Scientific- Research Quarterly of Geographical Data (SEPEHR)

Scientific- Research Quarterly of Geographical Data (SEPEHR)

Prediction of Land Use and Land Cover Changes Using the Cellular Automata Markov Chain Approach - Case study: west of Gilan Province

Document Type : Research Paper

Authors
Leila Vosoughi Rad 1
Seyed Hossein Mirmousavi 2
Hossein Asakereh 3
1 PhD student Climatology, University of Zanjan, Zanjan, Iran
2 Associate Professor , University of Zanjan Zanjan, Iran
3 Professor, University of Zanjan, Zanjan, Iran
10.22131/sepehr.2024.2021622.3055
Abstract
Extended Abstract
Introduction:
The changes of land use and land cover is a multifaceted process influenced by human activities and natural processes, leading to disruptions in ecosystem functions.
To mitigate the adverse effects of changes in land use and land cover, a fundamental strategy involves the systematic assessment of these changes. In this regard, remote sensing, as a key technology, provides the ability to collect spatial data from the Earth's surface without the need for physical contact. By using remote sensing data, geographic information systems (GIS), and advanced modeling techniques, it is possible to identify and model land use and land cover changes across different temporal and spatial scale. The CA-Markov model, by combining two main approaches cellular automata for simulating spatial changes based on the neighborhood of cells and Markov chains for modeling temporal changes based on the probability of transitions between different states, enables precise analysis of these changes. This research aims to identify and monitor land use and land cover changes in the western region of Gilan Province, one of the most important tourist and residential areas in northern Iran, and attempts to reveal changes between the years 1999, 2010, and 2023, as well as predict land use land cover changes in this region from 2023 to 2043. By using the results of this prediction, the necessary groundwork for planning to implement appropriate policies regarding land management and the optimal use of agricultural and forest lands will be provided.
Materials & Methods:
The base data in this study are Landsat 5, 7, and 8 images, and the data source is the Google Earth Engine platform. The images were classified using the random forest algorithm in Google Earth Engine. To evaluate the accuracy of the classified images, the quantity and allocation disagreement index was used, and after ensuring the classification accuracy, the areas converted between different land uses were calculated using GIS. Before modeling, in order to improve the accuracy of the prediction model, land suitability maps were created based on criteria such as slope, elevation, soil type, etc., as well as socio-economic factors for each class using the multi-criteria evaluation method and integrated with the Cellular Automata-Markov Chain model. Then, the simulated map for 2023 was generated and compared with the 2023 ground truth map using the Allocation Disagreement, Quantity Disagreement, and Figure of Merit indices for validation. Finally, after confirming the validation results, the pattern of land use and land cover classes for 2043 was predicted using the Cellular Automata-Markov Chain method within the IDRISI TerrSet software platform.
Results and discussion:
The present study investigates land use and land cover changes in the western region of Gilan Province from 1999 to 2023 and provides a prediction of changes until 2043. This research was conducted using remote sensing techniques and geographic information systems (GIS). After classifying the images, the accuracy of the classified maps was calculated using the quantity and allocation disagreement index (QADI). The QADI values for 1999, 2010, and 2023 were 0.009, 0.01, and 0.02, respectively, indicating high accuracy of classification. Also, Kappa coefficient (KC) and overall accuracy (OA) of more than 96% confirm the very good efficiency of RF algorithm in decision making and classification. For validating the Markov Chain Cellular Automata model, three main criteria were used: spatial allocation disagreement, quantity disagreement, and figure of merit. The values obtained for these criteria were 4.65% for spatial allocation disagreement, 2.02% for quantity disagreement, and 48.60% for the figure of merit. These values indicate the good performance of the model in simulating and predicting land use/cover changes. The examination of the area of each class indicates a decrease in the area of forest lands, agricultural lands, and wetland zones, as well as an increase in the area of built-up areas and rangelands during the baseline study period (1999-2023) and in the predicted future decades. This study highlights the ongoing trend of decreasing natural land areas and the increasing human activities and urban development in the upcoming periods.
