorithms provide efficient search algorithms to select a model, from mixed media data, based on some preference criterion/objective function.  ...  They have employed a neural oscillatory elastic graph matching model with hybrid radial basis functions for tropical cyclone identification and tracking. C.  ... 
doi:10.1109/72.977258 pmid:18244404 fatcat:wz6gxwj3mvgexl6slz3dl4q54i

An evaluation of CNN and ANN in prediction weather forecasting: A review

Shahab Kareem, Zhala Jameel Hamad, Shavan Askar
2021 Sustainable Engineering and Innovation, ISSN 2712-0562  
And also, Convolutional Neural Networks (CNNs) are a form of deep learning technique that can help classify, recognize, and predict trends in climate change and environmental data.  ...  The prediction technique relies solely upon learning previous input values from intervals in order to forecast future values.  ...  CNN models in two and three dimensions, as well as a two-dimensional framework via the attention layer, and a two-dimensional system with upscaling with distance-wise separable convolutions are all compared  ... 
doi:10.37868/sei.v3i2.id146 fatcat:kwf7twyy4zfbzflringf3yd3hu

The art and science of large-scale disasters

M. Gad-El-Hak
2009 Bulletin of the Polish Academy of Sciences: Technical Sciences  
A universal, quantitative metric that puts all natural and manmade disasters on a common scale is proposed. Issues of prediction, control and mitigation of catastrophes are presented.  ...  Three take-home messages are conveyed, however: a universal metric for all natural and manmade disasters is presented; all facets of the genre are described; and a proposal is made to view all disasters  ...  Super Typhoon Tip is the most intense tropical cyclone on record at 870 mbar.  ... 
doi:10.2478/v10175-010-0101-8 fatcat:66olp2hzlva6pppizpuc56bfye

State of the Climate in 2011

Jessica Blunden, Derek S. Arndt
2012 Bulletin of The American Meteorological Society - (BAMS)  
1 and http://www.ncdc.noaa. gov/bams-state-of-the-climate/ This report was printed on 85%-100% post-consumer recycled paper.  ...  Chapter 4: Charles "Chip" Guard, NOAA/NWS/Guam Weather Forecast Office is thanked for his contributions to and assistance with the section dealing with tropical cyclones in the Western North Paci c basin  ...  Speci cally, Lesley Williams and Melissa Fernau provided valuable editorial advice and logistical support.  ... 
doi:10.1175/2012bamsstateoftheclimate.1 fatcat:yfped6efmzbddoz7w574pcgzg4

Social physics [article]

Marko Jusup, Petter Holme, Kiyoshi Kanazawa, Misako Takayasu, Ivan Romic, Zhen Wang, Suncana Gecek, Tomislav Lipic, Boris Podobnik, Lin Wang, Wei Luo, Tin Klanjscek (+3 others)
2021 arXiv   pre-print
Here, we dub the physics-inspired and physics-like work on societal problems "social physics", and pay our respect to intellectual mavericks who nurtured the field to its maturity.  ...  with social scientists, environmental scientists, philosophers, and more.  ...  Meta-learning approaches can be metric-based, model-based, and optimisation based.  ... 
arXiv:2110.01866v1 fatcat:ccfxyezl6zgddd6uvrxubmaxua

Changing Landscapes Of Disasters In India

Janki Andharia, Prabhakar Jayaprakash
2014 Zenodo  
The paper points to significance of structural, social, and political processes that define the relationship between communities, ecosystems and technologies in disaster research.  ...  With the global increase in frequency and intensity of disasters, the need to address diverse challenges in the field of disaster research and practice requires a perspective beyond the current hazard-centric  ...  It had encountered similar problems in Andhra Pradesh and Maharashtra.  ... 
doi:10.5281/zenodo.268939 fatcat:bu3ckndbq5awzbvajkp2jeki4i

Spatial machine learning: new opportunities for regional science

Katarzyna Kopczewska
2021 The annals of regional science  
It provides an overview of the existing spatial toolbox proposed in the literature: unsupervised learning, which deals with clustering of spatial data, and supervised learning, which displaces classical  ...  It provides details of spatial machine learning models, which are combined with spatial data integration, modelling, model fine-tuning and predictions to deal with spatial autocorrelation and big data.  ...  Cai et al. (2020) estimate tropical cyclone risk with ST-DBSCAN.  ... 
doi:10.1007/s00168-021-01101-x fatcat:me54gjscejevla5g23vcho74ai

A trans-disciplinary review of deep learning research and its relevance for water resources scientists

Chaopeng Shen
2018 Water Resources Research  
Deep learning (DL), a new-generation of artificial neural network research, has transformed industries, daily lives and various scientific disciplines in recent years.  ...  The review reveals that various physical and geoscientific disciplines have utilized DL to address data challenges, improve efficiency, and gain scientific insights.  ...  Michigan State and three anonymous reviewers whose suggestions and comments have helped to improve this paper greatly. This review paper is theoretical and does not contain any dataset to be shared.  ... 
doi:10.1029/2018wr022643 fatcat:ruopsnchg5eg5hsiccyadinf54
« Previous Showing results 1 — 15 out of 232 results