CELLULAR AUTOMATA (CA) CONTIGUITY FILTERS IMPACTS ON CA MARKOV MODELING OF LAND USE LAND COVER CHANGE PREDICTIONS RESULTS

Abstract. An attempt has been made to explore, evaluate and identify the sensitive parameter(s) of Cellular Automata Markov chain modeling to monitor and predict the future land use land cover pattern scenario in a part of Brahmaputra River Basin, India. For this purpose, land use land cover maps derived from satellite images of Landsat MSS image of 1987 and Landsat TM image of 1997 were used to predict future land use land cover of 2007 using Cellular Automata Markov model. Sensitivity analysis has been carried out to identify the land use land cover parameter(s), which have the highest, lowest or intermediate influence on predicted results. The validity of the Cellular Automata Markov process for projecting future land use and cover changes in the study area calculates various Kappa Indices of Agreement (Kstandard) which indicate how well the comparison map agrees and disagrees with the reference map (land use land cover map derived from IRS-P6 LISS III image of 2007). The results shows that the land with or without scrub appeared to be most sensitive parameter as it has highest influences on predicted results of land use land cover of 2007. The second most sensitive parameter was lakes / reservoirs / ponds to predict land use land cover of 2007, followed by river, agricultural crop land, plantation, open land, marshy / swampy, sandy area, aquatic vegetation, built up land, dense forest, degraded forest, waterlogged area and agricultural fallow land. The least sensitive parameter is agricultural fallow land, which has minimum influence on predicted results of land use land cover of 2007. The validation of CA Markov land use land cover prediction results shows Kstandard is 0.7928.

An attempt has been made to explore and evaluate the Cellular Automata (CA) Markov modelling to monitor and predict the future land use and land cover (LULC) scenario in a part of Brahmaputra River basin using LULC maps derived from multi-temporal satellite images. CA Markov is a combined cellular automata/Markov chain/multi-criteria/multi-objective land allocation (MOLA) LULC prediction procedure that adds an element of spatial contiguity as well as knowledge base of the likely spatial distribution of transitions to Markov chain analysis. Evidence likelihood map was used for as knowledge base of the likely spatial procedure in CA Markov model. The predicting quantity and predicting location change have been analysed and statistically evaluated. The validation statistics indicated how well the comparison map agreed and disagreed with the reference map. Predicted results accuracy is slightly higher when compare to others studies of LULC change using CA Markov approaches.

Statistical independence test and validation of CA Markov land use land cover (LULC) prediction results

The study aimed to map and predict land use and land cover change dynamics in a human-wildlife mediated landscape of Save Valley Conservancy (SVC), south-eastern lowveld of Zimbabwe. In April 2018, remote sensing was used to quantify land use and land cover changes between 1990 and 2015 based on satellite images acquired from North Atlantic Space Agency (LANDSAT TM, path 170 raw 73). Household surveys were administered using a structured questionnaire to 100 communal settlers to collect biophysical/socioecological data on explanatory variables which included; density of human and livestock, fuelwood consumption and area under cultivation. The study used multi-criteria evaluation procedure based on dynamic adjustments of socio-ecological data to generate transitional probability maps of SVC. Thresholds of socio-ecological data were then computed in the Markov-cellular automata model through a multi-objective land allocation procedure and a cellular automata spatial filter in order to simulate future land use and land cover maps of 2020, 2030 and 2040 for SVC. If the Zimbabwe land reform and its agricultural resettlement program is not properly coordinated and planned in the study area, the study predicted a continuing downward trend in woodland cover category and a significant upward trend of land under agriculture. For the period 1990 to the 2040s, the woodland cover is likely to decrease by 46.7% changing into agricultural land use and/or bare land in SVC. Future land use and land cover simulations indicated that if the current land use and land cover trends continue unabated across the study area without a holistic sustainable agricultural land-wildlife management plan and community development measures, severe woodland degradation will occur. The study recommends ecological restoration and/or re-planning on agriculture-wildlife land use and zonation, delineating agriculture and human settlement in the southern part of the conservancy while the northern part of SVC is exclusively reserved and protected for wildlife management. Key words: Land use, land cover, human encroachment, protected area, savanna

