Explainability in Practice: Estimating Electrification Rates from Mobile Phone Data in Senegal
Explainable artificial intelligence (XAI) provides explanations for not interpretable machine learning (ML) models. While many technical approaches exist, there is a lack of validation of these techniques on real-world datasets. In this work, we present a use-case of XAI: an ML model which is trained to estimate electrification rates based on mobile phone data in Senegal. The data originate from the Data for Development challenge by Orange in 2014/15. We apply two model-agnostic, local explanation techniques and find that while the model can be verified, it is biased with respect to the population density. We conclude our paper by pointing to the two main challenges we encountered during our work: data processing and model design that might be restricted by currently available XAI methods, and the importance of domain knowledge to interpret explanations.
Code (1)
Tasks
Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Interpretable Machine LearningSimilar Papers 제목 키워드 기반
A Higher Purpose: Measuring Electricity Access Using High-Resolution Daytime Satellite Imagery
Governments and international organizations the world over are investing towards the goal of achieving universal energy access for improving socio-economic development. However, in developing settings, monitoring electri…
Electrification of Clay Calcination: A First Look into Dynamic Modeling and Energy Management for Integration with Sustainable Power Grids
This article explores the electrification in clay calcination, proposing a dynamic model and energy management strategy for the integration of electrified calcination plants into sustainable power grids. A theoretical dy…
energy managementManagementImpact of the Inflation Reduction Act and Carbon Capture on Transportation Electrification for a Net-Zero Western U.S. Grid
The electrification of transportation is critical to mitigate Greenhouse Gas (GHG) emissions. The United States (U.S.) government's Inflation Reduction Act (IRA) of 2022 introduces policies to promote the electrification…
System-Level Performance Metrics Sensitivity of an Electrified Heavy-Duty Mobile Manipulator
The shift to electric and hybrid powertrains in vehicular systems has propelled advancements in mobile robotics and autonomous vehicles. This paper examines the sensitivity of key performance metrics in a electrified hea…
Autonomous VehiclesSensitivityLess is More: The Influence of Pruning on the Explainability of CNNs
Over the last century, deep learning models have become the state-of-the-art for solving complex computer vision problems. These modern computer vision models have millions of parameters, which presents two major challen…
Network Pruning