satellite_leak_detection:使用机器学习检测卫星图像中的漏水-源码
泄漏检测
草稿2017-05-01
迈克尔·克拉克（Michael.clark via wassname dot org），克雷格·巴尔达奇诺（Craig Baldacchino）
该项目探讨了我们可以使用卫星图像和机器学习来发现泄漏的想法。 主要假设是，鉴于泄漏维修的时间和地点以及给定的10-15m2分辨率的卫星图像，我们可以比随机猜测所定义的基准更好地预测泄漏。 我们使用随机森林模型，然后使用超优化调整数据过滤器和模型参数。 我们的结果显示f1得分约为0.6，而虚拟f1得分为0.5。 这个小的改进支持了我们的假设，但是它表示预测能力太差，无法用于管道维护。 我们预计，以更高分辨率的图像重复实验可能会提供有用的预测能力水平。
介绍
西澳大利亚州的漏水造成了超过100亿升的水，每年造成的损失超过10亿美元。 西澳大利亚州自来水公司每年只能人工检查10-12％的管网是否有不可见的泄漏 。
文件下载
资源详情
[{"title":"（ 51 个子文件 20.05MB ） satellite_leak_detection:使用机器学习检测卫星图像中的漏水-源码","children":[{"title":"satellite_leak_detection-master","children":[{"title":".gitattributes <span style='color:#111;'> 210B </span>","children":null,"spread":false},{"title":"notebooks","children":[{"title":"leak_helpers","children":[{"title":"modelling","children":[{"title":"dice_loss.py <span style='color:#111;'> 680B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 95B </span>","children":null,"spread":false},{"title":"multichannel_imagedatagenerator.py <span style='color:#111;'> 6.99KB </span>","children":null,"spread":false},{"title":"filters.py <span style='color:#111;'> 6.20KB </span>","children":null,"spread":false}],"spread":true},{"title":"geometry.py <span style='color:#111;'> 2.14KB </span>","children":null,"spread":false},{"title":"analysis.py <span style='color:#111;'> 3.79KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"models.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"visualization.py <span style='color:#111;'> 856B </span>","children":null,"spread":false},{"title":"earth_engine.py <span style='color:#111;'> 7.35KB </span>","children":null,"spread":false}],"spread":true},{"title":"2_qc_scraped_data.ipynb <span style='color:#111;'> 1.32MB </span>","children":null,"spread":false},{"title":"scraped_satellite_images","children":[{"title":"scraping_earth_engine_s1-all.ipynb <span style='color:#111;'> 89.39KB </span>","children":null,"spread":false},{"title":"scraping_earth_engine_sentinel_2-austin_leaks.ipynb <span style='color:#111;'> 34.53KB </span>","children":null,"spread":false},{"title":"scraping_earth_engine_landsat-8_AUTX.ipynb <span style='color:#111;'> 59.12KB </span>","children":null,"spread":false},{"title":"scraping_earth_engine_sentinel_1b_AUTX.ipynb <span style='color:#111;'> 63.42KB </span>","children":null,"spread":false},{"title":"scraping_earth_engine_landsat-7_AUTX.ipynb <span style='color:#111;'> 28.72KB </span>","children":null,"spread":false},{"title":"scraping_earth_engine_NAIP_all_v2.ipynb <span style='color:#111;'> 140.56KB </span>","children":null,"spread":false}],"spread":true},{"title":"3_model.ipynb <span style='color:#111;'> 727.96KB </span>","children":null,"spread":false},{"title":"0_process_data","children":[{"title":"process_SA_AU_leaks.ipynb <span style='color:#111;'> 215.94KB </span>","children":null,"spread":false},{"title":"process_austin_leaks.ipynb <span style='color:#111;'> 581.74KB </span>","children":null,"spread":false}],"spread":true},{"title":"3a_hyperopt.ipynb <span style='color:#111;'> 515.89KB </span>","children":null,"spread":false}],"spread":true},{"title":"images","children":[{"title":"Example_of_S2_without_leak.png <span style='color:#111;'> 58.80KB </span>","children":null,"spread":false},{"title":"Example_of_S2_with_leak.png <span style='color:#111;'> 64.64KB </span>","children":null,"spread":false}],"spread":true},{"title":"requirements.txt <span style='color:#111;'> 833B </span>","children":null,"spread":false},{"title":"data","children":[{"title":"leak_datasets","children":[{"title":"sawater_leaks","children":[{"title":"SN840 - Updated table.xlsx <span style='color:#111;'> 2.96MB </span>","children":null,"spread":false},{"title":"readme.md <span style='color:#111;'> 313B </span>","children":null,"spread":false}],"spread":true},{"title":"austin_leaks","children":[{"title":"PIR_Leaks2.txt <span style='color:#111;'> 15.82MB </span>","children":null,"spread":false},{"title":"readme.md <span style='color:#111;'> 1.45KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"scraped_satellite_images","children":[{"title":"s2-AUTX_COPERNICUS-S2","children":[{"title":"data_metadata.json <span style='color:#111;'> 12.21MB </span>","children":null,"spread":false},{"title":"script_metadata.json <span style='color:#111;'> 576B </span>","children":null,"spread":false},{"title":"readme.md <span style='color:#111;'> 499B </span>","children":null,"spread":false},{"title":"data.h5 <span style='color:#111;'> 133B </span>","children":null,"spread":false}],"spread":true},{"title":"l7-AUTX_LANDSAT-LE7_L1T","children":[{"title":"data_metadata.json <span style='color:#111;'> 74.99MB </span>","children":null,"spread":false},{"title":"script_metadata.json <span style='color:#111;'> 503B </span>","children":null,"spread":false},{"title":"readme.md <span style='color:#111;'> 499B </span>","children":null,"spread":false},{"title":"data.h5 <span style='color:#111;'> 134B </span>","children":null,"spread":false}],"spread":true},{"title":"l8-AUTX_LANDSAT-LC8_L1T","children":[{"title":"data_metadata.json <span style='color:#111;'> 35.19MB </span>","children":null,"spread":false},{"title":"script_metadata.json <span style='color:#111;'> 594B </span>","children":null,"spread":false},{"title":"readme.md <span style='color:#111;'> 499B </span>","children":null,"spread":false},{"title":"data.h5 <span style='color:#111;'> 134B </span>","children":null,"spread":false}],"spread":true},{"title":"s1-AUTX_COPERNICUS-S1_GRD","children":[{"title":"data_metadata.json <span style='color:#111;'> 4.70MB </span>","children":null,"spread":false},{"title":"script_metadata.json <span style='color:#111;'> 479B </span>","children":null,"spread":false},{"title":"readme.md <span style='color:#111;'> 499B </span>","children":null,"spread":false},{"title":"data.h5 <span style='color:#111;'> 133B </span>","children":null,"spread":false}],"spread":true},{"title":"NAIP_AUTX_USDA-NAIP-DOQQ","children":[{"title":"data_metadata.json <span style='color:#111;'> 70.23KB </span>","children":null,"spread":false},{"title":"script_metadata.json <span style='color:#111;'> 477B </span>","children":null,"spread":false},{"title":"readme.md <span style='color:#111;'> 499B </span>","children":null,"spread":false},{"title":"data.h5 <span style='color:#111;'> 132B </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true},{"title":".gitignore <span style='color:#111;'> 2.05KB </span>","children":null,"spread":false},{"title":"readme.md <span style='color:#111;'> 15.94KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}]
评论信息
其他资源
- 线性代数导论第5版课后答案
- phpmyadmin批量爆破
- DM8与Oracle12c兼容性白皮书.pdf
- adb全部源码
- 图像畸变校正
- 外推法求解抛物型偏微分方程MATLAB
- Unix内核源码剖析-Unix内核源码剖析.[日]青柳隆宏 高清PDF版.pdf
- MEMS和微系统——设计与制造
- 基于ZigBee + HXD019D 的万能红外转发器
- Directshow SDK包（无须安装）
- stm32f107 lan8720
- Android 仿QQ后台运行时收到推送消息 在顶部弹出 源码
- 北邮复试笔试题（回忆版）
- 60W boost电路的设计.rar
- Crack_dsp_builder_11.0
- USBQD_V3.0_XiTongZhiJia.rar
- MFC 窗口分割源码
- UML类图入门，看完基本懂了怎么画图了
- 铁威马指定硬盘复制文件1.docx
- 度假村项目（SSH框架版）
- 医学图像处理概述
- c#qq仿真程序源码
- asp酒店订房系统
- Spring Cloud Consul服务消费方集成JSP和Mybatis完成示例
- Writing Efficient Programs.pdf
免责申明
【只为小站】的资源来自网友分享，仅供学习研究，请务必在下载后24小时内给予删除，不得用于其他任何用途，否则后果自负。基于互联网的特殊性，【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查；无论 【只为小站】 经营者是否已进行审查，用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场，基于网友分享，根据中国法律《信息网络传播权保护条例》第二十二条之规定，若资源存在侵权或相关问题请联系本站客服人员，zhiweidada#qq.com，请把#换成@，本站将给予最大的支持与配合，做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明
本站所有资源不代表本站的观点或立场，基于网友分享，根据中国法律《信息网络传播权保护条例》第二十二条之规定，若资源存在侵权或相关问题请联系本站客服人员，zhiweidada#qq.com，请把#换成@，本站将给予最大的支持与配合，做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明