Code Repository for: "Characterization of Industrial Smoke Plumes from Remote Sensing Data", presented at Tackling Climate Change with Machine Learning workshop at NeurIPS 2020.

Zephyr is a platform which provides users with the predicted Air Quality Index levels of air pollution for 39 cities of India with daily, monthly and yearly trends. It also provides some of the statistics observed for AQI over these cities and various latest articles and blogs related to air pollution.

Used Tensorflow Object Detection API to detect different vehicles in a picture and predict pollution levels.

Command-line application providing some information about air quality in Poland. Tested using Mockito and JUnit

Research Paper on the prediction of pollutants concentration in Lille using Machine Learning Methods

Tools 🧰 to preprocess and post process data for air quality assessment.

Build an iOS Application to Predict Air Pollution Using a Random Forest Regressor

Creation of an ecological carpooling app with the possibility of doing stopovers

Using long short term memory networks to analysis the pollution of Beijing, China.

Time series prediction models, exploratory data analysis and clustering on air pollution data

Prediction of PM 2.5 using transfer learning approaches.

Python tool to sense, predict and push pollution data to Firebase Realtime Database

A Python notebook that aims to analyze the change in air quality index (AQI) for 4 major pollutants (Nitrogen Dioxide, Sulphur Dioxide, Carbon Monoxide, Ozone) that cover all 50 states of the United States from 2000 to 2016.

Python script that allows to modify dates of input files of modules of CALMET/CALPUFF model

a platform which provides users with the predicted Air Quality Index levels of air pollution for 39 cities of India with daily, monthly and yearly trends. It also provides some of the statistics observed for AQI over these cities and various latest articles and blogs related to air pollution.

自强不吸——基于上海市天气与交通状况的空气质量分析报告

Aeolus: Air Pollution Assistant

SCMPM: An open source and efficient calibration and mapping approach based on real-time spatial model that calibrates measurements from low-cost sensor in an environment with high relative humidity. The model provides spatial calibration of low cost PM2.5 sensors

Deep Neural Network for the prediction of NO2 level in the air, using two different satellite images of a specific zone.