![\"\"](\"https://www.clarizen.com/wp-content/uploads/2017/02/sustain_projects.jpg\")
![\"\"](\"https://media2.giphy.com/media/rxD7ZkXW3viBa/giphy.gif?cid=790b76118fbddb42eed34454c46cb1a8da9709094563407a&rid=giphy.gif\")
![\"\"](\"https://media.giphy.com/media/oSr6UuF3iS7aE/giphy.gif\")
![\"\"](\"http://fizz.phys.dal.ca/~atmos/animation/o3_movie.gif\")
\nsource: http://fizz.phys.dal.ca/~atmos/martin/?page_id=100
Emissions Factors and Use of the WebFIRE\nDatabase](https://www3.epa.gov/ttn/chief/efpac/procedures/procedures81213.pdf)
\n\n[NOx lifetimes and emissions of cities and power plants in polluted\n\nbackground estimated by satellite observations](NOx lifetimes and emissions of cities and power plants in polluted\nbackground estimated by satellite observations)
\n\nsatellite retrievals](https://www.atmos-chem-phys.net/16/5283/2016/acp-16-5283-2016.pdf)
\n\nbackground estimated by satellite observations](https://www.atmos-chem-phys.net/16/5283/2016/acp-16-5283-2016.pdf)
\n\nJoint Learning from Earth Observation and OpenStreetMap Data to Get Faster Better Semantic Maps\n\nAir Emissions Factors and Quantification\n\nHow much carbon dioxide is produced per kilowatthour of U.S. electricity generation?\n\nThe Need for Alternate PM2.5 Emission Factors for Gas-Fired Combustion Unit\n\nHow to Calculate Air Emissions ?\n\nGlobal Power Plant database by WRI\n> Description\nThe Global Power Plant Database is a comprehensive, open source database of power plants around the world. It centralizes power plant data to make it easier to navigate, compare and draw insights for one’s own analysis. The database covers approximately 30,000 power plants from 164 countries and includes thermal plants (e.g. coal, gas, oil, nuclear, biomass, waste, geothermal) and renewables (e.g. hydro, wind, solar). Each power plant is geolocated and entries contain information on plant capacity, generation, ownership, and fuel type. It will be continuously updated as data becomes available.
\n\nSentinel 5P OFFL NO2 by EU/ESA/Copernicus\n> Sentinel-5 Precursor\nSentinel-5 Precursor is a satellite launched on 13 October 2017 by the European Space Agency to monitor air pollution. The onboard sensor is frequently referred to as Tropomi (TROPOspheric Monitoring Instrument). The OFFL/NO2 is a dataset that provides offline high-resolution imagery of NO2 concentration.
\n\nGlobal Forecast System 384-Hour Predicted Atmosphere Data by NOAA/NCEP/EMC\n> The Global Forecast System (GFS) is a weather forecast model produced by the National Centers for Environmental Prediction (NCEP). The GFS dataset consists of selected model outputs (described below) as gridded forecast variables. The 384-hour forecasts, with 3-hour forecast interval, are made at 6-hour temporal resolution (i.e. updated four times daily). Use the 'creation_time' and 'forecast_time' properties to select data of interest.
\n\nGlobal Land Data Assimilation System by NASA\n> Global Land Data Assimilation System (GLDAS) ingests satellite and ground-based observational data products. Using advanced land surface modeling and data assimilation techniques, it generates optimal fields of land surface states and fluxes. his dataset provided by NASA ingest satellite.
\n\nTrade commodities for fuel types, total fuel consumed, and/or data from the US Energy Information Agency (EIA).
\n\nAtmospheric Composition Analysis Group\n> GEOS-Chem Community Mission: to advance understanding of human and natural influences on the environment through a comprehensive, state-of-the-science, readily accessible global model of atmospheric composition.
\n\n\n\nGeographic 2D CRS used in World
\n\n(https://www.gov.uk/government/organisations/defence-science-and-technology-laboratory)
\n\nhttps://www.cosmiqworks.org/\n> Since 2015, CosmiQ Works has focused on the geospatial analytics market and provided technical insights, targeted research, and reports.
The Spacenet Challenge\n> Winning Solution for the Spacenet Challenge: Joint Learning with OpenStreetMap
SATELLITE IMAGERY MULTISCALE RAPID DETECTION WITH WINDOWED NETWORKS (SIMRDWN) REPOSITORY
SPACENET 6 Multimodal Data Analysis for Travel Routing and Time Estimation
SATELLITE IMAGERY MULTISCALE RAPID DETECTION WITH WINDOWED NETWORKS (SIMRDWN) REPOSITORY
-Resources for deep learning with satellite & aerial imagery
\n\n[🌏🌿DS4G: Go to the Green Future!] (https://www.kaggle.com/caesarlupum/ds4g-go-to-the-green-future) by @caesarlupum
\n\nSimilar comp. [Satellite Imagery]\nDstl Satellite Imagery Feature Detection
\n\n👍 ✔️ Thanks Everyone✔️
", "messages": [ { "id": 743212, "postDate": "2020-02-11T22:11:22.150Z", "content": "
\nsource: http://fizz.phys.dal.ca/~atmos/martin/?page_id=100
Emissions Factors and Use of the WebFIRE\nDatabase](https://www3.epa.gov/ttn/chief/efpac/procedures/procedures81213.pdf)
\n\n[NOx lifetimes and emissions of cities and power plants in polluted\n\nbackground estimated by satellite observations](NOx lifetimes and emissions of cities and power plants in polluted\nbackground estimated by satellite observations)
\n\nsatellite retrievals](https://www.atmos-chem-phys.net/16/5283/2016/acp-16-5283-2016.pdf)
\n\nbackground estimated by satellite observations](https://www.atmos-chem-phys.net/16/5283/2016/acp-16-5283-2016.pdf)
\n\nJoint Learning from Earth Observation and OpenStreetMap Data to Get Faster Better Semantic Maps\n\nAir Emissions Factors and Quantification\n\nHow much carbon dioxide is produced per kilowatthour of U.S. electricity generation?\n\nThe Need for Alternate PM2.5 Emission Factors for Gas-Fired Combustion Unit\n\nHow to Calculate Air Emissions ?\n\nGlobal Power Plant database by WRI\n> Description\nThe Global Power Plant Database is a comprehensive, open source database of power plants around the world. It centralizes power plant data to make it easier to navigate, compare and draw insights for one’s own analysis. The database covers approximately 30,000 power plants from 164 countries and includes thermal plants (e.g. coal, gas, oil, nuclear, biomass, waste, geothermal) and renewables (e.g. hydro, wind, solar). Each power plant is geolocated and entries contain information on plant capacity, generation, ownership, and fuel type. It will be continuously updated as data becomes available.
