Future Land Change Research Articles

An online tool with Google Earth Engine and cellular automata for seamlessly simulating global urban expansion at high resolutions

Projecting global urban expansion is crucial for environmental assessment under climate change scenarios. However, existing global future urban land products are typically provided at coarse resolutions (1 km) due to data and computing limitations. This hinders the accurate assessment of the impacts of global urban development at finer scales. Thus, we develop the first Cellular Automata (CA) online tool for simulating future global urban expansion in Google Earth Engine (GEE-CA), which can simulate future urban land change at a 30 m resolution under different SSP scenarios. GEE-CA enables seamless simulations of future urban land at high resolution through a partitioned parallel strategy. Seven large urban agglomerations are simulated under shared socioeconomic pathways as representative regions to present our fine-scale results. Comparatively, our datasets preserve significantly more spatial details than existing global urban land products. The improvement in resolution from 1 km to 30 m reduces errors by a range from 7.11% to 21.27% in the estimation of future urban area. So far, the proposed GEE-CA tool allows users to generate urban land projection maps for any defined region with a resolution as high as 30 m.

On the macroecology of rarity and vulnerability to extinction in terrestrial mammals

Understanding the interplay between rarity and vulnerability in the decline and extinction of species is a major challenge for modern conservation biology. In addition to traditional approaches, answering this question necessarily requires integrating new methodologies and information on species' life-history traits and responses to environmental stressors. Here we use data for over 4000 mammal species to: (1) assess which forms and levels of rarity are most represented across current IUCN threat categories; (2) test whether interspecific variation in vulnerability is more closely linked to intrinsic traits related to their rarity, or to extrinsic factors related to anthropogenic pressures; and (3) identify geographical areas where species with high potential vulnerability are particularly common and assess their overlap with forecasts of land cover change. To achieve these goals, we model the directional influence of life-history traits related with rarity and extrinsic correlates on vulnerability. Our results confirm the strong link between rarity and vulnerability within mammalian orders. A model encompassing the three main rarity traits (i.e. range size, population density, and habitat breadth) correlates with vulnerability, despite not being directly correlated with population density. Recent habitat changes (within the past 35 years) did not show a direct relationship with vulnerability, but the contractions in range size reveal a more complex long-term effect on species vulnerability. Given the current scenario of limited conservation resources, we anticipate that knowledge about the characteristics most associated with vulnerability, coupled with mapping species possessing these traits and facing potential future land changes, can facilitate the development of more precise and effective conservation strategies aimed at preventing species extinctions.

Integrated assessment of future climate and land use changes on urban floods: A Markov chain and PCSWMM-based approach for Hyderabad case study.

This research examines the impact of climate change and urban expansion on urban drainage systems in Hyderabad (Zone-XII, Zone-IV&V), India. It employs a Markov chain-based framework to simulate future climate and land changes. Integrated 1D-2D PCSWMM model is used to assess the hazards posed by these changes. Present and future extreme rainfall event(s) (1-10 days) are simulated to determine maximum flooding hours, valuable for resilience studies. Future rainfall events are simulated under four SSP scenarios using CMIP6 Global Climate Models (GCMs): EC-Earth3-Veg, MPI-ESM-1-2-HR, and MPI-ESM-1-2-LR. The Markov Chain Precipitation Generator (MCPG) model downscales grid-scale precipitation data to station-scale. Future urban land expansion is simulated using the Markov Chain-Cellular Automata (MC-CA) model with Terrset. MCPG model is validated using performance measures, and it showed most increased rainfall events under EC-Earth3-Veg. The MC-CA model obtained a Kappa coefficient of 0.89, indicating an increase in imperviousness in future LULC; 6.1% of vegetation and 29.06% of barren land in 2022 will be urbanized by 2075. A significant increase in extreme flood hazard areas for the 1-day and above 7-day events in the both zones is observed from the PCSWMM results. The study highlighted the importance of Markov chains and event duration in flood hazard assessments.