The Markov-cellular automata is suitable to study complex spatial-temporal geographic system, especially for regional land use, and it has been an important tool and research focus for regional land use change modeling. Previous researchers focused on a few kind of land use type at the regional scale and the data resolution was cursory because land use maps were usually derived from TM image. Few researchers involved precise scale of land use change within a region. To solve this problem, we took the data of land-use survey as a data source maps that include detailed multiple land use types. The case study area was Changping District, which is a rapidly growing area of Beijing. We select the land use map of 2001 and 2005 which include the multiple land use types as data source to simulate the land use of 2012. The results of simulation show that simulation accuracy of multiple land use types is better than them of cursory scale land use types, although it takes a substantial amount of time to run. The statistical result derived from Moran's I and fractal parameter indicates that simulation shows the high spatial stability. The simulation results showed that the number of cropland is keeping on decrease from 2005 to 2012 without the holistic sustainable development measures and severe land policy. This paper represents a good try to local land use change modeling as shown combined Markov chain analysis and cellular automata models. The simulated future land use changes have significant environmental and socioeconomic implications for sustainable region land detailed planning in the study area.

Land use changes can majorly affect many parameters that are directly or indirectly interlinked to various human-environmental systems, including hydrological processes and flood risks. The knowledge of future land cover changes is crucial for better managing human-environmental interactions and addressing potential environmental challenges, such as floods. In this work, the impact of future land cover changes in flood inundation is assessed, using a case study in northeast Indiana, US. A Cellular Automata Markov (CAM) model is applied, combining Geographic Information Systems (GIS) and Python, to predict land changes and provide future land cover maps, along with statistical validation measures. The land use map outputs are then used in a HEC-RAS hydraulic model, to test the different flooding impacts under a design storm, using the rain-on-grid routine. The results indicate that even slightly more urbanized and deforested areas can increase the potential flood extent. Furthermore, the impacts of these forecasted land cover changes are quantified in monetary terms, based on a spatial Ecosystem Services Valuation (ESV) model. The findings indicate that as certain land uses (mainly wetlands, followed by forests) give their place to build-up areas, barren land, or even agricultural lands, the ‘lost’ value due can reach 1.5 million USD in 2051. The novelty of this study lies in int integrated character, combining for the first time to our knowledge land cover forecast with hydrologic-hydraulic modelling and spatial ESV, showing thus the future changes, risks, and potential economic losses, respectively. This application uses the minimum necessary input data to perform the analyses, and all data and codes are publicly available, contributing thus to the transferability and reproducibility of the approach.

Land use changes can majorly affect many parameters that are directly or indirectly interlinked with various human-environmental systems, including hydrological processes and flood risks. The knowledge of future land cover changes is crucial for better managing human-environmental interactions and addressing potential environmental challenges, such as floods. In this work, the impact of future land cover changes on flood inundation is assessed, using a case study in northeast Indiana, US. A Cellular Automata Markov (CAM) model is applied, combining Geographic Information Systems (GIS) and Python, to predict land changes and provide future land cover maps, along with statistical validation measures. The land use map outputs are then used in a HEC-RAS hydraulic model to test the different flooding impacts under a design storm, using the rain-on-grid routine. The results indicate that even slightly more urbanized and deforested areas can increase the potential flood extent. Furthermore, the impacts of these forecasted land cover changes are quantified in monetary terms, based on a spatial Ecosystem Services Valuation (ESV) model. The findings indicate that as certain land uses (mainly wetlands, followed by forests) give their place to build-up areas, barren land, or even agricultural lands, the ‘lost’ value can reach 1.5 million USD in 2051. The novelty of this study lies in its integrated character, combining for the first time to our knowledge land cover forecast with hydrologic-hydraulic modelling and spatial ESV, thus showing the future changes, risks, and potential economic losses, respectively. This application uses the minimum necessary input data to perform the analyses, and all data and codes are publicly available, contributing thus to the transferability and reproducibility of the approach.