\n\nSentinel 5P OFFL NO2 by EU/ESA/Copernicus\n> Sentinel-5 Precursor\nSentinel-5 Precursor is a satellite launched on 13 October 2017 by the European Space Agency to monitor air pollution. The onboard sensor is frequently referred to as Tropomi (TROPOspheric Monitoring Instrument). The OFFL/NO2 is a dataset that provides offline high-resolution imagery of NO2 concentration.
\n\nGlobal Forecast System 384-Hour Predicted Atmosphere Data by NOAA/NCEP/EMC\n> The Global Forecast System (GFS) is a weather forecast model produced by the National Centers for Environmental Prediction (NCEP). The GFS dataset consists of selected model outputs (described below) as gridded forecast variables. The 384-hour forecasts, with 3-hour forecast interval, are made at 6-hour temporal resolution (i.e. updated four times daily). Use the 'creation_time' and 'forecast_time' properties to select data of interest.
\n\nGlobal Land Data Assimilation System by NASA\n> Global Land Data Assimilation System (GLDAS) ingests satellite and ground-based observational data products. Using advanced land surface modeling and data assimilation techniques, it generates optimal fields of land surface states and fluxes. his dataset provided by NASA ingest satellite.
\n\nTrade commodities for fuel types, total fuel consumed, and/or data from the US Energy Information Agency (EIA).
\n\nAtmospheric Composition Analysis Group\n> GEOS-Chem Community Mission: to advance understanding of human and natural influences on the environment through a comprehensive, state-of-the-science, readily accessible global model of atmospheric composition.
\n\n\n\nGeographic 2D CRS used in World
\n\n(https://www.gov.uk/government/organisations/defence-science-and-technology-laboratory)
\n\nhttps://www.cosmiqworks.org/\n> Since 2015, CosmiQ Works has focused on the geospatial analytics market and provided technical insights, targeted research, and reports.
The Spacenet Challenge\n> Winning Solution for the Spacenet Challenge: Joint Learning with OpenStreetMap
SATELLITE IMAGERY MULTISCALE RAPID DETECTION WITH WINDOWED NETWORKS (SIMRDWN) REPOSITORY
SPACENET 6 Multimodal Data Analysis for Travel Routing and Time Estimation
SATELLITE IMAGERY MULTISCALE RAPID DETECTION WITH WINDOWED NETWORKS (SIMRDWN) REPOSITORY
-Resources for deep learning with satellite & aerial imagery
\n\n[🌏🌿DS4G: Go to the Green Future!] (https://www.kaggle.com/caesarlupum/ds4g-go-to-the-green-future) by @caesarlupum
\n\nSimilar comp. [Satellite Imagery]\nDstl Satellite Imagery Feature Detection
\n\n👍 ✔️ Thanks Everyone✔️
", "rawMarkdown": "\n\n# For everyone’s reference. I already separated a material for this great competition! Going to be adding here more as I keep searching!\n\n\n### Animations\n\n\n\n\n\n\nsource: http://fizz.phys.dal.ca/~atmos/martin/?page_id=100\n\n### Articles\n\n### [Recommended Procedures for Development of\nEmissions Factors and Use of the WebFIRE\nDatabase](https://www3.epa.gov/ttn/chief/efpac/procedures/procedures81213.pdf)\n\n#### [NOx lifetimes and emissions of cities and power plants in polluted\nbackground estimated by satellite observations](NOx lifetimes and emissions of cities and power plants in polluted\nbackground estimated by satellite observations)\n\n### [Estimates of power plant NOx emissions and lifetimes from OMI NO2\nsatellite retrievals](https://www.atmos-chem-phys.net/16/5283/2016/acp-16-5283-2016.pdf)\n\n### [NOx lifetimes and emissions of cities and power plants in polluted\nbackground estimated by satellite observations](https://www.atmos-chem-phys.net/16/5283/2016/acp-16-5283-2016.pdf)\n\n#### [Joint Learning from Earth Observation and OpenStreetMap Data to Get Faster Better Semantic Maps](https://arxiv.org/abs/1705.06057)\n\n#### [Air Emissions Factors and Quantification](https://www.epa.gov/air-emissions-factors-and-quantification/basic-information-air-emissions-factors-and-quantification#About%20Emissions%20Factors) \n\n#### [How much carbon dioxide is produced per kilowatthour of U.S. electricity generation?](https://www.eia.gov/tools/faqs/faq.php?id=74&t=11)\n\n#### [The Need for Alternate PM2.5 Emission Factors for Gas-Fired Combustion Unit](https://www.powermag.com/the-need-for-alternate-pm2-5-emission-factors-for-gas-fired-combustion-units/)\n\n#### [How to Calculate Air Emissions ?](https://www.enveraconsulting.com/how-to-calculate-air-emissions/)\n\n### Videos\n\n#### [US energy startup builds power plant that produces no carbon emissions](https://youtu.be/4_w9BId_Pms?t=2)\n\n#### [AIR POLLUTION](https://youtu.be/_dTtvtlct9k)\n\n#### [WATCH: NO2 pollution rocketing thorugh Europe pushed by mild weather](https://youtu.be/9ZeaP8ljc9E)\n\n#### [NASA ARSET: Remote Sensing of NO2 with OMI, Part 1/3](https://youtu.be/rvSjD-vGI4k)\n\n#### [NASA ARSET: Introducing TROPOMI - High Resolution NO2 Observations from Space, Part 2/3](https://youtu.be/-yOInEUJTYM)\n\n#### [NASA ARSET: Python Tools for Analyzing NO2, Part 3/3](https://youtu.be/MxBg5ZMH2nM)\n\n\n\n### Datasets\n\n[Global Power Plant database ](https://developers.google.com/earth-engine/datasets/catalog/WRI_GPPD_power_plants) by WRI\n> Description\nThe Global Power Plant Database is a comprehensive, open source database of power plants around the world. It centralizes power plant data to make it easier to navigate, compare and draw insights for one’s own analysis. The database covers approximately 30,000 power plants from 164 countries and includes thermal plants (e.g. coal, gas, oil, nuclear, biomass, waste, geothermal) and renewables (e.g. hydro, wind, solar). Each power plant is geolocated and entries contain information on plant capacity, generation, ownership, and fuel type. It will be continuously updated as data becomes available.\n\n[Sentinel 5P OFFL NO2](https://developers.google.com/earth-engine/datasets/catalog/COPERNICUS_S5P_OFFL_L3_NO2) by [EU/ESA/Copernicus](https://sentinel.esa.int/web/sentinel/user-guides/sentinel-5p-tropomi/document-library)\n> Sentinel-5 Precursor\nSentinel-5 Precursor is a satellite launched on 13 October 2017 by the European Space Agency to monitor air pollution. The onboard sensor is frequently referred to as Tropomi (TROPOspheric Monitoring Instrument). The OFFL/NO2 is a dataset that provides offline high-resolution imagery of **NO2 concentration**.