Commercial land use change and growth processes – An assessment of retail location in Lisbon, Portugal, 1995–2020

Land use modelling is essential to understanding future land use and change dynamics. Analyses of land use and change using Cellular Automata (CA) have been frequent in the literature since the latter were introduced to geography in the 1970s. In this paper, the statistical subsections – city blocks – of a previous analysis of Lisbon's commercial structure are used as the cells of a CA. A multi-layer perceptron (MLP) models the transition potential of those cells between 1995 and 2020, considering the impact of street centrality, subway development and other proxies of urban growth. The results confirm that commercial growth and change can be simulated as a function of street centrality and that using Local integration and Choice as drivers of a CA may help improve predictions of commercial growth and change. Moreover, the CA results reinforce that street centrality positively affects street commerce, especially when combined with access to transit and amenities. While these results can already inform planning practice and policymaking, the framework presented in this paper may be replicated to simulate ​future commercial land use, thus helping planners and policymakers prepare for change.

Scenario Simulation of Land Use and Cover under Safeguarding Ecological Security: A Case Study of Chang-Zhu-Tan Metropolitan Area, China

Scenario-based simulation in land use and cover change (LUCC) is a practical approach to maintaining ecological security. Many studies generally set constraints of LUCC utilizing ecological patches but without consideration of corridors connecting these patches. Here, we constructed a framework to balance urban growth and ecological security by integrating ecological security patterns (ESPs) into the PLUS model. This study selected Chang-Zhu-Tan Metropolitan Area (CZTMA) in central China as a typical case. Specifically, coupling quantitative demand with spatial constraints of multiple levels of ESPs, this study designed four scenarios, including historical tendency (HT), urban growth (UG), ecological conservation (EC), and coordinating city development and ecological protection (CCE). Then, the transformations and landscape patterns of LUCC were analyzed to evaluate the future land change from 2020 to 2050. The results show sixty-one key ecological sources in the CZTMA, mainly in higher-elevation forested areas. Forty-six ecological corridors were estimated using circuit theory. The building expansion was driven by accessibility to transportation and government locations and will contribute to the loss of forest and cropland in the future. The feature of different scenarios in alleviating the increasing fragmentation of patches and reducing the loss amount of ecological land showed EC > CCE > HT > UG. This study developed the ESP-PLUS framework and its modeling idea, which has the potential to be applied in other regions. This extension would assist decision-makers and urban planners in formulating sustainable land strategies that effectively reconcile eco-environmental conservation with robust economic growth, achieving a mutually beneficial outcome.

Quantifying Formative Processes in River‐ and Tide‐Dominated Deltas for Accurate Prediction of Future Change

AbstractAlthough most deltas are expected to lose land due to climate change and urbanization, tide‐dominated deltas have been suggested to gain land. The processes of land change in such deltas are, however, not well understood, and tide‐dominated deltas with all their known morphological attributes have not been simulated before. Our Delft3D simulations successfully reproduce tide‐dominated delta morphology, and show that tide‐dominated deltas with seaward widening and stable channels, elongate tidal bars and a funnel shape form when bidirectional tidal flow occurs along the whole delta. In contrast, tide‐influenced but river‐dominated deltas protrude from shoreline, and are efficient at gaining land by mouth bar deposition and bifurcations. These differences are a function of tidal‐fluvial interactions expressed by month‐averaged seaward and lateral velocities. Identification of delta types is thus critical for predicting future land change. We propose morphological metrics to differentiate river‐ and tide‐dominated deltas and test metrics on 40 modern deltas.

Relocating built-up land for biodiversity conservation in an uncertain future

Land use changes associated with habitat loss, fragmentation, and degradation exert profoundly detrimental impacts on biodiversity conservation. Urban development is one of the prevailing anthropogenic disturbances to wildlife habitat, because these developments are often considered permanent and irreversible. As a result, the potential benefits of built-up land relocation for biodiversity conservation have remained largely unexplored in environmental management practices. Here, we analyze recent built-up land relocation in Shanghai and explore how such restoration programs can affect future land change trajectories with regards to biodiversity conservation. Results show that 187.78 km2 built-up land in Shanghai was restored to natural habitat between 2017 and 2020. Further simulation analysis highlights that relocating built-up land can substantially promote conserve biodiversity. In particular, there would be less habitat loss, better natural habitat quality and more species habitat-suitable range under the scenarios with built-up land relocation. Species extinction assessment suggest that amphibians, mammals, and reptiles will all have an increasingly high extinction risk without built-up land relocation. However, there will even be a marginal decrease in extinction risk over time for mammals and reptiles if the relocation of built-up land is permitted, but still a moderate increase in extinction risk for amphibians. This study highlights the importance of incorporating rigorous conservation planning prior to development activities, thereby underpinning a sustainable approach to environmental management.

