scholarly journals Comparisons of Statistical Approaches for Modelling Land-Use Change

Land ◽  
2018 ◽  
Vol 7 (4) ◽  
pp. 144 ◽  
Author(s):  
Bo Sun ◽  
Derek Robinson
Keyword(s):  
Land Use ◽  
Logistic Regression ◽  
Markov Chain ◽  
Survival Analysis ◽  
Land Use Change ◽  
Sample Size ◽  
Statistical Methods ◽  
Cross Validation ◽  
Land Use Type ◽  
Statistical Approaches

Land-use change can have local-to-global environment impacts such as loss of biodiversity and climate change as well as social-economic impacts such as social inequality. Models that are built to anaPlyze land-use change can help us understand the causes and effects of change, which can provide support and evidence to land-use planning and land-use policies to eliminate or alleviate potential negative outcomes. A variety of modelling approaches have been developed and implemented to represent land-use change, in which statistical methods are often used in the classification of land use and land cover as well as to test hypotheses about the significance of potential drivers of land-use change. The utility of statistical models is found in the ease of their implementation and application as well as their ability to provide a general representation of land-use change, given a limited amount of time, resources, and data. Despite the use of many different statistical methods for modelling land-use change, comparison among more than two statistical methods is rare and an evaluation of the performance of a combination of different statistical methods with the same dataset is lacking. The presented research fills this gap in land-use change modelling literature using four statistical methods—Markov chain, logistic regression, generalized additive models and survival analysis—to quantify their ability to represent land-use change. The selection of these methods is based on criteria: (1) the popularity of a method, (2) the difficulty level of implementation, and (3) the ability of accounting for different scenarios. The four methods were compared across three dimensions: accuracy (overall and by land-use type), sample size, and spatial independence via conventional and spatial cross-validation. Our results show that generalized additive model outperformed the other three in terms of overall accuracy and were the best for modelling most of land-use changes with both conventional and spatial cross-validation regardless of sample size. Logistic regression and survival analysis were more accurate for specific land-use types, and Markov chain was able to represent those changes that could not be modeled by other approaches due to sample size restrictions. The overall spatial cross-validation accuracies were slightly lower than the conventional cross-validation accuracies. Our results also demonstrate that not only is the choice of model by land-use type more important than sample size, but also that a hybrid land-use model comprising the best statistical modelling approaches for each land-use change outperformed the individual statistical approaches. While Markov chain was not competitive, it was useful in providing representation using other methods or in other cases where there is no predictor data.

scholarly journals ANALISIS PERUBAHAN PENGGUNAAN LAHAN MENJADI LAHAN TERBANGUN PASCA PERPINDAHAN IBUKOTA KABUPATEN SUKABUMI DI WILAYAH TELUK PALABUHANRATU

2019 ◽  
Vol 21 (3) ◽  
pp. 407
Author(s):  
Yuda Pringgo Bayusukmara ◽  
Baba Barus ◽  
Akhmad Fauzi
Keyword(s):  
Land Use ◽  
Markov Chain ◽  
Land Use Change ◽  
Landsat Imagery ◽  
Beach Sand ◽  
Bay Area ◽  
Future Situation ◽  
Type Of Land Use ◽  
Key Variables ◽  
Spatial Plan

The determination of the Capital of Sukabumi Regency had implications on Palabuhanratu Bay area in terms of the physical area marked by the change of land use. This research was begun by analyzing land use change using Landsat imagery. Markov Chain and CA-Markov Chain method were used to predict land use change. Prospective Structural Analysis assume that the future is different from the past and is not imposed, but can be built. MICMAC method were used to determine key variables in influencing the change of land use into built-area. The results showed that in the period of post-relocation, the built-up area had a significant increase than the period of pre-relocation. The prediction results of 2030 indicate the type of land use which had a significant decrease from 2016-2030 were beach sand and waterbodies. The type of land use which had higher increase was built-up area and shrub. The key variables that influence the change of land use into built-up area in Palabuhanratu Bay area in the present situation are distance to the city center, Regional Spatial Plan policy, and slope. In future situation, variables such as distance to cities, Regional Spatial Plan policy, and the proportion of paddy field would be the key variables in influencing the change of land use into built-up area.

scholarly journals If They Come, Where will We Build It? Land-Use Implications of Two Forest Conservation Policies in the Deep Creek Watershed

Forests ◽  
2019 ◽  
Vol 10 (7) ◽  
pp. 581
Author(s):  
Markandu Anputhas ◽  
Johannus Janmaat ◽  
Craig Nichol ◽  
Adam Wei
Keyword(s):  
Land Use ◽  
Land Use Change ◽  
Population Growth ◽  
Forest Conservation ◽  
Agricultural Land ◽  
Urban Land Use ◽  
Land Use Type ◽  
Land Uses ◽  
Conservation Policies ◽  
Creek Watershed

