Multi-Layer Perceptron Markov Chain Research Articles

Monitoring of Plant Ecological Units Cover Dynamics in a Semiarid Landscape from Past to Future Using Multi-Layer Perceptron and Markov Chain Model

Anthropogenic activities and natural disturbances cause changes in natural ecosystems, leading to altered Plant Ecological Units (PEUs). Despite a long history of land use and land cover change detection, the creation of change detection maps of PEUs remains problematic, especially in arid and semiarid landscape. This study aimed to determine and describe the changes in PEUs patterns in the past and present, and also predict and monitor future PEUs dynamics using the multi-layer perceptron-Markov chain (MLP-MC) model in a semiarid landscape in Central Zagros, Iran. Analysis of PEUs classification maps formed the basis for the identification of the main drivers in PEUs changes. First, an optimal time-series dataset of Landsat images were selected to derive PEUs classification maps in three periods, each separated by 16 years. Then, PEUs multi-temporal maps classified for period 1 (years 1986–1988) period 2 (years 2002–2004), and period 3 (years 2018–2020) were employed to analyze and predict PEUs dynamics. The dominant transitions were identified, and the transition potential was determined by developing twelve sub-models in the final change prediction process. Transitions were modeled using a Multi-Layer Perceptron (MLP) algorithm. To predict the PEU map for period 3, two PEUs classification maps of period 1 and period 2 were used using the MLP-MC method. The classified map and the predicted map of period 3 were used to evaluate and validate the predicted results. Finally, based on the results, transitions of future PEUs were predicted for the year 2036. The MLP-MC model proved to be a powerful model that can predict future PEUs dynamics that are the result of current human and managerial activities. The findings of this study demonstrate that the impact of anthropogenic processes and management activities will become visible in the natural environment and ecosystem in less than a decade.

Monitoring and predicting land use/land cover dynamics in Djelfa city, Algeria, using Google Earth Engine and a Multi Layer Perceptron Markov Chain model

Understanding the historical and projected changes in land use and land cover (LULC) in Djelfa city is crucial for sustainable land management, considering both natural and human influences. This study employs Landsat images from the Google Earth Engine and the support vector machine (SVM) technique for LULC classification in 1990, 2005, and 2020, achieving over 90% accuracy and kappa coefficients above 88%. The Land Change Modeler (LCM) was used for detecting changes and predicting future LULC patterns, with Markov Chain (MC) and Multi Layer Perceptron (MLP) techniques applied for 2035 projections, showing an average accuracy of 83.96%. Key findings indicate a substantial urban expansion in Djelfa city, from 924.09 hectares in 1990 to 2742.30 hectares in 2020, with a projected increase leading to 1.6% of nonurban areas transitioning to urban by 2035. There has been significant growth in steppe areas, while forested, agricultural, and barren lands have seen annual declines. Projections suggest continued degradation of bare land and a slight reduction in steppe areas by 2035. These insights underscore the need for reinforced policies and measures to enhance land management practices within the region to cater to its evolving landscape and promote sustainable development.

LAND USE AND LAND COVER SIMULATION BASED ON INTEGRATION OF ARTIFICIAL NEURAL NETWORKS WITH CELLULAR AUTOMATA-MARKOV CHAIN MODELS APPLIED TO EL-FAYOUM GOVERNORATE

Abstract. The paper aims to evaluate the effectiveness of the multi-layer perceptron-Markov chain analysis (MLP-MCA) integrated method in predicting future Land Use and Land Cover (LULC) change scenarios in Fayoum due to rapid urbanization. The study employed machine learning algorithms for image classification using Google Earth Engine (GEE) for classification techniques to derive LULC maps from Landsat imagery taken in 2001, 2011, and 2021. The 2001 and 2011 LULC maps were used to predict the LULC scenario for 2021 using MLP-MCA, and the predicted result was validated against the observed 2021 LULC map using Area under the curve (AUC) that was derived from the Receiver Operating Characteristics (ROC). Subsequently, the study predicted future LULC changes for 2031 using two sub-models; sub- Agri and sub-built. The results show that a rapid growth in both built and agricultural area. The findings of this study highlight the potential of the MLP-MCA method in predicting future LULC changes due to urbanization.

