Land Use Cover Mapping Research Articles

Modeling and Prediction of Land Use Land Cover Change Dynamics Based on Land Change Modeler (LCM) in Nashe Watershed, Upper Blue Nile Basin, Ethiopia

Change of land use land cover (LULC) has been known globally as an essential driver of environmental change. Assessment of LULC change is the most precise method to comprehend the past land use, types of changes to be estimated, the forces and developments behind the changes. The aim of the study was to assess the temporal and spatial LULC dynamics of the past and to predict the future using Landsat images and LCM (Land Change Modeler) by considering the drivers of LULC dynamics. The research was conducted in Nashe watershed (Ethiopia) which is the main tributary of the Upper Blue Nile basin. The total watershed area is 94,578 ha. The Landsat imagery from 2019, 2005, and 1990 was used for evaluating and predicting the spatiotemporal distributions of LULC changes. The future LULC image prediction has been generated depending on the historical trends of LULC changes for the years 2035 and 2050. LCM integrated in TerrSet Geospatial Monitoring and Modeling System assimilated with MLP and CA-Markov chain have been used for monitoring, assessment of change, and future projections. Markov chain was used to generate transition probability matrices between LULC classes and cellular automata were used to predict the LULC map. Validation of the predicted LULC map of 2019 was conducted successfully with the actual LULC map. The validation accuracy was determined using the Kappa statistics and agreement/disagreement marks. The results of the historical LULC depicted that forest land, grass land, and range land are the most affected types of land use. The agricultural land in 1990 was 41,587.21 ha which increased to 57,868.95 ha in 2019 with an average growth rate of 39.15%. The forest land, range land, and grass land declined annually with rates of 48.38%, 19.58%, and 26.23%, respectively. The predicted LULC map shows that the forest cover will further degrade from 16.94% in 2019 to 8.07% in 2050, while agricultural land would be expanded to 69,021.20 ha and 69,264.44 ha in 2035 and 2050 from 57,868.95 ha in 2019. The findings of this investigation indicate an expected rapid change in LULC for the coming years. Converting the forest area, range land, and grass land into other land uses, especially to agricultural land, is the main LULC change in the future. Measures should be implemented to achieve rational use of agricultural land and the forest conversion needs to be well managed.

Land Use and Land Cover Mapping Using RapidEye Imagery Based on a Novel Band Attention Deep Learning Method in the Three Gorges Reservoir Area

Land use/land cover (LULC) change has been recognized as one of the most important indicators to study ecological and environmental changes. Remote sensing provides an effective way to map and monitor LULC change in real time and for large areas. However, with the increasing spatial resolution of remote sensing imagery, traditional classification approaches cannot fully represent the spectral and spatial information from objects and thus have limitations in classification results, such as the “salt and pepper” effect. Nowadays, the deep semantic segmentation methods have shown great potential to solve this challenge. In this study, we developed an adaptive band attention (BA) deep learning model based on U-Net to classify the LULC in the Three Gorges Reservoir Area (TGRA) combining RapidEye imagery and topographic information. The BA module adaptively weighted input bands in convolution layers to address the different importance of the bands. By comparing the performance of our model with two typical traditional pixel-based methods including classification and regression tree (CART) and random forest (RF), we found a higher overall accuracy (OA) and a higher Intersection over Union (IoU) for all classification categories using our model. The OA and mean IoU of our model were 0.77 and 0.60, respectively, with the BA module and were 0.75 and 0.58, respectively, without the BA module. The OA and mean IoU of CART and RF were both below 0.51 and 0.30, respectively, although RF slightly outperformed CART. Our model also showed a reasonable classification accuracy in independent areas well outside the training area, which indicates the strong model generalizability in the spatial domain. This study demonstrates the novelty of our proposed model for large-scale LULC mapping using high-resolution remote sensing data, which well overcomes the limitations of traditional classification approaches and suggests the consideration of band weighting in convolution layers.

Spatial modeling of land use and land cover change in Sulaimani, Iraq, using multitemporal satellite data.

