#77: Scikit-learn 74:Supervised Learning 52: Project: Predict Greenhouse gases conc.

The video discusses a machine learning project to build prediction models that can forecast the concentration of greenhouse gases in the atmosphere over next 10 to 30 years using Gaussian Process methods. The data is analyzed for Carbon Dioxide, Methane and Nitrous Oxide gases. The models are build using .GaussianProcessRegressor from Scikit-learn in Python. Timeline (Python 3.8) 00:00 - Outline of video 00:28 - Data Source 00:46 - Story of greenhouse gases 03:24 - A look at the data files, preformat 04:22 - Open Juptyer notebook 05:11 - Carbon Dioxide: CO2 prediction 05:27 - Carbon Dioxide: Data: read file 06:43 - Carbon Dioxide: Data: X, y 08:02 - Carbon Dioxide: Create kernels and combine 13:06 - Carbon Dioxide: Gaussian Process: fit using .GaussianProcessRegressor() 16:09 - Carbon Dioxide: Predict 17:41 - Carbon Dioxide: Plot 20:33 - Carbon Dioxide: Plot: discuss kernel effect on seasonality 26:09 - Methane: read data file 27:00 - Methane: copy/paste code from Carbon Dioxide 28:06 - Methane: visualize data 29:07 - Methane: kernels 32:37 - Methane: run code to plot predictions 36:06 - Nitrous Oxide: copy/paste code from Methane 36:34 - Nitrous Oxide: change file name 37:30 - Nitrous Oxide: kernel 38:20 - Nitrous Oxide: run code to plot predictions 41:07 - Ending notes ############### # Download data ############### Greenhouse Gases Data from Mauna Loa Observatory, Hawaii - Authors: Ed Dlugokencky, Dr. Pieter Tans, Dr. Ralph Keeling - Source Link: https://www.esrl.noaa.gov/gmd/ccgg/trends/ - Download 1: https://www.esrl.noaa.gov/gmd/webdata/ccgg/trends/co2/co2_mm_mlo.txt - Download 2: https://www.esrl.noaa.gov/gmd/webdata/ccgg/trends/ch4/ch4_mm_gl.txt - Download 3: https://www.esrl.noaa.gov/gmd/webdata/ccgg/trends/n2o/n2o_mm_gl.txt ############### # Code ############### https://github.com/learndataa/projects