Conclusion:
Predicted maps play an important role in estimating land use changes and natural resources, such as forests, water bodies, biodiversity, soil, minerals and other elements. These maps serve as practical tools for informed decision-making in environmental planning and resource management and enable policy makers to prevent adverse environmental consequences. In this research, three-time Landsat satellite images and random forest classification algorithm were used in Google Earth Engine platform to detect historical changes in land use and land cover from 1999 to 2023. The accuracy of the classified images was verified using the QADI index. In order to improve the efficiency of the of Cellular Automata-Markov chain model, in predicting future spatial changes, the multi-criteria evaluation method was integrated with this model. Then, by confirming the validity of the simulator model, it was possible to predict land use and land cover changes for 2043. The results showed that in the study area during the historical period, built-up areas and rangelands grew by 99.75% and, 6.57%, respectively, while forest cover, wetlands, and agricultural lands lost 3.33, 24.38 and 1.96%, of their area, respectively. Also, for the future period, the CA-Markov model predicted a significant reduction in the extent of forest lands, wetlands, and agricultural lands, while predicting an increase in built-up areas. This observed decrease shows the alarming trend of destruction of natural resources and environment. This information can help decision makers in natural resource management to implement preventive measures and continuous management to preserve natural environments.
Keywords
Land use/Cover changes⸲ Change detection⸲ Prediction⸲ Gilan Province
Subjects
1.     Ahadnezhad Roshti, M., & Hosseinalizadeh, M. (2021). Monitoring and predicting spatial changes in urban land use and land cover (Case Study: Babol and Amirkala urban areas). Physical Development Planning, 8(3), 57-73.
2.     Ahmad, S., Israr, M., Ahmed, R., Ashraf, A., Amin, M., & Ahmad, N. (2022). Land use and cover changes in the Northern Mountains of Pakistan; A spatio-temporal change using MODIS (MCD12Q1) time series. Sarhad J. Agric, 38, 1419,1419-1429.
3.     Altartouri, A., & Jolma, A. (2013). A Naive Bayes classifier for modeling distributions of the common reed in Southern Finland. Paper presented at the 20th International Congress on Modelling and Simulation MODSIM 2013; Adelaide, Australia; 1-6 December 2013,1645-1651.
4.     Alyaquby, A, & Asal Kzar, A. (2024). Change Detection Using Multispectral Satellite Images for Sustainable Development in Regions of Al-Najaf Al-Ashraf, Iraq. Journal of Kufa-Physics, 16(01), 42–55. https://doi.org/10.31257/2018/JKP/2024/v16.i01.14155.
5.     Amirnejad, H. (2014). Investigating factors influencing farmers' tendency to change land use in Mazandaran Province. Economics Agricultural Research, 5(20), 87-106.
6.     Arabi Aliabad, F., Zare, M., & Ghafarian Malmiri, H. R. (2021). Predicting land cover changes using the integrated Markov chain and cellular automata model (Case Study: Shirkouh Basin). Geography and Development, 19(62), 251-270. https://doi.org/10.22111/gdij.2021.6022.
7.     Asif, M., Kazmi, J. H., Tariq, A., Zhao, N., Guluzade, R., Soufan, W., . . . Aslam, M. (2023). Modelling of land use and land cover changes and prediction using CA-Markov and Random Forest. Geocarto International, 38(1), 2210532.
8.     Basukala, A. K., Oldenburg, C., Schellberg, J., Sultanov, M., & Dubovyk, O. (2017). Towards improved land use mapping of irrigated croplands: Performance assessment of different image classification algorithms and approaches. European Journal of Remote Sensing, 50(1), 187-201.
9.     Black, R., Adger, W. N., Arnell, N. W., Dercon, S., Geddes, A., & Thomas, D. (2011). The effect of environmental change on human migration. Global environmental change, 21, S3-S11.
10.  Buraka, T., Elias, E., & Lelago, A. (2021). Analysis and Prediction of Land Use/land Cover Changes and Driving Forces by Using GIS and Remote Sensing in the Coka Watershed, Southern Ethiopia.  Indian Journal of Agricultural Research. 56(5): 581-587. doi: 10.18805/IJARe.A-699.
11.  Cai, W., & Fangyuan, T. (2020). Spatiotemporal characteristics and driving forces of construction land expansion in Yangtze River economic belt, China. PLoS One, 15(1), e0227299.
12.  Chen, Z., Liu, Y., Chen, D., & Peng, B. (2024). Exploring the impacts of land use and land cover change on ecosystem services in Dongting Lake, China: a spatial and temporal analysis. Frontiers in Environmental Science, 12, 1395557.
