Changes In Land Cover Types Research Articles

Artificial Intelligence for Computational Remote Sensing: Quantifying Patterns of Land Cover Types around Cheetham Wetlands, Port Phillip Bay, Australia

This paper evaluates the potential of using artificial intelligence (AI) and machine learning (ML) approaches for classification of Landsat satellite imagery for environmental coastal mapping. The aim is to identify changes in patterns of land cover types in a coastal area around Cheetham Wetlands, Port Phillip Bay, Australia. The scripting approach of the Geographic Resources Analysis Support System (GRASS) geographic information system (GIS) uses AI-based methods of image analysis to accurately discriminate land cover types. Four ML algorithms are applied, tested and compared for supervised classification. Technical approaches are based on using the ‘r.learn.train’ module, which employs the scikit-learn library of Python. The methodology includes the following algorithms: (1) random forest (RF), (2) support vector machine (SVM), (3) an ANN-based approach using a multi-layer perceptron (MLP) classifier, and (4) a decision tree classifier (DTC). The tested methods using AI demonstrated robust results for image classification, with the highest overall accuracy exceeding 98% and reached by the SVM and RF models. The presented scripting approach for GRASS GIS accurately detected changes in land cover types in southern Victoria over the period of 2013–2024. From our findings, the use of AI and ML algorithms offers effective solutions for coastal monitoring by analysis of change detection using multi-temporal RS data. The demonstrated methods have potential applications in coastal and wetland monitoring, environmental analysis and urban planning based on Earth observation data.

Geospatial assessment of built environment on land surface temperature in district Sheikhupura, Punjab Pakistan

The built environment is associated with higher air and surface temperatures in urban areas compared to rural counterparts. This study focuses on the Sheikhupura district in Punjab, Pakistan, where rapid urbanization and deforestation have significantly impacted land surface temperature (LST) from 2000 to 2020. Utilizing Geographic Information Systems (GIS) and Remote Sensing (RS) techniques, four Landsat images from the United States Geological Survey (USGS) were analyzed to assess spatiotemporal variations in LULC and LST. The single infrared channel approach was employed to calculate LST, and LULC maps were created using supervised classification for the years 2000, 2010, and 2020. The results indicate a substantial increase in built-up areas from 66.9708 square kilometers in 2000 to 259.8147 square kilometers in 2020, accompanied by a significant reduction in vegetation and agricultural land. Correspondingly, the maximum LST rose from 28.9354 °C in 2000 to 31.5173 °C in 2020, highlighting the urban heat island effect. Zonal statistics revealed a decrease in mean high temperatures from 24.45 to 20.3 °C over the same period, suggesting variability in temperature distribution due to changes in land cover types. These findings underscore the need for sustainable urban planning to mitigate the adverse effects of urbanization on local climates. Future work should focus on developing strategies to increase green spaces and reforestation efforts to counteract rising temperatures. Additionally, further research is recommended to explore the long-term impacts of these changes on local biodiversity and ecosystem services, providing a holistic approach to urban sustainability.

Water bodies as a stable reference for urban heat islands intensity measurements

Accurate measurement of urban heat islands (UHI) intensity is a necessary prerequisite for understanding UHI formation mechanisms and subsequently implementing effective prevention and control measures. The selection of a stable reference is a significant challenge in this process. In particular, rapid urbanization can lead to changes in land cover types. This process hinders the selection of a typical non-urban area as a stable reference for accurately measuring surface urban heat islands (SUHI) intensity. Among various land cover types, water bodies are widely distributed and stable during urban development. Nevertheless, the use of water bodies as a stable reference for SUHIs remains controversial. For 185 global cities, we first clustered the land cover transformation rates and then compared the interannual variations in SUHIW and SUHIR in these cities by using remote sensing data from MODIS. The trends of interannual intensities of the SUHIW and SUHIR in the stable group are similar, indicating that water bodies have the same effect on SUHI measurements as stable rural areas. However, the magnitude of the difference between the SUHIW and the SUHIR (SD) becomes more significant in cities with rapid changes in rural areas. As a stable reference, water bodies can be used to accurately measure the variation in the SUHI affected only by urbanization under the background climate, while the land cover transformation of rural areas changes the land surface temperature (LST) and thus affects the SUHI intensity. The findings of this study quantitatively demonstrate the feasibility of using water bodies as SUHI references from an urban dynamics perspective and provide direction for studying SUHIs under climate change.