\n\n[Global Forecast System 384-Hour Predicted Atmosphere Data](https://developers.google.com/earth-engine/datasets/catalog/NOAA_GFS0P25) by NOAA/NCEP/EMC\n> The Global Forecast System (GFS) is a weather forecast model produced by the National Centers for Environmental Prediction (NCEP). The GFS dataset consists of selected model outputs (described below) as gridded forecast variables. The 384-hour forecasts, with 3-hour forecast interval, are made at 6-hour temporal resolution (i.e. updated four times daily). Use the 'creation_time' and 'forecast_time' properties to select data of interest.\n\n[Global Land Data Assimilation System](https://developers.google.com/earth-engine/datasets/catalog/NASA_GLDAS_V021_NOAH_G025_T3H) by NASA\n> Global Land Data Assimilation System (GLDAS) ingests satellite and ground-based observational data products. Using advanced land surface modeling and data assimilation techniques, it generates optimal fields of land surface states and fluxes. his dataset provided by NASA ingest satellite.\n\nTrade commodities for fuel types, total fuel consumed, and/or data from the [US Energy Information Agency (EIA)](https://www.eia.gov/state/data.php?sid=RQ#CarbonDioxideEmissions).\n\n\n### Public Dataset\n\n[Atmospheric Composition Analysis Group](http://fizz.phys.dal.ca/~atmos/martin/?page_id=100#)\n> GEOS-Chem Community Mission: to advance understanding of human and natural influences on the environment through a comprehensive, state-of-the-science, readily accessible global model of atmospheric composition.\n\n[Global Power Plant Database](http://datasets.wri.org/dataset/globalpowerplantdatabase)\n\n[Geographic 2D CRS used in World](https://georepository.com/crs_4326/WGS-84.html)\n\n(https://www.gov.uk/government/organisations/defence-science-and-technology-laboratory)\n\n### Remote Sensing Tools\n- [QGIS- A Free and Open Source Geographic Information System](https://www.qgis.org/en/site/)\n- [Manifold GIS Systems](https://gisgeography.com/manifold-gis-systems/)\n- [MapInfo Professional] (https://gisgeography.com/mapinfo-professional-pitney-bowes/)\n- [ArcGIS Pro](https://gisgeography.com/arcgis-pro/)\n\n\n### Just useful links\n\n- [How To Compute Satellite Image Statistics](https://towardsdatascience.com/how-to-compute-satellite-image-statistics-and-use-it-in-pandas-81864a489144)\n\n- https://www.cosmiqworks.org/\n > Since 2015, CosmiQ Works has focused on the geospatial analytics market and provided technical insights, targeted research, and reports. \n\n- [The Spacenet Challenge](https://i.ho.lc/winning-solution-for-the-spacenet-challenge-joint-learning-with-openstreetmap.html)\n > Winning Solution for the Spacenet Challenge: Joint Learning with OpenStreetMap\n\n- [Image processing with Python and SciPy](http://prancer.physics.louisville.edu/astrowiki/index.php/Image_processing_with_Python_and_SciPy)\n- [A tool for Swarm satellite data analysis and anomaly detection](https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0212098)\n\n### Libs - Satellite Imagery\n- [Solaris](https://github.com/CosmiQ/solaris)\n > An open source ML pipeline for overhead imagery by CosmiQ Works \n\n### Projects\n- [SATELLITE IMAGERY MULTISCALE RAPID DETECTION WITH WINDOWED NETWORKS (SIMRDWN) REPOSITORY](https://www.cosmiqworks.org/category/archived-projects/)\n\n- [SPACENET 6 Multimodal Data Analysis for Travel Routing and Time Estimation](https://www.cosmiqworks.org/category/current-projects/)\n\n- [SATELLITE IMAGERY MULTISCALE RAPID DETECTION WITH WINDOWED NETWORKS (SIMRDWN) REPOSITORY](https://www.cosmiqworks.org/category/archived-projects/)\n\n-[COMET TIME SERIES (TS)](https://www.cosmiqworks.org/archived-projects/comet-time-series-ts/)\n\n-[Resources for deep learning with satellite & aerial imagery](https://github.com/robmarkcole/satellite-image-deep-learning)\n\n### Just some useful Codes\n#### [Overview of the EIE Analytics Challenge](https://www.kaggle.com/paultimothymooney/overview-of-the-eie-analytics-challenge) by @paultimothymooney \n\n#### [How to get started with the Earth Engine data](https://www.kaggle.com/paultimothymooney/how-to-get-started-with-the-earth-engine-data) by @paultimothymooney \n\n[🌏🌿DS4G: Go to the Green Future!] (https://www.kaggle.com/caesarlupum/ds4g-go-to-the-green-future) by @caesarlupum \n\nSimilar comp. [Satellite Imagery]\n[Dstl Satellite Imagery Feature Detection](https://www.kaggle.com/c/dstl-satellite-imagery-feature-detection/overview)\n\n\n👍 ✔️ Thanks Everyone✔️\n", "votes": 25 }, { "id": 743225, "postDate": "2020-02-11T22:33:23.897Z", "content": "Be sure that your searches include NO2 emissions since that is the focus of the data set (not CO2).
", "rawMarkdown": "Be sure that your searches include NO2 emissions since that is the focus of the data set (not CO2).", "votes": 3, "replies": [ { "id": 743245, "postDate": "2020-02-11T23:18:49.463Z", "content": "Thanks @pcjimmmy ! Done ! I change the searches, I'm sorry !
", "rawMarkdown": "Thanks @pcjimmmy ! Done ! I change the searches, I'm sorry !", "votes": 1 }, { "id": 743260, "postDate": "2020-02-12T00:01:43.010Z", "content": "No problems - did not want to have to search for NO2 stuff myself. I would assume that a model for CO2 and one for NO2 might be similar but suspect gas density will change the distribution from the source.
", "rawMarkdown": "No problems - did not want to have to search for NO2 stuff myself. I would assume that a model for CO2 and one for NO2 might be similar but suspect gas density will change the distribution from the source.", "votes": 1 }, { "id": 743327, "postDate": "2020-02-12T01:47:42.030Z", "content": "After reading more - I think you were right and I was wrong. The link in the overview takes you to a CO2 focused page. I think I went off course because the notebook example has NO2. Guess I have to make the assumption that the same data for CO2 can be extracted from Google.