To demonstrate potential future consequences of land cover and land use changes beyond those for physical climate and the carbon cycle, we present an analysis of large‐scale impacts of land cover and land use changes on atmospheric chemistry using the chemistry‐climate model EMAC (ECHAM5/MESSy Atmospheric Chemistry) constrained with present‐day and 2050 land cover, land use, and anthropogenic emissions scenarios. Future land use and land cover changes are expected to result in an increase in global annual soil NO emissions by ∼1.2 TgN yr−1 (9%), whereas isoprene emissions decrease by ∼50 TgC yr−1 (−12%). The analysis shows increases in simulated boundary layer ozone mixing ratios up to ∼9 ppbv and more than a doubling in hydroxyl radical concentrations over deforested areas in Africa. Small changes in global atmosphere‐biosphere fluxes of NOx and ozone point to compensating effects. Decreases in soil NO emissions in deforested regions are counteracted by a larger canopy release of NOx caused by reduced foliage uptake. Despite this decrease in foliage uptake, the ozone deposition flux does not decrease since surface layer mixing ratios increase because of a reduced oxidation of isoprene by ozone. Our study indicates that the simulated impact of land cover and land use changes on atmospheric chemistry depends on a consistent representation of emissions, deposition, and canopy interactions and their dependence on meteorological, hydrological, and biological drivers to account for these compensating effects. It results in negligible changes in the atmospheric oxidizing capacity and, consequently, in the lifetime of methane. Conversely, we expect a pronounced increase in oxidizing capacity as a consequence of anthropogenic emission increases.

Land use is a process that turns a piece of land’s natural ecosystem into an artificial one. The mix of plant and man-made covers on the Earth’s surface is known as land cover. Land use is the primary external force behind change in land cover, and land cover has an impact on how land use is carried out, resulting in a synergistic interaction between the two at the Earth’s surface. In China’s Shandong Peninsula city cluster, Dongying is a significant coastal port city. It serves as the administrative hub for the Yellow River Delta and is situated in Shandong Province, China’s northeast. The changes in its urban land use and land cover in the future are crucial to understanding. This research suggests a prediction approach that combines a patch-generation land use simulation (PLUS) model and long-term short-term memory (LSTM) deep learning algorithm to increase the accuracy of predictions of future land use and land cover. The effectiveness of the new method is demonstrated by the fact that the average inaccuracy of simulating any sort of land use in 2020 is around 5.34%. From 2020 to 2030, 361.41 km2 of construction land is converted to cropland, and 424.11 km2 of cropland is converted to water. The conversion areas between water and unused land and cropland are 211.47 km2 and 148.42 km2, respectively. The area of construction land and cropland will decrease by 8.38% and 3.64%, respectively, while the area of unused land, water, and grassland will increase by 5.53%, 2.44%, and 0.78%, respectively.

This research examines the impact of land use change on mobility. Spatial problems arise due to increased activity, population, and transportation in the same space, necessitating the development of modeling strategies. This aligns with SDG 11 on cities and settlements, as well as the PRN's focus on transportation innovation. The urgency of this research lies in its adaptive and sustainable spatial prediction efforts aimed at controlling future land use. This study aims to analyze land use change patterns using the Cellular Automata Markov Chain (CA-Markov) model in Kupang City until 2043. CA-Markov simulations efficiently evaluate land cover changes and movement. The quantitative research method was conducted based on spatial predictions and spatial configuration. Quantum GIS (QGIS) and GeoSOS-FLUS were used to obtain results from each stage. There are three research stages. First, identification of land cover (land use in 2018 and 2023), driving factors (distance to settlements, airports, highways, elevation, slope, slope orientation, rainfall, population density), and conservation areas. Second, standardisation of spatial data. Third, land cover prediction using GeoSOS software (five-year prediction) to identify patterns of land use change. These findings emphasize the importance of using CA-Markov-based spatial predictions as a foundation for adaptive spatial planning to control land-use conversion and maintain sustainable spatial connectivity in Kupang City until 2043.

