Xinrong Yan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Xinrong Yan has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Juanle Wang
State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China
3 shared publications Dong Lu
China Waterborne Transport Research Institute
1 shared publicationFang Wu
China Waterborne Transport Research Institute
1 shared publication- Fang Wu
China Waterborne Transport Research Institute, Beijing 100088, China
1 shared publication - Guiping Li
China Waterborne Transport Research Institute, Beijing 100088, China
1 shared publication - Haibo Fei
China Waterborne Transport Research Institute, Beijing 100088, China
1 shared publication
Latest Publications
- Open Access
- 31 July 2026
- Published by Frontiers Media SA in Frontiers in Environmental Science
- Vol. 14, 1909612
A generalized deep learning framework for automated marine oil spill detection using multi-source SAR cross-sea datasets
Marine oil spill detection using Synthetic Aperture Radar (SAR) imagery remains challenging due to complex sea-surface scattering mechanisms and interference from look-alike phenomena, which limit the generalization capability of deep learning models across different marine environments. To address this challenge, this study develops a multi-source remote sensing deep learning framework for automated oil spill detection based on Sentinel-1 SAR imagery. The research focuses on the integrated application of two publicly available datasets—DARTIS and CSIRO—to enhance the model’s adaptability across various marine environments. The results indicate that: (1) the proposed multi-source dataset fusion strategy improves the cross-regional generalization capability of the model compared with single-dataset training strategies; (2) scene-level validation using 27 Sentinel-1 SAR scenes demonstrates that the proposed framework achieves reliable oil spill mapping with Precision, Recall and F1-score of 0.811, 0.956 and 0.878, respectively; (3) the automated monitoring framework developed in this study enables end-to-end processing from SAR image acquisition to oil spill distribution mapping, providing timely monitoring and alerting results. It supports a transition from traditional passive post-event interpretation to an active automated monitoring paradigm, with improved efficiency and timeliness in marine oil spill surveillance.
- 31 July 2026
- Published by Frontiers Media SA in Frontiers in Environmental Science
- Vol. 14, 1909612
Open AccessA generalized deep learning framework for automated marine oil spill detection using multi-source SAR cross-sea datasets
Marine oil spill detection using Synthetic Aperture Radar (SAR) imagery remains challenging due to complex sea-surface scattering mechanisms and interference from look-alike phenomena, which limit the generalization capability of deep learning models across different marine environments. To address this challenge, this study develops a multi-source remote sensing deep learning framework for automated oil spill detection based on Sentinel-1 SAR imagery. The research focuses on the integrated application of two publicly available datasets—DARTIS and CSIRO—to enhance the model’s adaptability across various marine environments. The results indicate that: (1) the proposed multi-source dataset fusion strategy improves the cross-regional generalization capability of the model compared with single-dataset training strategies; (2) scene-level validation using 27 Sentinel-1 SAR scenes demonstrates that the proposed framework achieves reliable oil spill mapping with Precision, Recall and F1-score of 0.811, 0.956 and 0.878, respectively; (3) the automated monitoring framework developed in this study enables end-to-end processing from SAR image acquisition to oil spill distribution mapping, providing timely monitoring and alerting results. It supports a transition from traditional passive post-event interpretation to an active automated monitoring paradigm, with improved efficiency and timeliness in marine oil spill surveillance.