Integrated high-resolution, continental-scale land change forecasting

Predicting future land change is crucial in anticipating societal and environmental impacts and informing responses at different scales. We designed an integrated, high-resolution, land-change model and forecasted Australia's land change for the years 2020, 2025 and 2030 for Cropland, Forest, Grassland, and Built-up land-uses using cloud-based and high-performance computing. A spatially explicit set of drivers was fed into a random forest classifier to generate 30-m per-class suitability layers for the country, which were then used for allocating land-use. The model was validated against 2015 data, then land-use was projected until 2030. Accuracy at the national level was ∼94%. Forecasts showed increases in Grassland and Built-up areas and decreases in Forest and Cropland. Our modelling framework expands the current capabilities of large-scale land-change models and provides a first-of-its-kind multiclass land forecast for Australia that can inform land policy at multiple scales in Australia.

Four Fundamental Questions to Evaluate Land Change Models with an Illustration of a Cellular Automata–Markov Model

Numerous models exist for users to simulate land change to communicate with an audience concerning future land change. This article raises four fundamental questions to help model users decide whether to use any model: (1) Can the user understand the model? (2) Can the audience understand the model? (3) Can the user control the model? (4) Does the model address the goals of the specific application? This article applies these questions to the popular cellular automata–Markov (CA–Markov) model as IDRISI’s CA–Markov module expresses. Sensitivity analysis examines 120 ways to set the module’s parameters. Verification compares the module’s behavior to the software’s documentation. Results show that the cellular automata’s allocation fails to follow the quantity of change that the Markov module computes. The module’s behavior is likely to cause users to misinterpret the validation metrics and to miscommunicate with audiences. Thus, the answers to the four questions were not satisfactory for this article’s case study. This article’s framework helps users to judge a model’s appropriateness for a specific application by combining sensitivity analysis with verification in a manner that helps to interpret validation. Users should answer the four questions as they decide whether to use any software’s modules.

There’s no best model! Addressing limitations of land-use scenario modelling through multi-model ensembles

Cellular automata models are popular tools for exploring future land change pathways. But simulation modelling approaches often focus too narrowly on calibration against historic reference maps, limiting the diversity of possible outcomes. We argue that, contrary to what is commonly believed, there is no ‘best model’, and that model specification and calibration accuracy depend on the objective of the research. We propose a multi-model ensemble approach, in which a wide range of models and calibration rules sets are systematically tested against multiple metrics. We apply our approach to a case study in Spain. No single model performed well for all statistics, illustrating the danger of cherry-picking statistics for best performance. In our case study, accounting for historic land changes in model design was useful for simulating compact urban development, but limited the variability of simulation outcomes. The accessibility model driver improved urban pattern replication, while suitability without accessibility was useful for simulating low-density development encroaching on natural areas. Rather than abandoning calibrations that show low agreement with reference maps based on a small number of metrics we should seek to understand what each metric is telling us and use this information to enrich the diversity of simulated outcomes.

Multi-Criterion Spatial Optimization of Future Police Stations Based on Urban Expansion and Criminal Behavior Characteristics

Lanzhou’s rapid development has raised new security challenges, and improving public safety in areas under the jurisdiction of police stations is an effective way to address the problem of public security in urban areas. Unfortunately, the existing studies do not consider how factors such as future land changes, building functions, and characteristics of criminal behavior influence the choice of areas for police stations and the optimization of police stations with respect to traffic congestion. To solve these problems, we apply multiple methods and multi-source geospatial data to optimize police station locations. The proposed method incorporates a big data perspective, which provides new ideas and technical approaches to site selection models. First, we use the central city of Lanzhou as the study area and erase the exclusion areas from the initial layer to identify the undeveloped areas. Second, historical crime data, point of interest, and other data are combined to assess the potential crime risk. We then use the analytic hierarchy process to comprehensively assess undeveloped areas based on potential crime hotspots and on socioeconomic drivers and orography. In addition, according to China’s Road Traffic Safety Law and the current traffic congestion in the city, a minimum speed is determined, so that the target area can be reached in time even in congested traffic. Finally, we draw the spatial coverage map of police stations based on the location-allocation model and network analysis and optimize the map by considering the coverage rate of high-risk areas and building construction, in addition to maintenance and other objectives. The result shows that crime concentrates mainly in densely populated areas, indicating that people and wealth are the main drivers of crime. The differences in the spatial distribution of crime hotspots and residential areas at different spatial scales mean that the ratio of public security police force to household police force allocated to different police stations is spatially nonuniform. The method proposed herein reduces the overlap of police station service areas by 22.8% and increases the area coverage (12.01%) and demand point coverage (7.25%). The area coverage means an area potentially accessible within five minutes, and point coverage implies an effective drive. Within reasonable optimization, this allows us to eventually remove 13 existing police stations and add 24 candidate police stations.

