Land Cover Change Detection Research Articles

Land use land cover change detection by using remote sensing in Meknes province, Morocco with an indicator based (DPSIR) approach

Land use land cover change detection by using remote sensing in Meknes province, Morocco with an indicator based (DPSIR) approach

Integration of ChatGPT and GeoAI in Change Detection of Landcover on Landsat Images 2000-2020: A Critical & Empirical Review

Integration of ChatGPT and GeoAI in Change Detection of Landcover on Landsat Images 2000-2020: A Critical & Empirical Review

Analysis of Land Use and Land Cover Dynamics in the Highlands of Northern Ethiopia

In the highlands of northern Ethiopia, many land use and land cover changes (LULCC) have occurred during different activities of the populations. Despite its coverage and unwise use of natural resources, these land uses and land covers are facing increasing or decreasing their area coverage. Information derived from land use and land cover change detection is important to land conservation, sustainable development, and management of Natural resources. This purpose of this study is therefore concerned with identifying the change in land use and land cover detection of the Wejic watershed. To identify land cover changes detection; remote sensing data, satellite imagery and image processing techniques had done within two dates of 1998 and 2017 using Land sat TM 30 m resolution images using Arc GIS 10.1. Hence, a field survey was carried out in 2017 to identify the major land cover types in the watershed. Detection Analysis of land use and land cover dynamics were calculated from the selected watershed in Southern Tigray, Northern Ethiopia. These land use types were cultivated, forest, bush, shrub, and homestead lands. Furthermore, a normalized difference vegetation index (NDVI) was developed for both years. The land use and land cover change results indicated that forest, cultivated land, and bush land decreased by 4.4%, 2.2%, and 2.4%, respectively. However, shrub land and homestead increased by 5.5% and 3.6%, respectively. Therefore The change detection analysis using GIS and remote sensing could deliver useful information to understand the seasonal patterns of land use dynamics for planners and decision makers; consequently, sustainable land management planning is possible.

Land-Use-Change-Driven Erosion and Sediment Transport in the Yaqui River Sub-Basin (Mexico): Insights from Satellite Imagery and Hydraulic Simulations

Soil erosion and sediment transport are significant concerns in the Yaqui River sub-basin in northwest Mexico, driven by land use changes and environmental degradation. This study aims to evaluate erosion processes between 2000 and 2020 using a combination of satellite imagery and numerical simulations with Iber software (Version 2.5.2). The primary objective is to assess the impacts of land use changes, particularly the conversion of forest to grassland, on erosion rates and sediment transport. Satellite images from 2000 and 2020 were analyzed to detect land cover changes, while Iber’s sediment transport module was used to simulate erosion patterns based on the Meyer–Peter and Müller equation for bedload transport. Hydrological and topographical data were incorporated to provide accurate simulations of flow velocity, depth, and erosion potential. The results reveal a 35.3% reduction in forest cover, leading to increased erosion and sediment transport in steep areas. Simulation predictions highlighted areas with high future erosion potential, which are at risk of further soil loss if current trends continue. Flow velocity increased, contributing to riverbank destabilization and higher sediment yield, posing a risk to infrastructure such as the Álvaro Obregón Dam. This study underscores the need for targeted erosion control measures and sustainable land management practices to mitigate future risks and protect vital infrastructure in the Yaqui River Basin.

Iterative Training Sample Augmentation for Enhancing Land Cover Change Detection Performance With Deep Learning Neural Network.

Labeled samples are important in achieving land cover change detection (LCCD) tasks via deep learning techniques with remote sensing images. However, labeling samples for change detection with bitemporal remote sensing images is labor-intensive and time-consuming. Moreover, manually labeling samples between bitemporal images requires professional knowledge for practitioners. To address this problem in this article, an iterative training sample augmentation (ITSA) strategy to couple with a deep learning neural network for improving LCCD performance is proposed here. In the proposed ITSA, we start by measuring the similarity between an initial sample and its four-quarter-overlapped neighboring blocks. If the similarity satisfies a predefined constraint, then a neighboring block will be selected as the potential sample. Next, a neural network is trained with renewed samples and used to predict an intermediate result. Finally, these operations are fused into an iterative algorithm to achieve the training and prediction of a neural network. The performance of the proposed ITSA strategy is verified with some widely used change detection deep learning networks using seven pairs of real remote sensing images. The excellent visual performance and quantitative comparisons from the experiments clearly indicate that detection accuracies of LCCD can be effectively improved when a deep learning network is coupled with the proposed ITSA. For example, compared with some state-of-the-art methods, the quantitative improvement is 0.38%-7.53% in terms of overall accuracy. Moreover, the improvement is robust, generic to both homogeneous and heterogeneous images, and universally adaptive to various neural networks of LCCD. The code will be available at https://github.com/ImgSciGroup/ITSA.