Forecasting land use/cover changes and their influence on groundwater recharge in Chennai, India: Recommendations for sustainable urban development

ABSTRACT Land use/cover (LULC) changes significantly impact various environmental and social factors. In this study, we used a hybrid model that integrates Multi-Layer Perceptron-Markov Chain Analysis to forecast changes in LULC of Chennai city and its surrounding area until the year 2101. We also evaluated the impact of these changes on groundwater recharge potential zones (RPZ) and suggested policy recommendations for better urban planning. Our results indicate a rapid increase in built-up areas (238 km2/decade) and a corresponding decrease in agricultural lands (167 km2/decade), with a continuous reduction in the area occupied by the waterbodies (15 km2/decade). Furthermore, the estimated changes in RPZ demonstrate a decline in high recharge potential areas, emphasizing the need for effective policies to enhance groundwater recharge. The study provides insights into sustainable urban development. We recommended policies for promoting green urban spaces to mitigate LULC impacts on groundwater recharge.

A multi-layer perceptron–Markov chain based LULC change analysis and prediction using remote sensing data in Prayagraj district, India

Land use land cover (LULC) mapping and temporal observations are indispensable drivers for sustainable development. This research showed the growth trends and land use transition for the Prayagraj district in the last three decades. Supervised classification of Landsat images was performed on 5-year temporal intervals using a maximum likelihood classifier. All satellite images were organized into six major LULC feature classes viz agriculture/open land, barren land, built-up, forest, sand, and water. The overall accuracy of LULC classification was achieved by more than 89% in all seven temporal points. Furthermore, the accuracy of the classified maps was estimated through area-based error matrix. The Land Change Modeler tool of TerrSet 2020 software was used to analyze the transition of classes and to incorporate the multi-layer perceptron-Markov chain (MLP-MC) technique. The transition potentials were included in MLP-MC with the help of sensitive explanatory variables and significant transitions of classes. Furthermore, these transition potentials and the Markov chain transition matrix were used to predict the future LULC dynamics and vulnerability. The change analysis revealed that a significant portion of the agriculture/open land gradually decreased and got converted to built-up land. The results depicted that agriculture/open land was reduced by 8.03% in the last three decades while the built-up region was grown by 199.61%. Forest area was continuously decreasing while the sand area increased due to river meandering. Overall, more than 75% of accuracy was achieved in MLP. The prediction model was first validated with observed data, and then the LULC scenario of 2035 and 2050 was simulated. LULC of 2050 showed that the built-up area would likely reach 13.90% of district area whereas the forest area would remain only 0.79%. The prediction model has given the output in the form of future LULC map along with projected potential transition maps. This would be useful for sustainable urban planning to deal with the alarming rate of built-up growthand agriculture/open landshrinkage.

Evaluating land use/cover change associations with urban surface temperature via machine learning and spatial modeling: Past trends and future simulations in Dera Ghazi Khan, Pakistan

