Forest landscape visual quality evaluation using artificial intelligence techniques as a decision support system

Forest management should be directed towards multifunctional management and utilization of forest services (other than wood production) in order to achieve maximum utilization and minimum degradation. Artificial intelligence enables forest managers to plan for utilization of forest landscape aesthetic values. Visual quality evaluation is a stochastic problem in natural forest landscapes and it is influenced by forest characteristics. We aimed to landscape visual quality evaluation by expert/human-perception-based approach and application of artificial intelligence modeling techniques for the visual quality prediction of forest landscapes. Therefore, we recorded five landscape attributes in 100 forest landscapes. We developed the stochastic model to evaluate visual quality potential by artificial intelligence techniques. Comparing to multi-layer regression (R 2  = 0.588) and multi-layer perceptron (R 2  = 0.847), the radial basis function (RBF) (R 2  = 0.887) model represents the highest value of R 2 in the test data set. The water, shrubs, roads, rocky hills, and trees, in forest landscapes were introduced respectively as the most important attributes which influence the RBF model. The designed graphical user interface tool, as an environmental decision support system, evaluates landscape visual quality of forests, and it helps to solve stochastic problems such as visual quality value.

[1]  Abdolrassoul Salmanmahiny,et al.  Performance evaluation of multiple methods for landscape aesthetic suitability mapping: A comparative study between Multi-Criteria Evaluation, Logistic Regression and Multi-Layer Perceptron neural network , 2017 .

[2]  J. Lucio,et al.  Relationship between landscape visual attributes and spatial pattern indices: A test study in Mediterranean-climate landscapes , 2006 .

[3]  Ali Jahani,et al.  Forest landscape aesthetic quality model (FLAQM): A comparative study on landscape modelling using regression analysis and artificial neural networks , 2019, Journal of Forest Science.

[4]  Gabriele Zanetto,et al.  The impact of agroforestry networks on scenic beauty estimation: The role of a landscape ecological network on a socio-cultural process , 2003 .

[5]  A. Jahani,et al.  MLR and ANN Approaches for Prediction of Synthetic/Natural Nanofibers Diameter in the Environmental and Medical Applications , 2020, Scientific Reports.

[6]  M. Depledge,et al.  Blue space: The importance of water for preference, affect, and restorativeness ratings of natural and built scenes , 2010 .

[7]  Jingwei Zhao,et al.  Urban woodland understory characteristics in relation to aesthetic and recreational preference , 2017 .

[8]  Bo Chen,et al.  Assessment of aesthetic quality and multiple functions of urban green space from the users’ perspective: The case of Hangzhou Flower Garden, China , 2009 .

[9]  Pouya Aghelpour,et al.  Evaluation of stochastic and artificial intelligence models in modeling and predicting of river daily flow time series , 2020, Stochastic Environmental Research and Risk Assessment.

[10]  B. Shelby,et al.  Changes in Scenic Quality after Harvest: A Decade of Ratings for Six Silviculture Treatments , 2003, Journal of Forestry.

[11]  Eric Renshaw,et al.  Analysis of forest thinning strategies through the development of space–time growth–interaction simulation models , 2009 .

[12]  Yousef Azimi,et al.  Prediction of blast induced ground vibration (BIGV) of quarry mining using hybrid genetic algorithm optimized artificial neural network , 2019, Measurement.

[13]  M. Arriaza,et al.  Assessing the visual quality of rural landscapes , 2004 .

[14]  Kyle Eyvindson,et al.  Value of information in multiple criteria decision making: an application to forest conservation , 2019, Stochastic Environmental Research and Risk Assessment.

[15]  A. Arnberger,et al.  Exploring visual preferences for structural attributes of urban forest stands for restoration and heat relief , 2019, Urban Forestry & Urban Greening.

[16]  Marc Antrop,et al.  Comparing saliency maps and eye-tracking focus maps: The potential use in visual impact assessment based on landscape photographs , 2016 .

[17]  H. Goshtasb,et al.  Tourism impact assessment modeling of vegetation density for protected areas using data mining techniques , 2020, Land Degradation & Development.

[18]  Y. Azimi,et al.  Prediction of Seismic Wave Intensity Generated by Bench Blasting Using Intelligence Committee Machines , 2019, International Journal of Engineering.

