Remote Sensing Object Detection in the Deep Learning Era—A Review DOI Creative Commons
Shengxi Gui, Shuang Song, Rongjun Qin

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(2), P. 327 - 327

Published: Jan. 12, 2024

Given the large volume of remote sensing images collected daily, automatic object detection and segmentation have been a consistent need in Earth observation (EO). However, objects interest vary shape, size, appearance, reflecting properties. This is not only reflected by fact that these exhibit differences due to their geographical diversity but also appear differently from different sensors (optical radar) platforms (satellite, aerial, unmanned aerial vehicles (UAV)). Although there exists plethora methods area sensing, given very fast development prevalent deep learning methods, still lack recent updates for methods. In this paper, we aim provide an update informs researchers about close sibling era, instance segmentation. The integration will cover approaches data at scales modalities, such as optical, synthetic aperture radar (SAR) images, digital surface models (DSM). Specific emphasis be placed on addressing label limitations era. Further, survey examples applications benefited discuss future trends EO.

Language: Английский

Annual maps of global artificial impervious area (GAIA) between 1985 and 2018 DOI
Peng Gong, Xuecao Li, Jie Wang

et al.

Remote Sensing of Environment, Journal Year: 2019, Volume and Issue: 236, P. 111510 - 111510

Published: Nov. 19, 2019

Language: Английский

Citations

913
Mapping global urban boundaries from the global artificial impervious area (GAIA) data DOI Creative Commons
Xuecao Li, Peng Gong, Yuyu Zhou

et al.

Environmental Research Letters, Journal Year: 2020, Volume and Issue: 15(9), P. 094044 - 094044

Published: June 11, 2020

Abstract Urban boundaries, an essential property of cities, are widely used in many urban studies. However, extracting boundaries from satellite images is still a great challenge, especially at global scale and fine resolution. In this study, we developed automatic delineation framework to generate multi-temporal dataset (GUB) using 30 m artificial impervious area (GAIA) data. First, delineated initial boundary by filling inner non-urban areas each city. A kernel density estimation approach cellular-automata based growth modeling were jointly step. Second, improved the around fringe areas, morphological dilating eroding derived extent. We implemented on Google Earth Engine platform generated resolution seven representative years (i.e. 1990, 1995, 2000, 2005, 2010, 2015, 2018). Our extracted show good agreement with results nighttime light data human interpretation, they can well delineate extent cities when compared high-resolution images. The total 65 582 GUBs, which exceeds 1 km 2 , 809 664 2018. surface account for approximately 60% total. From 1990 2018, proportion increased 53% 60%, suggesting compact over past decades. found that United States has highest per capita more than 900 ) among top 10 most urbanized nations This provides physical be study impact urbanization food security, biodiversity, climate change, health. GUB accessed http://data.ess.tsinghua.edu.cn .

Language: Английский

Citations

507
Mapping essential urban land use categories in China (EULUC-China): preliminary results for 2018 DOI
Peng Gong, Бин Чэн, Xuecao Li

et al.

Science Bulletin, Journal Year: 2019, Volume and Issue: 65(3), P. 182 - 187

Published: Dec. 9, 2019

Language: Английский

Citations

437
Tracking Air Pollution in China: Near Real-Time PM2.5 Retrievals from Multisource Data Fusion DOI Creative Commons
Guannan Geng, Qingyang Xiao, Shigan Liu

et al.

Environmental Science & Technology, Journal Year: 2021, Volume and Issue: 55(17), P. 12106 - 12115

Published: Aug. 19, 2021

Air pollution has altered the Earth's radiation balance, disturbed ecosystem, and increased human morbidity mortality. Accordingly, a full-coverage high-resolution air pollutant data set with timely updates historical long-term records is essential to support both research environmental management. Here, for first time, we develop near real-time database known as Tracking Pollution in China (TAP, http://tapdata.org.cn/) that combines information from multiple sources, including ground observations, satellite aerosol optical depth (AOD), operational chemical transport model simulations, other ancillary such meteorological fields, land use data, population, elevation. Daily PM2.5 at spatial resolution of 10 km our product. The TAP estimated based on two-stage machine learning coupled synthetic minority oversampling technique tree-based gap-filling method. Our an averaged out-of-bag cross-validation R2 0.83 different years, which comparable those studies, but improves its performance high levels fills gaps missing AOD daily scale. full coverage allow us track day-to-day variations concentrations over manner. since 2000 will also policy assessments health impact studies. are publicly available through website sharing communities.

Language: Английский

Citations

361
A global record of annual terrestrial Human Footprint dataset from 2000 to 2018 DOI Creative Commons
Haowei Mu, Xuecao Li,

Yanan Wen

et al.

Scientific Data, Journal Year: 2022, Volume and Issue: 9(1)

Published: April 19, 2022

Human Footprint, the pressure imposed on eco-environment by changing ecological processes and natural landscapes, is raising worldwide concerns biodiversity conservation. Due to lack of spatiotemporally consistent datasets Footprint over a long temporal span, many relevant studies this topic have been limited. Here, we mapped annual dynamics global from 2000 2018 using eight variables that reflect different aspects human pressures. The accuracy assessment revealed good agreement between our results previously developed in years. We found more than two million km

Language: Английский

Citations

283
Forest expansion dominates China’s land carbon sink since 1980 DOI Creative Commons
Zhen Yu, Philippe Ciais, Shilong Piao

et al.