- Open Access
- 27 May 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (11) , 1861
Spatial and Temporal Variation Characteristics of Air Pollutants in Coastal Areas of China: From Satellite Perspective
Under increasingly stringent global policies aimed at reducing emissions from shipping, the impact of maritime activities on air quality has garnered significant attention. However, the absence of comprehensive macro-evaluation methods and a limited understanding of regional-scale pollutant emissions introduce substantial uncertainties in assessing emission reduction effectiveness and identifying pollution sources. In this study, we utilized Sentinel-5P satellite data from 2019 to 2024 to examine the spatiotemporal characteristics of six air pollutants (SO2, NO2, HCHO, O3, CO, and CH4) in China’s coastal areas. We further investigated the correlation between ship density and pollutant concentrations and analyzed the distribution of pollutant concentrations in major coastal ports across China. The results indicate the following: (1) The concentrations of SO2, HCHO, and CH4 exhibited a continuous increasing trend, whereas NO2, CO, and O3 remained relatively stable or showed a slight decline. All six pollutants demonstrated obvious seasonal variations, with NO2 and HCHO following a double-peak pattern and O3, SO2, CH4, and CO exhibiting a single-peak pattern. (2) Pollutant concentrations were higher along the northern coast (Yellow Sea and Bohai Sea) and relatively lower in the South China Sea region. Specifically, NO2, SO2, and O3 were higher in the Bohai Sea region; HCHO and CO were more concentrated in the northern coastal area; and CH4 was elevated in the north and certain ports of the Yangtze River Delta. (3) Ship density displayed a significant positive correlation with NO2, SO2, HCHO, CO, and CH4, indicating that ship emissions are an important source of these pollutants. Although O3 is not directly emitted by ships, a positive correlation was observed in certain ship-dense areas, primarily due to photochemical reactions involving NO2 and volatile organic compounds (VOCs). (4) Higher concentrations of NO2, SO2, HCHO, CO, and CH4 were observed in northern ports (e.g., Tianjin Xingang, Qinhuangdao, Tangshan, and Dalian), whereas southern Chinese ports (e.g., Shenzhen, Xiamen, and Haikou) exhibited lower pollution levels. These findings provide a scientific foundation for coastal air pollution control and highlight the necessity of ship emission regulation and integrated multi-pollutant management.
- 27 May 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (11) , 1861
Open AccessSpatial and Temporal Variation Characteristics of Air Pollutants in Coastal Areas of China: From Satellite Perspective
Under increasingly stringent global policies aimed at reducing emissions from shipping, the impact of maritime activities on air quality has garnered significant attention. However, the absence of comprehensive macro-evaluation methods and a limited understanding of regional-scale pollutant emissions introduce substantial uncertainties in assessing emission reduction effectiveness and identifying pollution sources. In this study, we utilized Sentinel-5P satellite data from 2019 to 2024 to examine the spatiotemporal characteristics of six air pollutants (SO2, NO2, HCHO, O3, CO, and CH4) in China’s coastal areas. We further investigated the correlation between ship density and pollutant concentrations and analyzed the distribution of pollutant concentrations in major coastal ports across China. The results indicate the following: (1) The concentrations of SO2, HCHO, and CH4 exhibited a continuous increasing trend, whereas NO2, CO, and O3 remained relatively stable or showed a slight decline. All six pollutants demonstrated obvious seasonal variations, with NO2 and HCHO following a double-peak pattern and O3, SO2, CH4, and CO exhibiting a single-peak pattern. (2) Pollutant concentrations were higher along the northern coast (Yellow Sea and Bohai Sea) and relatively lower in the South China Sea region. Specifically, NO2, SO2, and O3 were higher in the Bohai Sea region; HCHO and CO were more concentrated in the northern coastal area; and CH4 was elevated in the north and certain ports of the Yangtze River Delta. (3) Ship density displayed a significant positive correlation with NO2, SO2, HCHO, CO, and CH4, indicating that ship emissions are an important source of these pollutants. Although O3 is not directly emitted by ships, a positive correlation was observed in certain ship-dense areas, primarily due to photochemical reactions involving NO2 and volatile organic compounds (VOCs). (4) Higher concentrations of NO2, SO2, HCHO, CO, and CH4 were observed in northern ports (e.g., Tianjin Xingang, Qinhuangdao, Tangshan, and Dalian), whereas southern Chinese ports (e.g., Shenzhen, Xiamen, and Haikou) exhibited lower pollution levels. These findings provide a scientific foundation for coastal air pollution control and highlight the necessity of ship emission regulation and integrated multi-pollutant management.