Assessment of vegetation net primary productivity variation and influencing factors in the Beijing-Tianjin-Hebei region

Exploring the spatiotemporal variations of vegetation net primary productivity (NPP) and analyzing the relationships between NPP and its influencing factors are vital for ecological protection in the Beijing-Tianjin-Hebei (BTH) region. In this study, we employed the CASA model in conjunction with spatiotemporal analysis techniques to estimate and analyze the spatiotemporal variations of NPP in BTH and different ecological function sub-regions over the past two decades. Subsequently, we established three scenarios (actual, climate-driven and land cover-driven) to assess the influencing factors and quantify their relative contributions. The results indicated that the overall NPP in BTH exhibited a discernible upward trend from 2000 to 2020, with a growth rate of 3.83 gC·m−2a−1. Furthermore, all six sub-regions exhibited an increase. The Bashang Plateau Ecological Protection Zone (BP) exhibited the highest growth rate (5.03 gC·m−2a−1), while the Low Plains Ecological Restoration Zone (LP) exhibited the lowest (2.07 gC·m−2a−1). Geographically, the stability of NPP exhibited a spatial pattern of gradual increase from west to east. Climate and land cover changes collectively increased NPP by 0.04 TgC·a−1 and 0.07 TgC·a−1, respectively, in the BTH region. Climate factors were found to have the greatest influence on NPP variations, contributing 40.49% across the BTH region. This influence exhibited a decreasing trend from northwest to southeast, with precipitation identified as the most influential climatic factor compared to temperature and solar radiation. Land cover change has profound effects on ecosystems, which is an important factor on NPP. From 2000 to 2020, 15.45% area of the BTH region underwent land cover type change, resulting in a total increase in NPP of 1.33 TgC. The conversion of grass into forest brought about the 0.89 TgC increase in NPP, which is the largest of all change types. In the area where land cover had undergone change, the land cover factor has been found to be the dominant factor influencing variations in NPP, with an average contribution of 49.37%. In contrast, in the south-central area where there has been no change in land cover, the residual factor has been identified as the most influential factor influencing variations in NPP. Our study highlights the important role of land cover change in influencing NPP variations in BTH. It also offers a novel approach to elucidating the influences of diverse factors on NPP, which is crucial for the scientific assessment of vegetation productivity and carbon sequestration capacity.

Assessing the Nonlinear Relationship between Land Cover Change and PM10 Concentration Change in China

Inhalable particulate matter (PM10) is a major air pollutant that has significant impacts on environmental climate and human health. Land-cover change is also a key factor influencing changes in atmospheric pollution. Changes in land-cover types can lead to changes in the sources and sinks of air pollutants, thus affecting the spatial distribution of PM10, which poses a threat to human health. Therefore, exploring the relationship between PM10 concentration change and land-cover change is of great significance. In this study, we constructed an extreme randomized trees model (ET) based on ground PM10 monitoring data, satellite-based aerosol optical depth (AOD) data, and auxiliary data including meteorological, vegetation, and population data to retrieve ground-level PM10 concentrations across China. The coefficient of determination (R2), the mean absolute error (MAE), and the root mean square error (RMSE) of the model were 0.878, 5.742 μg/m3, and 8.826 μg/m3, respectively. Based on this, we analyzed the spatio-temporal distribution of PM10 concentrations in China from 2015 to 2021. High PM10 values were mainly observed in the desert areas of northwestern China and the Beijing–Tianjin–Hebei urban agglomeration. The majority of China showed a significant decrease in PM10 concentrations. Additionally, we also analyzed the nonlinear response mechanism of the PM10 concentration change to land-cover change. The PM10 concentration is sensitive to forest and barren land change. Therefore, strengthening the protection of forests and desertification control can significantly reduce air pollution. Attention should also be paid to emission management in agricultural activities and urbanization processes.