Land use/land cover (LULC) change is an important indicator used for assessing the function and health of ecosystems. Understanding the patterns of LULC change assists in managing natural resources effectively, especially for regions where there are minimal or no reported data on the status of LULC. In this study, remotely sensed Landsat satellite imagery from 5years (i.e., 1988, 1996, 2002, 2008, and 2017), geographic information systems (GIS), and the hybrid cellular automata (CA)-Markov model were used to (i) quantify the past and present LULC changes and (ii) model the future changes in Sulaimani Province in the Kurdistan region of Iraq (KRI). To accomplish these objectives, five LULC maps with various class categories were generated using the maximum likelihood classifier (MCL). The classified maps for 1996, 2002, 2008, and 2017 were used in the hybrid model to simulate LULC maps for 2017 and 2037. The map simulated for 2017 was validated with the classified 2017 LULC map. The change analysis demonstrated that between 1988 and 2017, the built-up areas and agricultural fallow land increased by 419% and 226%, respectively. In the future predictions for 2037, built-up areas and agricultural fallow land showed increasing trends of 5.5% and 26.5%, respectively. In contrast, agricultural land, plantation land, and sparse vegetation areas were predicted to decrease by 29.4%, 65.8%, and 36.9%, respectively. In addition, in 2008, waterbodies shrank by 43.36% in comparison with their status in 1988, suggesting that 2008 was a severe drought year. These findings provide invaluable baseline information with which conservation biologists, agricultural engineers, urban planners, and decision makers can better manage natural resources and monitor environmental changes. Based on these results, sustainable development actions and an early warning system can be established.

Mapping Land use/land cover using a combination of Radar Sentinel-1A and Sentinel-2A optical images

The current study used a combination of Sentinel-1A (SE-1A) radar and Sentinel-2A (SE-2A) optical images in mapping land use/land cover (LULC) in Dak Nong province in 2018. The Random Forest (RF) algorithm was adopted to digitally categorize Landsat images into LULC maps according to ten different LULC classes included: evergreen forest, semi-evergreen forest, deciduous forest, plantation, rubber, industrial plants, crop land, residential area, water surface and others. The results indicated an overall accuracy (OA) and kappa coefficient of 81.40%, Kappa = 0.79, respectively. Based on the results of classified image, a 2018 LULC map of the study area was simulated. Accordingly, the natural forests account for 34.27% of the total area of the province, distributed scattered in districts. In which, the evergreen forest occupies the highest area with more than 166.600 ha, equivalent to 74.54% of the total natural forest area, and concentrated in the high mountain areas. Non-forest covers occupy more than 63% area of Dak Nong province. The industrial and agricultural cropland indicated a high area in the study area with a rate of 34.82% and 11.38%, respectively. This shows a strong development in the scale of industrial and agricultural crops in the study area. The objective information on current land use/land cover in this study can serve as the basis for policymakers to orient the local forest resource sustainability strategies. Besides, the study also shows that the use of a combination of Sentinel-1A radar and Sentinel-2A optical image to classify and construct the LU/LC map is a high-efficiency research direction.

Spatial and transient modelling of land use/land cover (LULC) dynamics in a Sahelian landscape under semi-arid climate in northern Burkina Faso

Sahelian landscapes have gone through rapid changes over the past decades under high pressure from an ever-growing population, climate hazards and land degradation. Understanding drivers of change and forecasting LULC dynamics in time and space are critical for sustainable land management. This research aimed at analyzing LULC patterns and forecasting future changes in the landscape at the watershed level in semi-arid climate in northern Burkina Faso. Three LULC categories (natural vegetation, degradation soils, and cultivated areas) were considered. Seasonal vegetation dynamics were assessed through the monitoring of radiometric indices over the years 2015, 2016 and 2017. The post-harvest period (October-November) was found to be optimal for single-date LULC mapping. Furthermore, LULC maps for 1986, 1999, 2009 and 2017 were produced through a supervised classification of Landsat satellite images. For land change modelling and prediction, a Multilayer Perceptron (MLP) neural network was calibrated between 1999 and 2009 and validated against 2017 reference map, then used to simulate prediction maps for 2030 and 2050, in conjunction with population growth forecasts. Analysis of LULC changes revealed degradation soils were the major contributor to cultivated areas expansion between 1986 and 2017. Land use maps predicted for 2030 and 2050 indicated an expected increase in cultivated areas of 10.4 % and 22.7 % respectively. These results highlight the strength of the human-environment relationship in the watershed and call for careful planning and conservation actions for a sustainable balance between sustainable agricultural production and natural resources conservation.