[19]  Christer Thrane,et al.  Vegetation density of urban parks and perceived appropriateness for recreation , 2006 .

[20]  Ataur Rahman,et al.  Application of artificial neural networks in regional flood frequency analysis: a case study for Australia , 2014, Stochastic Environmental Research and Risk Assessment.

[21]  T. Daniel.  Whither scenic beauty? Visual landscape quality assessment in the 21st century , 2001 .

[22]  H. Özgüner,et al.  Public attitudes towards naturalistic versus designed landscapes in the city of Sheffield (UK) , 2006 .

[23]  Yousef Azimi,et al.  Evolving multilayer perceptron, and factorial design for modelling and optimization of dye decomposition by bio-synthetized nano CdS-diatomite composite. , 2019, Environmental research.

[24]  J. Dwyer,et al.  The Significance of Urban Trees and Forests: Toward a Deeper Understanding of Values , 1991, Arboriculture & Urban Forestry.

[25]  R. Mercurio,et al.  Assessing visual impacts of forest operations on a landscape in the Serre Regional Park of southern Italy , 2011, Landscape and Ecological Engineering.

[26]  K. P. Sudheer,et al.  Methods used for quantifying the prediction uncertainty of artificial neural network based hydrologic models , 2017, Stochastic Environmental Research and Risk Assessment.

[27]  R. Halvorsen,et al.  Methods for landscape characterisation and mapping: A systematic review , 2018, Land Use Policy.

[28]  Li-Li Wang,et al.  Automatic incident classification for large-scale traffic data by adaptive boosting SVM , 2018, Inf. Sci..

[29]  Peter M. Howley,et al.  Landscape aesthetics: Assessing the general publics' preferences towards rural landscapes , 2011 .

[30]  Jean-Christophe Foltête,et al.  Spatial modelling of landscape aesthetic potential in urban-rural fringes. , 2016, Journal of environmental management.

[31]  Ali Jahani,et al.  Air carbon monoxide forecasting using an artificial neural network in comparison with multiple regression , 2020, Modeling Earth Systems and Environment.

[32]  V. Etemad,et al.  Soil texture and plant degradation predictive model (STPDPM) in national parks using artificial neural network (ANN) , 2020, Modeling Earth Systems and Environment.

[33]  S. Zare,et al.  Effects of Shift Work on Health and Satisfaction of Workers in the Mining Industry , 2017 .

[34]  A. Misgav.  Visual preference of the public for vegetation groups in Israel. , 2000 .

[35]  James F. Palmer,et al.  Rating reliability and representation validity in scenic landscape assessments , 2001 .

[36]  James Hitchmough,et al.  All about the ‘wow factor’? The relationships between aesthetics, restorative effect and perceived biodiversity in designed urban planting , 2017 .

[37]  Kaiqi Huang,et al.  Hierarchical aesthetic quality assessment using deep convolutional neural networks , 2016, Signal Process. Image Commun..

[38]  Mahmoud Omid,et al.  Optimized forest degradation model (OFDM): an environmental decision support system for environmental impact assessment using an artificial neural network , 2016 .

[39]  Reza Pourbabaki,et al.  Application of ANN modeling techniques in the prediction of the diameter of PCL/gelatin nanofibers in environmental and medical studies , 2019, RSC advances.

[40]  A. Jahani.  Sycamore failure hazard classification model (SFHCM): an environmental decision support system (EDSS) in urban green spaces , 2019, International Journal of Environmental Science and Technology.

[41]  Jingwei Zhao,et al.  Characteristics of urban green spaces in relation to aesthetic preference and stress recovery , 2019, Urban Forestry & Urban Greening.

[42]  F. Barroso,et al.  Is land cover an important asset for addressing the subjective landscape dimensions , 2013 .

[43]  A. Jahani,et al.  Road impact assessment modelling on plants diversity in national parks using regression analysis in comparison with artificial intelligence , 2020, Modeling Earth Systems and Environment.

[44]  Brian Voigt,et al.  Landscape aesthetic modelling using Bayesian networks: Conceptual framework and participatory indicator weighting , 2019, Landscape and Urban Planning.

[45]  Marc Antrop,et al.  Cognitive attributes and aesthetic preferences in assessment and differentiation of landscapes. , 2009, Journal of environmental management.