", "rawMarkdown": "After reading more - I think you were right and I was wrong. The link in the overview takes you to a CO2 focused page. I think I went off course because the notebook example has NO2. Guess I have to make the assumption that the same data for CO2 can be extracted from Google.", "votes": 1 }, { "id": 743412, "postDate": "2020-02-12T03:33:38.780Z", "content": "To clarify, we are most interested in NO2 emissions (in part because NO2 emissions can often be directly linked to fossil fuel usage), and therefore we have included it in the dataset starter pack. That being said, you can find CO2 emissions data on the Earth Engine platform, and this data can very much be used to supplement and strengthen an approach for calculating emissions factors in Puerto Rico.
", "rawMarkdown": "To clarify, we are most interested in NO2 emissions (in part because NO2 emissions can often be directly linked to fossil fuel usage), and therefore we have included it in the [dataset starter pack](https://www.kaggle.com/c/ds4g-environmental-insights-explorer/data). That being said, you can find CO2 emissions data on the Earth Engine platform, and this data can very much be used to supplement and strengthen an approach for calculating emissions factors in Puerto Rico.", "votes": 4 }, { "id": 743415, "postDate": "2020-02-12T03:36:08.540Z", "content": "Yes, I think that a lot of useful information ! Consider see this external link pls: maybe will help you http://fizz.phys.dal.ca/~atmos/martin/?page_id=100
\n\nThanks buddy !
", "rawMarkdown": "Yes, I think that a lot of useful information ! Consider see this external link pls: maybe will help you http://fizz.phys.dal.ca/~atmos/martin/?page_id=100\n\nThanks buddy !\n" }, { "id": 743420, "postDate": "2020-02-12T03:38:37.067Z", "content": "![\"Annual](\"http://individual.utoronto.ca/jged/worldnoj.png\")
\nsource: http://fizz.phys.dal.ca/~atmos/martin/?page_id=232
@pcjimmmy I want to append a bit more to my comment about CO2 vs NO2. An advantage of NO2 is that we have access to high resolution remote sensing data, whereas CO2 is difficult to measure via remote sensing. NO2 is often used as a tracer gas for NO2 because it is difficult to generate NO2 in an urban environment without also generating CO2. You could also consider looking at NO emissions and SO2 emissions, but we are particularly optimistic about models that are based off of NO2 emissions because we have high resolution remote sensing data that covers the entire globe.
", "rawMarkdown": "@pcjimmmy I want to append a bit more to my comment about CO2 vs NO2. An advantage of NO2 is that we have access to high resolution remote sensing data, whereas CO2 is difficult to measure via remote sensing. NO2 is often used as a tracer gas for NO2 because it is difficult to generate NO2 in an urban environment without also generating CO2. You could also consider looking at NO emissions and SO2 emissions, but we are particularly optimistic about models that are based off of NO2 emissions because we have high resolution remote sensing data that covers the entire globe.", "votes": 2 }, { "id": 745559, "postDate": "2020-02-13T23:32:00.653Z", "content": "Thanks for the additional information. Spent lots of time looking at Puerto Rico over the last 24 hours. I am seeing what I believe is a huge disadvantage to NO2 for the island. I need to do more work but my current conclusion is that urban area NO2 from emissions sources completely hide any power plant effect. My assumption (yet to be confirmed) is that a high percentage of automobiles on the island are diesel and an annualized image that I generated is best correlated (Mark One Eyeball) to the Google Earth Engine world population data set. While NO2 makes sense hopefully a model can find the corrections needed to account for urban emissions not related to power plants. For sure a machine learning opportunity but the short time scale for the competition makes me pretty sure my weak Python skills will not let me fully execute my theory of the problem.
\n\nHeading to Atlanta for long weekend but will generate a kernel to demonstrate the urban issue when I return middle of the week. I already have some images from the Google Earth Engine and have struggled over the last hours converting the java scripts that run great on GEE to Python in a Kaggle kernel.
\n\nThis is a screen shot of the GEE output and a 2nd with transparency down so you can see the island map.
\n\n![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F1062256%2F2fcf330b1f531b2c1e208b64add53432%2FPR%20Annualized_transparent.png?generation=1581636674400857&alt=media\"){kind=spacer}
\n![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F1062256%2Fca2b4018fef756879073dfcacfbfdad7%2FPR%20Annualized.png?generation=1581636674590789&alt=media\")
Separating vehicle emissions from industry emissions can be a major challenge, this is an interesting question. I suspect that traffic patterns and energy demands are fairly predictable. Maybe you can determine what fraction is the result of vehicle emissions by looking at the increase in emissions during peak traffic hours? Likewise, it could be informative to identify power plants that went offline during this time period and then to look for any noticeable changes in NO2 emissions.
", "rawMarkdown": "Separating vehicle emissions from industry emissions can be a major challenge, this is an interesting question. I suspect that traffic patterns and energy demands are fairly predictable. Maybe you can determine what fraction is the result of vehicle emissions by looking at the increase in emissions during peak traffic hours? Likewise, it could be informative to identify power plants that went offline during this time period and then to look for any noticeable changes in NO2 emissions.", "votes": 3 }, { "id": 746270, "postDate": "2020-02-14T19:53:41.590Z", "content": "@pcjimmmy I want to append a bit more to my comment about separating vehicle emissions from industry emissions. One reason that we selected Puerto Rico is that the power plants are isolated from the population by mountains. In the example image that you provided you can see the plume of NO2 centered on San Juan and then dispersing westward by the winds. You might want to try focusing on the large power plants on the south of the island.
", "rawMarkdown": "@pcjimmmy I want to append a bit more to my comment about separating vehicle emissions from industry emissions. One reason that we selected Puerto Rico is that the power plants are isolated from the population [by mountains](https://www.google.com/maps/place/Puerto+Rico/@17.9892465,-66.7582972,925a,35y,13.25h,78.52t/data=!3m1!1e3!4m5!3m4!1s0x8c0296261b92a7f9:0xf336ec2818049b1a!8m2!3d18.220833!4d-66.590149). In the example image that you provided you can see the plume of NO2 centered on San Juan and then dispersing westward by the winds. You might want to try focusing on the large power plants on the south of the island.", "votes": 1 }, { "id": 746474, "postDate": "2020-02-15T04:11:51.587Z", "content": "Icons for plants on the map image. You can see one plume very clearly in the south.
", "rawMarkdown": "Icons for plants on the map image. You can see one plume very clearly in the south. ", "votes": 1 }, { "id": 757570, "postDate": "2020-02-26T23:17:49.707Z", "content": "@pcjimmmy , https://www3.epa.gov/airnow/no2.pdf\nAir Quality Guide for Nitrogen Dioxide\n![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F3595464%2Fddee8ae4291ec68e079d10c4bb9f0710%2Faiq.PNG?generation=1582759059965631&alt=media\")
Have not looked at the data yet but the USA monitoring stations for NO2 can be found at the link below. Pre-packaged data sets can be downloaded and you can sign up for access to build the July to July data set we would need. Might help with the issue of separating urban emissions from power plant emissions. Hopefully there are a few for Puerto Rico.
