Hello,\nWe humans in many times take more difficult paths in the hope of finding solutions. This is why we need to think backwards and go to basics to canalize our thrive to complexity.\nBack to our subject, why not just use edge sensor data, I imagine the installation of sensors near power plants would be far more accurate to measure production and carbon/NO footprint. Knowing that using satellite images to estimate which powerplant is responsible for any amount of pollution is subject to many complex climatological factors.\nWe can address randomness and interference using Simulations, Bayesian models or so. But don't we have way more easier option in hand in this situation ?\nMany thanks !
", "messages": [ { "id": "776339", "postDate": "03/17/2020 10:10:22", "content": "Hello,\nWe humans in many times take more difficult paths in the hope of finding solutions. This is why we need to think backwards and go to basics to canalize our thrive to complexity.\nBack to our subject, why not just use edge sensor data, I imagine the installation of sensors near power plants would be far more accurate to measure production and carbon/NO footprint. Knowing that using satellite images to estimate which powerplant is responsible for any amount of pollution is subject to many complex climatological factors.\nWe can address randomness and interference using Simulations, Bayesian models or so. But don't we have way more easier option in hand in this situation ?\nMany thanks !
", "rawMarkdown": "Hello,\nWe humans in many times take more difficult paths in the hope of finding solutions. This is why we need to think backwards and go to basics to canalize our thrive to complexity.\nBack to our subject, why not just use edge sensor data, I imagine the installation of sensors near power plants would be far more accurate to measure production and carbon/NO footprint. Knowing that using satellite images to estimate which powerplant is responsible for any amount of pollution is subject to many complex climatological factors.\nWe can address randomness and interference using Simulations, Bayesian models or so. But don't we have way more easier option in hand in this situation ?\nMany thanks !", "votes": null }, { "id": "776676", "postDate": "03/17/2020 14:47:29", "content": "Participants are free to use any datasets in addition to the official Kaggle dataset, but those datasets must also be publicly available on either Earth Engine or Kaggle for the submission to be valid.
\n\nThe ultimate goal of this challenge is to test if calculations of emissions factors using remote sensing techniques are possible and on par with calculations of emissions factors from current methodologies. We are particularly optimistic about models that are based off of remote sensing data because we have access to high resolution remote sensing data that covers the entire globe.
\n\nYou can read more about the competition overview here.
", "rawMarkdown": "Participants are free to use any datasets in addition to the [official Kaggle dataset](https://www.kaggle.com/c/ds4g-environmental-insights-explorer), but those datasets must also be publicly available on either Earth Engine or Kaggle for the submission to be valid.\n\nThe ultimate goal of this challenge is to test if calculations of emissions factors using remote sensing techniques are possible and on par with calculations of emissions factors from current methodologies. We are particularly optimistic about models that are based off of remote sensing data because we have access to high resolution remote sensing data that covers the entire globe. \n\nYou can read more about the competition overview [here](https://www.kaggle.com/c/ds4g-environmental-insights-explorer/overview/description).", "votes": null }, { "id": "776816", "postDate": "03/17/2020 16:44:20", "content": "Hey!
\n\nI'm a remote sensing engineer, so I might be able to answer some of those questions, or at least provide a few paths of reflection.
\n\nYou're right, putting some sensors is a great idea if we want to get access to the data for these specific plants. But it does not offer a scalable method for finding (in this case) emissions anywhere. Say we want to export this method outside of Puerto Rico? That means we need to put down some sensors everywhere now, this isn't very scalable. You'd also probably introduce a lot of different variables depending on where you put your sensors. You'd still probably need to take into account wind and weather data to know how were the conditions when you took your measurements.
\n\nNow having on site sensors can be great to create ground truth data and validate models that you are making using remote sensing techniques! In that case, it's very helpful to verify that the methods you're creating do work and provide useful and accurate information.
\n\nHope that helps to provide some info! :)
", "rawMarkdown": "Hey!\n\nI'm a remote sensing engineer, so I might be able to answer some of those questions, or at least provide a few paths of reflection.\n\nYou're right, putting some sensors is a great idea if we want to get access to the data for _these_ specific plants. But it does not offer a scalable method for finding (in this case) emissions anywhere. Say we want to export this method outside of Puerto Rico? That means we need to put down some sensors everywhere now, this isn't very scalable. You'd also probably introduce a lot of different variables depending on where you put your sensors. You'd still probably need to take into account wind and weather data to know how were the conditions when you took your measurements.\n\nNow having on site sensors can be great to create ground truth data and validate models that you are making using remote sensing techniques! In that case, it's very helpful to verify that the methods you're creating do work and provide useful and accurate information.\n\nHope that helps to provide some info! :)", "votes": null }, { "id": "776847", "postDate": "03/17/2020 17:14:56", "content": "Many thanks Maxime! \nYou are right, Very clear about scalability to other problems with satellite imaging all over the globe.