While urbanization puts lots of pressure on green areas, the transition of green-to-grey surfaces under land use land cover change is directly related to increased land surface temperature–compromising livability and comfort in cities due to the heat island effect. In this context, we evaluate historical and future associations between land use land cover changes and land surface temperature in Dera Ghazi Khan–one of the top cities in Pakistan–using multi-temporal Landsat data over two decades (2002–2022). After assessing current land use changes and future predictions, their impact on land surface temperature and urban heat island effect is measured using machine learning via Multi-Layer Perceptron-Markov Chain, Artificial Neural Network and Cellular Automata. Significant changes in land use land cover were observed in the last two decades. The built-up area expanded greatly (874 ha) while agriculture land (−687 ha) and barren land (−253 ha) show decreasing trend. The water bodies were found the lowest changes (57 ha) and vegetation cover got the largest proportion in all the years. This green-grey conversion in the last two decades (8.7%) and prospect along the main corridors show the gravity of unplanned urban growth at the cost of vegetation and agricultural land (−6.8%). The land surface temperature and urban heat island effect shows a strong positive correlation between urbanization and vegetation removal. The simulation results presented in this study confirm that by 2032, the city will face a 5° C high mean temperature based on historical patterns, which could potentially lead to more challenges associated with urban heat island if no appropriate measures are taken. It is expected that due to land cover changes by 2032, ~60% of urban and peri-urban areas will experience very hot to hot temperatures (> 31.5°C). Our results provide baseline information to urban managers and planners to understand the increasing trends of land surface temperature in response to land cover changes. The study is important for urban resource management, sustainable development policies, and actions to mitigate the heat island effect. It will further asset the broader audience to understand the impact of land use land cover changes on the land surface temperature and urban heat island effect in the light of historic pattern and machine learning approach.

Analyzing and Predicting Land Use and Land Cover Changes in New Jersey Using Multi-Layer Perceptron–Markov Chain Model

This study analyzed the changes of land use and land cover (LULC) in New Jersey in the United States from 2007 to 2012. The goal was to identify the driving factors of these changes and to project the five-year trend to 2100. LULC data was obtained from the New Jersey Department of Environmental Protection. The original 86 classes were reclassified to 11 classes. Data analysis and projection were performed using TerrSet 2020. Results from 2007 to 2012 showed that the rate of LULC changes was relatively small. Most changes happened to brush/grasslands, mixed forest lands, farmlands and urban/developed lands. Urban/developed lands and the mixed-forest cover gained while farmlands lost. Using a multi-layer perceptron–Markov chain (MLP–MC) model, we projected the 2015 LULC and validated by actual data to produce a 2100 LULC. Changes from 2012 to 2100 showed that urban/developed lands, as well as brush/grasslands, would continue to gain, while farmlands would lose, although the projected landscape texture would likely be identical to the 2012 landscape. Human and natural factors were discussed. It was concluded that the MLP–MC model could be a useful model to predict short-term LULC change. Unexpected factors are likely to interfere in a long-term projection.

Predicting land-use change: Intercomparison of different hybrid machine learning models

Land Use Land Cover (LULC) change assessment and prediction are essential for optimised water resources planning and management. This paper attempts to intercompare the different LULC change modelling techniques (two-hybrid and two traditional models) to predict the future LULC change. These include Multi-Layer Perceptron Markov Chain (MLP_MC), Logistic Regression-Markov Model (LR-MC), and two hybrid models, namely, Multi-Layer Perceptron Markov Chain Cellular Automata (MLP_MC_CA), Logistic Regression Markov Model Cellular Automata (LR_MC_CA) models. These models were tested on Nagavali River Basin (NRB), a river basin in Southern India, which has seen significant land-use changes over the past two decades. Over the past two decades, the study region experienced dominant changes on the order of 17.42% and 15.22% decrease in scrubland and forest, respectively. At the same time, the agricultural land cover is increased by 35.28%. For the LULC prediction, the model was initially trained using the relevant driver variables and LULC maps of 2010 and 2015. The calibrated model was validated using the 2020 LULC map. The statistical results in terms of Kappa values and chi-square results reveal that the hybrid model MLP-MC-CA has a better agreement (Kappa coefficient 0.902) compared to the other models. Further, it is also observed that the CA-based models have a better ability to capture spatial connections. After combining the MLP_MC model with the Cellular Automata, the former model was improved by 10.8% in terms of the overall Kappa coefficient. The best model for LULC prediction over the next decade (LULC map of 2030) showed that the forest area would decrease by 9.02%, and the agricultural land would increase by 8.74%. Further, the results from the study indicate that the hybrid machine learning models provide a promising alternative for land-use change prediction.

