Spatiotemporal Monitoring and Prediction of Land Use Integrating the Markov Chain and Cellular Automata in the Coastal Chaouia

Souidi, Hanane; Ouadif, Latifa; Bahi, Lahcen; Habitou, N.

doi:10.35940/ijrte.c5760.118419

Cited by 4 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Five land use and land cover classes (dense vegetation, sparse vegetation, bare land, water and built-up) were identified and classified. Confusion Matrix using the training samples, ground truth points and Google Earth were used to determine the accuracy of the LULCC classification; Cellular Automata and Markov Chain algorithm were employed in Idrisi Software for the prediction of LULC [15]. Postclassification approach was used to evaluate the spatio-temporal changes from 1988-2021; and those that would take place between 2021 -2054.…”

Section: Discussionmentioning

confidence: 99%

Spatio-Temporal Classification and Prediction of Land Use and Land Cover Change in Finima Nature Park Bonny Island, Nigeria

Ubaekwe

Chima²,

Eguakun³

2022

JGEESI

View full text Add to dashboard Cite

Land Use Land Cover (LULC) is naturally dynamic, thus change is inevitable. However, its changes have greatly increased to a frightening proportion as a result of high rate of anthropogenic and natural processes. Consequently, land use and land cover classes of Finima Nature Park were classified and changes were observed within the last 33 years (1987 - 2021) and predicted for the next 33 years (2021 – 2054). Remote sensing and Geographic Information System (GIS) were used to achieve the goal. Coordinate points were collected from the various land use and land cover classes as a reference data for accuracy assessment of the classification. Landsat imageries of 1987, 1999, 2010 and 2021 were acquired from The United States Geological Survey (USGS). The imageries were pre-processed, processed and classified into various LULC classes using Maximum Likelihood Classification in Idrisi and ArcGis10.5. Confusion matrix and Cellular Automata (CA) Markov Chain algorithm were used for accuracy assessment and prediction of LULC respectively. Results showed that dense vegetation, sparse vegetation, bare land, and water body were the main LULC class in 1987 and 1999, while dense vegetation, sparse vegetation, bare land, water body and built up were observed in the years 2010, 2021 and 2054. The Kappa Coefficient values were 93%, 81%, 83% and 90% for 1987, 1999, 2010 and 2021 respectively; an indication of strong accuracy of the classification. Generally, there were changes in land use and land cover within the study periods. However, changes were mostly observed in the areas of water body and bare lands closer to the sea coast. Hence, the sea was implicated as the major driver of land use and land cover change in the park. The slight decrease in dense vegetation and sparse vegetation from 1999 to 2021, and 2021 to 2054 underscores the importance and benefit of conservation.

show abstract

Section: Discussionmentioning

confidence: 99%

Spatio-Temporal Classification and Prediction of Land Use and Land Cover Change in Finima Nature Park Bonny Island, Nigeria

Ubaekwe

Chima²,

Eguakun³

2022

JGEESI

View full text Add to dashboard Cite

show abstract

“…Не менш важливими є дослідження науковців [3][4][5], які вивчають екологічні процеси в різних ландшафтах, включаючи урбанізовані області. Їх роботи часто зосереджені на екологічних наслідках змін у використанні землі міських територій, де підкреслено застосування даних дистанційного зондування Землі.…”

Section: аналіз останніх досліджень і публікаційunclassified

Modern Methods of Urban Environment Land Use Monitoring

Pilicheva,

Kondrashchenko,

Shterndok

2023

MEC

View full text Add to dashboard Cite

In the context of urbanization and global climate change, the need to adapt and respond to land use dynamics is becoming increasingly important. Cities are constantly transforming, and this transformation affects the social, economic and environmental aspects of the lives of their inhabitants. Accordingly, monitoring tools and methods must be flexible, adaptive and capable of working in real time. Thanks to the latest technologies and monitoring methods, it became possible to quickly analyse changes and predict the future of urban development. In this aspect, remote sensing of the Earth should be noted. The advantages of this tool include: large territorial coverage; high frequency of pictures; the possibility of analysis in different spectral ranges, etc. Geoinformation systems are an equally important tool. GIS allows you to combine, analyse and visualize spatial data. 3D modelling can also be noted as an important tool. With the help of modern technologies, such as laser scanning, it has become possible to create detailed three-dimensional models of urban areas. Separately, automated systems for controlling the use of the territory of cities should be singled out. Due to the proliferation of digital technologies, citizens can actively participate in monitoring processes using mobile applications, public observation platforms and other tools for data collection and sharing. In the monitoring processes of urban land use, mathematical modelling plays a key role in predicting urban land use. The models help researchers and authorities understand current trends and make predictions about the future development of urban areas. Several mathematical modelling approaches can be distinguished, which include: city growth models, geostatistical models, agent-based models, regression models, system dynamic models, optimization models, landscape ecology, diffusion models, socio-economic models, scenario analysis models , combined models. Several different modelling methods are often combined to obtain the most complete and accurate picture. Keywords: monitoring, geoinformation system, modeling methods, land use, factors influencing land use.

show abstract

Evolution of Vegetation and Forests with Future Expectations of Changes in Lakhdar Sub-basin

Ait El Haj,

Ouadif,

Akhssas

2023

Springer Proceedings in Earth and Environmental Sciences

View full text Add to dashboard Cite

Spatiotemporal Monitoring and Prediction of Land Use Integrating the Markov Chain and Cellular Automata in the Coastal Chaouia

Cited by 4 publications

References 6 publications

Spatio-Temporal Classification and Prediction of Land Use and Land Cover Change in Finima Nature Park Bonny Island, Nigeria

Spatio-Temporal Classification and Prediction of Land Use and Land Cover Change in Finima Nature Park Bonny Island, Nigeria

Modern Methods of Urban Environment Land Use Monitoring

Evolution of Vegetation and Forests with Future Expectations of Changes in Lakhdar Sub-basin

Contact Info

Product

Resources

About