Envairo

https://github.com/nainaiurk/Envairo

https://youtu.be/NK6ba3ub9C4

Introduction

The current global carbon dioxide emission has turned out to be an alarming concern. Fossil-fuel burning and industrial processes produced carbon dioxide twice over the past 40 years, going up from 16.9 gigatons (Gt) in 1974 to 35.5 Gt in 2014, with a yearly growth rate of 1.8% [1]. Energy utilization in industries, homes, and transportation is totally accountable for greater than 73% of worldwide carbon dioxide emissions [2]. Transportation itself contributes to one-fifth of global carbon dioxide emissions. Anthropogenic activities have raised the CO2 amount in the atmosphere by 50% since the Industrial Revolution began in 1750[3]. The 2015 Paris agreement states that the increase in temperature of the Earth’s interior should be under 2°C compared to the preindustrial levels, and the increase in Earth’s temperature should be less than 1.5°C. In a study conducted by Van-Soest et al. [4] to attain the target set in the Paris agreement at least 1 gigaton (Gt) of CO2 should be captured and stored until 2030. Researchers have shown that CO2, SO2, CH4, and N2O are the main greenhouse gasses attracting global attention at this time [5] and among those CO2 is the one that is emitted due to anthropogenic causes. If the emission of anthropogenic greenhouse gasses like CO2 is not reduced, the Earth will face consequences like an increase in atmospheric temperature in coastal areas by 2°C by 2050 and 4°C by 2100 [6,7]. Solomon et al. stated that if the world stopped emitting carbon dioxide at the beginning of 2050, almost half of the gas would remain in the atmosphere for 750 years afterward. Even after carbon dioxide emissions cease, due to ocean inertia, sea level should continue to increase, measuring two times the level of 2050 estimates for 100 years, and four times that value for another 500 years [8]. 

The Big Idea

We are introducing a developing web application capable of visualizing a country's current API, CO2 emission rate, temperature increase with coastal area risk and sea level rise. With the help of a machine learning algorithm, this application can predict and forecast the data with significant accuracy. To mitigate climate issues this application utilizes Normalized Difference Vegetation Index (NDVI) data to measure current vegetation coverage and predict the required number of greeneries. With a goal to develop a better sustainable Earth, this application can help a country predict the CO2 emission from vehicles from spatial data with a Machine Learning algorithm to ensure regulation and responsible consumption and carbon emission by strict Govt. Law, raising carbon taxes to industries that are responsible for higher carbon emissions, and paving the way by shifting toward renewable energy systems.

How does it work

inEarth uses temporal data of CO2 concentration to forecast the future concentration of carbon emission. The prediction was conducted using three machine learning algorithms which include the ‘Naïve Seasonal Model’, ‘Linear regression’, and ‘TCN Model’. This methodology was conducted for other data including Air Pollution Index, Sea Level Rise, and Increase in global temperature. With this forecasting, this app can graphically visualize the future conditions of a country and global conditions. The visualization enables the user to know the urgency of the climate conditions and habitable risks in a user-friendly method. To make a suitable estimation of actions to counter negative climate conditions inEarth works with the vegetation coverage of a country based on Normalized Difference Vegetation Index (NDVI) data and predict the required number of greeneries to mitigate the climate issue. The NDVI data will be used to measure current forestry and the number of greeneries in certain locations from imaging. Inspired by Carlson et al. we processed the data using ‘supervised classification’ to remove clouds and terrain effects [9]. The pixels identifying the steep slope are removed to run the prediction for flat regions. As our solution influences responsible consumption and maintenance of strict government laws inEarth will predict vehicular emissions from spatial data using ‘Spatiotemporal Graph Convolution Multifusion Network (ST-MFGCN)’ to measure the current trend of carbon emissions inspired by Zhenyi Xu et al. [10]. Analysis of quantitative greeneries and vehicular emissions the application provides an estimation of necessary actions that should be taken like carbon tax required tree plantation etc.

Presenting inEarth 

Global Emission of CO2 

Region-based prediction of requirements

Tools

• FLUTTER for web application,
• GOOGLE SHEET for backend data,
• Python,Google Colab, jupyter notebook for ML.
• Github pages for web deployment.

Impact 

inEarth can predict the CO2 emission rate to certain regions using its own algorithm and help track the vegetation index demand of those regions to reduce air impurities. With this application, we can provide a legal benchmark for stakeholders to shift toward a more habitable environment. It regulates responsible uses of CO2 by strictly imposing Govt. Laws, raising carbon taxes, and paving the way to develop a better sustainable Earth by shifting to a renewable energy system. 