Sensitivity of a standard Land Use Cover change cellular automata model to resample input Land Use Cover maps

ABSTRACT Input data is one of the main sources of uncertainty in Land Use Cover Change (LUCC) modelling. Research has focussed on the sensitivity of LUCC models to the spatial resolution of Land Use Cover (LUC) maps. However, little attention has been paid to the way that spatial resolution is changed. Both the spatial resolution and the resampling method change the modelled landscape composition and configuration. This may affect the way Cellular Automata LUCC models behave and, accordingly, the landscapes they simulate. This paper analyses the sensitivity of a standard LUCC model (Metronamica) to changes in the spatial resolution and resampling method of input LUC maps. Results prove how the model is more sensitive to changes in the spatial resolution than to variations of the resampling method. This last component has not much influence in the simulated landscape, although it alters the landscape composition.

Land Use/Land Cover Change Detection Study Using Remote Sensing and GIS Technique in Puthimari River Basin-A Transboundary Basin Between Bhutan and India

Using remote sensing and GIS technique, we analyse the change detection of different land use/land cover (LULC) types that has taken place in Puthimari river basin during a two-decade period from 1999 to 2019. Supervised classification method with maximum likelihood algorithm have been applied to prepare the LULC maps. The LULC change detection has been performed employing a post-classification detection method. Puthimari is a north bank sub-catchment of River Brahmaputra, the northern part of which falls in Bhutan and the rest falls in the Assam state of India. The primary LULC types of the basin are, dense vegetation which is predominant in the upper catchment, crop land and rural settlement. Thus, five different classes have been considered for the analysis, viz., dense vegetation, water bodies, silted water, cropland and rural settlement. The results showed that the rural settlement and water bodies in the basin increased by 42.70% and 30.31% from 1999 to 2019. However, dense vegetation, silted water and cropland decreased by 9.24%, 27.47% and 28.10% during these two decades.

Land use and Land Cover Change Analysis, Causes and Effects on Agricultural Productivity, Case of Anlemo District in Hadiya zone, Ethiopia

Change in land use land cover (LULC) is one of the constraints which can influence the development of sustainable agricultural in the study area. The change in LULC can negatively affect the possible use of land and completely lead to soil and vegetation degradation that have an influences on crop productivity. LULC change analysis was conducted in Anlemo District in Hadiya zone, Ethiopia for the period of 2000-2018, using Remote Sensing satellite image and Geographic Information System with field verifications. This was to look at LULC change, its causes and influences on crop productivity in Anlemo District. In this study, LULC maps of 2000, 2010 and 2018, and change maps of 2000-2010 and 2010- 2018 were produced. Results from LULC change analysis revealed an increase in agricultural land from 36.6% in 2000 to 55.764% in 2018. The increase of agricultural land was mainly at the cost of vegetation and grazing land cover change. Vegetation cover decreased from 21.81% in 2000 to 14.601% in 2018. Shrub land area was 38.81% in 2000 that decreased to 19.933% in 2018 and wetland which was 0.817% in 2000 increased to 1.057% in 2018. The study also made known that the main reasons of LULC changes were mainly, expansion of agricultural land and clearing vegetation. Therefore, these urges to initiate mechanized farming system that permits small land holder farmers to obtain more crop products from their small plot of land and to use alternative sources for fuel to reduce the complete reliance of rural community on forest products.

Mapping Urban Land Use in India and Mexico using Remote Sensing and Machine Learning

This technical note describes the data sources and methodology underpinning a computer system for the automated generation of land use/land cover (LULC) maps of urban areas based on medium-resolution (10–30m/pixel) satellite imagery. The system and maps deploy the LULC taxonomy of the Atlas of Urban Expansion—2016 Edition: open, nonresidential, roads, and four types of residential space. We used supervised machine learning techniques to apply this taxonomy at scale. Distinguishing between recognizable, clearly defined types of land use within a built-up area, rather than merely delineating artificial land cover, enables a huge variety of potential applications for policy, planning, and research. We demonstrate the training and application of machine-learning-based algorithms to characterize LULC over a large spatial and temporal range in a way that avoids many of the onerous constraints and expenses of the traditional LULC mapping process: manual identification and classification of features. This document supersedes the previous technical note, Spatial Characterization of Urban Land Use through Machine Learning, and the methodology described here supersedes our previously reported techniques.

