{
    "info": {
        "author": "jimmy",
        "author_email": "jimmy60504@gmail.com",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 2 - Pre-Alpha",
            "License :: OSI Approved :: MIT License",
            "Operating System :: POSIX :: Linux",
            "Programming Language :: Python :: 3.5",
            "Programming Language :: Python :: 3 :: Only",
            "Topic :: Scientific/Engineering :: Artificial Intelligence"
        ],
        "description": "# SeisNN\n\nSeismic event P phase picking project\n\nMain framework: Obspy, Seisan, Tensorflow with Keras, Pytorch\n\nUsing U-net to generate pick probability\n\n![example](example.png)\n\n---\n\nEarly access\n\nThe code is still in the development state, API will change frequently. \n\nPlease star us for upcoming updates!\n\n---\n\nPrerequisite:\n\n- S-File catalog from [SEISAN](http://seisan.info/)\n- SeisComP Data Structure (SDS) database. The directory and file layout of SDS is defined as:\n\n      SDSROOT/YEAR/NET/STA/CHAN.TYPE/NET.STA.LOC.CHAN.TYPE.YEAR.DAY\n\nInstallation:\n\n- pip install seisnn\n- Clone this repository\n- Follow the instructions in the [Docker](docker) folder to create a Docker container.\n- SSH into the Docker container you create.\n\nIn the [scripts](scripts) folder:\n\n- [generate_dataset.py](scripts/generate_dataset.py)\n  - Make S-Files into training .pkl datasets.\n- [evalution.py](seisnn/qc.py)\n  - Calculate precision, recall and F1 score.\n  - Plot error distribution.\n- [plot_instance.py](scripts/plot_instance.py)\n  - Plot the wavefile, picks and the probability form the .pkl dataset.\n- [scanning.py](scripts/scanning.py)\n  - Scan through all stations available in the given time window, transfer into .pkl dataset.\n\nTraining:\n\nYou can choose between [scripts/tensorflow](scripts/tensorflow) or [scripts/pytorch](scripts/pytorch)\n\n- [pre_training.py](scripts/tensorflow/pre_training.py)\n  - Pre-train the model using small dataset.\n- [training.py](scripts/tensorflow/training.py)\n  - Train the model with the pre-trained weight.\n- [prediction.py](scripts/tensorflow/prediction.py)\n  - Predict the probability of the picks and write into the dataset.\n\nModel:\n\nThe model is stored in [seisnn/tensorflow](seisnn/tensorflow) or [seisnn/pytorch](seisnn/pytorch) \n\n- Nest_Net\n  - Unet++ code modified from [MrGiovanni](https://github.com/MrGiovanni/Nested-UNet/blob/master/model_logic.py)\n\n---\n\nReference:\n\n [PhaseNet](https://arxiv.org/abs/1803.03211)\n\n Zhu, W., & Beroza, G. C. (2018). PhaseNet: A Deep-Neural-Network-Based Seismic Arrival Time Picking Method. arXiv preprint arXiv:1803.03211.\n\n [U-net](https://lmb.informatik.uni-freiburg.de/people/ronneber/u-net/)\n\n Ronneberger, O., Fischer, P., & Brox, T. (2015, October). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention (pp. 234-241). Springer, Cham.\n\n [U-net ++](https://doi.org/10.1007/978-3-030-00889-5_1)\n\n Zhou, Z., Siddiquee, M. M. R., Tajbakhsh, N., & Liang, J. (2018). Unet++: A nested u-net architecture for medical image segmentation. In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support (pp. 3-11). Springer, Cham.\n\n\n\n---\n\n[Jimmy Lab wordpress](https://jimmylab.wordpress.com/)\n\n[![License](http://img.shields.io/:license-mit-blue.svg?style=flat-square)](http://badges.mit-license.org)\n\n\n",
        "description_content_type": "",
        "docs_url": null,
        "download_url": "",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/jimmy60504/SeisNN",
        "keywords": "",
        "license": "MIT",
        "maintainer": "",
        "maintainer_email": "",
        "name": "SeisNN",
        "package_url": "https://pypi.org/project/SeisNN/",
        "platform": "",
        "project_url": "https://pypi.org/project/SeisNN/",
        "project_urls": {
            "Homepage": "https://github.com/jimmy60504/SeisNN"
        },
        "release_url": "https://pypi.org/project/SeisNN/0.0.2.dev1/",
        "requires_dist": [
            "matplotlib (>=3.0.3)",
            "numpy (>=1.16.2)",
            "obspy (>=1.1.1)",
            "scipy (>=1.2.1)"
        ],
        "requires_python": ">=3.5",
        "summary": "Deep learning seismic phase picking package",
        "version": "0.0.2.dev1"
    },
    "last_serial": 5290502,
    "releases": {
        "0.0.2.dev1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "afefe5264d4b09cab62672ece48ef249",
                    "sha256": "8f1dbc191e2f3a1c79dab4750c2d525f7c85f469115c15fad7a839967ab2e535"
                },
                "downloads": -1,
                "filename": "SeisNN-0.0.2.dev1-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "afefe5264d4b09cab62672ece48ef249",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": ">=3.5",
                "size": 12067,
                "upload_time": "2019-05-20T05:55:39",
                "url": "https://files.pythonhosted.org/packages/15/4b/2c25874e955dea22b209609b1166ee358fe4952dd23f4208e587d09fc348/SeisNN-0.0.2.dev1-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "da3663920c110752700a092f3ee1d2bd",
                    "sha256": "4d20ed8f3a7e9e077a0c3114910a0145049c53ab2d71e8139def12c13825f075"
                },
                "downloads": -1,
                "filename": "SeisNN-0.0.2.dev1.tar.gz",
                "has_sig": false,
                "md5_digest": "da3663920c110752700a092f3ee1d2bd",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": ">=3.5",
                "size": 9510,
                "upload_time": "2019-05-20T05:55:40",
                "url": "https://files.pythonhosted.org/packages/e0/ed/0500055a454357a6be27901b1ddc05fbf935f216cfe9ec6eda97db817f64/SeisNN-0.0.2.dev1.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "afefe5264d4b09cab62672ece48ef249",
                "sha256": "8f1dbc191e2f3a1c79dab4750c2d525f7c85f469115c15fad7a839967ab2e535"
            },
            "downloads": -1,
            "filename": "SeisNN-0.0.2.dev1-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "afefe5264d4b09cab62672ece48ef249",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.5",
            "size": 12067,
            "upload_time": "2019-05-20T05:55:39",
            "url": "https://files.pythonhosted.org/packages/15/4b/2c25874e955dea22b209609b1166ee358fe4952dd23f4208e587d09fc348/SeisNN-0.0.2.dev1-py3-none-any.whl"
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "da3663920c110752700a092f3ee1d2bd",
                "sha256": "4d20ed8f3a7e9e077a0c3114910a0145049c53ab2d71e8139def12c13825f075"
            },
            "downloads": -1,
            "filename": "SeisNN-0.0.2.dev1.tar.gz",
            "has_sig": false,
            "md5_digest": "da3663920c110752700a092f3ee1d2bd",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.5",
            "size": 9510,
            "upload_time": "2019-05-20T05:55:40",
            "url": "https://files.pythonhosted.org/packages/e0/ed/0500055a454357a6be27901b1ddc05fbf935f216cfe9ec6eda97db817f64/SeisNN-0.0.2.dev1.tar.gz"
        }
    ]
}