Comparative evaluation of geospatial scenario-based land change simulation models using landscape metrics

Assessing the performance of land change simulation models is a critical step when predicting the future landscape scenario. The study was conducted in the district of Varanasi, Uttar Pradesh, India because the city being “the oldest living city in the world” attracts a vast population to reside here for short and long-term, leaving the city’s ecosystem more exposed to fragility and less resilient. In this work, an approach based on landscape metrics is introduced for comparing the performance of the ensemble models designed to simulate the landscape changes. A set of landscape metrics were applied in this study that offered comprehensive information on the performance of scenario-based simulation models from the viewpoint of the spatial ordering of simulated results against the related reference maps. A supervised support vector machine classification technique was applied to derive the LULC maps using Landsat satellite images of the year 1988, 2001, and 2015. The LULC maps of 1988 and 2001 were used to simulate the LULC scenario for 2015 using three Markov chain-based simulation models namely, multi-layer perceptron-Markov chain (MLP_Markov), cellular automata-Markov chain (CA_Markov), and stochastic-Markov chain (ST_Markov) respectively. The mean relative error (MRE), as a measure of the success of simulation models, was calculated for metrics. The MRE values at both the class and landscape levels were accounted for 21.63 and 11.45% respectively using MLP_Markov simulation model. The MRE values at both the class and landscape levels were accounted for 39.61 and 28.31% respectively using CA_Markov simulation model. The MRE values at both the class and landscape levels were accounted for 55.36 and 45.75% respectively using ST_Markov simulation model. The MRE values considered at class and landscape levels are further evaluated qualitatively for comparing the performance of simulation models. The results indicate that the MLP_Markov performed excellently, followed by CA_Markov and ST_Markov simulation models. This work showed an ordered and multi-level spatial evaluation of the models’ performance into the decision-making process of selecting the optimum approach among them. Landscape metrics as a vital characteristic of the utilized method, employ the maximum potential of the reference and simulated layers for a performance evaluation process. It extends the insight into the main strengths and drawbacks of a specific model when simulating the spatio-temporal pattern. The quantified information of transition among landscape categories also provides land policy managers a better perception to build a sustainable city master plan.

Geospatial modelling of changes in land use/land cover dynamics using Multi-layer Perceptron Markov chain model in Rajshahi City, Bangladesh

Cities are developing rapidly and subsequently influences the land use/land cover (LU/LC) changes. Rajshahi city in Bangladesh facing rapid urban expansion by replacing LU/LC such as vegetation cover, water bodies (natural resources) and bare land to urban settlements. This study aims to identify the LU/LC changing patterns of Rajshahi city for 2000, 2010 and 2020 and simulate future LU/LC changes for 2040. Multi-temporal cloud-free Landsat satellite images were used to estimate the LU/LC and urban settlement changing pattern using remote sensing and geographic information system techniques. A support vector machine algorithm was used to classify the LU/LC classes. All the classified LU/LC maps demonstrate excellent accuracy by showing more than 85% overall accuracy. The multi-layer perception Markov chain (MLP-MC) model was used to predict the future LU/LC scenario for 2040. Validation of the predicted LU/LC map demonstrated more than 90% overall accuracy. The study found that an average of 3.6 km2 urban settlements increased at 10 years interval by replacing the natural resources. The future prediction shows that more than 60% of the total city area will be transformed into urban settlements by 2040. The dramatic increase in urban settlements and reduction in green cover and water bodies will damage the environmental sustainability of Rajshahi city by increasing temperature and heatwaves. This study will help the urban planners and policymakers to make proper sustainable development decisions by understanding the LU/LC changing pattern.