Evaluation of soil erosion and sediment yield spatio-temporal pattern during 1990–2019

Land use/land cover (LULC) change is an important measure to monitor the land degradation. This study focused on the Sebeya watershed located in the western province of Rwanda to evaluate the soil erosion and sediment yield spatio-temporal pattern from 1990 to 2019 occurred due to LULC change. Multi-temporal LULC maps of 1990–2019 and RUSLE model were used to achieve the objectives. The sediment yield was computed as a product of sediment delivery ratio (SDR) and the gross soil erosion. From the period 1990–2019, each year forestland decreased by 2.6%/yr, whereas the grassland, cropland, and settlement increased by 23.6%/yr, 14.5%/yr, and 81.6%/yr respectively. As a result, the mean soil erosion for 1990, 2000, 2010, and 2019 was 14.7, 28.3, 34, and 34.7 t ha−1 yr−1 whereas the total sediment yield was 3254.15, 5029.8, 6814.56, and 9074.04 t yr−1 respectively. Cropland was an exception to the other LULC classes because it has generated soil erosion in very high severity > 50 t ha−1 yr−1, while this severity class showed an upward trend. The study demonstrated that LULC change has a significant impact on soil erosion and sediment yield and suggests proper land-use planning and encourages afforestation to arrest soil loss.

A Three Decades Urban Growth Monitoring in Hadejia, Nigeria Using Remote Sensing and Geospatial Techniques

Overpopulation growth and urban center crowd became a global phenomenon which mainly cause urban growth in both developed and developing countries cities including Nigeria. Understanding the extent and pattern of such growth required spatial information as well as earth observation data that will be analyse on a temporal dimension. Remote sensing data and geospatial approach together with other auxiliary’s data were used to detect and monitor the spatio-temporal growth pattern and extent in the three decades of Hadejia town. The aim of this research is to understand how Hadejia town are spatial expand in terms of size and population between the years 1984-2019. Nevertheless, the spatio-temporal analysis over the three decades of 1984, 1999 and 2019 have been made. The research was carried out via remote sensing and geospatial method, satellite data were acquired across the region; atmospheric corrected using QUAC in Envi software; and also produced landuse landcover map. However, the research utilized object based image analysis (OBIA) for image classification and then built-up area were extracted in order to evaluate the urban expansion. The results indicate that the overall urban expansion occurred in between 1999 – 2019 with expansion of 566 hectares. Most of the changes happens along town major highway especial along interstate routes. The city has experienced an extreme growth geographically at East- Northern part due to plain terrain than Southern part because of present of river Hadejia.

Modeling and prediction of effects of land use change in an agroforestry dominated southeastern Rift-Valley escarpment of Ethiopia

Through the increased use of innovation, human population has been growing rapidly in its ability to derive resources from the environment. Predicting how land use/cover (LUC) changes affect regions and the society requires a good understanding of the dynamic human-environment interactions associated with land use change. This article addresses the future spatial distribution of land use and the impacts that ongoing LUC change have on the ecosystems of Gedeo-Abaya landscape. The actual LUC maps of 2000 and 2015 reference years together with natural and socioeconomic indicators were used in a combined Markov–CA model with GIS technology to simulate and forecast the changes in 2025 and 2035. Our prediction processes shows among the indicators used, distance to the nearest road and slope have more significant effects on the transition potential maps followed by elevation. Area based prediction change generally shows significant increase in agroforestry, cultivation land, and wetland/marshes LUC classes, while most natural vegetation classes, particularly woodland/shrubland (−29.8%), and grazing land (−5.7%) show significant reduction from 2015 to 2035. The present and forecasted trend of LUC changes has visible environmental and socioeconomic impacts, particularly on woodland ecosystems and on the well-being of (agro)pastoral communities in the downstream. Whilst, the betterment of the upstream study region strongly depends on the continuity with the current government landscape restoration policy as well as on the permanence of farmers current environmental friendly land management practices. Forecasting LUC changes in the study landscape offers the possibility that unwanted changes are prevented through proper and timely interventions.