13.   Congalton, R.G., & Green, K. (2019). Assessing the Accuracy of Remotely Sensed Data: Principles and Practices, Third Edition (3rd ed.). CRC Press,127-142.
14.  Dos Santos, W. P., Acuña-Guzman, S. F., de Oliveira, P. T., Beniaich, A., Cardoso, D. P., Silva, M. L., Avanzi, J. C. (2024). CA-Markov prediction modeling for the assessment of land use/land cover change in two sub-basins of the Tocantins-Araguaia River Basin. Environmental Monitoring and Assessment, 196(6), 499.
15.  Feizizadeh, B., Darabi, S., Blaschke, T., & Lakes, T. (2022). QADI as a New Method and Alternative to Kappa for Accuracy Assessment of Remote Sensing-Based Image Classification. Sensors, 22(12), 4506. 1-21.
16.  Feizizadeh, B., Garajeh, M. K., Blaschke, T., & Lakes, T. (2021). An object based image analysis applied for volcanic and glacial landforms mapping in Sahand Mountain, Iran. Catena, 198, 105073,1-19.
17.  Fu, F., Deng, S., Wu, D., Liu, W., & Bai, Z. (2022). Research on the spatiotemporal evolution of land use landscape pattern in a county area based on CA-Markov model. Sustainable Cities and Society, 80, 103760.
18.  Gemmechis, W. A. (2022). Land Use Land Cover Dynamics Using CA-Markov Chain Model and Geospatial techniques: A Case of Belete Gera Regional Forest Priority Area, South Western Ethiopia.
19.  Getachew, B., Manjunatha, B., & Bhat, H. G. (2021). Modeling projected impacts of climate and lanuse/landcover changes on hydrological responses in the Lake Tana Basin, upper Blue Nile River Basin, Ethiopia. Journal of Hydrology, 595, 125974.
20.  GOLMOHAMMADİ, F. (2021). Land fragmentation in confronting to sustainable agricultural development and food security in Iran. Black Sea Journal of Public and Social Science, 4(1), 1-10.
21.  Gómez, C., White, J. C., & Wulder, M. A. (2016). Optical remotely sensed time series data for land cover classification: A review. ISPRS Journal of Photogrammetry and Remote Sensing, 116, 55-72. Hassanzadeh, M., Zarkami, R., & Sadeghi, R. (2021). Uptake and accumulation of heavy metals by water body and Azolla filiculoides in the Anzali wetland. Applied Water Science, 11(6), 91,1-8.
22.  Hasan, F. (2024). Urban Growth Modeling in Kurunegala, Sri Lanka using Cellular Automata/Markov Chain Multi-Criteria Analysis and Markov-Markovian Transition Estimator. 
23.  He, Y., Wu, W., Xie, X., Ke, X., Song, Y., Zhou, C., . . . Song, P. (2023). Land Use/Cover Change Prediction Based on a New Hybrid Logistic-Multicriteria Evaluation-Cellular Automata-Markov Model.
24.  Hellwig, N., Walz, A., & Markovic, D. (2019). Climatic and socioeconomic effects on land cover changes across Europe: Does protected area designation matter? PLoS One, 14(7), e0219374.1-20.
25.  Kamyab, H., & Asadolahi, Z. (2020). Targeting area and comparing the effect of different land use/land cover (LULC) scenarios on greenhouse gases (GHGs) emission reduction (Case study: Hyrcanian forests in Iran),1-21.
26.  Keshtkar, H., & Voigt, W. (2016). A spatiotemporal analysis of landscape change using an integrated Markov chain and cellular automata models. Modeling Earth Systems and Environment, 2(1), 1-13.
27.  Kianpour Kolkhaje, M., Pazhouhesh, M., & Emamgholizadeh, S. (2022). Evaluating the integrated Markov chain and cellular automata model in simulating land use and land cover changes in Gotvand Dam. Water and Sustainable Development, 9(2).
28.  Leta, M. K., Demissie, T. A., & Tränckner, J. (2021a). Hydrological responses of watershed to historical and future land use land cover change dynamics of Nashe watershed, Ethiopia. Water, 13(17), 2372,1-20.
