Comparing the input, output, and validation maps for several models of land change

Pontius, Robert Gilmore; Boersma, Wideke; Castella, Jean-Christophe; Clarke, Keith; Nijs, Ton de; Dietzel, Charles; Duan, Zengqiang; Fotsing, Éric; Goldstein, Noah; Kok, Kasper; Koomen, E.; Lippitt, Christopher D.; McConnell, William J.; Sood, Alias Mohd; Pijanowski, Bryan C.; Pithadia, Snehal; Sweeney, Sean; Trung, Tran Ngoc; Veldkamp, A.; Verburg, Peter H.

doi:10.1007/s00168-007-0138-2

Cited by 758 publications

(481 citation statements)

References 35 publications

Supporting

Mentioning

405

Contrasting

Unclassified

Order By: Relevance

“…These methods can be used to verify the internal properties of the simulation processes itself. Also, if consistent high-resolution data for 2 years are available, validation may be possible by comparing the simulated results to past or current land use patterns (Brown et al 2005;Pontius et al 2008). Another challenge is linked to the interactions between agents and their social networks.…”

Section: Discussionmentioning

confidence: 99%

An agent-based approach to model land-use change at a regional scale

et al. 2009

Self Cite

View full text Add to dashboard Cite

Land-use/cover change (LUCC) is a complex process that includes actors and factors at different social and spatial levels. A common approach to analyse and simulate LUCC as the result of individual decisions is agent-based modelling (ABM). However, ABM is often applied to simulate processes at local scales, while its application in regional studies is limited. This paper describes first a conceptual framework for ABM to analyse and explore regional LUCC processes. Second, the conceptual framework is represented by combining different concepts including agent typologies, farm trajectories and probabilistic decision-making processes. Finally, the framework is illustrated through a case study in the Netherlands, where processes of farm cessation, farm expansion and farm diversification are shaping the structure of the landscape. The framework is a generic, straightforward approach to analyse and explore regional LUCC with an explicit link to empirical approaches for parameterization of ABM.

show abstract

Section: Discussionmentioning

confidence: 99%

An agent-based approach to model land-use change at a regional scale

et al. 2009

Self Cite

View full text Add to dashboard Cite

show abstract

“…Few studies have rigorously compared the performance of different approaches for modelling forest loss. To rigorously compare different modelling approaches in their performance in predicting forest loss Pontius et al (2008) argue that the methods being compared must be applied to the same study landscape, but very few published studies have done this.…”

Section: Introductionmentioning

confidence: 99%

“…First, we evaluated the effects of varying the ratio of loss to persistence cells in the training data set on the predicted probability of forest loss in both logistic regression and Random Forest. Second, as suggested by Pontius et al (2008), we sought to compare the performance of three modelling methods (random forest, logistic regression and a naïve model) by applying them in the same landscape in the same time interval. Third, we sought to formally evaluate the utility of using landscape structure as predictors by computing models with and without landscape metrics.…”

Section: Introductionmentioning

confidence: 99%

Multiple-scale prediction of forest loss risk across Borneo

et al. 2017

View full text Add to dashboard Cite

Context The forests of Borneo have among the highest biodiversity and also the highest forest loss rates on the planet. Objectives Our objectives were to: (1) compare multiple modelling approaches, (2) evaluate the utility of landscape composition and configuration as predictors, (3) assess the influence of the ratio of forest loss and persistence points in the training sample, (4) identify the multiple-scale drivers of recent forest loss and (5) predict future forest loss risk across Borneo. Methods We compared random forest machine learning and logistic regression in a multi-scale approach to model forest loss risk between 2000 and 2010 as a function of topographical variables and landscape structure, and applied the highest performing model to predict the spatial pattern of forest loss risk between 2010 and 2020. We utilized a naïve model as a null comparison and used the total operating characteristic AUC to assess model performance. Results Our analysis produced five main results. We found that: (1) random forest consistently outperformed logistic regression and the naïve model; (2) including landscape structure variables substantially improved predictions; (3) a ratio of occurrence to nonoccurrence points in the training dataset that does not match the actual ratio in the landscape biases the predictions of both random forest and logistic regression; (4) forest loss risk differed between the three nations that comprise Borneo, with patterns in Kalimantan highly related to distance from the edge of the previous frontier of forest loss, while Malaysian Borneo showed a more diffuse pattern related to the structure of the landscape; (5) we predicted continuing 123Landscape Ecol (2017) 32:1581-1598 DOI 10.1007 very high rates of forest loss in the 2010-2020 period, and produced maps of the expected risk of forest loss across the full extent of Borneo. Conclusions These results confirm that multiplescale modelling using landscape metrics as predictors in a random forest modelling framework is a powerful approach to landscape change modelling. There is immense immanent risk to Borneo's forests, with clear spatial patterns of risk related to topography and landscape structure that differ between the three nations that comprise Borneo.

show abstract

“…It ranges from 0 %, meaning no overlap between observed and predicted change, to 100 %, meaning perfect overlap between observed and predicted change . In this case, the figure of merit was 17 % which is a low performance, although higher than in some of the case studies presented in Pontius et al (2008). The reasons for this performance may be explained by the small urbanised area between 1994 and 2005 (1.7 % of the total study area) and also by not having considered all the factors responsible for urban growth in the modelling process.…”

Section: Urban Modelling For Year 2016 With Geomodmentioning

confidence: 56%

“…The low performance of the model, as indicated by the figure of merit (17 %), calls for future experimentations using other factors/constraints and/or modelling approaches. The scenario for 2016 is, as in any future scenario (Pontius et al, 2008), to be interpreted with caution.…”

Section: N Martins Et Al: Urban Modelling For Seismic Prone Areasmentioning

confidence: 99%

Urban modelling for seismic prone areas: the case study of Vila Franca do Campo (Azores Archipelago, Portugal)

Martins

Cabral

Silva³

2012

Nat. Hazards Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. Seismic risk mitigation comprises of land-use planning policies that enable risk reduction in areas exposed to earthquakes. Thus, the assessment of land-use plans regarding urban growth in seismic prone areas is very important. This article analyses the urban expansion of Vila Franca do Campo (island of S. Miguel, Azores, Portugal) from 1994 to 2005 based on ortophotomaps interpretations and simulates a scenario of urban growth for the year 2016 with a Land-use and Cover-Change (LUCC) model (Geomod). The goal is to evaluate the potential impact of land-use plans in managing urban growth and promoting seismic risk mitigation. Results indicate that the urban expansion, between 1994 and 2005, was done according to the Municipal Master Plan (MMP) restrictions. The scenario modelled for the year 2016 is potentially stricter for urban growth because it adds to the previous plan the constraints defined by the South Coast Management Plan (SCMP) that entered into force in 2007. In both time periods, a continuing urban growth towards seismic areas was identified. The absence of seismic risk mitigation policies and measures on both plans may contribute to increase the seismic hazard exposure and vulnerability. The results of this study strongly suggest the reformulation of future land-use plans to include seismic risk mitigation goals and policies.

show abstract

Comparing the input, output, and validation maps for several models of land change

Cited by 758 publications

References 35 publications

An agent-based approach to model land-use change at a regional scale

An agent-based approach to model land-use change at a regional scale

Multiple-scale prediction of forest loss risk across Borneo

Urban modelling for seismic prone areas: the case study of Vila Franca do Campo (Azores Archipelago, Portugal)

Contact Info

Product

Resources

About