\n\nUSA NO2 Monitoring Stations Data
", "rawMarkdown": "Have not looked at the data yet but the USA monitoring stations for NO2 can be found at the link below. Pre-packaged data sets can be downloaded and you can sign up for access to build the July to July data set we would need. Might help with the issue of separating urban emissions from power plant emissions. Hopefully there are a few for Puerto Rico.\n\n[USA NO2 Monitoring Stations Data](https://aqs.epa.gov/aqsweb/airdata/download_files.html#Meta)", "votes": 1 }, { "id": 757695, "postDate": "2020-02-27T02:54:35.870Z", "content": "Looking at the list of sites there should be 4 stations for NO2 in Puerto Rico. NO2 is a bit tricky as its reaction with sunlight and ozone is very rapid - but one would assume the USA EPA would have set up collection with that in mind. State code 72 should be Puerto Rico in all the data files you can grab here.
", "rawMarkdown": "Looking at the list of sites there should be 4 stations for NO2 in Puerto Rico. NO2 is a bit tricky as its reaction with sunlight and ozone is very rapid - but one would assume the USA EPA would have set up collection with that in mind. State code 72 should be Puerto Rico in all the data files you can grab here.", "votes": 1 } ] }, { "id": 744724, "postDate": "2020-02-13T04:24:44.820Z", "content": "Thank you very much for sharing :) really appreciate this!
", "rawMarkdown": "Thank you very much for sharing :) really appreciate this! ", "replies": [ { "id": 745103, "postDate": "2020-02-13T13:38:28.103Z", "content": "Thanks @vikramank !Please share some tips with us ! \nWaiting for your work on DS4G comp.
", "rawMarkdown": "Thanks @vikramank !Please share some tips with us ! \nWaiting for your work on DS4G comp.", "votes": 1 }, { "id": 749590, "postDate": "2020-02-18T19:47:38.937Z", "content": "Consider see this: A tool for Swarm satellite data analysis and anomaly detection
", "rawMarkdown": "Consider see this: [A tool for Swarm satellite data analysis and anomaly detection](https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0212098)" } ] }, { "id": 744577, "postDate": "2020-02-13T00:10:44.137Z", "content": "Can you read one of that files? farm-ads and farm-ads-vect? https://www.kaggle.com/devvret/farm-ads-binary-classification I've already done it. The K -Notebook is in the oven.
", "rawMarkdown": "Can you read one of that files? farm-ads and farm-ads-vect? https://www.kaggle.com/devvret/farm-ads-binary-classification I've already done it. The K -Notebook is in the oven.", "replies": [ { "id": 744641, "postDate": "2020-02-13T02:36:09.237Z", "content": "it looks very interesting! The kaggle is always full of fantastic problems to study.
", "rawMarkdown": "it looks very interesting! The kaggle is always full of fantastic problems to study.", "votes": 2 } ] }, { "id": 744575, "postDate": "2020-02-13T00:03:52.207Z", "content": "Cris I think I´ll be killed since I wrote Best Topic ever: https://www.kaggle.com/c/google-quest-challenge/discussion/130165#744541
", "rawMarkdown": "Cris I think I´ll be killed since I wrote Best Topic ever: https://www.kaggle.com/c/google-quest-challenge/discussion/130165#744541", "replies": [ { "id": 744640, "postDate": "2020-02-13T02:35:00.727Z", "content": "Very interesting ! Share with careful! Learn fast to share fast improve your skills, learn with others.
", "rawMarkdown": "Very interesting ! Share with careful! Learn fast to share fast improve your skills, learn with others.", "votes": 2 } ] }, { "id": 744574, "postDate": "2020-02-13T00:01:28.513Z", "content": "I love you so much for all the 15!😄
🙌 ✔️
", "rawMarkdown": "🙌 ✔️ ", "votes": 2 } ] }, { "id": 743904, "postDate": "2020-02-12T11:32:41.417Z", "content": "Thanks for share 💯
", "rawMarkdown": "Thanks for share 💯 ", "replies": [ { "id": 744390, "postDate": "2020-02-12T19:38:16.493Z", "content": "Thanks for your support @dasmehdixtr ! Keep going !
", "rawMarkdown": "Thanks for your support @dasmehdixtr ! Keep going ! ", "votes": 1 }, { "id": 744392, "postDate": "2020-02-12T19:39:35.927Z", "content": "Consider see this: Indirect validation of tropospheric nitrogen dioxide retrieved\nfrom the OMI satellite instrument: Insight into the seasonal\nvariation of nitrogen oxides at northern midlatitudes\nHave a good day!
", "rawMarkdown": "Consider see this: I[ndirect validation of tropospheric nitrogen dioxide retrieved\nfrom the OMI satellite instrument: Insight into the seasonal\nvariation of nitrogen oxides at northern midlatitudes](http://fizz.phys.dal.ca/~atmos/publications/Lamsal_2010_JGR.pdf)\nHave a good day!", "votes": 1 }, { "id": 747021, "postDate": "2020-02-15T21:27:46.367Z", "content": "Look this, maybe help you in some analysis: TS
", "rawMarkdown": "Look this, maybe help you in some analysis: [TS](https://www.cosmiqworks.org/archived-projects/comet-time-series-ts/)", "votes": 1 } ] }, { "id": 817892, "postDate": "2020-04-23T13:58:03.900Z", "content": "Excellent work and a great idea. The animation is very good too. What was the most challenging aspect of this project?
", "rawMarkdown": "Excellent work and a great idea. The animation is very good too. What was the most challenging aspect of this project?" }, { "id": 743955, "postDate": "2020-02-12T12:43:01.190Z", "rawMarkdown": "", "isDeleted": true, "replies": [ { "id": 744394, "postDate": "2020-02-12T19:40:33.123Z", "content": "Thanks @ykobay ! Share with us some insights ! Waiting for your great kernel !
", "rawMarkdown": "Thanks @ykobay ! Share with us some insights ! Waiting for your great kernel !", "votes": 1 }, { "id": 749594, "postDate": "2020-02-18T19:49:26.480Z", "content": "Consider see this: Consider see this: Image processing with Python and SciPy
", "rawMarkdown": "Consider see this: Consider see this: [Image processing with Python and SciPy](http://prancer.physics.louisville.edu/astrowiki/index.php/Image_processing_with_Python_and_SciPy)" } ] } ], "comments": [ { "id": 743225, "author_name": "PC Jimmmy", "author_url": "", "post_date": "2020-02-11T22:33:23.897000", "content": "Be sure that your searches include NO2 emissions since that is the focus of the data set (not CO2).