Integrating a deep forest algorithm with vector‐based cellular automata for urban land change simulation

AbstractWith the capacity to represent irregular geographical entities precisely, vector‐based cellular automata (VCA) have been extensively employed in urban land change simulation at the land parcel level. However, while more driving factors are considered, modeling the complicated nonlinear relationship between land parcel attributes and multiple land‐use changes is increasingly difficult. Moreover, in VCA, the driving factors are unstructured and cannot be directly modeled by traditional deep learning methods, which can only be applied to structured data processing. In order to address these problems, a new VCA model DF‐VCA that adopts the deep forest (DF) algorithm for mining CA transition rules was proposed to simulate urban land‐use change at the parcel level. The DF algorithm is a new deep learning method that can directly mine high‐level features from unstructured data and obtain accurate land‐use transition rules. The proposed DF‐VCA model was applied to simulate the urban land change in Shenzhen, China. Compared with several traditional VCA models, the DF‐VCA model achieved the best simulation performance at parcel‐level (Figure of Merit = 39.88%), pattern‐level (similarity = 96.47%), and community‐level (correlation coefficient = 0.9269). The results show that the DF‐VCA model with strong representative learning ability could simulate urban land change at fine scales precisely. Furthermore, the proposed DF‐VCA model was applied in Shenzhen's future land change simulations to guide sustainable urban development.

Soil particle and moisture-related factors determine landward distribution of bacterial communities in a lateral riverside continuum of the Xilin River Basin

Continuous landscape components along the lateral riverside are affected by both hydrologic connectivity and disconnectivity. In recent years, anthropogenic activities and climate changes have caused wetland shrinkage and land degradation along the lateral riverside of many arid and semiarid regions. Since microorganisms are major drivers of soil biochemical cycling, it is essential to examine soil microbial communities along the lateral landscape continuum to understand their ecosystem functioning and predict future land changes. Here, we collected samples along a lateral riverbed center-riverbed edge-oxbow lake-floodplain-terrace continuum (i.e., landward distribution) in the Xilin River Basin, Inner Mongolia, China. The floodplain had the highest microbial diversity and heterogeneity, with Bacteroidetes, β- and γ-Proteobacteria being the most abundant taxa. In contrast, the terrace had the lowest microbial diversity and heterogeneity, with Acidobacteria, Actinobacteria, Verrucomicrobia, Gemmatimonadetes, and α-Proteobacteria as the most abundant taxa. Silt particle, salinity, and moisture were the most influential factors for landward variation of bacterial communities along the riverside continuum. Altogether, we demonstrate that dominant bacterial lineages, soil particles, and moisture-related factors are valuable indicators of this continuum, which can be leveraged for the early prediction of drought-induced wetland shrinkage and grassland desertification.

Assessment of Land-Use Scenarios at a National Scale Using Intensity Analysis and Figure of Merit Components

To address the impacts of future land changes on biodiversity and ecosystem services, land-use scenarios have been developed at the national scale in Japan. However, the validation of land-use scenarios remains a challenge owing to the lack of an appropriate validation method. This research developed land-use maps for 10 land-use categories to calibrate a land-change model for the 1987–1998 period, simulate changes during the 1998–2014 period, and validate the simulation for the 1998–2014 period. Following an established method, this study assessed the three types of land change: (1) reference change during the calibration time interval, (2) simulation change during the validation time interval, and (3) reference change during the validation time interval, using intensity analysis and figure of merit components (hits, misses, and false alarms). The results revealed the cause of the low accuracy of the national scale land-use scenarios as well as priority solutions, such as aligning the underlying spatial vegetation maps and improving the model to reduce two types of disagreement between the simulation and reference maps. These findings should help to improve the accuracy of model predictions and help to better inform policymakers during the decision-making process.

