Simulating urban land use and cover dynamics using cellular automata and Markov chain approach in Addis Ababa and the surrounding

Mohamed, Asfaw; Worku, Hailu

doi:10.1016/j.uclim.2019.100545

Cited by 119 publications

(63 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, Maithani (2010) implemented a Logistic Regression Model and achieved an accuracy of 81%. In a more recent study done on Addis Ababa using CA-MC model, the overall accuracy showed 86%, 87%, and 87% for the years 2005, 2011, and 2015, respectively ( Mohamed and Worku, 2020 ). However, in our research, the employment of ANN with CA-MC model resulted in higher overall accuracy (90.04%).…”

Section: Discussionmentioning

confidence: 98%

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

Gharaibeh

Shaamala

Obeidat

et al. 2020

Heliyon

152

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 98%

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

Gharaibeh

Shaamala

Obeidat

et al. 2020

Heliyon

152

View full text Add to dashboard Cite

show abstract

“…This integration of the CA-Markov model offers a strong method in spatial and temporal dynamic modelling [ 58 , 59 ]. In other words, the CA-Markov chain can simulate and predict any transitions among any number of categories [ 60 , 61 ]. CA is a dynamic procedure model that is frequently used in a spatial model for predicting future land use/land cover change [ 61 – 63 ].…”

Section: Methodsmentioning

confidence: 99%

“…In other words, the CA-Markov chain can simulate and predict any transitions among any number of categories [ 60 , 61 ]. CA is a dynamic procedure model that is frequently used in a spatial model for predicting future land use/land cover change [ 61 – 63 ]. The important properties of CA are that they show the spatial and dynamic process and that is why they have been broadly used in land use/land cover simulation [ 61 ].…”

Section: Methodsmentioning

confidence: 99%

“…CA is a dynamic procedure model that is frequently used in a spatial model for predicting future land use/land cover change [ 61 – 63 ]. The important properties of CA are that they show the spatial and dynamic process and that is why they have been broadly used in land use/land cover simulation [ 61 ]. The CA model is shown in the following equation ( 1 ) [ 53 , 64 , 65 ].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of the Current and Future Prediction of Land Use/Land Cover Change Using Remote Sensing and the CA-Markov Model in Majang Forest Biosphere Reserves of Gambella, Southwestern Ethiopia

Tadese

Soromessa

Bekele

2021

The Scientific World Journal

View full text Add to dashboard Cite

This study aimed to evaluate land use/land cover changes (1987–2017), prediction (2032–2047), and identify the drivers of Majang Forest Biosphere Reserves. Landsat image (TM, ETM+, and OLI-TIRS) and socioeconomy data were used for the LU/LC analysis and its drivers of change. The supervised classification was also employed to classify LU/LC. The CA-Markov model was used to predict future LU/LC change using IDRISI software. Data were collected from 240 households from eight kebeles in two districts to identify LU/LC change drivers. Five LU/LC classes were identified: forestland, farmland, grassland, settlement, and waterbody. Farmland and settlement increased by 17.4% and 3.4%, respectively; while, forestland and grassland were reduced by 77.8% and 1.4%, respectively, from 1987 to 2017. The predicted results indicated that farmland and settlement increased by 26.3% and 6.4%, respectively, while forestland and grassland increased by 66.5% and 0.8%, respectively, from 2032 to 2047. Eventually, agricultural expansion, population growth, shifting cultivation, fuel wood extraction, and fire risk were identified as the main drivers of LU/LC change. Generally, substantial LU/LC changes were observed and will continue in the future. Hence, land use plan should be proposed to sustain resource of Majang Forest Biosphere Reserves, and local communities’ livelihood improvement strategies are required to halt land conversion.

show abstract

“…Studies by Gashaw et al. (2017) ; Mohamed and Worku (2020) and Palmate et al. (2017) have also reported good agreement between simulated and classified LULC maps therefore confirming the model's robustness in predicting future LULC changes, both in Ethiopia and elsewhere.…”

Section: Resultsmentioning

confidence: 54%

Changes in landscape composition and configuration in the Beressa watershed, Blue Nile basin of Ethiopian Highlands: historical and future exploration

Yohannes

Soromessa

Argaw

et al. 2020

Heliyon

View full text Add to dashboard Cite

Analyzing long-term dynamics of landscape patterns can provide important insights into the changes in landscape functions, that are necessary for optimizing resource management strategies. This study primarily aimed at quantifying landscape structural change. The Land use/land cover (LULC) layers of 1972, 1987, 2002, and 2017 were mapped from Landsat images, and projected to 2032 and 2047. Factor analysis was then employed to select independent core metrics of landscape composition and configuration to characterize the landscape. A post-classification comparison indicated that, between 1972 and 2017, natural vegetation, grassland, barren land and waterbody covers declined by 89.9%, 67.9%, 67.8 and 15.9%, respectively. On the other hand, plantation increased by 692.1% followed by human settlement (138%) and farmland (21.8%). A similar trend is likely to continue in 2032 and 2047 with a slight decline in the plantation category in 2047. Analysis of landscape metrics revealed that between 1972 and 2017, the number of patches increased. Specifically, plantation, barren land, settlement and grassland increased by 171.4%, 69.7%, 65.8% and 28.6%, respectively. In contrast, natural vegetation, farmland and waterbody declined by 53.1%, 46.3% and 33.9%, respectively. Future predictions showed a declining trend of the number of patches for all LULC types. An increasing trend in the largest patch index and patch size for farmland, plantation, and settlement categories was observed across all years, suggesting intensified human activities in the landscape. Consequently, natural habitat category has declined and become fragmented. Landscape pattern has changed considerably and become more fragmented over the last 45 years. Nevertheless, the future projections suggest a decline in fragmentation and potentially increased assemblage of patches forming simple patterns with fewer number of large size class patches. The results of this study could perhaps be applied in designing strategies for landscape management planning and resource conservation decision-making.

show abstract

Simulating urban land use and cover dynamics using cellular automata and Markov chain approach in Addis Ababa and the surrounding

Cited by 119 publications

References 25 publications

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

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

Analysis of the Current and Future Prediction of Land Use/Land Cover Change Using Remote Sensing and the CA-Markov Model in Majang Forest Biosphere Reserves of Gambella, Southwestern Ethiopia

Changes in landscape composition and configuration in the Beressa watershed, Blue Nile basin of Ethiopian Highlands: historical and future exploration

Contact Info

Product

Resources

About