Integrating logistic regression and cellular automata–Markov models with the experts’ perceptions for detecting and simulating land use changes and their driving forces

Shahbazian, Zohreh; Faramarzi, Marzban; Rostami, Noredin; Mahdizadeh, Hossein

doi:10.1007/s10661-019-7555-4

Cited by 23 publications

(19 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This fact reinforces that CA model is indeed suitable for analysis of spatial phenomena with propagation patterns [6,41]. Integration of logistic regression with CA produces a probability scenario for LULC changes in the future [42,43]. In the first scenario, it is assumed that all drivers are constant, as happened in 2020, because the government and stakeholders are capable to undertake adaptive control.…”

Section: Lulc Simulation and Scenariosmentioning

confidence: 76%

Spatial dynamics model of land use and land cover changes: A comparison of CA, ANN, and ANN-CA

Dede

Asdak

Setiawan

2021

regist. j. ilm. teknol. sist. inf.

View full text Add to dashboard Cite

Land use and land cover (LULC) changes through built-up area expansion always increases linearly with land demand as a consequence of population growth and urbanization. Cirebon City is a center for Ciayumajakuning Region that continues to grow and exceeds its administrative boundaries. This phenomenon has led to peri-urban regions which show urban and rural interactions. This study aims to analyze (1) the dynamics of LULC changes using cellular automata (CA), artificial neural network (ANN), and ANN-CA; (2) the influential factors (drivers); and (3) change probability in the period 2030 and 2045 for Cirebon’s peri-urban. We used logistic regression as quantitative approach to analyze the interaction of drivers and LULC changes. The LULC data derived from Landsat series satellite imagery in 1999-2009 and 2009-2019, validation of dynamic spatial model refers to 100 LULC samples. This research shows that LULC changes are dominated by built-up area expansion which causes plantations and agricultural land to decrease. The drivers have a simultaneous effect on LULC changes with r-square of 0.43, where land slope, distance from existing built-up area, distance from CBD, and accessibility are significant triggers. LULC simulation of CA algorithm is the best model than ANN and ANN-CA based on overall accuracy and overall accuracy (0.96, 0.75, 0.73 and 0.95, 0.66, 0.66 respectively), it reveals urban sprawl through the ribbon and compact development. The average probability of built-up area expansion is 0.18 (2030) and 0.19 (2045). If there is no intervention in spatial planning, this phenomenon will decrease productive agricultural lands in Cirebon's peri-urban.

show abstract

Section: Lulc Simulation and Scenariosmentioning

confidence: 76%

Spatial dynamics model of land use and land cover changes: A comparison of CA, ANN, and ANN-CA

Dede

Asdak

Setiawan

2021

regist. j. ilm. teknol. sist. inf.

View full text Add to dashboard Cite

show abstract

“…This study predicted LULC during using a combination of logistic regression (LR), cellular automata (CA), and Markov Chain models, following an approach by Arsanjani et al (2013). A similar modelling approach has been used in several studies for detecting and simulating LULC change (Ahmed et al, 2013;Kityuttachai et al, 2013;Mitsova et al, 2011;Shahbazian et al, 2019;Wang et al, 2019). We applied this approach for following reasons:…”

Section: Modelling Lulc Changementioning

confidence: 99%

“…and (iv) the CA model can control spatial dynamics of LULC changes (Arsanjani et al, 2013;Shahbazian et al, 2019).…”

Section: Modelling Lulc Changementioning

confidence: 99%

“…The CA model uses a principle that areas tend to change to a state based on the state of their neighbouring areas (Arsanjani et al, 2013). A CA system includes four components such as cells, states, neighbourhoods, and rules (Shahbazian et al, 2019). Cells are defined as the smallest unit and the state of each cell is determined by its initial state, the conditions in the surrounding cells, and a set of transition rules (Arsanjani et al, 2013;Verburg et al, 2004).…”

Section: Modelling Lulc Changementioning

confidence: 99%

“…The LR models were established for all 12 transitions, to estimate the degree of influence of different factors (driving forces) on a type of LULC (Shahbazian et al, 2019).…”