Future ecosystem service value modeling with land cover dynamics by using machine learning based Artificial Neural Network model for Jashore city, Bangladesh

Land Use/Land Cover (LULC) provides provisional, supporting, cultural, and regulating ecosystem services that contribute to ecological environments, enhance human health and living, have economic advantages for sustaining living organisms. LULC transformation due to enormous urban expansion diminishing Ecosystem Services Values (ESVs) and discouraging sustainability. Though unplanned LULC transformation practice became more prevalent in developing countries, comprehensive assessment of LULC changes and their influences in ESVs are rarely attempted. This study aimed to illustrate and forecast the LULC changes and their influences on ESVs change in Jashore using remote sensing technologies. ESVs estimation and change analysis were conducted by utilizing -derived LULC data of the year 2000, 2010, and 2020 with the corresponding global value coefficients of each LULC type which are previously published. For simulating future LULC and ESVs, Land Change Modeler of TerrSet Geospatial Monitoring and Modeling Software was used in Multi-Layer Perceptron-Markov Chain and Artificial Neural Network method. The decline of agricultural land by 13.13% and waterbody by 5.79% has resulted in the reduction of total ESVs US$0.23 million (24.47%) during 2000–2020. The forecasted result shows that the built-up area will be dominant LULC in the future, and ESVs of provisioning and cultural services will be diminished by $0.107 million, $63400.3 by 2050 with the declination of agricultural, waterbody, vegetation, and vacant land covers. The study signifies the importance of a strategic rational land-use plan to strictly monitor and control the encroachment of built-up areas into vegetation, waterbodies, and agricultural land in addition to scientific mitigative policies for ensuring ecological sustainability.

Multi-layer perceptron-Markov chain-based artificial neural network for modelling future land-specific carbon emission pattern and its influences on surface temperature

Reliable and accurate environmental state prediction can help in long-term sustainable planning and management. Enormous land-use/ land-cover (LULC) transformation has been increasing the carbon emissions (CEs) and land surface temperature (LST) around the world. The study aimed to (i) examine the influences of land specific CEs on LST dynamics and (ii) simulate future potential LULC, CEs and LST pattern of Khulna City Corporation. Landsat satellite images of the year 2000, 2010 and 2020 were used to derive LULC, LST and CEs pattern and change. The correlation between land-use indices (NDBI, NDVI, NDWI) and LST was examined to explore the impacts of LULC change on LST. Unplanned urbanization has increased 11.79 Km2(26.10%) buildup areas and 25,268 tons of CEs during 2000–2020. The calculated R2 value indicates the strong positive correlation between CEs and LST. To simulate the future LULC, CEs and LST pattern for the year 2030 and 2040, multi-layer perceptron-Markov chain (MLP-MC)-based artificial neural network model was utilized with the accuracy rate of 94.12%, 99% and 98.48% for LULC, LST and CEs model, respectively. The simulation shows that by 2040, buildup area will increase to 87.33%, net CEs will increase by 19.82 × 104tons, and carbon absorptions will decrease by 23. 55 × 104tons and 69.54% of the total study area's LST will be above 390C. Such predictions signify the necessity of implementing a sustainable urban development plan immediately for the sustainable, habitable and sound urban environment.