A fast hybrid approach for continuous land cover change monitoring and semantic segmentation using satellite time series

Land cover change detection and classification, including both inter-class changes (land cover conversion, LCC) and intra-class changes (land cover modification, LCM), is critical for understanding the Earth’s dynamic processes and promoting sustainability. However, previous studies have predominantly focused on LCC, with less emphasis on LCM. Land cover classification remains challenging, and its mapping results are often affected by salt and pepper noise. Here, we propose a hybrid approach for continuous change detection and classification of LCC and LCM using Jinchang City, China, as a case study. Firstly, we combined the Continuous Change Detection and Classification (CCDC) and the Bayesian Estimator of Abrupt change, Seasonal change, and Trend (BEAST) algorithms to identify LCC and LCM using all available Landsat time series (TS) data from 2000 to 2020. Then, the harmonic regression coefficients and RMSE values derived from CCDC (hereafter called CCDC features) were fed into the DCNN model for LCC classification. Our findings indicate: (1) For LCC and LCM accuracy assessment, the CCDC and BEAST ensemble achieved a spatial F1 score of 82.7% and an average temporal F1 score of 79.7%. (2) In LCC classification, the DCNN model with CCDC features, particularly DeepLabV3+, outperformed the pixel-based XGBoost and other multi-year land cover products, with frequency-weighted intersection over union (FWIoU), overall accuracy, and Kappa scores of 88.7%, 94%, and 0.87, respectively. (3) Seasonal LCM showed a more concentrated distribution than trend LCM. (4) In Jinchang City, LCM larger than LCC in area, and grassland and cultivated land are the most distributed. Our approach can be contributed to wall-to-wall land surface monitoring and enhance land management capabilities.

An evaluation of single and multi-date Landsat image classifications using random forest algorithm in a semi-arid savanna of Ghana, West Africa

Accurate detection and quantification of land use and land cover (LULC) change is critical for understanding landscape patterns in heterogeneous semi-arid environments. This study investigates the performance of single-date and multi-date Landsat images as well as the relationship between different LULC schemes (simple [2 and 4 classes] and complex [6 and 9 classes]) and the resulting classification accuracy. Specifically, the random forest algorithm was applied to Landsat data comprised of different combinations of image dates (single-date and multi-date) captured in June, October, and December for multiple levels of LULC (scheme) mapping and accuracy evaluations due to its high performance when dealing with large data and heterogeneous landscapes. Results indicated that multi-date images consistently produced higher classification accuracies than single-date images. Significant negative correlations observed between the number of classes in LULC schemes and overall accuracy and kappa coefficient indicate that the more complex the LULC scheme, the lower the accuracy produced. Nevertheless, improvement in overall accuracy was negligible for simple schemes (e.g., ∼1 % for two LULC classes), while it was moderate for complex schemes (∼5 %) when using the best-performing images for multi-date (June-October-December) compared to single-date (October) classifications: however, the improvement was considerable when compared to the least performing single-date image (June, 8–15 %). These varying classification accuracies were due to differences or similarities in spectral responses of target classes in the various LULC schemes applied to the investigated images. Consequently, the resulting differences in the spatial distribution and quantification of LULC classes produced by the different approaches can affect policy and land management decisions, especially if inappropriate image dates are used for LULC mapping. Overall, the findings highlight the reliability of appropriate single-date and multi-date images for mapping LULC change using simple and complex schemes in heterogeneous semi-arid savanna landscapes.