", "rawMarkdown": "Many thanks Maxime! \nYou are right, Very clear about scalability to other problems with satellite imaging all over the globe.", "votes": null } ], "comments": [ { "id": 776676, "author_name": "paultimothymooney", "author_url": "", "post_date": "03/17/2020 14:47:29", "content": "Participants are free to use any datasets in addition to the official Kaggle dataset, but those datasets must also be publicly available on either Earth Engine or Kaggle for the submission to be valid.
\n\nThe ultimate goal of this challenge is to test if calculations of emissions factors using remote sensing techniques are possible and on par with calculations of emissions factors from current methodologies. We are particularly optimistic about models that are based off of remote sensing data because we have access to high resolution remote sensing data that covers the entire globe.
\n\nYou can read more about the competition overview here.
", "votes": null, "replies": [] }, { "id": 776816, "author_name": "maxlenormand", "author_url": "", "post_date": "03/17/2020 16:44:20", "content": "Hey!
\n\nI'm a remote sensing engineer, so I might be able to answer some of those questions, or at least provide a few paths of reflection.
\n\nYou're right, putting some sensors is a great idea if we want to get access to the data for these specific plants. But it does not offer a scalable method for finding (in this case) emissions anywhere. Say we want to export this method outside of Puerto Rico? That means we need to put down some sensors everywhere now, this isn't very scalable. You'd also probably introduce a lot of different variables depending on where you put your sensors. You'd still probably need to take into account wind and weather data to know how were the conditions when you took your measurements.
\n\nNow having on site sensors can be great to create ground truth data and validate models that you are making using remote sensing techniques! In that case, it's very helpful to verify that the methods you're creating do work and provide useful and accurate information.
\n\nHope that helps to provide some info! :)
", "votes": null, "replies": [ { "id": 776847, "author_name": "sracer2017", "author_url": "", "post_date": "03/17/2020 17:14:56", "content": "Many thanks Maxime! \nYou are right, Very clear about scalability to other problems with satellite imaging all over the globe.
", "votes": null, "replies": [] } ] } ], "raw_markdown_by_id": { "776339": "Hello,\nWe humans in many times take more difficult paths in the hope of finding solutions. This is why we need to think backwards and go to basics to canalize our thrive to complexity.\nBack to our subject, why not just use edge sensor data, I imagine the installation of sensors near power plants would be far more accurate to measure production and carbon/NO footprint. Knowing that using satellite images to estimate which powerplant is responsible for any amount of pollution is subject to many complex climatological factors.\nWe can address randomness and interference using Simulations, Bayesian models or so. But don't we have way more easier option in hand in this situation ?\nMany thanks !", "776676": "Participants are free to use any datasets in addition to the [official Kaggle dataset](https://www.kaggle.com/c/ds4g-environmental-insights-explorer), but those datasets must also be publicly available on either Earth Engine or Kaggle for the submission to be valid.\n\nThe ultimate goal of this challenge is to test if calculations of emissions factors using remote sensing techniques are possible and on par with calculations of emissions factors from current methodologies. We are particularly optimistic about models that are based off of remote sensing data because we have access to high resolution remote sensing data that covers the entire globe. \n\nYou can read more about the competition overview [here](https://www.kaggle.com/c/ds4g-environmental-insights-explorer/overview/description).", "776816": "Hey!\n\nI'm a remote sensing engineer, so I might be able to answer some of those questions, or at least provide a few paths of reflection.\n\nYou're right, putting some sensors is a great idea if we want to get access to the data for _these_ specific plants. But it does not offer a scalable method for finding (in this case) emissions anywhere. Say we want to export this method outside of Puerto Rico? That means we need to put down some sensors everywhere now, this isn't very scalable. You'd also probably introduce a lot of different variables depending on where you put your sensors. You'd still probably need to take into account wind and weather data to know how were the conditions when you took your measurements.\n\nNow having on site sensors can be great to create ground truth data and validate models that you are making using remote sensing techniques! In that case, it's very helpful to verify that the methods you're creating do work and provide useful and accurate information.\n\nHope that helps to provide some info! :)", "776847": "Many thanks Maxime! \nYou are right, Very clear about scalability to other problems with satellite imaging all over the globe." }, "source": "meta" }