Land Use Datasets Research Articles

Influences of wind speed, sky conditions, land use and land cover characteristics on the magnitude of the urban heat island in Seoul: An exploratory analysis

Prevailing weather conditions and urban morphology are among the fundamental drivers of the radiative and turbulent exchange processes that inherently result in an urban heat island (UHI). The influence of such drivers varies with temporal changes and must be estimated using recent and sufficiently large meteorological and land-use datasets. We used the most recent in-situ temperature observations collected from a spatially extensive network of 54 automatic weather stations (AWS) gathered over a period of nine years to quantify the influence of wind speed, cloud coverage and land use characteristics on the magnitude of UHI in Seoul city. Through an analysis of variance and combined clustering techniques, we found increased UHI intensities (UHII) under low wind speeds, clear skies and densely built areas. Changes of 0.5 m/s in wind speeds and 1 octa in cloud coverage corresponded to 0.20 °C and 0.24 °C reductions in UHII, respectively. Also, statistically significant differences in peak diurnal UHII values of 1.2 °C were estimated between densely built and sparsely built areas. The obtained results shed light on the factors likely to influence UHI development in Seoul city, and fuel scientific discourse on the development of sustainable cities and effective policies for the management of the built environment.

The Expansion Mechanism of Rural Residential Land and Implications for Sustainable Regional Development: Evidence from the Baota District in China’s Loess Plateau

Rural residential land is the main space of a farmer’s life, rural culture, and social relations. Prior research of rural residential land has focused more on its evolvement in plain and traditional agricultural areas. Yet, there is no clear picture of rural residential land expansion, especially in ecologically fragile areas. This study analyzed the characteristics of rural residential land expansion based on 30 m spatial resolution land-use datasets of the Baota District of Yan’an City, Shannxi Province, and further explored the influencing factors and mechanisms of rural residential land expansion through binary logistic regression (BLR) modeling. Our findings indicated that the area of rural residential land in the Baota District increased by 116.16% during 1990–2015. More than 75% of the residential land expansion came from the occupation of cropland. Moreover, rural residential land expansion was heterogeneous in the rural regional system. The expansion scale, speed, and mode diversity of rural residential land decreased with the increased distance to urban built-up areas. Geographical conditions and resource endowments are the primary internal driving factors; urbanization and policy implementation are two major external driving forces. The authors suggest that the realization of regional sustainable development in ecologically fragile areas should strengthen urban–rural integration, focus on constructing central towns, and ensure ecological protection measures.

Exploring the long-term vegetation dynamics of different ecological zones in the farming-pastoral ecotone in northern China.

The vegetation in the farming-pastoral ecotone in northern China is influenced by both natural and anthropogenic factors and has undergone drastic changes in the past decades. The farming-pastoral ecotone is the transition zone from agriculture to animal husbandry. The ecological environment of this ecotone is complex and fragile. Most researches have primarily focused on the entire farming-pastoral ecotone, seldomly considering the differences between different ecological zones characterized by soil, climate, and biome conditions. Based on the long time series of leaf area index (LAI) data, meteorological data, and land-use dataset, this study analyzed LAI variation trends, the correlations between LAI and climate factors, and the impact of land-use type change on vegetation in the farming-pastoral ecotone in northern China. Moreover, this paper makes a full study of the changes of the whole study area from the perspective of the differences between different ecological zones. The results showed that over 36years, areas with vegetation improvements were considerably larger than those with degradations. However, there were still 49.56% of the total area showing no significant vegetation change. There are differences in vegetation change and response to climate between the forest ecological zones and the grassland ecological zones. The vegetation improvement trends of the forest ecological zones were larger and more sensitive to temperature, while the vegetation improvements of the grassland ecological zones were relatively small, and were more sensitive to precipitation. Human activities promote LAI changes in areas close to the forest ecological zones. The change of land use indicates that the decrease of the overall natural vegetation area has not resulted in decreasing LAI. And there is a growing trend of woodland area in the grassland ecological zones. The study provides a theoretical basis for the management of the environment and vegetation in the farming-pastoral ecotone in northern China.