Land use land cover change detection in Baghdad city for the years 2000 and 2024 using random forest algorithm

Land use land cover change detection in Baghdad city for the years 2000 and 2024 using random forest algorithm

Temporal dynamics of land use land cover (LULC) changes and assessment of environmental and climatic parameters using remote sensing and GIS: A case study in Limboti Reservoir, Loha Taluka, Maharashtra, India

In this study, multispectral satellite data from Landsat 4-5 TM and Landsat 8 OLI/TIRS was used to analyse Land Use Land Cover (LULC) change detection and to retrieve environmental parameters. The LULC change detection was done between 2007 and 2021. This study used the supervised classification-maximum likelihood approach in ArcGIS 10.3 software to detect LULC in Loha Taluka, Maharashtra. The taluka was classified into four major LULC classes, viz. water, vegetation, settlement and barren-land. Changes in LULC directly or indirectly will also induce a change in the environmental parameters. Environmental parameters (water surface temperature, chlorophyll-a concentration and total suspended solids) were analysed for Limboti Reservoir. Data were predicted for next two years (2022 and 2023) using multiplicative seasonal decomposition and Holt-Winter’s multiplicative method and trends of each parameter were analysed using Mann-Kendall trend method. For both years, vegetative land was the most extensive LC in Loha Taluka, accounting for more than 60% of the total land area. However, throughout these years, urbanisation was rampant and vegetative land was converted to settlement. In these years, open water resources such as reservoirs, lakes and rivers covered a very small percentage of the total area, which is a serious threat to the ecosystem. As a result, proper water body management is essential; otherwise, these resources will be destroyed and will no longer be able to contribute to the area’s socioeconomic growth. Keywords: Change detection, Chlorophyll content, Land use land cover, Water quality, Water surface temperature

Land Use Land Cover Dynamics around a Western Himalayan Wetland using Geospatial Techniques

Despite having multitude of environmental advantages, wetlands are facing serious anthropogenic threats due to changes in the surrounding area. Therefore, the present investigation has been conducted to evaluate the landuse land cover (LULC) around a 6 km buffer strip of Nowgam wetland located in Kashmir valley. The detection of Land Use and Land Cover (LULC) changes was conducted using Landsat imagery within ArcGIS, spanning a 22-year period from 2000 to 2022. The Landsat imageries of three years (2000, 2010 and 2022) were classified using the supervised classification algorithm (maximum likelihood classification) in ArcGIS. Five LULC classes, viz., water, agriculture, settlement, vegetation and bareland were identified in the study region. The exploration of the classified images revealed the area under water decreased by about 56% while as area under agriculture and settlement increased by 44.7% and 30.9%, respectively. The area under vegetation decreased by 7.3% and area under bareland increased by 8.0%. The outcomes of the present discourse reveal that the changes in LULC around the Nowgam wetland are mostly anthropogenic which may pose serious threat to wetland ecosystem in near future. The present study provides a baseline data regarding ecosystem transformations and acts as an important stimulus for all the stakeholders of wetland in planning and implementation of the strategic conservational measures in Nowgam wetland (Bandipora).

Land Use and Land Cover Change Detection Using Remote Sensing in the Kal River Basin, Raigad District, Maharashtra, India

Land use and land cover (LULC) are distinct yet interrelated concepts that describe the characteristics and utilization of land. Land cover refers to the physical surface, such as vegetation, water bodies, or man-made features, while land use denotes the purpose of land utilization. Changes in LULC significantly impact water resources, making it a critical component in water resource studies. This study aims to detect changes in LULC over a five-year period (2017–2021) in the Kal River basin, a sub-basin of the Savitri River in Maharashtra, India. Sentinel-2 satellite imagery with a 10 m resolution was used, and the supervised classification method, specifically Maximum Likelihood Classification (MLC), was applied to classify LULC into six categories: cropland, bare ground, built-up areas, trees, rangeland, and water bodies. The results show that in 2017, the areas under cropland, tree cover, bare ground, built-up areas, and water bodies were 35.20 km², 187.61 km², 0.133 km², 7.77 km², and 1.89 km² respectively. By 2021, cropland, tree cover and bare ground decreased by 3.82%, 4.85%, and 0.01% respectively while water bodies, rangeland, and built-up areas increased by 0.02%, 8.34%, and 0.32% respectively. The overall accuracy of LULC classification was 77% for 2017 and 91% for 2021 with validation using the Kappa coefficient indicating good to excellent accuracy. This study highlights the importance of monitoring LULC changes for understanding the impacts of human activities and climate on watershed development and water resource management. Such analysis provides valuable insights for decision-makers to plan for sustainable development, land conservation and environmental management, ensuring balanced growth while protecting natural resources in the Kal River basin.