Regional carbon stock assessment and the potential effects of land cover change

Accurate assessment of carbon stocks remains a global challenge. High levels of uncertainty in Land Use, Land Use Change and Forestry reporting has hindered decision-makers and investors worldwide to support sustainable soil and vegetation management. Potential mitigation-driven activities and effects are likely to be locally/regionally unique. A spatially-targeted approach is thus required to optimise strategic carbon management. This study provides a new regional carbon assessment (tier 3) approach using biophysical-process modelling of high-resolution Land Cover (LC) data within a UK National Park (NFNP) to provide higher accuracy. Future Land Cover Change (LCC) scenarios were simulated. Vegetation-driven carbon dynamics were modelled by coupling two widely-used models, LPJ-GUESS and RothC-26.3. Transition and persistence analysis was conducted using Terrset's Land Change Modeller to predict likely future LCC for 2040 using Multi-Layer Perceptron Markov-Chain Analysis. Current total carbon in the NFNP is 7.32–8.73 Mt C, with current trajectories of LCC leading to minor losses of up to 0.39 Mt C. Alternative LCC scenarios indicated possible gains or losses of 1.27 Mt C, or 136.7 t C ha−1. The importance of vegetation-driven carbon storage was greater than the national average, with a VegC pool 12–14% of the soil organic C pool, placing greater significance on local/regional LC and management policy. The potential storage capacity of each LC class was ranked (highest to lowest): Coniferous > Broadleaved/Mixed > Coastal > Semi-natural Grassland > Heath > Improved Grassland > Arable (Cropland). Opportunities were prioritised to inform landscape-scale management to reduce future carbon losses and/or to enhance gains through LCC. Balancing the carbon budget relies upon maintaining existing LC. The more detailed LC classification facilitated accounting of management through stock change factors and disaggregation of classes, achieving greater detail and accuracy. Forthcoming policy decisions must optimise carbon storage at a local/regional landscape-scale.

Understanding the dynamics of landscape of greater Sundarban area using multi-layer perceptron Markov chain and landscape statistics approach

Sundarban mangrove is the largest continuous mangrove forest in the world and is the habitat of an incredible amount of biodiversity. Biodiversity loss and degradation of this highly ecologically productive mangrove forest due to climate change will have a tremendous impact on the livelihood of the people living in the deltaic region. The present study was aimed to find out the dynamics of change in different land cover for the greater Sundarban region. The multi-temporal Landsat images were used to understand the dynamics in three decades from 1998 to 2018. The analysis revealed that Sundarban mangrove forest changed very insignificantly. The change between 1998 and 2008 was approximately 1.2%, i.e. around 26.2 km2, and the change between the year 2008 and 2018 was approximately 1.27%, which consists of 28 km2. However, the dynamics of open mangrove forest and dense mangrove forest were found very high. The human habitat and aquaculture were found as the most rapidly expanding land-use type in this landscape. Area under human habitat has increased approximately 80%, i.e. nearly 654 km2 between 1998 and 2018; area under aquaculture has increased approximately 116% (i.e. around 231 km2) between 1998 and 2008. The MLP-Markov Chain based modelling of land-use has shown an overwhelming increase in human habitat in near future. However, being situated in the close vicinity of dense human population of the city Kolkata, the mangrove habitat remained intact, which is largely due to great amount of conservation efforts that have been exercised by the Govt. and the local forest department. The landscape statistical analysis for understanding the ecological dynamics of every land cover types showed that in 2018, the human habitat became second dominant category in this study area. The aquaculture practice for high economic value has pushed down the native agricultural practice in the region.

Modelling future land use land cover changes and their impacts on land surface temperatures in Rajshahi, Bangladesh

Urbanization causes enormous land use and land cover (LULC) changes, which creates a significant impacts on land surface temperature (LST) in rapidly growing mega-cities. The substantial increment of the LST creates urban heat island (UHI) effects in cities. This study first identified the pattern of the LULC changes, and later, investigated their impacts on LST in Rajshahi City Corporation (RCC) areas for the years of 1999, 2009 and 2019 using Landsat TM/OLI satellite images. This study explored the impact of LULC change on LST through LST distribution in different land use categories, cross-section profile of LULC wise LST variability, and a correlation between LULC indexes (NDVI, NDBI, NDBaI & NDWI) and LST. The Multi-Layer Perceptron-Markov Chain (MLP-MC) and Artificial Neural Network (ANN) methods were utilized to simulate the LULC and LST maps, respectively, for the years of 2029 and 2039. The accuracy of LULC and LST simulation models are more than 85% and 90% , respectively, based on the validation results. Simulation results show if the current trend of urban growth continues, 70% and 88% of RCC area will experience temperature more than 38 °C in 2029 and 2039, respectively. Such impacts need to be considered and evaluated immediately for ensuring sustainable urbanization and natural resource management in the RCC area. This study will be helpful for urban planners and environmental engineers to understand the impacts of LULC change (e.g. loss of vegetation cover, agricultural land and water bodies to accommodate extensive urban growth) on LST and to propose appropriate policy measures to control it.