Drivers and Dynamics of Land Use Land Cover in Phewa Watershed, Kaski, Nepal


 
 
 Geospatial tools play an important role in monitoring Land Use Land Cover (LULC) dynamics. This study assessed the extent of LULC changes during 2003, 2010 and 2018 using temporal satellite imageries, computed the rate of change in area of Phewa Lake and explored the drivers of LULC change and lake area change in Phewa watershed. It used Landsat Imageries for 2003, 2010 and 2018 and carried out purposive household survey (N=60), key informant survey (N=5), focus group discussion (N=4) and direct field observation to explore the drivers of LULC change and lake area change. It generated LULC maps by using supervised classification and computed LULC change by applying post classification change detection technique. On screen digitization was done to find the area of Phewa Lake during 2010 and 2018. Agricultural land and urban areas were found to have increased by 11.63% and 1.46% respectively while forest area, barren land and water bodies were found to have decreased by 9.21%, 3.56% and 0.5% respectively between 2003 and 2010. Forest area, urban areas and barren land were found to have increased by 5.9%, 3.28% and 5.02% respectively while agricultural landand water bodies were observed to have decreased by 7.83% and 0.16% respectively between 2010 and 2018. During 2010-2018, rate of change in lake area was found to have decreased by 0.61% with periodic annual decrement by 2.59 ha. The drivers responsible for LULC change were alternative form of energy, community forestry, promotion of private forestry, migration for foreign employment, inadequate market price of agricultural products, road construction, soil erosion and population pressure. Lake area was found to have decreased due to sedimentation, encroachment and road construction. Further study is important to know the exact contributions of these drivers of LULC change and lake area change for the sustainability of Phewa watershed.
 
 

Monitoring and Predicting Spatio-Temporal Land Use/Land Cover Changes in Zaria City, Nigeria, through an Integrated Cellular Automata and Markov Chain Model (CA-Markov)

Monitoring land use/land cover (LULC) change dynamics plays a crucial role in formulating strategies and policies for the effective planning and sustainable development of rapidly growing cities. Therefore, this study sought to integrate the cellular automata and Markov chain model using remotely sensed data and geographical information system (GIS) techniques to monitor, map, and detect the spatio-temporal LULC change in Zaria city, Nigeria. Multi-temporal satellite images of 1990, 2005, and 2020 were pre-processed, geo-referenced, and mapped using the supervised maximum likelihood classification to examine the city’s historical land cover (1990–2020). Subsequently, an integrated cellular automata (CA)–Markov model was utilized to model, validate, and simulate the future LULC scenario using the land change modeler (LCM) of IDRISI-TerrSet software. The change detection results revealed an expansion in built-up areas and vegetation of 65.88% and 28.95%, respectively, resulting in barren land losing 63.06% over the last three decades. The predicted LULC maps of 2035 and 2050 indicate that these patterns of barren land changing into built-up areas and vegetation will continue over the next 30 years due to urban growth, reforestation, and development of agricultural activities. These results establish past and future LULC trends and provide crucial data useful for planning and sustainable land use management.

Seasonal effect on the accuracy of Land use/Land cover classification in the Bilate Sub-basin, Abaya-Chamo Basin, Rift valley Lakes Basin of Ethiopia.

A correct and timely land use/land cover (LULC) classification provides indispensable information for the effective management of environmental and natural resources. However, earlier studies mapped the LULC map of Bilate Sub-basin using remote sensing images that were acquired for a single season. Hence, these studies did not consider the seasonal effects on the accuracy of LULC classification. Therefore, the objective of this study was to evaluate changes inclassification accuracy for images acquired during wet and dry seasons in the Bilate Sub-basin. LULC of the study area was classified using the Landsat 8 satellite imageries. Based on field observations, we classified the LULC of the study area into 9 dominant classes. The classification for the two seasons resulted in a noticeable difference between the LULC composition of the study area because of seasonal differences in the classification accuracy. The overall accuracy of theLULC maps was 80%for the wet season and 90% for the dry season with Kappa coefficient values of 0.8 and 0.9 respectively. Therefore, the two seasons showed a significant difference in the overall accuracy of the classification. However, we discovered that when the classification accuracy was tested locally, that is for individual pixels, the results were not the same. In Bilate Sub-basin, several pixels (14.71%) were assigned to different LULC classes on the two seasonsmaps while 85.29% of the LULC classes remained unaltered in the two maps. According to the classification results, the season had a noticeable effect on the accuracy of LULC classification. This suggests that for LULC classification, multitemporal images should be used rather than a single remote sensing image.