A Novel UNet 3+ Change Detection Method Considering Scale Uncertainty in High-Resolution Imagery

The challenge of detecting changes in high-resolution remote sensing imagery often stems from the difficulties in effectively extracting features and constructing appropriate change detection models considering the scale characteristics of ground objects. To solve these issues, we propose a novel UNet 3+ change detection method that considers the scale characteristics inherent in various land-cover change types. Our method includes three key steps: a multi-scale segmentation method, a class-specific UNet 3+ method, and an object-oriented change detection method based on UNet 3+. To verify the effectiveness of this method, we select two datasets for experiments and compare our proposed method with the UNet 3+ single-scale sampling method, the class-specific UNet 3+ single-scale sampling method, and the UNet 3+ multi-scale hierarchical sampling method. Our experimental results show that our proposed method has higher overall accuracy and F1, lower missed detection rate and false detection rate, and can detect more changes in ground features than other methods. To verify the scalability of this method, we compare this method with traditional change detection methods such as PCA-k-means, OCVA, a single-scale sampling method based on random forest, and a class-specific object-based method. Experimental results and accuracy indexes show that our proposed method better considers the scale characteristics of ground objects and achieves higher accuracy. Additionally, we compared our proposed method with other DLCD methods including LamboiseNet, BIT, CDNet, FCSiamConc, and FCSiamDiff. Our results show that our proposed method effectively considers edge information and has an acceptable time consumption. Our approach not only considers the full-scale characteristics of the feature extraction but also the scale characteristics of the change detection model. In addition, it considers a more practical feature extraction unit (object), making it more accurate.

Artificial Neural Networks for Mapping Coastal Lagoon of Chilika Lake, India, Using Earth Observation Data

This study presents the environmental mapping of the Chilika Lake coastal lagoon, India, using satellite images Landsat 8-9 OLI/TIRS processed using machine learning (ML) methods. The largest brackish water coastal lagoon in Asia, Chilika Lake, is a wetland of international importance included in the Ramsar site due to its rich biodiversity, productivity, and precious habitat for migrating birds and rare species. The vulnerable ecosystems of the Chilika Lagoon are subject to climate effects (monsoon effects) and anthropogenic activities (overexploitation through fishing and pollution by microplastics). Such environmental pressure results in the eutrophication of the lake, coastal erosion, fluctuations in size, and changes in land cover types in the surrounding landscapes. The habitat monitoring of the coastal lagoons is complex and difficult to implement with conventional Geographic Information System (GIS) methods. In particular, landscape variability, patch fragmentation, and landscape dynamics play a crucial role in environmental dynamics along the eastern coasts of the Bay of Bengal, which is strongly affected by the Indian monsoon system, which controls the precipitation pattern and ecosystem structure. To improve methods of environmental monitoring of coastal areas, this study employs the methods of ML and Artificial Neural Networks (ANNs), which present a powerful tool for computer vision, image classification, and analysis of Earth Observation (EO) data. Multispectral satellite data were processed by several ML image classification methods, including Random Forest (RF), Support Vector Machine (SVM), and the ANN-based MultiLayer Perceptron (MLP) Classifier. The results are compared and discussed. The ANN-based approach outperformed the other methods in terms of accuracy and precision of mapping. Ten land cover classes around the Chilika coastal lagoon were identified via spatio-temporal variations in land cover types from 2019 until 2024. This study provides ML-based maps implemented using Geographic Resources Analysis Support System (GRASS) GIS image analysis software and aims to support ML-based mapping approach of environmental processes over the Chilika Lake coastal lagoon, India.

Cultivation and dynamic cropping processes impart land-cover heterogeneity within agroecosystems: a metrics-based case study in the Yazoo-Mississippi Delta (USA)

ContextCultivation and crop rotation, influenced by federal policy, prices, and precipitation, are significant sources of land-cover heterogeneity. Characterization of heterogeneity is required to identify areas and trends of stability or change.ObjectivesWe analyzed a land-cover time series within a prominent agroecosystem in the US, the Yazoo-Mississippi Delta (the Delta), as a case study of which metrics capture dynamics of landscape composition, configuration, connectivity, and context.MethodsAn assessment of land cover- from 2008 to 2021- was conducted and analyzed for potential differences among three Farm Bill eras. Twelve out of 23 metrics (including three new ones presented herein) examined were useful in characterizing land-cover heterogeneity.ResultsAlthough there was no increase in cultivated land, > 72% of the Delta experienced changes in land-cover type, and ~ 3% of the Delta was stable monoculture. Configurational metrics varied across years for soybeans, cotton, and rice, indicating prevalence of field-level changes in composition; connectivity metrics revealed isolation of upland forest and rice. The amount of corn was positively associated with the previous year’s commodity prices and negatively with precipitation whereas soybean acreage was lower in high-precipitation years and more dependent on commodity prices. Farm Bill effects were mixed among categories, whereas CRP generally declined.ConclusionsThe Delta experienced land-cover change with no net loss or gain of cultivated lands. Using 12 metrics that captured temporal shifts in spatial patterns, we characterized this agroecosystem as a shifting mosaic. Our approach may be useful for identifying areas of spatio-temporal heterogeneity or stability, with implications on resource management.