", "votes": 3, "replies": [ { "id": 743245, "author_name": "Caesar Lupum", "author_url": "", "post_date": "2020-02-11T23:18:49.463000", "content": "Thanks @pcjimmmy ! Done ! I change the searches, I'm sorry !
", "votes": 1, "replies": [] }, { "id": 743260, "author_name": "PC Jimmmy", "author_url": "", "post_date": "2020-02-12T00:01:43.010000", "content": "No problems - did not want to have to search for NO2 stuff myself. I would assume that a model for CO2 and one for NO2 might be similar but suspect gas density will change the distribution from the source.
", "votes": 1, "replies": [] }, { "id": 743327, "author_name": "PC Jimmmy", "author_url": "", "post_date": "2020-02-12T01:47:42.030000", "content": "After reading more - I think you were right and I was wrong. The link in the overview takes you to a CO2 focused page. I think I went off course because the notebook example has NO2. Guess I have to make the assumption that the same data for CO2 can be extracted from Google.
", "votes": 1, "replies": [] }, { "id": 743412, "author_name": "Paul Mooney", "author_url": "", "post_date": "2020-02-12T03:33:38.780000", "content": "To clarify, we are most interested in NO2 emissions (in part because NO2 emissions can often be directly linked to fossil fuel usage), and therefore we have included it in the dataset starter pack. That being said, you can find CO2 emissions data on the Earth Engine platform, and this data can very much be used to supplement and strengthen an approach for calculating emissions factors in Puerto Rico.
", "votes": 4, "replies": [] }, { "id": 743415, "author_name": "Caesar Lupum", "author_url": "", "post_date": "2020-02-12T03:36:08.540000", "content": "Yes, I think that a lot of useful information ! Consider see this external link pls: maybe will help you http://fizz.phys.dal.ca/~atmos/martin/?page_id=100
\n\nThanks buddy !
", "votes": 0, "replies": [] }, { "id": 743420, "author_name": "Caesar Lupum", "author_url": "", "post_date": "2020-02-12T03:38:37.067000", "content": "\nsource: http://fizz.phys.dal.ca/~atmos/martin/?page_id=232
@pcjimmmy I want to append a bit more to my comment about CO2 vs NO2. An advantage of NO2 is that we have access to high resolution remote sensing data, whereas CO2 is difficult to measure via remote sensing. NO2 is often used as a tracer gas for NO2 because it is difficult to generate NO2 in an urban environment without also generating CO2. You could also consider looking at NO emissions and SO2 emissions, but we are particularly optimistic about models that are based off of NO2 emissions because we have high resolution remote sensing data that covers the entire globe.
", "votes": 2, "replies": [] }, { "id": 745559, "author_name": "PC Jimmmy", "author_url": "", "post_date": "2020-02-13T23:32:00.653000", "content": "Thanks for the additional information. Spent lots of time looking at Puerto Rico over the last 24 hours. I am seeing what I believe is a huge disadvantage to NO2 for the island. I need to do more work but my current conclusion is that urban area NO2 from emissions sources completely hide any power plant effect. My assumption (yet to be confirmed) is that a high percentage of automobiles on the island are diesel and an annualized image that I generated is best correlated (Mark One Eyeball) to the Google Earth Engine world population data set. While NO2 makes sense hopefully a model can find the corrections needed to account for urban emissions not related to power plants. For sure a machine learning opportunity but the short time scale for the competition makes me pretty sure my weak Python skills will not let me fully execute my theory of the problem.
\n\nHeading to Atlanta for long weekend but will generate a kernel to demonstrate the urban issue when I return middle of the week. I already have some images from the Google Earth Engine and have struggled over the last hours converting the java scripts that run great on GEE to Python in a Kaggle kernel.
\n\nThis is a screen shot of the GEE output and a 2nd with transparency down so you can see the island map.
\n\n\n
Separating vehicle emissions from industry emissions can be a major challenge, this is an interesting question. I suspect that traffic patterns and energy demands are fairly predictable. Maybe you can determine what fraction is the result of vehicle emissions by looking at the increase in emissions during peak traffic hours? Likewise, it could be informative to identify power plants that went offline during this time period and then to look for any noticeable changes in NO2 emissions.
", "votes": 3, "replies": [] }, { "id": 746270, "author_name": "Paul Mooney", "author_url": "", "post_date": "2020-02-14T19:53:41.590000", "content": "@pcjimmmy I want to append a bit more to my comment about separating vehicle emissions from industry emissions. One reason that we selected Puerto Rico is that the power plants are isolated from the population by mountains. In the example image that you provided you can see the plume of NO2 centered on San Juan and then dispersing westward by the winds. You might want to try focusing on the large power plants on the south of the island.
", "votes": 1, "replies": [] }, { "id": 746474, "author_name": "PC Jimmmy", "author_url": "", "post_date": "2020-02-15T04:11:51.587000", "content": "Icons for plants on the map image. You can see one plume very clearly in the south.
", "votes": 1, "replies": [] }, { "id": 757570, "author_name": "Caesar Lupum", "author_url": "", "post_date": "2020-02-26T23:17:49.707000", "content": "@pcjimmmy , https://www3.epa.gov/airnow/no2.pdf\nAir Quality Guide for Nitrogen Dioxide\n
Have not looked at the data yet but the USA monitoring stations for NO2 can be found at the link below. Pre-packaged data sets can be downloaded and you can sign up for access to build the July to July data set we would need. Might help with the issue of separating urban emissions from power plant emissions. Hopefully there are a few for Puerto Rico.
\n\nUSA NO2 Monitoring Stations Data
", "votes": 1, "replies": [] }, { "id": 757695, "author_name": "PC Jimmmy", "author_url": "", "post_date": "2020-02-27T02:54:35.870000", "content": "Looking at the list of sites there should be 4 stations for NO2 in Puerto Rico. NO2 is a bit tricky as its reaction with sunlight and ozone is very rapid - but one would assume the USA EPA would have set up collection with that in mind. State code 72 should be Puerto Rico in all the data files you can grab here.
", "votes": 1, "replies": [] } ] }, { "id": 744724, "author_name": "VikramanK", "author_url": "", "post_date": "2020-02-13T04:24:44.820000", "content": "Thank you very much for sharing :) really appreciate this!
", "votes": 0, "replies": [ { "id": 745103, "author_name": "Caesar Lupum", "author_url": "", "post_date": "2020-02-13T13:38:28.103000", "content": "Thanks @vikramank !Please share some tips with us ! \nWaiting for your work on DS4G comp.