Research Highlights: Forest conservation policies can drive land-use change to other land-use types. In multifunctional landscapes, forest conservation policies will therefore impact on other functions delivered by the landscape. Finding the best pattern of land use requires considering these interactions. Background and Objectives: Population growth continues to drive the development of land for urban purposes. Consequently, there is a loss of other land uses, such as agriculture and forested lands. Efforts to conserve one type of land use will drive more change onto other land uses. Absent effective collaboration among affected communities and relevant institutional agents, unexpected and undesirable land-use change may occur. Materials and Methods: A CLUE-S (Conversion of Land Use and its Effects at Small Scales) model was developed for the Deep Creek watershed, a small sub-basin in the Okanagan Valley of British Columbia, Canada. The valley is experiencing among the most rapid population growth of any region in Canada. Land uses were aggregated into one forested land-use type, one urban land-use type, and three agricultural types. Land-use change was simulated for combinations of two forest conservation policies. Changes are categorized by location, land type, and an existing agricultural land policy. Results: Forest conservation policies drive land conversion onto agricultural land and may increase the loss of low elevation forested land. Model results show where the greatest pressure for removing land from agriculture is likely to occur for each scenario. As an important corridor for species movement, the loss of low elevation forest land may have serious impacts on habitat connectivity. Conclusions: Forest conservation policies that do not account for feedbacks can have unintended consequences, such as increasing conversion pressures on other valued land uses. To avoid surprises, land-use planners and policy makers need to consider these interactions. Models such as CLUE-S can help identify these spatial impacts.

scholarly journals Integration of GIS and Markov chain model for land use change assessment: A case study in the upstream Ba river basin, Gia Lai province

2021 ◽  
Vol 20 (04) ◽  
pp. 69-77
Author(s):  
Huyen T. Nguyen
Keyword(s):  
Land Use ◽  
Markov Chain ◽  
Land Use Change ◽  
River Basin ◽  
Land Use Planning ◽  
Land Use Changes ◽  
Chain Model ◽  
Forest Land ◽  
Change Assessment ◽  
South Central

Ba river is the biggest river system in the South-Central Coast of Vietnam and plays a significant role in the socio-economic development of the region. Recently, land-use changes in Gia Lai province have been significantly transformed. Hence, to provide the information for land-use planning, there is an urgent need for land-use change assessment in the upstream Ba river basin. This study employed the Markov chain coupled with GIS to assess land-use changes between 2010 - 2015 and 2015 - 2020 periods. The results showed that during the period 2010 - 2015, there was no significant conversion of agricultural and reserve forest land. Meanwhile, a large proportion of unused (86%) and water and aquacultural land (57.5%) was converted into the other land-use types. Between 2020 and 2015, unused land decreased while the surface water and aquacultural land increased. The forest land accounted for a significant area (51.16%) during the 2015 - 2020 period. In addition, the driving forces leading to these changes were also analyzed, providing a more comprehensive of land-use change in the study area. In general, GIS and Markov were suitable for assessing land-use change. This study outcomes provide a general framework for land-use planning in Gia Lai province.

scholarly journals Comparison of Logistic Regression and Geomod Approaches to Forest Change Modeling in the Period of 1988 – 2025

2019 ◽  
pp. 1-15
Author(s):  
Somayeh Galdavi ◽  
Marjan Mohammadzadeh ◽  
Abdolrassoul Salman Mahiny ◽  
Ali Najafi Nejad
Keyword(s):  
Land Use ◽  
Logistic Regression ◽  
Land Use Change ◽  
Forest Area ◽  
Successful Implementation ◽  
Forest Change ◽  
Error Matrix ◽  
Time Period ◽  
The Future ◽  
Land Use Maps

Spatial modelling of land use change is a technique for understanding changes in terms of the location and amount. In this study, logistic regression and Geomod approaches were used for modelling forest change in Gorgan area in Northern Iran in the time period of 1988-2007. To do this, at first, remotely sensed imagery data of the years 1988, 1998 and 2007 were used to produce land use maps. Land use maps accuracy assessments were achieved using Error matrix method and then the maps were used to implement change detection process in two time periods of 1988-1998 and 1998-2007. Results indicated a reduction in forest areas during the mentioned time period. Next, the independent variables were extracted in order to land use change modeling. The Results of the models implementation showed the ability of both models for forest change modeling in this region. Also, the models were used to predict the future condition of forest area in the years 2016 and 2025. The results revealed that the forest area would be associated with a reduction in the future. Comparison of the results of the models using kappa indices showed the successful implementation of both models for forest change modelling in this region. The results of this research reveal the need for appropriate applications of the proper plans to control land use change in order to preserve the environment and ecological balance of the area. Therefore, careful planning can reduce the land use change and its impacts in the future in this region.

scholarly journals Simulation of land use change and effect on potential deforestation using Markov Chain - Cellular Automata

2017 ◽  
Author(s):  
Mujiono ◽  
T. L. Indra ◽  
D. Harmantyo ◽  
I. P. Rukmana ◽  
Z. Nadia
Keyword(s):  
Land Use ◽  
Markov Chain ◽  
Cellular Automata ◽  
Land Use Change
Sign in / Sign up

Export Citation Format

Share Document