- Open Access
- 21 September 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (19) , 4725
New Era for Geo-Parsing to Obtain Actual Locations: A Novel Toponym Correction Method Based on Remote Sensing Images
Geo-parsing, one of the key components of geographical information retrieval, is a process to recognize and geo-locate toponyms mentioned in texts. Such a process can obtain locations contained in toponyms successfully with consistent updating of neural network models and multiple contextual features. The significant offset distance between the geo-parsed locations and the actual occurrence locations still remains. This is because the geo-parsed locations sourced from toponyms in texts always point to the centers of cities, counties, or towns, and cannot directly represent the actual occurrence locations such as factories, farms, and activity areas. Consequently, The significant offset distances between the geo-parsed locations and the actual occurrence locations limit text mining applications in micro-scale geographic discoveries. This research aims at decreasing offset distances of geo-parsed locations by proposing a novel Toponym Correction Method based on satellite Remote Sensing Images (TC-RSI). The TC-RSI method uses satellite remote sensing images to provide extra detailed spatial information that can be associated with the sentence toponym by corresponding attributes. The TC-RSI method was validated in a case study of the forest ecological pattern dataset of An’hui province from visual, statistical, and robustness assessments. The correction results show that the TC-RSI method dramatically decreases the offset distances from about 50 km to about 1 km and promotes geographical discoveries on smaller scales. A series of analyses indicated that the TC-RSI is a valid, effective, and promising method to improve the accuracy of geo-parsed locations, which allows text mining to find more accurate geographical discoveries with lower offset distances. Moreover, toponym correction promotes the use of more diverse spatial data sources, such as Lidar, domain gazetteers, Wikimedia, and streetscapes, which are expected to usher in a new era of geo-parsing with toponym corrections.
- 21 September 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (19) , 4725
Open AccessNew Era for Geo-Parsing to Obtain Actual Locations: A Novel Toponym Correction Method Based on Remote Sensing Images
Geo-parsing, one of the key components of geographical information retrieval, is a process to recognize and geo-locate toponyms mentioned in texts. Such a process can obtain locations contained in toponyms successfully with consistent updating of neural network models and multiple contextual features. The significant offset distance between the geo-parsed locations and the actual occurrence locations still remains. This is because the geo-parsed locations sourced from toponyms in texts always point to the centers of cities, counties, or towns, and cannot directly represent the actual occurrence locations such as factories, farms, and activity areas. Consequently, The significant offset distances between the geo-parsed locations and the actual occurrence locations limit text mining applications in micro-scale geographic discoveries. This research aims at decreasing offset distances of geo-parsed locations by proposing a novel Toponym Correction Method based on satellite Remote Sensing Images (TC-RSI). The TC-RSI method uses satellite remote sensing images to provide extra detailed spatial information that can be associated with the sentence toponym by corresponding attributes. The TC-RSI method was validated in a case study of the forest ecological pattern dataset of An’hui province from visual, statistical, and robustness assessments. The correction results show that the TC-RSI method dramatically decreases the offset distances from about 50 km to about 1 km and promotes geographical discoveries on smaller scales. A series of analyses indicated that the TC-RSI is a valid, effective, and promising method to improve the accuracy of geo-parsed locations, which allows text mining to find more accurate geographical discoveries with lower offset distances. Moreover, toponym correction promotes the use of more diverse spatial data sources, such as Lidar, domain gazetteers, Wikimedia, and streetscapes, which are expected to usher in a new era of geo-parsing with toponym corrections.
- Open Access
- 5 February 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (3) , 744
The Forest Change Footprint of the Upper Indus Valley, from 1990 to 2020
The upper Indus Valley is the most important and vulnerable water tower in the South Asian subcontinent, which provides a vital water supply for 230 million people in the basin. Forests play an important role in water conservation in this region, and the security of upstream forests forms the foundation downstream water and food security. However, a big challenge is to effectively monitor the dynamics of the forest in this region. Thus, we used the LandTrendr spectral-temporal segmentation algorithm combined with 8203 scenes of multi-source remote sensing data to study the forest change footprint in the upper Indus Valley. The overall accuracy of LandTrendr extraction for forest disturbance and recovery was 86.01%, and the Kappa coefficient was 0.73. The results showed the following: (1) From 1990 to 2020, the area of forest recovery was 1.01% more than that of disturbance, 70% of disturbance occurred between 1990 and 2001, and 60% of recovery occurred between 1999 and 2012. (2) Although the overall trend of forest disturbance and recovery was balanced, there were significant differences in forest management status among the different regions. Nepal has the highest forest stability, India has the largest area of forest disturbance, and Pakistan and China have the largest areas of forest recovery. (3) India’s Himachal Pradesh and Jammu and Kashmir are the two provinces with the largest disturbed areas, primarily due to grazing, fires, and commercial tree planting. Pakistan’s North-West Frontier, Azad Kashmir, and China’s Tibet Ali region were major contributors to the recovery, which was driven by afforestation policies in both countries. This study provides an important data base and monitoring method for planning land and forest use in Indus Valley countries, protecting fragile environments, and promoting policies for the Sustainable Development Goals.