", "votes": 1, "replies": [] }, { "id": 749590, "author_name": "Caesar Lupum", "author_url": "", "post_date": "2020-02-18T19:47:38.937000", "content": "Consider see this: A tool for Swarm satellite data analysis and anomaly detection
", "votes": 0, "replies": [] } ] }, { "id": 744577, "author_name": "Marília Prata", "author_url": "", "post_date": "2020-02-13T00:10:44.137000", "content": "Can you read one of that files? farm-ads and farm-ads-vect? https://www.kaggle.com/devvret/farm-ads-binary-classification I've already done it. The K -Notebook is in the oven.
", "votes": 0, "replies": [ { "id": 744641, "author_name": "Caesar Lupum", "author_url": "", "post_date": "2020-02-13T02:36:09.237000", "content": "it looks very interesting! The kaggle is always full of fantastic problems to study.
", "votes": 2, "replies": [] } ] }, { "id": 744575, "author_name": "Marília Prata", "author_url": "", "post_date": "2020-02-13T00:03:52.207000", "content": "Cris I think I´ll be killed since I wrote Best Topic ever: https://www.kaggle.com/c/google-quest-challenge/discussion/130165#744541
", "votes": 0, "replies": [ { "id": 744640, "author_name": "Caesar Lupum", "author_url": "", "post_date": "2020-02-13T02:35:00.727000", "content": "Very interesting ! Share with careful! Learn fast to share fast improve your skills, learn with others.
", "votes": 2, "replies": [] } ] }, { "id": 744574, "author_name": "Marília Prata", "author_url": "", "post_date": "2020-02-13T00:01:28.513000", "content": "I love you so much for all the 15!😄
🙌 ✔️
", "votes": 2, "replies": [] } ] }, { "id": 743904, "author_name": "dasmehdixtr", "author_url": "", "post_date": "2020-02-12T11:32:41.417000", "content": "Thanks for share 💯
", "votes": 0, "replies": [ { "id": 744390, "author_name": "Caesar Lupum", "author_url": "", "post_date": "2020-02-12T19:38:16.493000", "content": "Thanks for your support @dasmehdixtr ! Keep going !
", "votes": 1, "replies": [] }, { "id": 744392, "author_name": "Caesar Lupum", "author_url": "", "post_date": "2020-02-12T19:39:35.927000", "content": "Consider see this: Indirect validation of tropospheric nitrogen dioxide retrieved\nfrom the OMI satellite instrument: Insight into the seasonal\nvariation of nitrogen oxides at northern midlatitudes\nHave a good day!
", "votes": 1, "replies": [] }, { "id": 747021, "author_name": "Caesar Lupum", "author_url": "", "post_date": "2020-02-15T21:27:46.367000", "content": "Look this, maybe help you in some analysis: TS
", "votes": 1, "replies": [] } ] }, { "id": 817892, "author_name": "Data-Science Sean", "author_url": "", "post_date": "2020-04-23T13:58:03.900000", "content": "Excellent work and a great idea. The animation is very good too. What was the most challenging aspect of this project?
", "votes": 0, "replies": [] }, { "id": 743955, "author_name": "", "author_url": "", "post_date": "2020-02-12T12:43:01.190000", "content": "", "votes": 0, "replies": [ { "id": 744394, "author_name": "Caesar Lupum", "author_url": "", "post_date": "2020-02-12T19:40:33.123000", "content": "Thanks @ykobay ! Share with us some insights ! Waiting for your great kernel !
", "votes": 1, "replies": [] }, { "id": 749594, "author_name": "Caesar Lupum", "author_url": "", "post_date": "2020-02-18T19:49:26.480000", "content": "Consider see this: Consider see this: Image processing with Python and SciPy
", "votes": 0, "replies": [] } ] } ], "raw_markdown_by_id": { "743212": "\n\n# For everyone’s reference. I already separated a material for this great competition! Going to be adding here more as I keep searching!\n\n\n### Animations\n\n\n\n\n\n\nsource: http://fizz.phys.dal.ca/~atmos/martin/?page_id=100\n\n### Articles\n\n### [Recommended Procedures for Development of\nEmissions Factors and Use of the WebFIRE\nDatabase](https://www3.epa.gov/ttn/chief/efpac/procedures/procedures81213.pdf)\n\n#### [NOx lifetimes and emissions of cities and power plants in polluted\nbackground estimated by satellite observations](NOx lifetimes and emissions of cities and power plants in polluted\nbackground estimated by satellite observations)\n\n### [Estimates of power plant NOx emissions and lifetimes from OMI NO2\nsatellite retrievals](https://www.atmos-chem-phys.net/16/5283/2016/acp-16-5283-2016.pdf)\n\n### [NOx lifetimes and emissions of cities and power plants in polluted\nbackground estimated by satellite observations](https://www.atmos-chem-phys.net/16/5283/2016/acp-16-5283-2016.pdf)\n\n#### [Joint Learning from Earth Observation and OpenStreetMap Data to Get Faster Better Semantic Maps](https://arxiv.org/abs/1705.06057)\n\n#### [Air Emissions Factors and Quantification](https://www.epa.gov/air-emissions-factors-and-quantification/basic-information-air-emissions-factors-and-quantification#About%20Emissions%20Factors) \n\n#### [How much carbon dioxide is produced per kilowatthour of U.S. electricity generation?](https://www.eia.gov/tools/faqs/faq.php?id=74&t=11)\n\n#### [The Need for Alternate PM2.5 Emission Factors for Gas-Fired Combustion Unit](https://www.powermag.com/the-need-for-alternate-pm2-5-emission-factors-for-gas-fired-combustion-units/)\n\n#### [How to Calculate Air Emissions ?](https://www.enveraconsulting.com/how-to-calculate-air-emissions/)\n\n### Videos\n\n#### [US energy startup builds power plant that produces no carbon emissions](https://youtu.be/4_w9BId_Pms?t=2)\n\n#### [AIR POLLUTION](https://youtu.be/_dTtvtlct9k)\n\n#### [WATCH: NO2 pollution rocketing thorugh Europe pushed by mild weather](https://youtu.be/9ZeaP8ljc9E)\n\n#### [NASA ARSET: Remote Sensing of NO2 with OMI, Part 1/3](https://youtu.be/rvSjD-vGI4k)\n\n#### [NASA ARSET: Introducing TROPOMI - High Resolution NO2 Observations from Space, Part 2/3](https://youtu.be/-yOInEUJTYM)\n\n#### [NASA ARSET: Python Tools for Analyzing NO2, Part 3/3](https://youtu.be/MxBg5ZMH2nM)\n\n\n\n### Datasets\n\n[Global Power Plant database ](https://developers.google.com/earth-engine/datasets/catalog/WRI_GPPD_power_plants) by WRI\n> Description\nThe Global Power Plant Database is a comprehensive, open source database of power plants around the world. It centralizes power plant data to make it easier to navigate, compare and draw insights for one’s own analysis. The database covers approximately 30,000 power plants from 164 countries and includes thermal plants (e.g. coal, gas, oil, nuclear, biomass, waste, geothermal) and renewables (e.g. hydro, wind, solar). Each power plant is geolocated and entries contain information on plant capacity, generation, ownership, and fuel type. It will be continuously updated as data becomes available.