Land use and land cover (LULC) changes are important indicators of environmental and socio-economic changes made by the natural and anthropogenic sources. The present study is based on the Cellular Automata (CA) Markov model for predicting the LULC changes in the Tawi Basin. To decipher the spatio-temporal distributions of LULC, the Landsat images of 2010 and 2020 were used to analyse the LULC classification. Further, CA Markov model simulations of various scenarios of eight decades (2030 to 2100) were generated based on LULC of 2010 and 2020 data to know the LULC perspective changes in the Tawi Basin, which has witnessed the enormous developmental activities such as growth in settlement, population, and agriculture sector over the years. The model predicts that a population explosion leading to rapid urbanization and rural expansions.Settlement is expected to increase from 5.29% of the total area in 2020 to 13.975% in the year 2100. The CA–Markov model results paint a picture of significant changes in land use and settlement patterns in the Tawi Basin. The study serves as a crucial tool for guiding future planning efforts, urging environmentalists, planners, and decision-makers to prioritize sustainable practices and make informed decisions for the well-being of the region.

Ecosystem services are closely related to human well-being and are vulnerable to high-intensity human land-use activities. Understanding the evolution of land use and land cover (LULC) changes and quantifying ecosystem service value (ESV) are significant for sustainable development. In this study, we used land use and land cover data and other data from 2000 to 2020 to analyze the evolution of land use and land cover and ESV in Tongliao, China. With the goal of exploring the characteristics of different cellular automata (CA)-based models, CA-Markov, Future Land Use Simulation (FLUS), and Patch-generating Land Use Simulation (PLUS) models were used to simulate future land use and land cover, and the results were verified and compared. Considering the impacts of policies for capital farmland (CF) and ecological protection red line (EPRL) in the context of territorial spatial planning, four scenarios (inertial development, S1; CF, S2; EPRL, S3; EPRL and CF, S4) were set. The results showed that from 2000 to 2020, farmland and built-up land increased the most (341.18 km2 and 220.56 km2), while grassland had the largest decrease (380.08 km2). The main mutual transitions were from grassland and farmland. The total ESV showed a decreasing trend (from 52,364.56 million yuan to 51,620.62 million yuan). The simulation results for 2035 under four scenarios were similar, where farmland would decrease the most (96.81 km2). The ESV in 2035 would decrease from 51,620.62 million yuan to 51,541.12 million. In addition, under scenarios for the impact of policy, the land showed a trend of scattered expansion. This study provides a scientific basis for making regional sustainable development policy decisions and implementing ecological environmental protection measures.

Increased anthropogenic activities in the Little Ruaha River Catchment have modulated the catchment condition, nevertheless, the future changes as a result of increased anthropogenic activities are unknown. Understanding the future changes is vitally important for the design of appropriate strategies towards sustainable management of the catchment resources. This study applied Remote Sensing and GIS techniques (Jensen & Lulla, 1987) to assess the historical long-term changes in land use and land cover using Landsat satellite images of 1990, 2005 and 2015, and modelled the future change in land use and land cover up to 2040 using the stochastic CA-Markov chain (Almeida et al., 2005). The historical land use and land cover change detection results indicate that between 1990 and 2005 the area under forest changed from 39,872 ha to 22,957 ha, woodland changed from 109,692 ha to 72,809 ha, wetland decreased from 19,157 ha to 11,785 ha, the cultivated land increased from 106,782 ha to 109,047 ha, likewise, the built-up area increased from 9408 ha to 11,674 ha. Results between 2005 and 2015 show the substantial changes where the forest decline from 22,957 ha to 15,950 ha, woodland decreased from 72,809 ha to 58,554 ha and the wetland changed from 11,785 ha to 5622 ha. Cultivated land and built up area increased from 109,047 ha and 11,674 ha to 143,468 ha and 13,765 ha respectively. Generally, the study has revealed the substantial decline in forest, woodland and wetland by 23,922 ha, 51,138 ha and 13,535 ha respectively, and an increase of cultivated land and built up area by 36,668 ha and 4357 ha respectively in 15 years, between 1990 and 2015. The predicted future land use and cover for the next 15 years (2040) showed an overall increase in cultivated land, built up area, grassland and bushland to 24.82%, 2.24%, 25.18% and 20.41% respectively, and a decrease in forest, woodland and wetland in the order of 1.87%, 7.87% and 0.03% respectively. The study concludes that, there have been significant changes in land use and cover in the catchment which likely to impend the sustainability of the catchment productivity, hence recommends the holistic system thinking and analysis approach in management and utilization of catchment resources.