29.  Li, S. (2022). Study of urbanization trend prediction in Nanchang based on CA-Markov model. Paper presented at the E3S Web of Conferences.
30.  Liping, C., Yujun, S., & Saeed, S. (2018). Monitoring and predicting land use and land cover changes using remote sensing and GIS techniques—A case study of a hilly area, Jiangle, China. PloS one, 13(7), e0200493.
31.  Liu, B., Pan, L., Qi, Y., Guan, X., & Li, J. (2021). Land use and land cover change in the Yellow River Basin from 1980 to 2015 and its impact on the ecosystem services. Land, 10(10), 1080, 1-23.
32.  Mahdian, M., Hosseinzadeh, M., Siadatmousavi, S. M., Chalipa, Z., Delavar, M., Guo, M., . . . Noori, R. (2023). Modelling impacts of climate change and anthropogenic activities on inflows and sediment loads of wetlands: case study of the Anzali wetland. Scientific Reports, 13(1), 5399, 1-18.
33.  Mahto, R., Sahu, M., & Kumar Soni, P. (2022). Change Detection of Vegetative Covers in Kalara Nala Watershed of Damoh District Using Remote Sensing and GIS. International Journal of Environment and Climate Change, 12(12), 1680-1689.
34.  Manakane, S. E., Latue, P. C., Somae, G., & Rakuasa, H. (2023). Prediction of Land Cover Change in Wae Heru Watershed Ambon City Using Celular Automata Markov Chain. Journal of Geographical Sciences and Education, 1(1), 1-11.
35.  Mansour, S., Al-Belushi, M., & Al-Awadhi, T. (2020). Monitoring land use and land cover changes in the mountainous cities of Oman using GIS and CA-Markov modelling techniques. Land Use Policy, 91, 104414.
36.  Mengistu, T. D., Chung, I.-M., Kim, M.-G., Chang, S. W., & Lee, J. E. (2022). Impacts and implications of land use land cover dynamics on groundwater recharge and surface runoff in East African Watershed. Water, 14(13), 2068,1-18.
37.  Moazzeni, M., & Pourmohammadi, M. R. (2020). Spatio-temporal modeling of urban development trends with emphasis on land use changes using the Markov-CA model (Case Study: Parsabad Moghan). Geography and Planning, 24(73), 349-377.
38.  Mustofa, M. (2019). The Countermeasure of Forest Destruction Through Communities Based on Land Utilization Empowerment in Gembong Sub-District, Pati Regency, Central Java Province. Paper presented at the Proceedings of the 1st International Conference on Environment and Sustainability Issues, ICESI 2019, 18-19 July 2019, Semarang, Central Java, Indonesia,1-9.
39.  Nasiri, V., Deljouei, A., Moradi, F., Sadeghi, S. M. M., & Borz, S. A. (2022). Land use and land cover mapping using Sentinel-2, Landsat-8 Satellite Images, and Google Earth Engine: A comparison of two composition methods. Remote Sensing, 14(9), 1977.
40.  Nguyen, C. H., Van Nguyen, C., & Nguyen, T. M. N. (2023). Monitoring and Modeling of Spatio-Temporal Urban Expansion and Land Use/Land-Cover Change in Mountain Landscape: A Case Study of Dalat City, Vietnam. Environment & Natural Resources Journal, 21(5).
41.  Nyatuame, M., Agodzo, S., Amekudzi, L. K., & Mensah-Brako, B. (2023). Assessment of past and future land use/cover change over Tordzie watershed in Ghana. Frontiers in Environmental Science, 11, 1139264.
42.  Paegelow, M., Mas, J.-F., Gallardo, M., Camacho Olmedo, M. T., & García-Álvarez, D. (2022). Pontius Jr. Methods based on a cross-tabulation matrix to validate land use cover maps Land Use Cover Datasets and Validation Tools: Validation Practices with QGIS (pp. 153-187): Springer International Publishing Cham.
43.  Prashanth, M., Kumar, A., Dhar, S., Verma, O., Rai, S. K., & Kouser, B. (2023). Land use/land cover change and its implication on soil erosion in an ecologically sensitive Himachal Himalayan watershed, Northern India. Frontiers in Forests and Global Change, 6, 1124677,1-17.