\n\n[Sentinel 5P OFFL NO2](https://developers.google.com/earth-engine/datasets/catalog/COPERNICUS_S5P_OFFL_L3_NO2) by [EU/ESA/Copernicus](https://sentinel.esa.int/web/sentinel/user-guides/sentinel-5p-tropomi/document-library)\n> Sentinel-5 Precursor\nSentinel-5 Precursor is a satellite launched on 13 October 2017 by the European Space Agency to monitor air pollution. The onboard sensor is frequently referred to as Tropomi (TROPOspheric Monitoring Instrument). The OFFL/NO2 is a dataset that provides offline high-resolution imagery of **NO2 concentration**.\n\n[Global Forecast System 384-Hour Predicted Atmosphere Data](https://developers.google.com/earth-engine/datasets/catalog/NOAA_GFS0P25) by NOAA/NCEP/EMC\n> The Global Forecast System (GFS) is a weather forecast model produced by the National Centers for Environmental Prediction (NCEP). The GFS dataset consists of selected model outputs (described below) as gridded forecast variables. The 384-hour forecasts, with 3-hour forecast interval, are made at 6-hour temporal resolution (i.e. updated four times daily). Use the 'creation_time' and 'forecast_time' properties to select data of interest.\n\n[Global Land Data Assimilation System](https://developers.google.com/earth-engine/datasets/catalog/NASA_GLDAS_V021_NOAH_G025_T3H) by NASA\n> Global Land Data Assimilation System (GLDAS) ingests satellite and ground-based observational data products. Using advanced land surface modeling and data assimilation techniques, it generates optimal fields of land surface states and fluxes. his dataset provided by NASA ingest satellite.\n\nTrade commodities for fuel types, total fuel consumed, and/or data from the [US Energy Information Agency (EIA)](https://www.eia.gov/state/data.php?sid=RQ#CarbonDioxideEmissions).\n\n\n### Public Dataset\n\n[Atmospheric Composition Analysis Group](http://fizz.phys.dal.ca/~atmos/martin/?page_id=100#)\n> GEOS-Chem Community Mission: to advance understanding of human and natural influences on the environment through a comprehensive, state-of-the-science, readily accessible global model of atmospheric composition.\n\n[Global Power Plant Database](http://datasets.wri.org/dataset/globalpowerplantdatabase)\n\n[Geographic 2D CRS used in World](https://georepository.com/crs_4326/WGS-84.html)\n\n(https://www.gov.uk/government/organisations/defence-science-and-technology-laboratory)\n\n### Remote Sensing Tools\n- [QGIS- A Free and Open Source Geographic Information System](https://www.qgis.org/en/site/)\n- [Manifold GIS Systems](https://gisgeography.com/manifold-gis-systems/)\n- [MapInfo Professional] (https://gisgeography.com/mapinfo-professional-pitney-bowes/)\n- [ArcGIS Pro](https://gisgeography.com/arcgis-pro/)\n\n\n### Just useful links\n\n- [How To Compute Satellite Image Statistics](https://towardsdatascience.com/how-to-compute-satellite-image-statistics-and-use-it-in-pandas-81864a489144)\n\n- https://www.cosmiqworks.org/\n > Since 2015, CosmiQ Works has focused on the geospatial analytics market and provided technical insights, targeted research, and reports. \n\n- [The Spacenet Challenge](https://i.ho.lc/winning-solution-for-the-spacenet-challenge-joint-learning-with-openstreetmap.html)\n > Winning Solution for the Spacenet Challenge: Joint Learning with OpenStreetMap\n\n- [Image processing with Python and SciPy](http://prancer.physics.louisville.edu/astrowiki/index.php/Image_processing_with_Python_and_SciPy)\n- [A tool for Swarm satellite data analysis and anomaly detection](https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0212098)\n\n### Libs - Satellite Imagery\n- [Solaris](https://github.com/CosmiQ/solaris)\n > An open source ML pipeline for overhead imagery by CosmiQ Works \n\n### Projects\n- [SATELLITE IMAGERY MULTISCALE RAPID DETECTION WITH WINDOWED NETWORKS (SIMRDWN) REPOSITORY](https://www.cosmiqworks.org/category/archived-projects/)\n\n- [SPACENET 6 Multimodal Data Analysis for Travel Routing and Time Estimation](https://www.cosmiqworks.org/category/current-projects/)\n\n- [SATELLITE IMAGERY MULTISCALE RAPID DETECTION WITH WINDOWED NETWORKS (SIMRDWN) REPOSITORY](https://www.cosmiqworks.org/category/archived-projects/)\n\n-[COMET TIME SERIES (TS)](https://www.cosmiqworks.org/archived-projects/comet-time-series-ts/)\n\n-[Resources for deep learning with satellite & aerial imagery](https://github.com/robmarkcole/satellite-image-deep-learning)\n\n### Just some useful Codes\n#### [Overview of the EIE Analytics Challenge](https://www.kaggle.com/paultimothymooney/overview-of-the-eie-analytics-challenge) by @paultimothymooney \n\n#### [How to get started with the Earth Engine data](https://www.kaggle.com/paultimothymooney/how-to-get-started-with-the-earth-engine-data) by @paultimothymooney \n\n[🌏🌿DS4G: Go to the Green Future!] (https://www.kaggle.com/caesarlupum/ds4g-go-to-the-green-future) by @caesarlupum \n\nSimilar comp. [Satellite Imagery]\n[Dstl Satellite Imagery Feature Detection](https://www.kaggle.com/c/dstl-satellite-imagery-feature-detection/overview)\n\n\n👍 ✔️ Thanks Everyone✔️\n", "743225": "Be sure that your searches include NO2 emissions since that is the focus of the data set (not CO2).", "744724": "Thank you very much for sharing :) really appreciate this! ", "744577": "Can you read one of that files? farm-ads and farm-ads-vect? https://www.kaggle.com/devvret/farm-ads-binary-classification I've already done it. The K -Notebook is in the oven.", "744575": "Cris I think I´ll be killed since I wrote Best Topic ever: https://www.kaggle.com/c/google-quest-challenge/discussion/130165#744541", "744574": "I love you so much for all the 15!😄 ", "743904": "Thanks for share 💯 ", "817892": "Excellent work and a great idea. The animation is very good too. What was the most challenging aspect of this project?", "743955": "" } }