Don’t throw the baby out with the bathwater: reappreciating the dynamic relationship between humans, machines, and landscape images

Portelli, Raechel A.

doi:10.1007/s10980-020-00992-z

Cited by 5 publications

(4 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ignoring human–AI interaction when ML methods are implemented in PPC was introduced as a reason for this issue. Portelli [ 7 ], by reviewing the efficiency of the ML methods to deal with heterogeneous, massive and dynamic ecological datasets, noted that the contribution of humans in understanding pattern, processes and relationships should not be neglected. She reviewed the tensions between ML methods and human interpretations and concluded that the humans should have remained in the design of landscape ecology applications when ML methods are implemented.…”

Section: Resultsmentioning

confidence: 99%

“…Especially when it comes to inducing new patterns and complicated processes. Although ML methods are able to provide well-expressed and exact responses to well-structured problems, they are not so good at solving vague and ill-posed problems [ 7 ]. So, the collaboration of humans with ML methods can result in more successful and impressive applications of the ML for these problems.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Review on Human–AI Interaction in Machine Learning and Insights for Medical Applications

Maadi

Khorshidi

Aickelin

2021

IJERPH

View full text Add to dashboard Cite

Objective: To provide a human–Artificial Intelligence (AI) interaction review for Machine Learning (ML) applications to inform how to best combine both human domain expertise and computational power of ML methods. The review focuses on the medical field, as the medical ML application literature highlights a special necessity of medical experts collaborating with ML approaches. Methods: A scoping literature review is performed on Scopus and Google Scholar using the terms “human in the loop”, “human in the loop machine learning”, and “interactive machine learning”. Peer-reviewed papers published from 2015 to 2020 are included in our review. Results: We design four questions to investigate and describe human–AI interaction in ML applications. These questions are “Why should humans be in the loop?”, “Where does human–AI interaction occur in the ML processes?”, “Who are the humans in the loop?”, and “How do humans interact with ML in Human-In-the-Loop ML (HILML)?”. To answer the first question, we describe three main reasons regarding the importance of human involvement in ML applications. To address the second question, human–AI interaction is investigated in three main algorithmic stages: 1. data producing and pre-processing; 2. ML modelling; and 3. ML evaluation and refinement. The importance of the expertise level of the humans in human–AI interaction is described to answer the third question. The number of human interactions in HILML is grouped into three categories to address the fourth question. We conclude the paper by offering a discussion on open opportunities for future research in HILML.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Review on Human–AI Interaction in Machine Learning and Insights for Medical Applications

Maadi

Khorshidi

Aickelin

2021

IJERPH

View full text Add to dashboard Cite

show abstract

“…Not only does independent validation allow estimates of accuracy and bias uniquely tailored to each system, but it also ensures that some human expertise is involved in the process. Although here we argue for increased automation in the annotation of benthic imagery, humans should remain involved throughout the process in some capacity (Portelli 2020). Without proper validation and/or spot‐checking of data by a trained human observer, the procedure could generate erroneous data, either due to human error during processing steps or poor performance by the computer vision system.…”

Section: Discussionmentioning

confidence: 99%

Using machine learning to achieve simultaneous, georeferenced surveys of fish and benthic communities on shallow coral reefs

Miller

Dubel

Adam

et al. 2023

Limnology & Ocean Methods

View full text Add to dashboard Cite

Surveying coastal systems to estimate distribution and abundance of fish and benthic organisms is labor‐intensive, often resulting in spatially limited data that are difficult to scale up to an entire reef or island. We developed a method that leverages the automation of a machine learning platform, CoralNet, to efficiently and cost‐effectively allow a single observer to simultaneously generate georeferenced data on abundances of fish and benthic taxa over large areas in shallow coastal environments. Briefly, a researcher conducts a fish survey while snorkeling on the surface and towing a float equipped with a handheld GPS and a downward‐facing GoPro, passively taking ~ 10 photographs per meter of benthos. Photographs and surveys are later georeferenced and photographs are automatically annotated by CoralNet. We found that this method provides similar biomass and density values for common fishes as traditional scuba‐based fish counts on fixed transects, with the advantage of covering a larger area. Our CoralNet validation determined that while photographs automatically annotated by CoralNet are less accurate than photographs annotated by humans at the level of a single image, the automated approach provides comparable or better estimations of the percent cover of the benthic substrates at the level of a minute of survey (~ 50 m2 of reef) due to the volume of photographs that can be automatically annotated, providing greater spatial coverage of the site. This method can be used in a variety of shallow systems and is particularly advantageous when spatially explicit data or surveys of large spatial extents are necessary.

show abstract

“…In addition, the research community has gained from parallel developments in other subject areas. For example, advances in machine learning (Portelli 2020;Stupariu et al 2022;Theron et al 2022), formation of new data streams such as citizen science (Callaghan et al 2019), developments in positioning technology (Hadjikyriakou et al 2020), and access to relevant and often free geo-data (Mercier et al 2021;Piedallu et al 2023) many of which are systematically collected in space and time (Santos et al 2016). Moreover, the generation of a plethora of mapping software (Rudge et al 2022) and provision of algorithmic code act to reduce the technical skill set required by researchers (Buettel et al 2018).…”

Section: Uses Of Remote Sensing In Landscape Ecologymentioning

confidence: 99%

Remote sensing in landscape ecology

Foody

2023

Landsc Ecol

View full text Add to dashboard Cite

Don’t throw the baby out with the bathwater: reappreciating the dynamic relationship between humans, machines, and landscape images

Cited by 5 publications

References 38 publications

A Review on Human–AI Interaction in Machine Learning and Insights for Medical Applications

A Review on Human–AI Interaction in Machine Learning and Insights for Medical Applications

Using machine learning to achieve simultaneous, georeferenced surveys of fish and benthic communities on shallow coral reefs

Remote sensing in landscape ecology

Contact Info

Product

Resources

About