A dynamic land use/land cover input helps in picturing the Sahelian paradox: Assessing variability and attribution of changes in surface runoff in a Sahelian watershed

In Sahelian landscapes, land use/land cover (LULC) dynamics and climate variability are already known to affect the water cycle. In its current practice however, hydrological modelling does not account for LULC changes. This issue pertains to rapidly evolving watersheds and might result in critical inaccuracies in the simulated processes. In this study, the Soil and Water Assessment Tool (SWAT) model was used to simulate surface runoff in the small Sahelian watershed of Tougou, which underwent significant LULC changes between 1952 and 2017. Based on rainfall/runoff data acquired from 2004 to 2018, the SWAT model was calibrated under two scenarios: a static land use scenario (SLU) using a single LULC map (in 1999) and a dynamic land use scenario (DLU) integrating 3 LULC maps (1999, 2009 and 2017). The DLU scenario estimated with higher accuracy surface runoff, deep aquifer infiltration and actual evapotranspiration processes. Based on the calibrated parameters, surface runoff was simulated during the historical period 1952–2003 under four scenarios with static LULC maps (in 1952, 1973, 1986 and 1999) opposed to a fifth scenario integrating these LULC maps dynamically. The DLU scenario was found to be more effective at picturing the so-called Sahelian paradox (i.e. the increase in surface runoff despite the decrease in rainfall), reported in the literature for small watersheds in the Sahel. The analysis of variability revealed that fluctuations in surface runoff were both influenced by rainfall and LULC changes. Furthermore, the isolated contributions of climate variability and LULC changes on surface runoff showed that LULC conditions played a dominant role (ηlulc = +393.1%) in the runoff increase over climate (ηcl = −297%) during the historical period. These results highlight the importance of accounting for LULC dynamics in hydrological modelling and advocate the development of integrated modelling frameworks for hydrologists and water resource managers.

An integrated simulation approach to the assessment of urban growth pattern and loss in urban green space in Kolkata, India: A GIS-based analysis

Urban green space (UGS) is although play a vital role in the mitigation of negative impacts of urbanization, but it often abominably affected by the process of land-use land-cover (LULC) changes in an urban area. Thus, the present study aims to examine the loss in urban green space (UGS) in relation to LULC change by using a multi-temporal land-use transition scenario and to predict the loss of UGS in the future in the city Kolkata. Landsat satellite data (for years 1980, 1991, 2001, 2011 and 2018) were used for analysis. We have adopted three comparative land classification algorithms for the assessment of urban growth pattern. An integrated cellular automata-Markov chain (CA-MC) model was applied to simulate LULC dynamics and the state of UGS in 2025 and 2035. Land use dynamic degree index (LUDD), UGS change intensity index (CII) and UGS land index were used to measure the rate and speed of urban growth, the ratio of change of green space and UGS coverage in respect to the total area of all LULC types, respectively. To measure UGS availability, per-capita urban green space (PCG) was estimated. The model was validated using observed and simulated LULC map 2018. The standard Kappa coefficient value was 0.861 and overall level of agreement was 91.15%, which signifies the efficiency of this simulation. The result shows that the built-up areas were increased from 92.71 sq. km in 1980 to 148.30 sq. km in 2018 and predicted to increase 155.67 sq. km which will be about 84% of the total area. Correspondingly, the predicted results displayed that, vegetation and grassland area were decreased about (−)17.42% and (−)11.69% for the period of 2025–2035, respectively. The present study provides some productive methodological approach for future LULC simulation research and also the findings of this study can help implement UGS management strategies not only for the Kolkata but other cities as well.

