Hierarchical probabilistic regression for AUV-based adaptive sampling of marine phenomena

Jnaneshwar Das, Julio Harvey, Frederic Py, Harshvardhan Vathsangam, Rishi Graham, Kanna Rajan, Gaurav S. Sukhatme

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

Marine phenomena such as algal blooms can be detected using in situ measurements onboard autonomous underwater vehicles (AUVs), but understanding plankton ecology and community structure requires retrieval and analysis of water specimens. This process requires shipboard or manual sample collection, followed by onshore lab analysis which is time-consuming. Better understanding of the relationship between the observable environmental features and organism abundance would allow more precisely targeted sampling and thereby save time. In this work, we present an approach to learn and improve models that predict this relationship. Coupled with recent advances in AUV technology allowing selective retrieval of water samples, this constitutes a new paradigm in biological sampling. We use organism abundance models along with spatial models of environmental features learned immediately after AUV deployments to compute spatial distributions of organisms in the coastal ocean purely from in situ AUV data. We use Gaussian process regression along with the unscented transform to fuse the two models, obtaining both the mean and variance of the organism abundance estimates. The uncertainty in organism abundance predictions is used in a sampling strategy to selectively acquire new water specimens that improves the organism abundance models. Simulation results are presented demonstrating the advantage of performing hierarchical probabilistic regression. After the validation through simulation, we show predictions of organism abundance from models learned on lab-analyzed water sample data, and AUV survey data.

Original languageEnglish (US)
Title of host publication2013 IEEE International Conference on Robotics and Automation, ICRA 2013
Pages5571-5578
Number of pages8
DOIs
StatePublished - Nov 14 2013
Externally publishedYes
Event2013 IEEE International Conference on Robotics and Automation, ICRA 2013 - Karlsruhe, Germany
Duration: May 6 2013May 10 2013

Other

Other2013 IEEE International Conference on Robotics and Automation, ICRA 2013
CountryGermany
CityKarlsruhe
Period5/6/135/10/13

Fingerprint

Autonomous underwater vehicles
Sampling
Water
Plankton
Electric fuses
Ecology
Spatial distribution

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Cite this

Das, J., Harvey, J., Py, F., Vathsangam, H., Graham, R., Rajan, K., & Sukhatme, G. S. (2013). Hierarchical probabilistic regression for AUV-based adaptive sampling of marine phenomena. In 2013 IEEE International Conference on Robotics and Automation, ICRA 2013 (pp. 5571-5578). [6631377] https://doi.org/10.1109/ICRA.2013.6631377

Hierarchical probabilistic regression for AUV-based adaptive sampling of marine phenomena. / Das, Jnaneshwar; Harvey, Julio; Py, Frederic; Vathsangam, Harshvardhan; Graham, Rishi; Rajan, Kanna; Sukhatme, Gaurav S.

2013 IEEE International Conference on Robotics and Automation, ICRA 2013. 2013. p. 5571-5578 6631377.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Das, J, Harvey, J, Py, F, Vathsangam, H, Graham, R, Rajan, K & Sukhatme, GS 2013, Hierarchical probabilistic regression for AUV-based adaptive sampling of marine phenomena. in 2013 IEEE International Conference on Robotics and Automation, ICRA 2013., 6631377, pp. 5571-5578, 2013 IEEE International Conference on Robotics and Automation, ICRA 2013, Karlsruhe, Germany, 5/6/13. https://doi.org/10.1109/ICRA.2013.6631377
Das J, Harvey J, Py F, Vathsangam H, Graham R, Rajan K et al. Hierarchical probabilistic regression for AUV-based adaptive sampling of marine phenomena. In 2013 IEEE International Conference on Robotics and Automation, ICRA 2013. 2013. p. 5571-5578. 6631377 https://doi.org/10.1109/ICRA.2013.6631377
Das, Jnaneshwar ; Harvey, Julio ; Py, Frederic ; Vathsangam, Harshvardhan ; Graham, Rishi ; Rajan, Kanna ; Sukhatme, Gaurav S. / Hierarchical probabilistic regression for AUV-based adaptive sampling of marine phenomena. 2013 IEEE International Conference on Robotics and Automation, ICRA 2013. 2013. pp. 5571-5578
@inproceedings{26c48784608e4e7e930a1e7fbfe4c364,
title = "Hierarchical probabilistic regression for AUV-based adaptive sampling of marine phenomena",
abstract = "Marine phenomena such as algal blooms can be detected using in situ measurements onboard autonomous underwater vehicles (AUVs), but understanding plankton ecology and community structure requires retrieval and analysis of water specimens. This process requires shipboard or manual sample collection, followed by onshore lab analysis which is time-consuming. Better understanding of the relationship between the observable environmental features and organism abundance would allow more precisely targeted sampling and thereby save time. In this work, we present an approach to learn and improve models that predict this relationship. Coupled with recent advances in AUV technology allowing selective retrieval of water samples, this constitutes a new paradigm in biological sampling. We use organism abundance models along with spatial models of environmental features learned immediately after AUV deployments to compute spatial distributions of organisms in the coastal ocean purely from in situ AUV data. We use Gaussian process regression along with the unscented transform to fuse the two models, obtaining both the mean and variance of the organism abundance estimates. The uncertainty in organism abundance predictions is used in a sampling strategy to selectively acquire new water specimens that improves the organism abundance models. Simulation results are presented demonstrating the advantage of performing hierarchical probabilistic regression. After the validation through simulation, we show predictions of organism abundance from models learned on lab-analyzed water sample data, and AUV survey data.",
author = "Jnaneshwar Das and Julio Harvey and Frederic Py and Harshvardhan Vathsangam and Rishi Graham and Kanna Rajan and Sukhatme, {Gaurav S.}",
year = "2013",
month = "11",
day = "14",
doi = "10.1109/ICRA.2013.6631377",
language = "English (US)",
isbn = "9781467356411",
pages = "5571--5578",
booktitle = "2013 IEEE International Conference on Robotics and Automation, ICRA 2013",