Little is known about the future land use and land cover (LULC) type in some parts of Ethiopia, but not in the study area. This study aims to predict and analyze the future scenarios of LULC (2015–2033) using cellular automata and Markov Chain model (CA_Markov) by taking into consideration the physical and socio-economic drivers of LULC dynamics. The historical LULC change data of 1984–1995, 1995–2015, and 1984–2015 were used as a baseline. Both transition rules and transition area matrix for the period 1984–1995, 1995–2015, and 1984–2015 were produced quantitatively using the Markov chain model. After that, the physical and socio-economic factors were standardized using fuzzy and then Multi-Criteria Evaluation (MCE) was used to produce the transition suitability image. The CA_Markov model was then applied as a standard contiguity filter of 5 × 5 to predict the 2033 LULC condition using the TerrSet Geospatial Modeling and Monitoring System software. The result indicated that forestland are predicted to increase by 108 sq km (44.5%), shrub/bush lands 710 sq km (20%), built-up area 286.2 sq km (48.3%), and grasslands 31 sq km (15%), respectively. However, significant reductions (losses) in a water body (Wb) 5.2 sq km (11.2%), croplands (Cl) 78.9 sq km (1.3%), barren lands (Bl) 800 sq km (27.4%), and floodplain area (Fp) 251.68 sq km (33.7%), respectively. Furthermore, the Pearson correlation result between the historical and predicted LULC type indicated that there are positive, strongly correlated, and are statistically significant relationships (r = 0.981, p = 0.000). The increase in forest land and reduction in barren and flood plain may benefit the study area. However, the decrease in the water body may contribute to the severity of drought in the area. This study may help to use as useful information to foster better decisions and improve policies in land use within the framework of sustainable land use planning system.

Using the Cellular Automata (CA) Markov Model in combination with Geographic Information System (GIS) and Remote Sensing (RS) technologies, this study examines the spatial and temporal dynamics of land use and land cover (LULC) in the Songwe sub-basin, Tanzania. By combining historical data spanning from 1990 to 2020 at a spatial resolution of 30 meters, the study aims to forecast future LULC changes up to the year 2100. GIS technologies made it easier to spatially analyze and visualize these changes, and LULC data was used to calibrate the CA-Markov model with transition probabilities taken from the historical era. The results highlight significant land use transitions, with significant transitions from woodland and natural vegetation to agricultural land and urban areas. These changes are largely driven by population growth and the rising demand for food production. Forest cover and woodland areas have notably decreased by 54.01% and 59.10%, respectively, while agricultural land has increased by 216.97%. Projections indicate that by 2100, forests and woodlands will largely disappear, being replaced by agricultural land. Additionally, significant reductions in wetlands and water bodies are expected. Rapid urbanization is anticipated to intensify the degradation of natural ecosystems, leading to further strain on hydrological systems. The study recommends the implementation of stronger conservation policies, including the expansion of protected areas for vital habitats, and the promotion of sustainable agricultural practices such as agroforestry and conservation tillage. To enhance long-term ecological resilience, the study also emphasizes the need for ecosystem-based management approaches that prioritize water resource preservation and biodiversity. Additionally, involving local communities in land management decisions is crucial for ensuring the sustainability of natural resources and ecosystem services in the Songwe sub-basin.