Analysis and mapping of present and future drivers of local urban climate using remote sensing: a case of Lahore, Pakistan

Urbanization is the main driver of expanding industry, transport, and buildings at the cost of green spaces in the world’s mega cities. Consequently, an immense land use change is related to local climate modification in urban areas. The process of urbanization in the city of Lahore is posing severe environmental issues such as recent smog events. The objective here is to determine and analyze the spatial variability of land surface temperature (LST) caused by the land use land cover (LULC) change between the year 1996 and 2016 in Lahore in the context of urbanization and, based on this, to predict the land use change and corresponding increase in LST in 2035. To quantify LULC change during the 1996–2016 period, we used supervised maximum likelihood method and ground observations from 400 locations to classify the satellite imagery from the Landsat Thematic Mapper (TM)/Enhanced Thematic Mapper Plus (ETM+)/Operational Land Imager (OLI) for the years 1996, 2010, and 2016. Moreover, to better understand spatial variability of surface urban heat island (UHI) with the process of urbanization, various indicators were derived from the remote sensing imagery, including the normalized difference vegetation and built-up indices (i.e., NDVI and NDBI, respectively). Moreover, we used an RS-integrated multi-layer perceptron-Markov chain analysis (MLP-MCA) model to predict the LULC change from the year 2016 to 2035 so that the predicted LULC change, as a driver of UHI, can be related to the future local climate of the city. Through relating LST with NDVI and NDBI, we reveal that rapid developments in the residential/infrastructural sectors are causing an immense degradation in the city vegetation areas. The LULC change analyses show that about 9% decrease in green areas during 1996–2016 caused an increase in 6∘C around the built-up areas and an overall difference of 4.8∘C between built-up and nearby sub-urban vegetation areas. Keeping this and MLP-MCA-based predictions for 2035 in view, we conclude that a future 3% decrease in vegetation-covered green areas will approximately cause an increase of 2∘C by 2035. The research output will help the city government and local developers to devise sustainable policies for land use planning and urban development.

Scenario-led modelling of broadleaf forest expansion in Wales.

Significant changes in the composition and extent of the UK forest cover are likely to take place in the coming decades. Current policy targets an increase in forest area, for example, the Welsh Government aims for forest expansion by 2030, and a purposeful shift from non-native conifers to broadleaved tree species, as identified by the UK Forestry Standard Guidelines on Biodiversity. Using the example of Wales, we aim to generate an evidence-based projection of the impact of contrasting policy scenarios on the state of forests in the near future, with the view of stimulating debate and aiding decisions concerning plausible outcomes of different policies. We quantified changes in different land use and land cover (LULC) classes in Wales between 2007 and 2015 and used a multi-layer perceptron–Markov chain ensemble modelling approach to project the state of Welsh forests in 2030 under the current and an alternative policy scenario. The current level of expansion and restoration of broadleaf forest in Wales is sufficient to deliver on existing policy goals. We also show effects of a more ambitious afforestation policy on the Welsh landscape. In a key finding, the highest intensity of broadleaf expansion is likely to shift from southeastern to more central areas of Wales. The study identifies the key predictors of LULC change in Wales. High-resolution future land cover simulation maps using these predictors offer an evidence-based tool for forest managers and government officials to test the effects of existing and alternative policy scenarios.