Improving land-use change modeling by integrating ANN with Cellular Automata-Markov Chain model

Urban growth and land-use change are a few of many puzzling factors affecting our future cities. Creating a precise simulation for future land change is a challenging process that requires temporal and spatial modeling. Many recent studies developed and trained models to predict urban expansion patterns using Artificial Intelligence (AI). This study aims to enhance the simulation capability of Cellular Automata Markov Chain (CA-MC) model in predicting changes in land-use. This study integrates the Artificial Neural Network (ANN) into CA-MC to incorporate several driving forces that highly impact land-use change. The research utilizes different socio-economic, spatial, and environmental variables (slope, distance to road, distance to urban centers, distance to commercial, density, elevation, and land fertility) to generate potential transition maps using ANN Data-driven model. The generated maps are fed to CA-MC as additional inputs. We calibrated the original CA-MC and our models for 2015 cross-comparing simulated maps and actual maps obtained for Irbid city, Jordan in 2015. Validation of our model was assessed and compared to the CA-MC model using Kappa indices including the agreement in terms of quantity and location. The results elucidated that our model with an accuracy of 90.04% substantially outperforms CA-MC (86.29%) model. The improvement we obtained from integrating ANN with CA-MC suggested that the influence imposed by the driving force was necessary to be taken into account for more accurate prediction. In addition to the improved model prediction, the predicted maps of Irbid for the years 2021 and 2027 will guide local authorities in the development of management strategies that balance urban expansion and protect agricultural regions. This will play a vital role in sustaining Jordan's food security.

A Review of Driving Factors, Scenarios, and Topics in Urban Land Change Models.

Due to the increase in future uncertainty caused by rapid environmental, societal, and technological change, exploring multiple scenarios has become increasingly important in urban planning. Land Change Modeling (LCM) enables planners to have the ability to mold uncertain future land changes into more determined conditions via scenarios. This paper reviews the literature on urban LCM and identifies driving factors, scenario themes/types, and topics. The results show that: (1) in total, 113 driving factors have been used in previous LCM studies including natural, built environment, and socio-economic factors, and this number ranges from three to twenty-one variables per model; (2) typical scenario themes include "environmental protection" and "compact development"; and (3) LCM topics are primarily growth prediction and prediction tools, and the rest are growth-related impact studies. The nature and number of driving factors vary across models and sites, and drivers are heavily determined by both urban context and theoretical framework.

Outline of the development of research on the impact of Neolithic settlements on the transformation on loess landscapes in southern Poland

Abstract During the last few decades, many case studies have focused on landscape transformations in response to water erosion, human impact, and climate changes. This article presents a review and comparison of the current state of knowledge on conducted research on the impact of the activities of early humans on the relief and forms of loess areas in Poland based on the results of a variety of dating methods (OSL, TL, C14, 137Cs, palynology, dendrochronology etc.). The influence of land-use activity since the first permanent settlements (8,000–5,200 BP) played a major role in the development of certain sand sediment terrain forms: gullies, river terraces, the filling of isolated depressions and alluvial fans in the loess areas. As a result, a simplified scheme of landscape evolution was created along with a map of the most investigated areas by authors. The main problem was to differentiate the influence of anthropogenic factors from natural ones occurring either simultaneously or alternatively. The developed deposits form a geo-archive which has recorded the history of environmental changes. A detailed analysis of the sedimentary structures provides the possibility to reconstruct and understand past functional responses in natural systems. It is important to consider the impact of climate change and human influence over the course of history on a specific geomorphological system. This can help to predict future land changes and likely hazards.

Insights on the historical and emerging global land cover changes: The case of ESA-CCI-LC datasets