Section: Driving Forces For Detecting Changementioning

confidence: 99%

See 2 more Smart Citations

The effects of changing land use and flood hazard on poverty in coastal Bangladesh

et al. 2020

View full text Add to dashboard Cite

The construction of polders in the coastal region of Bangladesh has significantly modified the patterns of flooding, as well as leading to significant land use/land cover (hereinafter, LULC) changes. The impact of LULC change and flooding on poverty is complex and poorly understood. This study presents a spatiotemporal appraisal of poverty in relation to LULC change and pluvial flood risk in the south western embanked area of Bangladesh. A combination of logistic regression (LR), cellular automata (CA), and Markov Chain models were utilised to predict future LULC based on historical data. Flood risk assessment was performed at present and for future LULC scenarios. A spatial regression model was developed, incorporating multiple parameters to estimate the wealth index (WI) for presentday and future scenarios. In the study area, agricultural lands reduced from 34% in 2005 to 8% in 2010, while aquaculture land cover increased from 17% to 39% during the same time. The rate of LULC change was relatively low between 2010 and 2019. Based on the recent trend, LULC was predicted for the year 2030. Flood risk was positively correlated with LULC and the expected annual damage (EAD) was estimated at $903 million in 2005, which is likely to increase to $2096 million by 2030, considering changes in LULC scenarios. The analysis further showed that the EAD and LULC change were negatively associated with the WI.Despite consistent national GDP growth in Bangladesh in recent years, the rate of increase of WI is likely to be low in the future because flood risk and patterns of LULC change have a negative effect on WI.

show abstract

Assessing the response of rare and common plant species to human induced rangeland degradation at a landscape scale in western Iran

Faramarzi,

Isselstein

2023

Land Degrad Dev

Self Cite

View full text Add to dashboard Cite

Knowledge of plant species distribution and abundance at different landscape scales and management‐induced degradation is essential for the conservation, planning, and enhancement of the biodiversity of rangelands. In this study, additive partitioning of species diversity based on contribution diversity was used to analyze the interaction of landscape scale and grazing intensity factor to better understand the distribution of rare and common species. A total of 64 units (quadrats) were sampled by using a nested hierarchical sampling design at three scales of two regions (semi‐arid vs. Mediterranean), four sites, and four quadrats in both exclosure and grazing areas. The regional‐scale species richness (γs(q)) was calculated by the sum of the quadrat (αs(q)) and site (βs(q)) scale contributions to the region. The calculated rank of αs(q) indicated that an abundance of rare species for exclosures (α < 0.05) and the Mediterranean area (α < 0.01) was significantly greater than for grazing and the arid area, respectively. The highly palatable plants significantly correlated (α < 0.01) with the contribution diversity components (alpha/beta) in the exclosure areas but not in grazed areas. Furthermore, of the measured explanatory variables, the electrical conductivity (EC) of the soil was significantly negatively related to γs(q) which shows a sensitivity of rare species to the variable environmental conditions that are related to human influences interacting with soil and climatic conditions. The vegetation attributes of biomass and vegetation cover were significantly (α < 0.01) higher for managed exclosure sites than the grazed areas. The findings of this investigation demonstrate an increasing trend for rare species in managed and better environmental conditions. In conclusion, the protection and restoration of plant species diversity in semi‐arid and Mediterranean grasslands in western Iran are possible through the application of sustainable management practices by decision‐makers and managers.

show abstract

Integrating logistic regression and cellular automata–Markov models with the experts’ perceptions for detecting and simulating land use changes and their driving forces

Cited by 23 publications

References 69 publications

Spatial dynamics model of land use and land cover changes: A comparison of CA, ANN, and ANN-CA

Spatial dynamics model of land use and land cover changes: A comparison of CA, ANN, and ANN-CA

The effects of changing land use and flood hazard on poverty in coastal Bangladesh

Assessing the response of rare and common plant species to human induced rangeland degradation at a landscape scale in western Iran

Contact Info

Product

Resources

About