Explainable Machine Learning Reveals Capabilities, Redundancy, and Limitations of a Geospatial Air Quality Benchmark Dataset

Explainable Machine Learning Reveals Capabilities, Redundancy, and Limitations of a Geospatial Air Quality Benchmark Dataset

Air quality is relevant to society because it poses environmental risks to humans and nature. We use explainable machine learning in air quality research by analyzing model predictions in relation to the underlying training data. The data originate from worldwide ozone observations, paired with geos...

Full description

Bibliographic Details
Main Authors: Scarlet Stadtler, Clara Betancourt, Ribana Roscher
Format: Article
Language:English
Published: MDPI AG 2022-02-01
Series:Machine Learning and Knowledge Extraction
Subjects:
explainable machine learning
air quality
k-nearest neighbors
neural network
random forest
Online Access:https://www.mdpi.com/2504-4990/4/1/8

Internet

https://www.mdpi.com/2504-4990/4/1/8

Similar Items