Global land cover (LC) mapping has been the main source of monitoring our global landscapes for a wide range of applications e.g., food production estimation, urbanization, deforestation, climate change studies, air/soil/water pollution, and CO2 emission. Several initiatives and organizations have attempted to generate global LC maps using remote sensing data and in-situ data. Noteworthy examples include IGBP-DISCover, GlobeCover 2009, FAO, GLC 2000, MODIS, GlobeLand30. While researchers including climate change scientists require fine LC maps in terms of spatial resolution and temporal coverage for continuous monitoring of the planet, these datasets lack of fulfilling this goal. Understanding the trend of LC changes as well as the direction of future changes at global level is of vital importance to a broad spectrum of stakeholders, and essential for addressing the sustainable development goals worldwide. European Space Agency has recently released its climate change initiative's LC dataset called CCI-LC, which aims at achieving this ambition with 300 m spatial resolution and 24-year continuous temporal coverage within 1992–2015. The main objective of this study is to quantify the global land changes within this timeframe and also to predict the future land change by 2050 in order to gain a global picture of our future planet. This is a timely objective since more than ever scientists, environmentalist, and governors require to know how our future will look like and how they can achieve the goals of the United Nations Framework Convention on Climate Change (UNFCCC) i.e., the Paris Agreement. The achieved results reveal massive land changes of different kinds e.g., deforestation, urbanization, desertification, forestry, water and ice shrinkage across different continents. The employed predictive modelling for year 2030 and 2050 messages dramatic changes among different LC types. Our discussions and conclusive comments can guide policy-makers, environmental planners, ecosystem services providers and climate change researchers to gain finer insights about our planet by 2050. Future research direction draws attention for investigating the underlying causes and consequences on our ecosystems and human population.

Investigative Spatial Distribution and Modelling of Existing and Future Urban Land Changes and Its Impact on Urbanization and Economy

Land use and land cover (LULC) change analysis is a critical instrument for studying urban growth across the world. Our objectives were to produce historical LULC maps during the 1988–2016 period for spatial and temporal analysis, forecast future LULC until 2040 by using the Markov model, and identify the impact of LULC on urbanization. Two scenes of Landsat-5 TM for 1988 and 2001 and one scene of Landsat-8 OLI for 2016 were processed and used. The Normalized Difference Vegetation Index (NDVI) model with precise class value ranges was applied to produce land cover maps with six classes of water, built-up, barren land, shrub and grassland, sparse vegetation, and dense vegetation. LULC maps for the years of 1988 and 2001 were used to develop an LULC transformation matrix. It was used to drive an LULC transformation probability matrix using a Markov model for future forecasting of LULC in 2014, 2027, and 2040. The accuracy of 2016 LULC classes was estimated by comparing it against Markov modeled classes. It was found that the areas for: (i) water decreased from 1.43% to 0.51%; (ii) built-up increased from 9.58% to 20.80%; (iii) barren land decreased from 29.50% to 13.40%; (iv) shrub and grass land decreased from 30.57% to 21.10%; (v) sparse vegetation increased from 18% to 20.10%; and (vi) dense vegetation increased from 10.57% to 24.10%. The variations in LULC classes could be noticed by 2040 as compared to 1988. This LULC variation revealed that the water could decrease to 5.32 km2 from 25.37 km2; the built-up could increase to 625.16 km2 from 168.29 km2; the barren land could decrease to 137.53 km2 from 514.13 km2; the shrub and grassland could decrease to 297.68 km2 from 539.46 km2; the sparse vegetation could decrease to 297.68 km2 from 539.46 km2; and the dense vegetation could increase to 409.65 km2 from 191.51 km2. The LULC classification accuracy was 90.27% and 95.11% for 1988 and 2001, respectively. The co-efficient of determination (R2) was found to be 0.90 for 2016 LULC classes obtained from Landsat-8 and derived from a Markov model. For District Lahore, the LULC changes could be related to increasing population and intense migration trends, which had progressive impact on infrastructure development, industrial and economic growth, and detrimental effects on water resources.

Modelling urban land change processes and patterns for climate change planning in the Durban metropolitan area, South Africa

ABSTRACTUrbanization is one of the most significant and irreversible forms of land change, but we lack empirical evidence of these changes in the Global South. This is the first study to quantify past and explore future land change for the Durban metropolitan, using Land Change Modeler (LCM) software. Results show between 1994–2016, the total changed area was 118,403 ha (47% of landscape) and eleven transition categories were responsible for these changes. Three scenarios were explored: Scenario 1: business as usual (BAU), Scenario 2: green space protection (GSP), and Scenario 3: integrated rapid public transport network (IRPTN), up to the year 2076. BAU and IRPTN show similar projected spatial change concentrated in the west and north. GSP shares temporal change trends with BAU, but projects spatial change concentrated in the north and south. We discuss the utility of this modelling approach to understand land change processes useful for climate change planning.