zhongtouwang2019

zhongtouwang2019's Stars

• justjavac/free-programming-books-zh_CN

  :books: 免费的计算机编程类中文书籍，欢迎投稿

  111k5.9k028.2k

• lencx/ChatGPT

  🔮 ChatGPT Desktop Application (Mac, Windows and Linux)

  Language:Rust52.6k4451.1k5.9k

• AZeC4/TelegramGroup

  2024最新悄咪咪收集的10000+个Telegram群合集，附全网最有趣好用的机器人BOT🤖【电报百科全书】

  14.5k19301k

• zotero-chinese/styles

  中文 CSL 样式

  Language:XML5.1k18315828

• matlab-deep-learning/transformer-models

  Deep Learning Transformer models in MATLAB

  Language:MATLAB202241960

• chrisleaman/awesome-coastal

  A curated list of awesome resources for coastal engineers and scientists

  95144813

• GMfatcat/ConvLSTM-CNN-for-tropical-cyclone

  Images timeseries sequence with ConvLSTM for windspeed prediction & CNN cyclone intensity

  Language:Jupyter Notebook31117

• akarimp/ScientiMate

  ScientiMate: Coastal and Ocean Data Analysis Library

  Language:Python24202

• openearth/pyswan

  Spectral oceanwaves classes and SWAN IO

  Language:Jupyter Notebook171202

• yty3805595/typhoon_prediction

  # typhoon Analysis satellite images of typhoons by deep-learning (CNN), based on PyTorch. This CNN learns to map the satellite images of typhoons to their max wind speed from. The labeled train set is obtained from agora/JMA. ## Requirements * BeautifulSoup * PIL * Pytorch ## Usage 1. Run `download.py`, download the satellite images of typhoons to folder `tys_raw`. 2. Run `create_samples.py`, convert raw data into the legal samples for our CNN, create two new forlder `train_set` and `test_set`. 3. Train CNN using `train_net.py`, the trained CNN will be saved as a disk file `net_relu.pt`. 4. Run `test_net.py`, analysis the test set. After 10 epoches training the CNN regressor reached mean loss about 8 (knots) in train set and about 10 (knots) in test set.  Here is what this CNN thinks of the top 20 typhoons sorted by max wind. ``` 1 ('197920', 130.27679443359375) 2 ('200914', 127.7662582397461) 3 ('199019', 122.92172241210938) 4 ('200918', 122.84004211425781) 5 ('201614', 122.66597747802734) 6 ('201601', 122.03250885009766) 7 ('201513', 121.75947570800781) 8 ('200922', 121.35771942138672) 9 ('201013', 120.0194091796875) 10 ('201330', 118.92587280273438) 11 ('201419', 117.6025390625) 12 ('198305', 117.10270690917969) 13 ('201422', 116.77259063720703) 14 ('198522', 116.46116638183594) 15 ('201327', 116.42304992675781) 16 ('201216', 116.36921691894531) 17 ('198221', 116.18096923828125) 18 ('199230', 115.96656799316406) 19 ('198210', 115.96611022949219) 20 ('201328', 115.57132720947266) ``` ## Tips * Memory should be at least 1.5G . * This project is written without `cuda()`, while you can use `cuda()` to transfer the CNN onto GPU and speedup the training. * The images and labels are crawled from agora.ax.nii.ac.jp/digital-typhoon , and the labels are refered to JMA(Japan Meteorological agency).

  Language:Python16204

• sobakrim/Two-stage-CNN-LSTM-

  Learning the spatio-temporal relationship between wind and significant wave height using deep learning

  Language:Jupyter Notebook144

• csherwood-usgs/SWAN_example

  Example Matlab scripts for prepping and viewing SWAN model runs.

  Language:MATLAB10405

• KouraniMEKA/SWAN-MAT

  A MATLAB code that generates necessary files to run SWAN (Simulating WAves Nearshore), and helps plotting results.

  Language:MATLAB93

• jmcconochie/wavespectra2dsplitfit

  Ocean wave 2D spectrum partitioning and fitting JONSWAP spectrum

  Language:Jupyter Notebook8101

• noaa-ocs-modeling/PaHM

  Parametric Hurricane Modeling System

  Language:C56276

• nguyenquangchien/OceanSpec

  🌊 Visualise ocean wave spectra - project in ECMWF hackathon 2022

  Language:Python40

• sccrosby/PartitionAlgorithm

  Partitions wave frequency spectra into various swell and sea sources

  Language:Matlab42

• halldm2000/TUTORIAL-PYTORCH-CYCLONES-2021

  Deep learning tutorial using PyTorch to classify tropical cyclones

  Language:Jupyter Notebook30

• Holmes-Alan/TeamViewer-Free

  Mac/Windows TeamViewer 破解版，解除被检测出商业用途限制

  Language:Python200

• jumpen/MASNUM-wave-model

  The third-generation Wave Model LAGFD-WAM was proposed early in 1990s in LAGFD (Laboratory of Geophysical Fluid Dynamics), FIO (First Institute of Oceanography) of SOA (State Oceanic Administration), China. It has marked originality in 1) The energy and action energy spectrum balance equations, 2) The source functions of dissipation and bottom friction, 3) The wave-current interaction source function and 4) The computational scheme. The model has been compared with WAM model in typical wind fields and gave concerted results in general sea state and good improvement in high sea state. Also the model has been used in China seas for forecast and hindcast practices and got results consistent with filed measured data.

  21

• oceanremotesensing/FigureBest-2.0

  A MATLAB plugin for automatic beautification of data plots (.fig)

  Language:MATLAB2000

• oulebsir-rafik/Wave_modelling

  This repository present some notebooks on modelling using machine learning

  Language:Jupyter Notebook2200

• Giants533/hurricane_tools

  Language:Python1100

• Giants533/NWP-Hurricane-Katrina

  Numerical weather predictions for the Hurricane Katrina using WRF model on real data

  Language:JavaScript1100

• GitContainer/wdm

  Implementation of the Wavelet Directional Method (WDM) to compute the directional wave spectrum from an array of surface elevation measurements.

  Language:Python10

• jhsa26/deeplearning_ai_books

  deeplearning.ai（吴恩达老师的深度学习课程笔记及资源）

  Language:HTML1100

• krober10nd/ADCIRC_MATLAB

  Series of MATLAB scripts and functions for manipulating ADCIRC meshes, interpolation of bathymetry, and calculation of specific quantities

  Language:Fortran1200

• raeedcho/circ-toolbox

  Combination of CircStat toolbox and CircKSDensity

  Language:Matlab1200

• zhongtouwang2019/Masterthesis_Code

  Language:Jupyter Notebook100

• zhongtouwang2019/ScientiMate

  ScientiMate, Earth-Science Data Analysis Library

  Language:MATLAB1000