Saved in:
Bibliographic Details
Main Authors: Pitsiorlas, Ioannis, Tsantalidou, Argyro, Arvanitakis, George, Kountouris, Marios, Kontoes, Charalambos
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.17342
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909220755996672
author Pitsiorlas, Ioannis
Tsantalidou, Argyro
Arvanitakis, George
Kountouris, Marios
Kontoes, Charalambos
author_facet Pitsiorlas, Ioannis
Tsantalidou, Argyro
Arvanitakis, George
Kountouris, Marios
Kontoes, Charalambos
contents This study presents a new approach for estimating confidence in machine learning model predictions, specifically in regression tasks utilizing Earth Observation (EO) data, with a particular focus on mosquito abundance (MA) estimation. We take advantage of a Variational AutoEncoder architecture, to derive a confidence metric by the latent space representations of EO datasets. This methodology is pivotal in establishing a correlation between the Euclidean distance in latent representations and the Absolute Error (AE) in individual MA predictions. Our research focuses on EO datasets from the Veneto region in Italy and the Upper Rhine Valley in Germany, targeting areas significantly affected by mosquito populations. A key finding is a notable correlation of 0.46 between the AE of MA predictions and the proposed confidence metric. This correlation signifies a robust, new metric for quantifying the reliability and enhancing the trustworthiness of the AI model's predictions in the context of both EO data analysis and mosquito abundance studies.
format Preprint
id arxiv_https___arxiv_org_abs_2401_17342
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Latent Space Metric for Enhancing Prediction Confidence in Earth Observation Data
Pitsiorlas, Ioannis
Tsantalidou, Argyro
Arvanitakis, George
Kountouris, Marios
Kontoes, Charalambos
Machine Learning
Artificial Intelligence
This study presents a new approach for estimating confidence in machine learning model predictions, specifically in regression tasks utilizing Earth Observation (EO) data, with a particular focus on mosquito abundance (MA) estimation. We take advantage of a Variational AutoEncoder architecture, to derive a confidence metric by the latent space representations of EO datasets. This methodology is pivotal in establishing a correlation between the Euclidean distance in latent representations and the Absolute Error (AE) in individual MA predictions. Our research focuses on EO datasets from the Veneto region in Italy and the Upper Rhine Valley in Germany, targeting areas significantly affected by mosquito populations. A key finding is a notable correlation of 0.46 between the AE of MA predictions and the proposed confidence metric. This correlation signifies a robust, new metric for quantifying the reliability and enhancing the trustworthiness of the AI model's predictions in the context of both EO data analysis and mosquito abundance studies.
title A Latent Space Metric for Enhancing Prediction Confidence in Earth Observation Data
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2401.17342