Land use classification of remote sensing images based on convolution neural network

In order to further improve the accuracy of land use classification, this paper uses UC Merced land use data set to fine-tune the parameters of CaffeNet, VGG-S, and VGG-F CNN models. Then, the fine-tuned network is used as the feature extractor, and the extracted full connection layer output features are cascaded as the final expression of the image. Finally, the cascaded features are input into the mcODM classifier to obtain the classification results. The results showed that the overall classification accuracy of the multi-structure CNN feature cascade method in UC Merced landuse dataset reached 97.55%, indicating an improvement between 2 and 5% compared with the single CNN model, and the classification accuracy after fine-tuning was improved in the range of 3–5%. In conclusion, this method can effectively improve the expression of features in scene level classification and improve classification performance.

A Dual-Model Architecture with Grouping-Attention-Fusion for Remote Sensing Scene Classification

Remote sensing images contain complex backgrounds and multi-scale objects, which pose a challenging task for scene classification. The performance is highly dependent on the capacity of the scene representation as well as the discriminability of the classifier. Although multiple models possess better properties than a single model on these aspects, the fusion strategy for these models is a key component to maximize the final accuracy. In this paper, we construct a novel dual-model architecture with a grouping-attention-fusion strategy to improve the performance of scene classification. Specifically, the model employs two different convolutional neural networks (CNNs) for feature extraction, where the grouping-attention-fusion strategy is used to fuse the features of the CNNs in a fine and multi-scale manner. In this way, the resultant feature representation of the scene is enhanced. Moreover, to address the issue of similar appearances between different scenes, we develop a loss function which encourages small intra-class diversities and large inter-class distances. Extensive experiments are conducted on four scene classification datasets include the UCM land-use dataset, the WHU-RS19 dataset, the AID dataset, and the OPTIMAL-31 dataset. The experimental results demonstrate the superiority of the proposed method in comparison with the state-of-the-arts.

Drivers of distributions and niches of North American cold‐adapted amphibians: evaluating both climate and land use

Species distribution estimates are often used to understand the niche of a species; however, these are often based solely on climatic predictors. When the influences of biotic factors are ignored, erroneous inferences about range and niche may be made. We aimed to integrate climate data with a unique set of available land cover and land use data for the six cold-adapted amphibians of North America (Ambystoma macrodactylum, Anaxyrus hemiophrys, Anaxyrus boreas, Pseudacris maculata, Rana sylvatica, Rana luteiventris) to determine the relative importance of climate and non-climate drivers through the use of ecological niche models for present-day range estimates. We compared climate-only, land use-only, and combination models of climate and land use, derived from two different model selection techniques, to determine which was most likely to drive current distributions of cold-adapted amphibian species. Land use layers included land cover type, human population, vegetation type, ecoregion, and the overall human footprint. The most supported models included both climate and land use, with climate and human footprint variables having the highest permutation importance and percent contribution. Models that incorporated climate and land use data performed best as measured with AIC and AUC, although qualitatively most underestimated the northern range edge, implying potential sampling bias or locations of reduced habitat quality for these species in the northern area of the ranges. There were small differences in overall combination models dependent on the method of model selection. The overall effect sizes of landscape factors within the combination models were small except for one landscape feature: human footprint, which incorporated multiple aspects of anthropogenic change on the landscape, including human population density, travel access, and agricultural impact. This aspect of the landscape was just as important as climate, and counter to what we expected, the association was mostly positive, with a negative response only occurring at very high levels. This highlights the importance of moving beyond climate only species range estimates as land cover, specifically human impact, may be driving the patterns of species' ranges.

Source Attributions of Radiative Forcing by Regions, Sectors, and Climate Forcers

Understanding the contributions of radiative forcings by different regions, sectors, or climate forcers can help policy-makers understand the relative importance of various sources in terms of meeting the Paris Agreement temperature targets. Here, we used the latest historical and future emissions data for a full suite of climate forcers as well as land-use datasets and applied a normalized marginal approach to quantify the forcing contributions of regions, sectors and forcing agents towards the 2°C and 1.5°C targets. We showed that developing regions, such as China, India, the Middle East and North Africa, sub-Saharan Africa and other areas in Asia, and certain sectors, such as housing and transport, yielded larger forcings in 2100 than at present under the 2°C and 1.5°C scenarios. Our results illustrated the importance of negative CO2 emissions, which contributed - 0.93 ± 0.56 Wm-2 and - 0.52 ± 0.32 Wm-2 to the 2°C and 1.5°C targets, respectively. Less negative forcings or more positive forcings were found for the land-use albedo for the 2°C and 1.5°C scenarios than those reported by earlier studies. Finally, we found that the 2°C and 1.5°C scenarios gave similar patterns of attributed forcings from regions, sectors, and climate forcers at the end of this century.

