Benchmarking and end-to-end considerations for GeoAI-enabled decision-making

H. Lexie Yang; Philipe Ambrozio Dias; Jacob Arndt; Jason Wohlgemuth; Abhishek Potnis; Dalton Lunga

doi:10.1016/B978-0-44-319077-3.00011-0

Benchmarking and end-to-end considerations for GeoAI-enabled decision-making

H. Lexie Yang, Philipe Ambrozio Dias, Jacob Arndt, Jason Wohlgemuth, Abhishek Potnis, Dalton Lunga

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Abstract

Many machine learning, computer vision, artificial intelligence-inspired approaches have been developed to process and analyze voluminous, heterogeneous, and distributed remote sensing data. The success of these effective imagery analytics has the potential to enable us end-to-end applications. However, determining the most effective data and algorithms remains challenging. Therefore it is crucial to have appropriate benchmarking methods and designs to ensure the effective adaptation of GeoAI systems and to leverage the rich remote sensing data for various applications. This chapter discusses recent developments and challenges (data, metrics, protocol-related) in benchmarking for GeoAI systems. We also highlight important considerations to support and maximize the impact of GeoAI benchmarking.

Original language	English
Title of host publication	Advances in Machine Learning and Image Analysis for GeoAI
Publisher	Elsevier
Pages	93-114
Number of pages	22
ISBN (Electronic)	9780443190773
ISBN (Print)	9780443190780
DOIs	https://doi.org/10.1016/B978-0-44-319077-3.00011-0
State	Published - Jan 1 2024

Keywords

Artificial intelligence
Benchmarking
GeoAI
Remote sensing

Access to Document

10.1016/B978-0-44-319077-3.00011-0

Cite this

@inbook{561672c5360b40a59705f2f09775b814,

title = "Benchmarking and end-to-end considerations for GeoAI-enabled decision-making",

abstract = "Many machine learning, computer vision, artificial intelligence-inspired approaches have been developed to process and analyze voluminous, heterogeneous, and distributed remote sensing data. The success of these effective imagery analytics has the potential to enable us end-to-end applications. However, determining the most effective data and algorithms remains challenging. Therefore it is crucial to have appropriate benchmarking methods and designs to ensure the effective adaptation of GeoAI systems and to leverage the rich remote sensing data for various applications. This chapter discusses recent developments and challenges (data, metrics, protocol-related) in benchmarking for GeoAI systems. We also highlight important considerations to support and maximize the impact of GeoAI benchmarking.",

keywords = "Artificial intelligence, Benchmarking, GeoAI, Remote sensing",

author = "{Lexie Yang}, H. and {Ambrozio Dias}, Philipe and Jacob Arndt and Jason Wohlgemuth and Abhishek Potnis and Dalton Lunga",

year = "2024",

month = jan,

day = "1",

doi = "10.1016/B978-0-44-319077-3.00011-0",

language = "English",

isbn = "9780443190780",

pages = "93--114",

booktitle = "Advances in Machine Learning and Image Analysis for GeoAI",

publisher = "Elsevier",

}

TY - CHAP

T1 - Benchmarking and end-to-end considerations for GeoAI-enabled decision-making

AU - Lexie Yang, H.

AU - Ambrozio Dias, Philipe

AU - Arndt, Jacob

AU - Wohlgemuth, Jason

AU - Potnis, Abhishek

AU - Lunga, Dalton

PY - 2024/1/1

Y1 - 2024/1/1

N2 - Many machine learning, computer vision, artificial intelligence-inspired approaches have been developed to process and analyze voluminous, heterogeneous, and distributed remote sensing data. The success of these effective imagery analytics has the potential to enable us end-to-end applications. However, determining the most effective data and algorithms remains challenging. Therefore it is crucial to have appropriate benchmarking methods and designs to ensure the effective adaptation of GeoAI systems and to leverage the rich remote sensing data for various applications. This chapter discusses recent developments and challenges (data, metrics, protocol-related) in benchmarking for GeoAI systems. We also highlight important considerations to support and maximize the impact of GeoAI benchmarking.

AB - Many machine learning, computer vision, artificial intelligence-inspired approaches have been developed to process and analyze voluminous, heterogeneous, and distributed remote sensing data. The success of these effective imagery analytics has the potential to enable us end-to-end applications. However, determining the most effective data and algorithms remains challenging. Therefore it is crucial to have appropriate benchmarking methods and designs to ensure the effective adaptation of GeoAI systems and to leverage the rich remote sensing data for various applications. This chapter discusses recent developments and challenges (data, metrics, protocol-related) in benchmarking for GeoAI systems. We also highlight important considerations to support and maximize the impact of GeoAI benchmarking.

KW - Artificial intelligence

KW - Benchmarking

KW - GeoAI

KW - Remote sensing

UR - http://www.scopus.com/inward/record.url?scp=85199068151&partnerID=8YFLogxK

U2 - 10.1016/B978-0-44-319077-3.00011-0

DO - 10.1016/B978-0-44-319077-3.00011-0

M3 - Chapter

AN - SCOPUS:85199068151

SN - 9780443190780

SP - 93

EP - 114

BT - Advances in Machine Learning and Image Analysis for GeoAI

PB - Elsevier

ER -

Benchmarking and end-to-end considerations for GeoAI-enabled decision-making

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this