SFA-Net: Semantic Feature Adjustment Network for Remote Sensing Image Segmentation

Advances in deep learning and computer vision techniques have made impacts in the field of remote sensing, enabling efficient data analysis for applications such as land cover classification and change detection. Convolutional neural networks (CNNs) and transformer architectures have been utilized in visual perception algorithms due to their effectiveness in analyzing local features and global context. In this paper, we propose a hybrid transformer architecture that consists of a CNN-based encoder and transformer-based decoder. We propose a feature adjustment module that refines the multiscale feature maps extracted from an EfficientNet backbone network. The adjusted feature maps are integrated into the transformer-based decoder to perform the semantic segmentation of the remote sensing images. This paper refers to the proposed encoder–decoder architecture as a semantic feature adjustment network (SFA-Net). To demonstrate the effectiveness of the SFA-Net, experiments were thoroughly conducted with four public benchmark datasets, including the UAVid, ISPRS Potsdam, ISPRS Vaihingen, and LoveDA datasets. The proposed model achieved state-of-the-art accuracy on the UAVid, ISPRS Vaihingen, and LoveDA datasets for the segmentation of the remote sensing images. On the ISPRS Potsdam dataset, our method achieved comparable accuracy to the latest model while reducing the number of trainable parameters from 113.8 M to 10.7 M.

Application of geospatial techniques for land use land cover change detection in Pairi river subbasin

Application of geospatial techniques for land use land cover change detection in Pairi river subbasin

Change detection due to ISPAAD Programme using geospatial techniques: A case study of Dinogeng Agricultural Extension Area of Kgatleng District, Botswan

Dinogeng Agricultural Extension Area (DAEA), located in the south eastern part of Botswana has witnessed tremendous land use changes due to the Integrated Support Programme for Arable Agriculture Development (ISPAAD). For over a decade, crop cultivation has been relatively small both in size and population. But today, Dinogeng is one of the fastest growing agricultural areas. Therefore, it is paramount to detect the nature and magnitude of land use changes for planning purpose. Remotely Sensed data from Landsat 5 and Landsat 8 were utilized for the purpose of Land Use Land Cover (LULC) change detection. Geographical Information Systems (GIS) and Remote Sensing (RS) were used to produce LULC maps for 2006 and 2020 for assessing the severity of land degradation. In a 14-year span (2006-2020), LULC of DAEA changed markedly. Cultivated land and bare areas increased by 19.4 and 18.3 % whereas shrub land and forest areas decreased by 36.9 and 0.7 %, respectively. Supervised classification algorithms and stratified random sampling design were adopted for the accuracy assessment. The classification process produced good results with overall accuracies of 93% and 94% for the 2006 and 2020 maps, respectively. The findings could be useful to guide the development of functional land use plan for DAEA.

Spatiotemporal variation in determinants of cropland abandonment across Yangtze River Economic Belt, China

Cropland abandonment is a widespread land-change phenomenon globally, driven by complex social, economic, and political transformations, with significant implications for the environment and society. However, the inconsistent definitions of cropland abandonment and the bias in the selection of study areas hinder the comparison of identified determinants of cropland abandonment. In this study, we defined cropland abandonment from the perspective of vegetation succession. By employing land-cover change detection with Landsat time-series images from 1990 to 2021, we analyzed the spatiotemporal patterns of cropland abandonment across the cities of Yibin, Huangshi, and Chaohu within the Yangtze River Economic Belt. Furthermore, we utilized the Gradient-Boosting Decision Tree model to identify the primary spatial determinants and their relative importance in each city. Our findings showed significant variations in abandonment rates by 2021. Huangshi exhibited the highest rate of cropland abandonment, leading with 53.81±2.1 %, followed by Yibin with 45.36±2.18 %, and Chaohu with the lowest at 36.94±2.21 %. Interestingly, a consistent spatiotemporal trend, areas with higher abandonment rates tended to be abandoned earlier, emerged in abandonment determinants across cities. Areas with lower bulk density, higher soil clay content, and greater organic carbon contents exhibited higher abandonment rates. However, the most influential determinants varied: the distance from water bodies was the most important in Yibin and Huangshi, while the distance from the forest had a greater impact in Chaohu. This study offers a more nuanced perspective on defining cropland abandonment and can be applied to other regions after some adjustment. Our results provide valuable insights for cropland abandonment management by protecting high-value croplands and setting aside some areas for environmental amenities.