Simulated Atmospheric Response to Four Projected Land-Use Land-Cover Change Scenarios for 2050 in the North-Central United States

AbstractLand-use land-cover change (LULCC) has become an important topic of research for the central United States because of the extensive conversion of the natural prairie into agricultural land, especially in the northern Great Plains. As a result, shifts in the natural climate (minimum/maximum temperature, precipitation, etc.) across the north-central United States have been observed, as noted within the Fourth National Climate Assessment (NCA4) report. Thus, it is necessary to understand how further LULCC will affect the near-surface atmosphere, the lower troposphere, and the planetary boundary layer (PBL) atmosphere over this region. The goal of this work was to investigate the utility of a new future land-use land-cover (LULC) dataset within the Weather Research and Forecasting (WRF) modeling system. The present study utilizes a modeled future land-use dataset developed by the Forecasting Scenarios of Land-Use Change (FORE-SCE) model to investigate the influence of future (2050) land use on a simulated PBL development within the WRF Model. Three primary areas of LULCC were identified within the FORE-SCE future LULC dataset across Nebraska and South Dakota. Variations in LULC between the 2005 LULC control simulation and four FORE-SCE simulations affected near-surface temperature (0.5°–1°C) and specific humidity (0.3–0.5 g kg−1). The differences noted in the temperature and moisture fields affected the development of the simulated PBL, leading to variations in PBL height and convective available potential energy. Overall, utilizing the FORE-SCE dataset within WRF produced notable differences relative to the control simulation over areas of LULCC represented in the FORE-SCE dataset.

The varying driving forces of urban land expansion in China: Insights from a spatial-temporal analysis

The impacts of socioeconomic development on urban land expansion in China vary across space and time; however, comprehensive investigation of this issue remains scarce in the existing literature. This study used a geographically and temporally weighted regression model (GTWR) to examine the spatiotemporally heterogeneous impacts of socioeconomic factors on urban land expansion in China using a newly available annual urban land-use dataset from 2000 to 2015. We found that although the eastern region has maintained its leading role (53.79%) in terms of urban expansion, the share of the central (20.34%) and western (16.13%) regions is gradually increasing. Cities with a higher administrative status tended to expand more rapidly; however, increasingly expansion has also taken place in the prefecture-level cities in recent years. We further found that Gross domestic product (GDP) growth, population density, and capital investment positively contributed to the expansion, although the directions and strengths of association between these factors and urban expansion varied across space and time. Industrial structure and foreign direct investment (FDI) showed a similar variation change trend, with the number of cities evidencing a negative relationship rapidly expanding and increasingly being seen not just in northwest China but also in the southeast during the study period. We also found that the correlation between public finance expenditure and urban expansion presented significant north-south differentiation. It is worth noting that governmental behavior plays a significant role in driving urban land expansion. Our empirical study confirmed the spatiotemporal heterogeneous effects of socioeconomic factors on urban expansion in China, providing useful insights for city governments and urban planners.

Global land use for 2015\u20132100 at 0.05\xb0 resolution under diverse socioeconomic and climate scenarios

Global future land use (LU) is an important input for Earth system models for projecting Earth system dynamics and is critical for many modeling studies on future global change. Here we generated a new global gridded LU dataset using the Global Change Analysis Model (GCAM) and a land use spatial downscaling model, named Demeter, under the five Shared Socioeconomic Pathways (SSPs) and four Representative Concentration Pathways (RCPs) scenarios. Compared to existing similar datasets, the presented dataset has a higher spatial resolution (0.05° × 0.05°) and spreads under a more comprehensive set of SSP-RCP scenarios (in total 15 scenarios), and considers uncertainties from the forcing climates. We compared our dataset with the Land Use Harmonization version 2 (LUH2) dataset and found our results are in general spatially consistent with LUH2. The presented dataset will be useful for global Earth system modeling studies, especially for the analysis of the impacts of land use and land cover change and socioeconomics, as well as the characterizing the uncertainties associated with these impacts.