Landsat sub-pixel land cover dynamics in the Brazilian Amazon

The Brazilian Amazon land cover changes rapidly due to anthropogenic and climate drivers. Deforestation and forest disturbances associated with logging and fires, combined with extreme droughts, warmer air, and surface temperatures, have led to high tree mortality and harmful net carbon emissions in this region. Regional attempts to characterize land cover dynamics in this region focused on one or two anthropogenic drivers (i.e., deforestation and forest degradation). Land cover studies have also used a limited temporal scale (i.e., 10–15 years), focusing mainly on global and country-scale forest change. In this study, we propose a novel approach to characterize and measure land cover dynamics in the Amazon biome. First, we defined 10 fundamental land cover classes: forest, flooded forest, shrubland, natural grassland, pastureland, cropland, outcrop, bare and impervious, wetland, and water. Second, we mapped the land cover based on the compositional abundance of Landsat sub-pixel information that makes up these land cover classes: green vegetation (GV), non-photosynthetic vegetation, soil, and shade. Third, we processed all Landsat scenes with <50% cloud cover. Then, we applied a step-wise random forest machine learning algorithm and empirical decision rules to classify intra-annual and annual land cover classes between 1985 and 2022. Finally, we estimated the yearly land cover changes in forested and non-forested ecosystems and characterized the major change drivers. In 2022, forest covered 78.6% (331.9 Mha) of the Amazon biome, with 1.4% of secondary regrowth in more than 5 years. Total herbaceous covered 15.6% of the area, with the majority of pastureland (13.5%) and the remaining natural grassland. Water was the third largest land cover class with 2.4%, followed by cropland (1.2%) and shrubland (0.4%), with 89% overall accuracy. Most of the forest changes were driven by pasture and cropland conversion, and there are signs that climate change is the primary driver of the loss of aquatic ecosystems. Existing carbon emission models disregard the types of land cover changes presented in the studies. The twenty first century requires a more encompassing and integrated approach to monitoring anthropogenic and climate changes in the Amazon biome for better mitigation, adaptation, and conservation policies.

Exchange means change: An unsupervised single-temporal change detection framework based on intra- and inter-image patch exchange

Change detection is a critical task in studying the dynamics of ecosystems and human activities using multi-temporal remote sensing images. While deep learning has shown promising results in change detection tasks, it requires a large number of labeled and paired multi-temporal images to achieve high performance. Pairing and annotating large-scale multi-temporal remote sensing images is both expensive and time-consuming. To make deep learning-based change detection techniques more practical and cost-effective, we propose an unsupervised single-temporal change detection framework based on intra- and inter-image patch exchange (I3PE). The I3PE framework allows for training deep change detectors on unpaired and unlabeled single-temporal remote sensing images that are readily available in real-world applications. The I3PE framework comprises four steps: (1) intra-image patch exchange method is based on an object-based image analysis (OBIA) method and adaptive clustering algorithm, which generates pseudo-bi-temporal image pairs and corresponding change labels from single-temporal images by exchanging patches within the image; (2) inter-image patch exchange method can generate more types of land-cover changes by exchanging patches between images; (3) a simulation pipeline consisting of several image enhancement methods is proposed to simulate the radiometric difference between pre- and post-event images caused by different imaging conditions in real situations; (4) self-supervised learning based on pseudo-labels is applied to further improve the performance of the change detectors in both unsupervised and semi-supervised cases. Extensive experiments on two large-scale datasets covering Hong Kong, Shanghai, Hangzhou, and Chengdu, China, demonstrate that I3PE outperforms representative unsupervised approaches and achieves F1 value improvements of 10.65% and 6.99% to the state-of-the-art method. Moreover, I3PE can improve the performance of the change detector by 4.37% and 2.61% on F1 values in the case of semi-supervised settings. Additional experiments on a dataset covering a study area with 144 km2 in Wuhan, China, confirm the effectiveness of I3PE for practical land-cover change analysis tasks.