Remote sensing reveals trends in vegetative recovery and land cover transformation post-reclamation at tar creek superfund site

The harmful effects of mining waste on human and ecosystem health make reclamation of former mine sites an environmental management priority. However, field-based monitoring of reclamation requires significant investments of time, labor, and money. Remote sensing offers a less expensive alternative to field-based monitoring, but work is still needed to determine which metrics can be reliably estimated using remote sensing techniques. This study uses remote sensing to examine over 20 years of reclamation efforts at Tar Creek Superfund Site and to assess revegetation after site restoration. Using the Normalized Difference Vegetation Index (NDVI), we quantify key factors affecting vegetation recovery and stability after reclamation across 123 surface mining waste cleanup locations within Tar Creek. Leveraging long-term imagery from Landsat and high-resolution PlanetScope imagery, we combine time series analysis of vegetation regrowth and landcover change detection for a comprehensive picture of recovery at each site. Across all reclamation sites, the average recovery duration was 3.5 years, and average recovery rate was 0.1 NDVI year−1. After vegetative growth had plateaued, reclaimed sites had an average NDVI of 0.70. All reclamation areas were converted from majority barren landcover to vegetated landcover classes after reclamation, and vegetative stability at reclamation sites was high (70% of reclaimed area saw continuous vegetative cover from 2017 to 2023). These results demonstrate a strong potential for multi-method remote sensing techniques in tracking and explaining vegetation recovery after reclamation and represent a cost-effective approach for real-time monitoring of reclamation progress and outcomes.

Towards Robust Pansharpening: A Large-Scale High-Resolution Multi-Scene Dataset and Novel Approach

Pansharpening, a pivotal task in remote sensing, involves integrating low-resolution multispectral images with high-resolution panchromatic images to synthesize an image that is both high-resolution and retains multispectral information. These pansharpened images enhance precision in land cover classification, change detection, and environmental monitoring within remote sensing data analysis. While deep learning techniques have shown significant success in pansharpening, existing methods often face limitations in their evaluation, focusing on restricted satellite data sources, single scene types, and low-resolution images. This paper addresses this gap by introducing PanBench, a high-resolution multi-scene dataset containing all mainstream satellites and comprising 5898 pairs of samples. Each pair includes a four-channel (RGB + near-infrared) multispectral image of 256 × 256 pixels and a mono-channel panchromatic image of 1024 × 1024 pixels. To avoid irreversible loss of spectral information and achieve a high-fidelity synthesis, we propose a Cascaded Multiscale Fusion Network (CMFNet) for pansharpening. Multispectral images are progressively upsampled while panchromatic images are downsampled. Corresponding multispectral features and panchromatic features at the same scale are then fused in a cascaded manner to obtain more robust features. Extensive experiments validate the effectiveness of CMFNet.

Typhoon-Induced Forest Damage Mapping in the Philippines Using Landsat and PlanetScope Images

Forests provide valuable resources for households in the Philippines, particularly in poor and upland communities. This makes forests an integral part of building resilient communities. This relationship became complex during extreme events such as typhoon occurrence as forests can be a contributor to the intensity and impact of disasters. However, little attention has been paid to forest cover losses due to typhoons during disaster assessments. In this study, forest damage caused by typhoons was measured using harmonic analysis of time series (HANTS) with Landsat-8 Operation Land Imager (OLI) images. The ΔHarmonic Vegetation Index was computed by calculating the difference between HANTS and the actual observed vegetation index value. This was used to identify damaged areas in the forest regions and create a damage map. To validate the reliability of the results, the resulting maps produced using ΔHarmonic VI were compared with the damage mapped from PlanetScope’s high-resolution pre- and post-typhoon images. The method achieved an overall accuracy of 69.20%. The accuracy of the results was comparable to the traditional remote sensing techniques used in forest damage assessment, such as ΔVI and land cover change detection. To further the understanding of the relationship between forest and typhoon occurrence, the presence of time lag in the observations was investigated. Additionally, different contributing factors in forest damage were identified. Most of the forest damage observed was in forest areas with slopes facing the typhoon direction and in vulnerable areas such as near the coast and hill tops. This study will help the government and forest management sectors preserve forests, which will ultimately result in the development of a more resilient community, by making it easier to identify forest areas that are vulnerable to typhoon damage.

Land use land cover change detection analysis in kodjai watershed using remote sensing and GIS

Land use land cover change detection analysis in kodjai watershed using remote sensing and GIS

Exploring Google Earth Engine, Machine Learning, and GIS for Land Use Land Cover Change Detection in the Federal Capital Territory, Abuja, between 2014 and 2023

Exploring Google Earth Engine, Machine Learning, and GIS for Land Use Land Cover Change Detection in the Federal Capital Territory, Abuja, between 2014 and 2023