Industrial land expansion in rural China threatens environmental securities

China’s rural industrialization has been a major driver for its rapid economic growth during the recent decades, but its myriad environmental risks are yet to be fully understood. Based on a comprehensive national land-use data set, our study shows that the area of China’s rural industrial land (RIL) quadrupled during 1990–2015, reaching 39338 km2 in 2015, comparable to urbanization in magnitude but with a much greater degree of landscape fragmentation which implies stronger ecological and environmental impacts. About 91% of the protected areas in the central China were within 50 km from rural industrial land, thus exposed to industrial disturbances. Accelerated rural industrial land expansion, particularly in regions under high geo-hazard risks, led to dramatically increased environmental risks, threatening the safety and health of both rural industrial workers and residents. Moreover, negative effects from rural industrial land expansion could partially offset the crop production growth in recent decades. The underprivileged rural population in the west bears a disproportionally large share of the increased environmental risks. China urgently needs to design and implement sustainable policies to restrict and reshape its rural industrialization. This study aims to inspire policy makers and researchers to rethink the current model of industrial expansion and improve rural industrial land planning, which is important for achieving the sustainable development goals of China.

A NOVEL SELF-TAUGHT LEARNING FRAMEWORK USING SPATIAL PYRAMID MATCHING FOR SCENE CLASSIFICATION

Abstract. Remote sensing earth observation images have a wide range of applications in areas like urban planning, agriculture, environment monitoring, etc. While the industrial world benefits from availability of high resolution earth observation images since recent years, interpreting such images has become more challenging than ever. Among many machine learning based methods that have worked out successfully in remote sensing scene classification, spatial pyramid matching using sparse coding (ScSPM) is a classical model that has achieved promising classification accuracy on many benchmark data sets. ScSPM is a three-stage algorithm, composed of dictionary learning, sparse representation and classification. It is generally believed that in the dictionary learning stage, although unsupervised, one should use the same data set as classification stage to get good results. However, recent studies in transfer learning suggest that it might be a better strategy to train the dictionary on a larger data set different from the one to classify.In our work, we propose an algorithm that combines ScSPM with self-taught learning, a transfer learning framework that trains a dictionary on an unlabeled data set and uses it for multiple classification tasks. In the experiments, we learn the dictionary on Caltech-101 data set, and classify two remote sensing scene image data sets: UC Merced LandUse data set and Changping data set. Experimental results show that the classification accuracy of proposed method is compatible to that of ScSPM. Our work thus provides a new way to reduce resource cost in learning a remote sensing scene image classifier.

Ensemble model with cascade attention mechanism for high-resolution remote sensing image scene classification.

Scene classification of high-resolution remote sensing images is a fundamental task of earth observation. And numerous methods have been proposed to achieve this. However, these models are inadequate as the number of labelled training data limits them. Most of the existing methods entirely rely on global information, while regions with class-specific ground objects determine the categories of high-resolution remote sensing images. An ensemble model with a cascade attention mechanism, which consists of two kinds of the convolutional neural network, is proposed to address these issues. To improve the generality of the feature extractor, each branch is trained on different large datasets to enrich the prior knowledge. Moreover, to force the model to focus on the most class-specific region in each high-resolution remote sensing image, a cascade attention mechanism is proposed to combine the branches and capture the most discriminative information. By experiments on four benchmark datasets, OPTIMAL-31, UC Merced Land-Use Dataset, Aerial Image Dataset and NWPU-RESISC45, the proposed end-to-end model cascade attention-based double branches model in this paper achieves state-of-the-art performance on each benchmark dataset.