1. GLOBAL CLIMATE CHANGE: For the data of global CO2 concentration, Sea Level Rise, and increase in global temperature.
2. NOAA: For the local data of CO2 concentration
3. World Bank: For the forest coverage data.
4. World Bank: For the CO2 emission per capita.
5. Earth Data: For the information regarding over all data of atmosphere, land surface and ocean.
6. NASA EARTH OBSERVATIONS: For the data of Normalized difference vegetation index for measuring vegetation coverage.
7. Moderate Resolution Imaging Spectroradiometer: For the data of NDVI and EVI to predict vegetation coverage.
8. IQAir: For the data of air quality index.
9. Other space agencies for local data and informations.

We are a group of enthusiasts from Shahjalal University of Science and Technology, Sylhet (SUST) who believe in the continual progress of the world. We view problems as nothing more than a chance to get better. The recent flood effect in Sylhet this May made the lives of coastal people harder in front of us. We, some people with similar concerns, were moved by that and thought of taking action that will benefit the coastal people of our country. In a matter of terror, around 60,000 women in the affected areas were pregnant. Of them, 6500 were about to give birth in the next month. With primary healthcare centers submerged and non-functional, most of these women have limited or no access to healthcare. 

This required a lot of background studies that indicated overall flood and natural disasters have relations with global temperature and CO2 emission and sea level rise which eventually cause massive floods and disasters. NASA Space Apps challenge provided us an opportunity to develop a solution regarding earth data which influenced us to enter this hackathon journey with the prospect to move forward with an Idea.

We would love to thank BASIS for not only hosting Space Apps Bangladesh round but also for their tremendous guidance and support during the process.

[1] BP, BP Statistical Review of World Energy 2015, 2015, BP press.

[2] Ritchie, H., Roser, M., & Rosado, P. (2020). CO₂ and Greenhouse Gas Emissions. Our World in Data. https://ourworldindata.org/emissions-by-sector

[3] The Causes of Climate Change. (n.d.). Climate Change: Vital Signs of the Planet. Retrieved October 1, 2022, from https://climate.nasa.gov/causes

[4] van Soest, H. L., de Boer, H. S., Roelfsema, M., den Elzen, M. G. J., Admiraal, A., van Vuuren, D. P., Hof, A. F., van den Berg, M., Harmsen, M. J. H. M., Gernaat, D. E. H. J., & Forsell, N. (2017). Early action on Paris Agreement allows for more time to change energy systems. Climatic Change, 144(2), 165–179. https://doi.org/10.1007/s10584-017-2027-8

[5] Berrou, A., Raybaut, M., Godard, A., & Lefebvre, M. (2009). High-resolution photoacoustic and direct absorption spectroscopy of main greenhouse gases by use of a pulsed entangled cavity doubly resonant OPO. Applied Physics B, 98(1), 217. https://doi.org/10.1007/s00340-009-3710-x

[6] Hossain, M. S., Arshad, M., Qian, L., Zhao, M., Mehmood, Y., & Kächele, H. (2019). Economic impact of climate change on crop farming in Bangladesh: An application of Ricardian method. Ecological Economics, 164, 106354. https://doi.org/10.1016/j.ecolecon.2019.106354

[7] Orimoloye, I. R., Mazinyo, S. P., Kalumba, A. M., Ekundayo, O. Y., & Nel, W. (2019). Implications of climate variability and change on urban and human health: A review. Cities, 91, 213–223. https://doi.org/10.1016/j.cities.2019.01.009

[8] Chu, J. (n.d.). Short-lived greenhouse gases cause centuries of sea-level rise. Climate Change: Vital Signs of the Planet. Retrieved October 1, 2022, from https://climate.nasa.gov/news/2533/short-lived-greenhouse-gases-cause-centuries-of-sea-level-rise

[9] Carlson, T. N., Gillies, R. R., & Perry, E. M. (1994). A method to make use of thermal infrared temperature and NDVI measurements to infer surface soil water content and fractional vegetation cover. Remote Sensing Reviews, 9(1–2), 161–173. https://doi.org/10.1080/02757259409532220

[10] Xu, Z., Kang, Y., Cao, Y., & Li, Z. (2021). Spatiotemporal Graph Convolution Multifusion Network for Urban Vehicle Emission Prediction. IEEE Transactions on Neural Networks and Learning Systems, 32(8), 3342–3354. https://doi.org/10.1109/TNNLS.2020.3008702

Climate Action; Sustainable Development; Carbon Emissions; Responsible Consumption & Production;