Local temperature responses to actual land cover changes present significant latitudinal variability and asymmetry

Land cover changes (LCCs) affect surface temperatures at local scale through biophysical processes. However, previous observation-based studies mainly focused on the potential effects of virtual afforestation/deforestation using the space-for-time assumption, while the actual effects of all types of realistic LCCs are underexplored. Here, we adopted the space-and-time scheme and utilized extensive high-resolution (1-km) satellite observations to perform the first such assessment. We showed that, from 2006 to 2015, the average temperature in the areas with LCCs increased by 0.08 K globally, but varied significantly across latitudes, ranging from −0.05 to 0.18 K. Cropland expansions dominated summertime cooling effects in the northern mid-latitudes, whereas forest-related LCCs caused warming effects elsewhere. These effects accounted for up to 44.6% of overall concurrent warming, suggesting that LCC influences cannot be ignored. In addition, we revealed obvious asymmetries in the actual effects, i.e., LCCs with warming effects occurred more frequently, with stronger intensities, than LCCs with cooling effects. Even for the mutual changes between two covers in the same region, warming LCCs generally had larger magnitudes than their cooling counterparts due to asymmetric changes in transition fractions and driving variables. These novel findings, derived from the assessment of actual LCCs, provide more realistic implications for land management and climate adaptation policies.

Exploring Land-Cover Types and Their Changes in the Open-Pit Mining Area of Ordos City Using Sentinel-2 Imagery

Exploring the land-cover types and their changes in open-pit mining areas is of great significance to the ecological restoration of Ordos City and its sustainable development. Therefore, in this study, the temporal features, spectral features, and the derived features from intra-annual images combined with the random forest method were used to determine the land-cover types and their changes in the open-pit mining area of Ordos City in 2019 and 2022. The results show that the land-cover types in the open-pit mining area of Ordos City are construction land, bare land, water, vegetation, and coal. The main land-cover types in the western open-pit mining area of Ordos City are different from those in the eastern open-pit mining area. The main land-cover type changes in the open-pit mining area from 2019 to 2022 are the conversion of bare land to vegetation and the conversion of coal to bare land, as well as the conversion of vegetation to bare land. This study provides the possibility of dynamic monitoring for the realization of green mine planning in Ordos City.

Image Segmentation of the Sudd Wetlands in South Sudan for Environmental Analytics by GRASS GIS Scripts

This paper presents the object detection algorithms GRASS GIS applied for Landsat 8-9 OLI/TIRS data. The study area includes the Sudd wetlands located in South Sudan. This study describes a programming method for the automated processing of satellite images for environmental analytics, applying the scripting algorithms of GRASS GIS. This study documents how the land cover changed and developed over time in South Sudan with varying climate and environmental settings, indicating the variations in landscape patterns. A set of modules was used to process satellite images by scripting language. It streamlines the geospatial processing tasks. The functionality of the modules of GRASS GIS to image processing is called within scripts as subprocesses which automate operations. The cutting-edge tools of GRASS GIS present a cost-effective solution to remote sensing data modelling and analysis. This is based on the discrimination of the spectral reflectance of pixels on the raster scenes. Scripting algorithms of remote sensing data processing based on the GRASS GIS syntax are run from the terminal, enabling to pass commands to the module. This ensures the automation and high speed of image processing. The algorithm challenge is that landscape patterns differ substantially, and there are nonlinear dynamics in land cover types due to environmental factors and climate effects. Time series analysis of several multispectral images demonstrated changes in land cover types over the study area of the Sudd, South Sudan affected by environmental degradation of landscapes. The map is generated for each Landsat image from 2015 to 2023 using 481 maximum-likelihood discriminant analysis approaches of classification. The methodology includes image segmentation by ‘i.segment’ module, image clustering and classification by ‘i.cluster’ and ‘i.maxlike’ modules, accuracy assessment by ‘r.kappa’ module, and computing NDVI and cartographic mapping implemented using GRASS GIS. The benefits of object detection techniques for image analysis are demonstrated with the reported effects of various threshold levels of segmentation. The segmentation was performed 371 times with 90% of the threshold and minsize = 5; the process was converged in 37 to 41 iterations. The following segments are defined for images: 4515 for 2015, 4813 for 2016, 4114 for 2017, 5090 for 2018, 6021 for 2019, 3187 for 2020, 2445 for 2022, and 5181 for 2023. The percent convergence is 98% for the processed images. Detecting variations in land cover patterns is possible using spaceborne datasets and advanced applications of scripting algorithms. The implications of cartographic approach for environmental landscape analysis are discussed. The algorithm for image processing is based on a set of GRASS GIS wrapper functions for automated image classification.