}

TY - GEN

T1 - Hierarchical probabilistic regression for AUV-based adaptive sampling of marine phenomena

AU - Das, Jnaneshwar

AU - Harvey, Julio

AU - Py, Frederic

AU - Vathsangam, Harshvardhan

AU - Graham, Rishi

AU - Rajan, Kanna

AU - Sukhatme, Gaurav S.

PY - 2013/11/14

Y1 - 2013/11/14

N2 - Marine phenomena such as algal blooms can be detected using in situ measurements onboard autonomous underwater vehicles (AUVs), but understanding plankton ecology and community structure requires retrieval and analysis of water specimens. This process requires shipboard or manual sample collection, followed by onshore lab analysis which is time-consuming. Better understanding of the relationship between the observable environmental features and organism abundance would allow more precisely targeted sampling and thereby save time. In this work, we present an approach to learn and improve models that predict this relationship. Coupled with recent advances in AUV technology allowing selective retrieval of water samples, this constitutes a new paradigm in biological sampling. We use organism abundance models along with spatial models of environmental features learned immediately after AUV deployments to compute spatial distributions of organisms in the coastal ocean purely from in situ AUV data. We use Gaussian process regression along with the unscented transform to fuse the two models, obtaining both the mean and variance of the organism abundance estimates. The uncertainty in organism abundance predictions is used in a sampling strategy to selectively acquire new water specimens that improves the organism abundance models. Simulation results are presented demonstrating the advantage of performing hierarchical probabilistic regression. After the validation through simulation, we show predictions of organism abundance from models learned on lab-analyzed water sample data, and AUV survey data.

AB - Marine phenomena such as algal blooms can be detected using in situ measurements onboard autonomous underwater vehicles (AUVs), but understanding plankton ecology and community structure requires retrieval and analysis of water specimens. This process requires shipboard or manual sample collection, followed by onshore lab analysis which is time-consuming. Better understanding of the relationship between the observable environmental features and organism abundance would allow more precisely targeted sampling and thereby save time. In this work, we present an approach to learn and improve models that predict this relationship. Coupled with recent advances in AUV technology allowing selective retrieval of water samples, this constitutes a new paradigm in biological sampling. We use organism abundance models along with spatial models of environmental features learned immediately after AUV deployments to compute spatial distributions of organisms in the coastal ocean purely from in situ AUV data. We use Gaussian process regression along with the unscented transform to fuse the two models, obtaining both the mean and variance of the organism abundance estimates. The uncertainty in organism abundance predictions is used in a sampling strategy to selectively acquire new water specimens that improves the organism abundance models. Simulation results are presented demonstrating the advantage of performing hierarchical probabilistic regression. After the validation through simulation, we show predictions of organism abundance from models learned on lab-analyzed water sample data, and AUV survey data.

UR - http://www.scopus.com/inward/record.url?scp=84887268683&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887268683&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2013.6631377

DO - 10.1109/ICRA.2013.6631377

M3 - Conference contribution

AN - SCOPUS:84887268683

SN - 9781467356411

SP - 5571

EP - 5578

BT - 2013 IEEE International Conference on Robotics and Automation, ICRA 2013

ER -