Nature Communications, Journal Year: 2022, Volume and Issue: 13(1)

Published: Sept. 13, 2022

Abstract Carbon budget accounting relies heavily on Food and Agriculture Organization land-use data reported by governments. Here we develop a new cover-change database for China, finding that differing historical survey methods biased China’s causing large errors in databases. Land ecosystem model simulations driven with the reveal strong carbon sink of 8.9 ± 0.8 Pg from 1980 to 2019 which was not captured data-based estimations due signals. The characterized rapid forest expansion 2019, contributed nearly 44% national terrestrial sink. In contrast, climate changes (22.3%), increasing nitrogen deposition (12.9%), rising dioxide (8.1%) are less important contributors. This indicates previous studies have greatly underestimated impact balance China. study underlines importance reliable databases global accounting.

Language: Английский

Citations

224
Urban and air pollution: a multi-city study of long-term effects of urban landscape patterns on air quality trends DOI Creative Commons
Lü Liang, Peng Gong

Scientific Reports, Journal Year: 2020, Volume and Issue: 10(1)

Published: Oct. 29, 2020

Abstract Most air pollution research has focused on assessing the urban landscape effects of pollutants in megacities, little is known about their associations small- to mid-sized cities. Considering that biggest growth projected occur these smaller-scale cities, this empirical study identifies key form determinants decadal-long fine particulate matter (PM 2.5 ) trends all 626 Chinese cities at county level and above. As first its kind, comprehensively examines quality different population sizes, development levels, spatial-autocorrelation positions. Results demonstrate evolution long-term PM level, but dominant factors shift over urbanization stages: area metrics play a role small-sized early stage, whereas aggregation determine such mostly For large exhibiting higher degree urbanization, spatial connectedness patches positively associated with increases. We suggest that, depending city’s developmental aspects should be emphasized achieve clean goals.

Language: Английский

Citations

219
Rebound in China’s coastal wetlands following conservation and restoration DOI
Xinxin Wang, Xiangming Xiao, Xiao Xu

et al.

Nature Sustainability, Journal Year: 2021, Volume and Issue: 4(12), P. 1076 - 1083

Published: Oct. 28, 2021

Language: Английский

Citations

206
Changes in spatial patterns of PM2.5 pollution in China 2000–2018: Impact of clean air policies DOI Creative Commons
Qingyang Xiao, Guannan Geng, Fengchao Liang

et al.

Environment International, Journal Year: 2020, Volume and Issue: 141, P. 105776 - 105776

Published: May 8, 2020

To improve air quality, China has been implementing strict clean policies since 2013. These not only substantially improved quality but may also modify the spatial distribution of pollution, urban emission sources were under stricter control and some moved to rural regions with lower improvement targets lacking monitoring. Here, we predicted satellite-based monthly PM2.5 concentrations during 2000-2018 at a 1-km resolution complete spatial-temporal coverage analyze changes in pattern pollution China. We found that concentration was higher than same city by an average 3.3 μg/m3 2000-2018. This urban-rural disparity significantly increased from 2.5 2000 peaked 2007 3.8 μg/m3, then it sharply declined 49% 2013-2018 implementation policies. shrinkage gap partly due 1.3 greater decrease level region town on average. observed cities started monitoring earlier experienced decreases difference, surrounding monitor showed far away 2013-2018. Additionally, modified relationship between per capita gross domestic product (GDP), leading GDP after Emissions suburban should be considered further

Language: Английский

Citations

197
Separating emission and meteorological contributions to long-term PM<sub>2.5</sub> trends over eastern China during 2000–2018 DOI Creative Commons
Qingyang Xiao, Yixuan Zheng, Guannan Geng

et al.

Atmospheric chemistry and physics, Journal Year: 2021, Volume and Issue: 21(12), P. 9475 - 9496

Published: June 23, 2021

Abstract. The contribution of meteorology and emissions to long-term PM2.5 trends is critical for air quality management but has not yet been fully analyzed. Here, we used the combination a machine learning model, statistical method, chemical transport model quantify meteorological impacts on pollution during 2000–2018. Specifically, first developed two-stage prediction with synthetic minority oversampling technique improve satellite-based estimates over highly polluted days, thus allowing us better characterize effects haze events. Then two methods examine PM2.5: generalized additive (GAM) driven by full-coverage daily retrievals Weather Research Forecasting/Community Multiscale Air Quality (WRF/CMAQ) modeling system. We found good agreements between GAM estimations CMAQ monthly scale (correlation coefficient 0.53–0.72). Both revealed dominant role emission changes in trend concentration China 2000–2018, notable influence from condition. interannual variabilities meteorology-associated were dominated fall winter conditions, when regional stagnant stable conditions more likely happen events frequently occurred. From 2000 2018, became unfavorable across North Plain central beneficial control southern part, e.g., Yangtze River Delta. meteorology-adjusted eastern (denoted East figures) peaked 2006 2011, mainly peaks primary gas precursors these years. Although trends, meteorology-driven anomalies also contributed −3.9 % 2.8 annual mean concentrations estimated GAM. contributions even higher regionally, −6.3 4.9 Beijing-Tianjin-Hebei region, −5.1 4.3 Fenwei Plain, −4.8 Delta, −25.6 12.3 Pearl Considering remarkable possible worsening northern part where severe population clustered, stricter clean actions are needed avoid future.

Language: Английский

Citations

175