Browse Projects > Detailed View

Artificial Intelligence Methods, Quantitative Mapping, and Stakeholder Perceptions in Visual Quality Research


The technology in this area has greatly expanded with artificial intelligence (AI) and the creation of new AI variables. Current technology has advanced to produce affordable equipment such as a bicycle with data recorder to collect data from a multi-spectrum scanner and instantly obtain visual quality scores (thousands of them) along a route that nicely covary with past visual quality variables and equations (in a forthcoming publication by Burley, Hui, Yue, Yilma, and Kuinii). This predictive science has advanced from explaining about 60% of the variance (Burley 1997) to over 90% of the variance with an accuracy of 9,999 correct predictions in 10,000 (Burley and Yilmaz 2014, Yilmaz and Burley 2013) . There is a need to explore this technology on the US highway roadsides and investigate its feasibility.

In addition, mapping visual quality has greatly changed as illustrated by (Jin et al. 2018; Ylimaz, Liu, and Burley 2018; and Lu et al. 2012). They completed their formative work in Michigan concerning the validity of predicting visual quality based upon land cover. Currently they are working upon a map of Eurasia and North America. Landscape management and transportation professionals employing these metric approaches could be highly useful in quantifying the impacts of proposed projects and alternatives.

Furthermore, very little has been accomplished in partitioning and comparing environmental perception of various stakeholders. Studies have shown that cultural background affects how environmental features are perceived (Mo et al 2011). There is much more work that could be researched in this area (across the nation) with various stakeholders: African Americans, Latin Americans, and Native American populations. Stakeholder perception is important in transportation planning and design and relatively little has been accomplished in this area. Various stakeholder groups should be sampled to see how they are ordinated with the general population.


A. Sample stakeholder populations across the nation in various states/regions with methods established by Burley and Yilmaz 2014, Yilmaz and Burley 2013, Burley et al. 2011, Mo et al. 2011, and Burley 1997).

B. Construction state/regional maps of visual/environmental quality (using a process similar to Yilmaz et al. 2018, Jin et al. 2012, and Lu et al. 2012) as a baseline for assessing projects and proposals.

C. Employ real time artificial intelligence sensing methods (in a forthcoming article) along corridors across states/regions to build a set of case studies and to train practitioners on how to gather inventory and analysis information to assess environmental/visual quality for projects.

Related Research:

Burley, J.B. 1997. Visual and ecological environmental quality model for transportation planning and design. Transportation Research Record, 1549:54-60.

Burley, J.B., G. Deyoung, S. Partin and J. Rokos. 2011. Reinventing Detroit: grayfields—new metrics in evaluating urban environments. Challenges, 2011 (2):45-54.

Burley, J. B. and R. Yilmaz. 2014. Visual quality preference: the Smyser index variables. International Journal of Energy and Environment, 8:147-153.

Jin, Y., J.B. Burley, P. Machemer, P Crawford, H. Xu, Z. Wu, and L. Loures. 2018. The Corbusier dream and Frank Lloyd Wright vision: cliff detritus vs. urban savanna. Ergen, M. (ed.) In: Urban Agglomeration. Intech Rijeka, Croatia, 211-230.

Lu, Di, J.B. Burley, P. Crawford, R. Schutzki, and Luis Loures. 2012. Chapter 7: Quantitative methods in environmental and visual quality mapping and assessment: a Muskegon, Michigan watershed case study with urban planning implications. Advances in Spatial Planning, InTech: 127-142.

Mo, F., G. Le Cléach, M. Sales, G. Deyoung, and J.B. Burley. 2011. Visual and environmental quality perception and preference in the People's Republic of China, France, and Portugal. International Journal of Energy and Environment, 4(5): 549-556.

Yilmaz, R. and J.B. Burley. 2013. Dissecting the Smyser index in visual quality. Modern Landscape Architecture. Proceedings of the 6th WSEAS International Conference on Landscape Architecture (LA’13), Nanjing, China, November 17-19:32-36.

Yilmaz, R., C.Q. Liu, and J.B. Burley. 2018 A visual quality predication map for Michigan, USA: an approach to validate spatial content. Loures, L. (ed.) In: Land Use – Assessing the Past, Envisioning the Future. Intech Rijeka, Croatia.

Sponsoring Committee:AFB40, Landscape and Environmental Design
Research Period:6 - 12 months
Research Priority:Medium
RNS Developer:Jon Burley, Michigan State University
Date Posted:01/06/2020
Date Modified:02/21/2020
Index Terms:Artificial intelligence, Mapping, Stakeholders, Ethnic groups, Visual perception, Environmental quality,
Cosponsoring Committees: 
Data and Information Technology
Transportation (General)

Please click here if you wish to share information or are aware of any research underway that addresses issues in this research needs statement. The information may be helpful to the sponsoring committee in keeping the statement up-to-date.