Land Use Land Cover (LULC) Dynamics by CA-ANN and CA-Markov Model Approaches: A Case Study of Ranipet Town, India

The present study analyzed the spatio-temporal variations in the Land Use Land Cover types within Ranipet Municipal town in Ranipet District, Tamil Nadu State, India, using two different platforms (QGIS and IDRISI Selva v.17.0). The possible parameters driven the net changes in the Land Use Land Cover (LULC) types were also incorporated for the analysis. Results revealed the positive net changes in the built-up area are about 26.8%, and combined other classes like vegetation, barren land, and water bodies have net negative changes during 1997-2019. Particularly barren land was found to have a reduction of 17.4% due to the massive industrialization in the study area. Further, the LULC maps were used for future prediction (2029) using the dynamic models of CA-ANN (Cellular Automata and Artificial Neural Network) and CA-Markov. Predicted maps yielded a kappa index of 81.6% and 82.6% for CA-ANN and CA-Markov, representing their respective accuracy levels. The CA-Markov model is extended for determining the probable long-term changes for 2080 in LULC with a kappa index of 76.2%. Compared to the CA-ANN model using the QGIS platform, CA-Markov provided better analysis, particularly from one cell to the other. According to the survey and the ground truth in the locality, industrialization and occupational shift were the most influential drivers of LULC dynamics. Moreover, the results of this study assist the stakeholders in the decision-making process for future sustainable land use management.

Spatial enhanced spatiotemporal reflectance fusion model for heterogeneous regions with land cover change

Numerous spatiotemporal fusion models have been developed to fuse dense time-series data with a high spatial resolution for monitoring land surface dynamics. Nonetheless, enhancing spatial details of fused images, eliminating the obvious ‘plaque’ phenomenon and image blurring in fused images, and developing relatively simple and 1 easy-to-implement algorithms remain a challenge for spatiotemporal fusion algorithms. Therefore, this paper presents a newly proposed spatial enhanced spatiotemporal reflectance fusion model (SE-STRFM) for image fusions in heterogeneous regions with land cover change. The SE-STRFM model predicts temporal changes of reflectance in sub-pixel details based on the spectral unmixing theory, and allocates reflectance changes caused by abrupt land cover change in fine-resolution images with a relatively simple algorithm and easy implementation. SE-STRFM only needs one pair of input data, comprising one fine-resolution image and one coarse-resolution image, to achieve high-precision reflectance prediction with spatial details. To verify the reliability and applicability of the SE-STRFM, we use Landsat image and simulated MODIS-like image to fuse high spatial and temporal resolution images and select two study areas with heterogeneous landscape and land cover type change for fusion experiments and accuracy evaluation. The results show that the images fused by SE-STRFM have clearer spatial details and a more accurate spectral distribution compared with those fused by the most widely used STARFM, ESTARFM and FSDAF. In two study areas with heterogeneous landscape and land cover type change, compared with STARFM, ESTARFM and FSDAF, the RMSE of SE-STRFM is 10.52%, 28.39% and 6.58% lower on average, respectively; r is 3.67%, 10.33% and 1.65% higher on average, respectively; AAD is 9.05%, 24.58% and 7.29% lower on average, respectively; and SSIM is 3.16%, 10.16% and 1.92% higher on average, respectively. SE-STRFM can accurately capture temporal changes with spatial details and effectively predict abrupt land-cover changes.

Nonparametric assessment of mangrove ecosystem in the context of coastal resilience in Ghana.