44.  Rahnemaii, M. T., Kalantari, M., & Safari, P. (2010). Examining the role of government in the physical expansion of Masal city with an emphasis on changing agricultural land use in the surrounding areas. Geography (Scientific Iranian Geographic Association), 8(26), 1-31.
45.  Ramazannejad, Y., Zarghamfard, M., Hajisharifi, A., & Azar, S. (2021). Factors behind tourists’ travel motivation: The case of the Gilan region, Iran. Quaestiones Geographicae, 40(4), 101-112.
46.  Reddy, C. S., Singh, S., Dadhwal, V., Jha, C., Rao, N. R., & Diwakar, P. (2017). Predictive modelling of the spatial pattern of past and future forest cover changes in India. Journal of Earth System Science, 126, 1-16.
47.  Rimal, B., Zhang, L., Keshtkar, H., Wang, N., & Lin, Y. (2017). Monitoring and modeling of spatiotemporal urban expansion and land-use/land-cover change using integrated Markov chain cellular automata model. ISPRS International Journal of Geo-Information, 6(9), 288.
48.  Rodaro, E., & Yeldan, Ö. (2013). A multi-lane traffic simulation model via continuous cellular automata. arXiv preprint arXiv:1302.0488,1-32.
49.  Rwanga, S. S., & Ndambuki, J. M. (2017). Accuracy assessment of land use/land cover classification using remote sensing and GIS. International Journal of Geosciences, 8(04), 611-622.
50.  Sabzpoushan, S. H., & Pourhasanzade, F. (2011). A cellular automata-based model for simulating restitution property in a single heart cell. Journal of medical signals and sensors, 1(1), 19,19-23.
51.  Sadeghi Pasvisheh, R., Eurie Forio, M. A., Ho, L. T., & Goethals, P. L. (2021). Evidence-based management of the Anzali Wetland system (Northern Iran) based on innovative monitoring and modeling methods. Sustainability, 13(10), 5503, 1-16.
52.  Sang, L., Zhang, C., Yang, J., Zhu, D., & Yun, W. (2011). Simulation of land use spatial pattern of towns and villages based on CA–Markov model. Mathematical and Computer Modelling, 54(3-4), 938-943.
53.  Saputro, D. R. S., & Sidiq, K. (2023). CABLE NEWS NETWORK (CNN) ARTICLES CLASSIFICATION USING RANDOM FOREST ALGORITHM WITH HYPERPARAMETER OPTIMIZATION. BAREKENG: Jurnal Ilmu Matematika dan Terapan, 17(2), 0847-0854.
54.  Saraf, P., & Regulwar, D. G. (2024). Land Use Land Cover Analysis for Godavari Basin in Maharashtra Using Geographical Information System and Remote Sensing. Journal of Geographic Information System, 16(1), 21-31.
55.  Singh, M., & Mohapatra, S. (2023). Land Use and Land Cover Change Scenario of the Betwa River Basin of Madhya Pradesh: An Analysis Using Remote Sensing and GIS. International Journal for Research in Applied Science and Engineering Technology, 11 (2), 1199-1203.
56.  Sun, J., & Ongsomwang, S. (2023). Optimal parameters of random forest for land cover classification with suitable data type and dataset on Google Earth Engine. Frontiers in Earth Science, 11, 1188093.
57.  Wang, S. W., Gebru, B. M., Lamchin, M., Kayastha, R. B., & Lee, W.-K. (2020). Land use and land cover change detection and prediction in the Kathmandu district of Nepal using remote sensing and GIS. Sustainability, 12(9), 3925.
58.  Wu, Y., Han, Z., Faisal Koko, A., Zhang, S., Ding, N., & Luo, J. (2022). Analyzing the Spatio-Temporal Dynamics of Urban Land Use Expansion and Its Influencing Factors in Zhejiang Province, China. International Journal of Environmental Research and Public Health, 19(24), 16580.
59.  Zhang, Z., Wei, Y., Li, X., Wan, D., & Shi, Z. (2024). Study on Tianjin Land-Cover Dynamic Changes, Driving Factor Analysis, and Forecasting. Land, 13(6), 726.
60.  Zimba, H. M., Banda, K. E., Mbewe, S., & Nyambe, I. A. (2024). Integrated use of the CA–Markov model and the Trends. Earth module to enhance the assessment of land cover degradation. Environmental Systems Research, 13(1), 25.