Scenario-based land change modelling in the Indian Sundarban delta: an exploratory analysis of plausible alternative regional futures

The paper narrates an empirical research conducted for developing four alternative socio-ecological scenarios for the lower Gangetic delta in India (aka the Indian Sundarban). We used the ‘Story and Simulation (SAS) approach’ to build four short-term, landscape-scale scenarios for 2030, which include a ‘Business as Usual (BAU)’, and three alternative scenarios, namely ‘Market forces’, ‘Delta Republic’ and ‘Green Sundarban’. The storylines were built after careful screening of existing development and conservation plans, as well as by consulting local government officials. The storylines were then simulated using the Multi-Layer Perceptron–Markov Chain Analysis (MLP–MCA) model, with a multitude of factors, constraints, and attributes for each scenario. Historical and current land use maps of 2006 and 2016, derived from Landsat series (ETM+ and OLI), were used as the fundamental input to the model, which were also utilized to locate decadal changes, create several independent driver variables, calculate transition potentials and ultimately to develop future land use maps. To generate the scenarios, we used a Linear Programming (LP)-based land demand optimization method to alter the transition potential matrix. Our results indicated considerable loss of mud/tidal flats and viz.-a-viz. increase in river/water areas under all the four scenarios. We further observed moderate to a significant expansion of aquaculture for all the scenarios, with an almost two-fold increase under the Market forces scenario. In addition, three of the four scenarios indicated moderate loss of mangroves. The future extent of mangroves may vary from 1997.92 km2 (BAU) to 2172.25 km2 (Green Sundarban), which indicates to 3.72% overall decline (0.31% decline/year) to 4.67% (or 0.38% increase/year) overall gain from the present extent. As such, the Green Sundarban scenario was identified to the best possible pathway to serve the conservation interests and future sustainability of the delta. The results from the scenario analysis remain imperative to understand, plan and prepare for the plausible alternative regional futures, thereby optimizing conservation and development through proactive policy planning.

Prediction of spatio-temporal land use/land cover dynamics in rapidly developing Varanasi district of Uttar Pradesh, India, using geospatial approach: a comparison of hybrid models

Land use/land cover changes (LULCC) are one of the foremost aspects of environmental changes caused by human-induced activities mainly in rapidly developing areas. This study endeavors to evaluate and compare three hybrid models: stochastic Markov chain (ST-MC), cellular automata-Markov chain (CA-MC), and multi-layer perceptron-Markov chain (MLP-MC) to predict future land use/land cover (LULC) scenario in Varanasi district. LULC information extracted for years 1988 and 2001 was first employed to predict LULC scenario for 2015 using three hybrid models. The predicted results were compared with the observed LULC information for the year 2015 to appraise the validity of models through kappa index statistics. The MLP-MC model yielded reliable and best results. Finally, based on this consequence, the prediction of future LULC scenarios for years 2030 and 2050 was performed. The findings of this study exhibited the constant but overall increase of built up area and a considerable reduction in agricultural land. The results also demonstrate the potentiality of MLP-MC hybrid model for better understanding of spatio-temporal dynamics and predicting future landsacpe scenario in Varanasi district of Uttar Pradesh, India.

Predicting land use/cover change in Long Island Sound Watersheds and its effect on invasive species: a case study for glossy buckthorn

ABSTRACTLand use/cover change (LUCC) is a major threat to ecosystems. It may affect the abundance and distribution of species. Despite the importance of LUCC to ecological patterns and processes, few quantitative projections are available for use in ecological modelling. To fill in this literature gap, we constructed a LUCC model for Long Island Sound Watersheds (LISW) and explored the potential effect of the future LUCC on the range size of an invasive species (glossy buckthorn, Frangula alnus). We first applied the multi-layer perceptron–Markov chain model to predict the future LUCC in the LISW area within New England, USA, and then used the predicted land use/cover data as input into a species distribution model to simulate the future range size of glossy buckthorn. Our results indicate that under the current LUCC trend, there is a continued loss of forest and an increase of developed land in the near future, and this LUCC affects the relative suitability for glossy buckthorn.