Cloud cover effects make it difficult to evaluate the mangrove ecosystem in tropical locations using solely optical satellite data. Therefore, it is essential to conduct a more precise evaluation using data from several sources and appropriate models in order to manage the mangrove ecosystem as effectively as feasible. In this study, the status of the mangrove ecosystem and its potential contribution to coastal resilience were evaluated using the Google Earth Engine (GEE) and the InVEST model. The GEE was used to map changes in mangrove and other land cover types for the years 2009 and 2019 by integrating both optical and radar data. The quantity allocation disagreement index (QADI) was used to assess the classification accuracy. Mangrove height and aboveground biomass density were estimated using GEE by extracting their values from radar image clipped with a digital elevation model and mangrove vector file. A universal allometric equation that relates canopy height to aboveground biomass was applied. The InVEST model was used to calculate a hazard index of every 250 m of the shoreline with and without mangrove ecosystem. Our result showed that about 16.9% and 21% of mangrove and other vegetation cover were lost between 2009 and 2019. However, water body and bare land/built-up areas increased by 7% and 45%, respectively. The overall accuracy of 2009 and 2019 classifications was 99.6% (QADI = 0.00794) and 99.1% (QADI = 0.00529), respectively. Mangrove height and aboveground biomass generally decreased from 12.7 to 6.3 m and from 105 to 88 Mg/ha on average. The vulnerability index showed that 23%, 51% and 26% of the coastal segment in the presence of mangrove fall under very low/low, moderate and high risks, respectively. Whereas in the absence of mangrove, 8%, 38%, 39% and 15% fall under low, moderate, high and very high-risk zones, respectively. This study will among other things help the stakeholders in coastal management and marine spatial planning to identify the need to focus on conservation practices.

Natural revegetation has dominated annual runoff reduction since the Grain for Green Program began in the Jing River Basin, Northwest China

The Grain for Green Program (GFGP) has successfully increased the vegetation cover in northern China over the last two decades through large-scale natural and artificial revegetation approaches. Unfortunately, an obvious runoff reduction has been observed in many basins, especially on the semiarid Loess Plateau. Past studies generally attributed this runoff reduction to the artificial revegetation of the GFGP, i.e., the land cover type change from cropland to forest, since there was no significant annual precipitation decrease. Such cognition has led to widespread concern about the hydrological effects of the GFGP. In fact, in addition to artificial revegetation, natural revegetation relies on natural processes of vegetation succession without land cover type changes directed by humans. Therefore, it is necessary to separate and quantify the contributions of natural and artificial revegetation to runoff reduction to assess the GFGP and optimize revegetation in the future. In this study, the contributions of natural and artificial revegetation to annual runoff change after the implementation of the GFGP were quantified in fifteen subbasins of the Jing River Basin in the central Loess Plateau. The mean annual runoff of the Jing River Basin decreased by 11.8 mm after the GFGP, although the climate (precipitation and potential evapotranspiration) inversely increased the mean annual runoff by 6.6 mm. This is due to that the direct effect of climate change was much less than the ecohydrological effect of revegetation on runoff reduction, i.e., the revegetation caused the mean annual runoff reduction of 18.4 mm. Natural revegetation (50.5% of basin area) was the dominant reason for runoff reduction rather than artificial revegetation (9% of basin area). The natural revegetated area with vegetation quality improvement, i.e., an NDVI increase without land cover type change, contributed to a runoff reduction of 15.5 mm, accounting for 131.1% of the total runoff reduction after the GFGP, and the grassland of natural revegetation was the main vegetation type, with runoff reductions of 9.8 mm. However, artificial revegetation by area increase and quality improvement, i.e., NDVI increase, contributed to a runoff reduction of 8.4 mm, accounting for 49.6% of the total runoff reduction. These results demonstrated that the GFGP needs to be properly adjusted, i.e., natural revegetated areas should be opened in a timely manner and properly utilized, and improving vegetation quality improvement rather than increasing vegetation area would be a priority management measure in artificial revegetated areas.

Evaluating land restoration based on the land cover in the Horqin Sandy Land, China.