Urban heat island circulations over the Beijing-Tianjin region under calm and fair conditions

The Beijing-Tianjin-Hebei region has experienced severe urban heat island (UHI) effects in recent decades. Using the Weather Research and Forecasting (WRF) model and the new World Urban Database and Access Portal Tools (WUDAPT) land-use dataset, the urban heat island circulations (UHICs) and other local atmospheric circulations over Beijing and Tianjin were studied during a severe UHI event in 2012. It was shown that in the daytime, various UHICs over Beijing and Tianjin developed separately under a southerly background wind. Two of these UHICs formed over Beijing due to multiple hot regions, involving a chain flow mechanism in which the outflows from one UHIC over nearby mountains were connected to the inflows to the other UHICs in a west-to-east direction. At night, more robust UHICs occurred and a chain flow mechanism again formed over the Beijing-Tianjin region, as the upper-level outflows from the UHIC over Tianjin were connected to the inflows of the UHIC over Beijing. Moreover, the rotary air movements formed by the flows over the mountain and the down-slope winds formed a convergent region in the northwest of Beijing. In particular, sensitivity experiments replacing either Beijing or Tianjin with cropland grids revealed that the presence of either of those urban areas modified the penetration of the sea-breeze circulation. The city shape was found to affect the UHIC over Beijing at night, as the convergent zones were distributed diagonally and the wind speeds were higher in the diagonal direction.

Residual Dense Network Based on Channel-Spatial Attention for the Scene Classification of a High-Resolution Remote Sensing Image

The scene classification of a remote sensing image has been widely used in various fields as an important task of understanding the content of a remote sensing image. Specially, a high-resolution remote sensing scene contains rich information and complex content. Considering that the scene content in a remote sensing image is very tight to the spatial relationship characteristics, how to design an effective feature extraction network directly decides the quality of classification by fully mining the spatial information in a high-resolution remote sensing image. In recent years, convolutional neural networks (CNNs) have achieved excellent performance in remote sensing image classification, especially the residual dense network (RDN) as one of the representative networks of CNN, which shows a stronger feature learning ability as it fully utilizes all the convolutional layer information. Therefore, we design an RDN based on channel-spatial attention for scene classification of a high-resolution remote sensing image. First, multi-layer convolutional features are fused with residual dense blocks. Then, a channel-spatial attention module is added to obtain more effective feature representation. Finally, softmax classifier is applied to classify the scene after adopting data augmentation strategy for meeting the training requirements of the network parameters. Five experiments are conducted on the UC Merced Land-Use Dataset (UCM) and Aerial Image Dataset (AID), and the competitive results demonstrate that our method can extract more effective features and is more conducive to classifying a scene.

Assessment of a Coastal Offshore Wind Climate by Means of Mesoscale Model Simulations Considering High-Resolution Land Use and Sea Surface Temperature Data Sets

In this study, offshore wind climate assessments are carried out by using mesoscale model Weather Research and Forecasting (WRF) and validated by measurement at a demonstration site located 3.1 km offshore of Choshi. An optimal nudging method is investigated by using offshore and meteorological observations. The land-use datasets are then created from a higher-resolution land-use data by using a maximum area sampling scheme according to the horizontal resolution of the mesoscale model. Finally, the sea surface temperature datasets are corrected by observation data. It is found that the relative error of annual wind speed is reduced from 7.3% to 2.2% and the correlation coefficient between predicted and measured wind speed is improved from 0.80 to 0.84 by considering the effects of land-use and sea surface temperature.

An improved unsupervised representation learning generative adversarial network for remote sensing image scene classification

ABSTRACTUnsupervised representation learning plays an important role in remote sensing image applications. Generative adversarial network (GAN) is the most popular unsupervised learning method in recent years. However, due to poor data augmentation, many GAN-based methods are often difficult to carry out. In this paper, we propose an improved unsupervised representation learning model called multi-layer feature fusion Wasserstein GAN (MF-WGANs) which considers extracting the feature information for remote sensing scene classification from unlabelled samples. First, we introduced a multi-feature fusion layer behind the discriminator to extract the high-level and mid-level feature information. Second, we combined the loss of multi-feature fusion layer and WGAN-GP to generate more stable and high-quality remote sensing images with a resolution of 256 × 256. Finally, the multi-layer perceptron classifier (MLP-classifier) is used to classify the features extracted from the multi-feature fusion layer and evaluated with the UC Merced Land-Use, AID and NWPU-RESISC45 data sets. Experiments show that MF-WGANs has richer data augmentation and better classification performance than other unsupervised representation learning classification models (e.g., MARTA GANs).