- 5 February 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (3) , 744
Open AccessThe Forest Change Footprint of the Upper Indus Valley, from 1990 to 2020
The upper Indus Valley is the most important and vulnerable water tower in the South Asian subcontinent, which provides a vital water supply for 230 million people in the basin. Forests play an important role in water conservation in this region, and the security of upstream forests forms the foundation downstream water and food security. However, a big challenge is to effectively monitor the dynamics of the forest in this region. Thus, we used the LandTrendr spectral-temporal segmentation algorithm combined with 8203 scenes of multi-source remote sensing data to study the forest change footprint in the upper Indus Valley. The overall accuracy of LandTrendr extraction for forest disturbance and recovery was 86.01%, and the Kappa coefficient was 0.73. The results showed the following: (1) From 1990 to 2020, the area of forest recovery was 1.01% more than that of disturbance, 70% of disturbance occurred between 1990 and 2001, and 60% of recovery occurred between 1999 and 2012. (2) Although the overall trend of forest disturbance and recovery was balanced, there were significant differences in forest management status among the different regions. Nepal has the highest forest stability, India has the largest area of forest disturbance, and Pakistan and China have the largest areas of forest recovery. (3) India’s Himachal Pradesh and Jammu and Kashmir are the two provinces with the largest disturbed areas, primarily due to grazing, fires, and commercial tree planting. Pakistan’s North-West Frontier, Azad Kashmir, and China’s Tibet Ali region were major contributors to the recovery, which was driven by afforestation policies in both countries. This study provides an important data base and monitoring method for planning land and forest use in Indus Valley countries, protecting fragile environments, and promoting policies for the Sustainable Development Goals.
- Open Access
- 4 March 2021
- Published by MDPI AG in Remote Sensing
- Vol. 13 (5) , 973
Mapping Forest Types in China with 10 m Resolution Based on Spectral–Spatial–Temporal Features
The comprehensive application of spectral, spatial, and temporal (SST) features derived from remote sensing images is a significant technique for classifying and mapping forest types. Facing limitations in the availability of detailed forest type identification processes for large regions, a forest type classification framework based on SST features was developed in this study. The advantages of Sentinel-2 and Landsat series imagery were used to extract SST forest type classification features, using red-edge bands, a gray-level co-occurrence matrix, and harmonic analysis, with the assistance of the Google Earth Engine platform. Considering four representative Chinese geographic regions—middle and high latitudes, complex mountainous areas, cloudy and rainy areas, and the N–S climate transition zone—our method was proven to be effective, with overall classification accuracies > 85%. The scheme to assess the importance of SST features for forest classification in various regions was designed using the Gini criterion in the random forest algorithm and revealed that spectral features were more effective in classifying forest types with complex compositions. Temporal features were found to be favorable for identifying forest types with obvious evergreen and deciduous growth patterns, while spatial features produced better classification results for forest types with different spatial structures, such as needle- or broad-leaved forests. The findings of this study can provide a reference for feature selection in remote sensing forest type classification processes, and identifying forest types in this way could provide support for the accurate and sustainable management of forest resources.
- 4 March 2021
- Published by MDPI AG in Remote Sensing
- Vol. 13 (5) , 973
Open AccessMapping Forest Types in China with 10 m Resolution Based on Spectral–Spatial–Temporal Features
The comprehensive application of spectral, spatial, and temporal (SST) features derived from remote sensing images is a significant technique for classifying and mapping forest types. Facing limitations in the availability of detailed forest type identification processes for large regions, a forest type classification framework based on SST features was developed in this study. The advantages of Sentinel-2 and Landsat series imagery were used to extract SST forest type classification features, using red-edge bands, a gray-level co-occurrence matrix, and harmonic analysis, with the assistance of the Google Earth Engine platform. Considering four representative Chinese geographic regions—middle and high latitudes, complex mountainous areas, cloudy and rainy areas, and the N–S climate transition zone—our method was proven to be effective, with overall classification accuracies > 85%. The scheme to assess the importance of SST features for forest classification in various regions was designed using the Gini criterion in the random forest algorithm and revealed that spectral features were more effective in classifying forest types with complex compositions. Temporal features were found to be favorable for identifying forest types with obvious evergreen and deciduous growth patterns, while spatial features produced better classification results for forest types with different spatial structures, such as needle- or broad-leaved forests. The findings of this study can provide a reference for feature selection in remote sensing forest type classification processes, and identifying forest types in this way could provide support for the accurate and sustainable management of forest resources.