Land degradation is a severe ecological environmental issue in arid and semiarid areas. Evaluating land degradation exactly is essential for maintaining the security of the ecological environment. This study evaluated land restoration in terms of land cover changes in the Horqin Sandy Land from 2000 to 2018 and analyzed the related influencing factors. The results showed that land restoration and land degradation accounted for 37.55% and 4.47% of the total area, respectively. Land restoration has improved substantially, and desertification control has achieved remarkable effects. NPP trends should be analyzed in combination with land cover types. When the land cover has changed, the type of land cover change and the period need to be clarified before analyzing the corresponding NPP trend to depict the land productivity accurately. The vegetation NPP changes following land cover conversions were more essential than land cover change types. Changes in precipitation and temperature had positive effects on the growth of vegetation and land restoration. In general, human activities promoted land restoration, including grazing policies, cropland utilization activities, and ecological restoration projects. Current land restoration, however, essentially sacrifices the groundwater resources, which challenges the sustainability of land restoration. Appropriate land use strategies were proposed to promote sustainable land use, including preventing vegetation degradation following land cover conversions, improving grassland construction, and coordinating the usage of cropland and water resources. Such results are meaningful for promoting land restoration and realizing sustainable land development.

Four decades of urban land cover change in Philadelphia

Given ambitious tree canopy goals, land cover change analyses in cities are imperative. Urban tree canopy change analyses have been hindered by data with low categorical resolution (e.g., canopy vs. not canopy), over relatively short time horizons (5–10 years), representing only two points in time, and scarce linkages to other temporal datasets (e.g., historical socioeconomic data). In this study, using a land cover change data set with five cover classes spanning 40 years (1970–2010) for Philadelphia, PA (US), we asked: which types of land cover changes are most common, and how do those relate to and co-vary with socioeconomic change? Specifically, we tabulated land cover changes (i.e., transition sequences), applied multinomial logistic regression with socioeconomic variables as predictors of land cover change, and used cluster analyses to characterize neighborhood changes associated with land cover change. Land cover stability dominated the transition sequences: the four most common sequences were stable road (e.g. road-road-road-road-road), stable building, tree canopy, and herbaceous vegetation, collectively accounting for 62.57% of all sequences. Multinomial logistic regression identified that increases in homeownership, income, and educational attainment were associated with a higher probability of tree canopy persistence. Cluster analyses via Affinity Propagation showed that some Census tracts have similar land cover change trajectories, and yet different socioeconomic trends. These findings point towards opportunities to focus on tree preservation alongside the importance of establishing new tree canopy through planting. Our study demonstrates the mix of stability and dynamism in multidecadal urban land cover change, and the importance of connecting land cover changes with socioeconomic changes.

Study of Land Cover Change in the City with the Fastest Economic Growth in China (Hefei) from 2000 to 2020 Based on Google Earth Engine Platform

Hefei’s gross domestic product (GDP) growth rate ranks first among all cities in China, and it was the fastest-growing city in China from 2000 to 2020. The high-speed economic development inevitably led to rapid changes in land cover types, e.g., an increment in artificial features (built-up) and decrement in natural features (vegetation). However, (1) many previous studies focus on the land cover change in metropolis or at the global scale, yet few focus on underdeveloped but fast-growing cities; (2) land cover studies mainly focus on global variations, yet seldom on local characteristics. Thus, it is of great significance to monitor the land cover change for the city with the fastest economic growth in China based on the long time-series satellite images from both global and local perspectives. In this study, with support from huge amounts of data (including 719 Landsat TM/ETM+/OLI satellite images, land surface temperature, nighttime satellite images, DEM, multiple land cover products, and various auxiliary data), processing and parallel computing abilities of the GEE platform, classification maps of land cover in Hefei from 2000 to 2020 are produced based on a random forest machine learning method, and the spatio-temporal variations and driving factors are analyzed from both global and local viewpoints. The results show that: (1) the classification accuracy is excellent; the average overall accuracy is 93% and the Kappa coefficient is 0.88; (2) the general spatio-temporal variations in land cover in Hefei from 2000 to 2020 are obvious; the built-up area expanded from 419.72 km2 to 1530.20 km2, with a total growth rate of 264.58%. With the expansion of the built-up area, the vegetation coverage decreased by 16.61% (1652.56 km2); (3) the land surface temperature shows an increment trend in the new town yet a decrement trend in the old town due to the change in vegetation coverage and the decentration of administration centers; further analysis shows that the population and the social economy are two driving factors for land cover changes. It is worth noting that both the area and coverage of vegetation in the old town and water body area in Hefei increased significantly, although the fast urbanization inevitably caused a decrement in vegetation and water area in the whole city, indicating both the high-speed economic development and improvement in green surfaces simultaneously experienced in Hefei from 2000 to 2020.