A New Land-Use Dataset for the Weather Research and Forecasting (WRF) Model

The USGS (United States Geological Survey) land-use data used in the Weather Research and Forecasting (WRF) model have become obsolete as they are unable to accurately represent actual underlying surface features. Therefore, this study developed a new multi-satellite remote-sensing land-use dataset based on the latest GLC2015 (Global Land Cover, 2015) land-use data, which had 300 m spatial resolution. The new data were used to update the default USGS land-use dataset. Based on observational data from national meteorological observing stations in Xinjiang, northwest China, a comparison of the old USGS and new GLC2015 land-use datasets in the WRF model was performed for July 2018, where the simulated variables included the sensible heat flux (SHF), latent heat flux (LHF), surface skin temperature (Tsk), two-meter air temperature (T2), wind speed (Winds), specific humidity (Q2) and relative humidity (RH). The results indicated that there were significant differences between the two datasets. For example, our statistical verification results found via in situ observations made by the MET (model evaluation tools) illustrated that the bias of T2 decreased by 2.54%, the root mean square error (RMSE) decreased by 1.48%, the bias of Winds decreased by 10.46%, and the RMSE decreased by 6.77% when using the new dataset, and the new parameter values performed a net positive effect on land–atmosphere interactions. These results suggested that the GLC2015 land-use dataset developed in this study was useful in terms of improving the performance of the WRF model in the summer months.

Impacts of Anthropogenic Heat Flux and Urban Land-Use Change on Frontal Rainfall near Coastal Regions: A Case Study of a Rainstorm over the Pearl River Delta, South China

AbstractThis study investigated heavy frontal rainfall that occurred on 13–14 October 2011 over the Pearl River Delta (PRD) in China. The frontal rainstorm was simulated using the WRF-ARW Model (version 3.3), which included its urban canopy model. Although the model-simulated convection occurred 2 h early and the second precipitation peak was underestimated, the model represented the formation, development, and extinction of the frontal rainfall and captured the distribution of the peak value. In addition, the averaged value of 49.7 W m−2was taken as the anthropogenic heat flux (AHF) of the PRD, and two land-use datasets were adopted: one for 1992 and the other for 2011. The simulation revealed that AHF and urban land-use change (ULUC) increased the total rainfall over the PRD by 6.3% and 7.4% and increased the maximum hourly rainfall intensity by 24.6% and 21.2%, respectively. Furthermore, to elucidate the mechanism of AHF and ULUC influence, the rainstorm structure, low-level jet (LLJ), and CAPE of the rainfall event were analyzed. It was found that AHF and ULUC enhanced two strong southward LLJs located over the urban areas, which carried abundant water vapor to the PRD and generated additional upper-level CAPE. This not only sustained steady ascent of the air, but it also created conditions favorable for downward motion, resulting in large persistent convective clouds and heavy frontal rainfall.

Impact of land-use changes on the genesis and evolution of extreme rainfall event: a case study over Uttarakhand, India

This study is about the impact assessment of different land-use data sets on the simulation of an Extreme Rainfall Event (ERE) which is one of the unusually rare events that occurred between 14th to 18th of June 2013 over Uttarakhand in India. In this work, high-resolution (2-km), time ensemble simulations are carried out using Weather Research and Forecasting model (WRFV3.5) with a 3-nest configuration. The sensitivity analysis of the model in simulating rainfall to different land-use data i.e. USGS-24 category (1992–93), ISRO (2004–05) and (2012–13) are carried out. Comparison of simulated rainfall which is averaged over the study region with that of IMD observed station data (averaged over 23 stations) showed that the simulations based on ISRO land-use data are comparatively more accurate with lesser simulation error when compared to simulations with USGS land-use data. The percentage of error in rainfall for the 3 simulations was found to be 24% (USGS), 9.5% (ISRO-2005) and 10% (ISRO-2013) with respect to the IMD observation. During the initial stage, the results have shown maximum convergence and vorticity with a strong updraft. The strong updraft, however, persisted throughout the simulation period. The increasing tendency of positive vorticity both in the simulation and observation suggests an intensification of cyclonic circulation in a vertical direction and hence creates instability in the boundary layer causing ERE over Uttarakhand. This study shows that ISRO land-use data is a relatively more realistic representation of the study region than the USGS data, and found to be useful in reducing the model error in the simulation of such rare events over this kind of mountainous region.