Predicting and mapping land cover/land use changes in Erbil /Iraq using CA-Markov synergy model

One of the most dynamic components of the environment is land use land cover (LULC), which have been changing remarkably since after the industrial revolution at various scales. Frequent monitoring and quantifying LULC change dynamics provide a better understanding of the function and health of ecosystems. This study aimed at modelling the future changes of LULC for the Erbil governorate in the Kurdistan region of Iraq (KRI) using the synergy Cellular Automata (CA)-Markov model. For this aim, three consecutive-year Landsat imagery (i.e., 1988, 2002, and 2017) were classified using the Maximum Likelihood Classifier. From the classification, three LULC maps with several class categories were generated, and then change-detection analysis was executed. Using the classified (1988–2002) and (2002–2017) LULC maps in the hybrid model, LULC maps for 2017 and 2050 were modelled respectively. The model output (modelled 2017) was validated with the classified 2017 LULC map. The accuracy of agreements between the classified and the modelled maps were Kno = 0.8339, Klocation = 0.8222, Kstandard = 0.7491, respectively. Future predictions demonstrate between 2017 and 2050, built-up land, agricultural land, plantation, dense vegetation and water body will increase by 173.7% (from 424.1 to 1160.8 km2), 79.5% (from 230 to 412.9 km2), 70.2% (from 70.2 to 119.5 km2), 48.9% (from 367.2 to 546.9 km2) and 132.7% (from 10.7 to 24.9 km2), respectively. In contrast, sparse vegetation, barren land will decrease by 9.7% (2274.6 to 2052.8 km2), 18.4% (from 9463.9-7721 km2), respectively. The output of this study is invaluable for environmental scientists, conservation biologists, nature-related NGOs, decision-makers, and urban planners.

Evaluating the rate of change and predicting the future scenario of spatial pattern using Markov chain model: a study from Baghmundi C.D. Block of Purulia district, West Bengal

In the era of twenty-first century, the endless demands of human have promoted land use land cover (LULC) change, and its understanding is more essential for proper management and future planning towards the sustainable development. An analysis of LULC is made for the Baghmundi Community Development (C.D.) Block of Purulia district of West Bengal, India to observe the changes over time. The Landsat images of 1972, 1992, 1999, 2009 and 2019 are taken to prepare the LULC maps using RS and GIS techniques. Moreover, the Markov chain model is computed to estimate LULC change of 2039. Thematic maps of different years show several changes in LULC. An accuracy assessment of the classifications of LULC of the years 1999, 2009 and 2019 is calculated as 81.32%, 81.36% and 80.16% respectively. The kappa coefficient is also computed for the same years to understand the level of agreement between classified LULC type and ground level LULC type. The values of kappa coefficient are 0.76 for 1999, 0.77 for 2009 and 0.75 for 2019. Within the time frame of 1972 to 2019, the vegetation cover declined to 44.79 km2, while the built-up area increased to 40.21 km2. Based on the predicted model, the vegetation cover may lose 33.60 km2 in 2039 from the year 2019, and it may mainly be acquired by the agricultural land (21.94 km2) and built-up area (7.93 km2).

Automatic Extraction and Filtering of OpenStreetMap Data to Generate Training Datasets for Land Use Land Cover Classification

This paper tests an automated methodology for generating training data from OpenStreetMap (OSM) to classify Sentinel-2 imagery into Land Use/Land Cover (LULC) classes. Different sets of training data were generated and used as inputs for the image classification. Firstly, OSM data was converted into LULC maps using the OSM2LULC_4T software package. The Random Forest classifier was then trained to classify a time-series of Sentinel-2 imagery into 8 LULC classes with samples extracted from: (1) The LULC maps produced by OSM2LULC_4T (TD0); (2) the TD1 dataset, obtained after removing mixed pixels from TD0; (3) the TD2 dataset, obtained by filtering TD1 using radiometric indices. The classification results were generalized using a majority filter and hybrid maps were created by merging the classification results with the OSM2LULC outputs. The accuracy of all generated maps was assessed using the 2018 official “Carta de Ocupação do Solo” (COS). The methodology was applied to two study areas with different characteristics. The results show that in some cases the filtering procedures improve the training data and the classification results. This automated methodology allowed the production of maps with overall accuracy between 55% and 78% greater than that of COS, even though the used nomenclature includes classes that can be easily confused by the classifiers.