Caihong Ma
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
Caihong Ma has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Jianbo Liu
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
7 shared publications - Fu Chen
Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
6 shared publications - Jianbo Duan
Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China
6 shared publications - Wei Liu
Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China
4 shared publications - Qin Dai
Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China
3 shared publications - Rui Guo
Key Laboratory of Big Data of Xinjiang Social Security Risk Prevention and Control, Xinjiang Lianhaichuangzhi Information Technology Company Ltd., rmqi, China
3 shared publications
Latest Publications
- Open Access
- 8 June 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (12) , 1890
Analysis of the Effect of Vegetation Types in Industrial Heat Source Radiation Areas on PM2.5 Concentration Reduction in the Beijing–Tianjin–Hebei Region
Industrial heat source (IHS) radiation areas are key accumulation zones for fine particulate matter with an aerodynamic diameter of 2.5 μm or less (PM2.5) in heavily industrialized regions, but PM2.5 concentration reduction rates by vegetation types have not been systematically assessed. A systematic analysis of PM2.5 concentration reduction rates by vegetation types using IHS, PM2.5, land-cover, and digital elevation model (DEM) data was conducted to assess PM2.5 concentration reduction rates by vegetation types within IHS radiation areas. First, this study adopted the published IHS radiation-area dataset developed by Xin Sui et al. to define the spatial extent of industrially influenced areas. Second, PM2.5 concentrations were extracted within IHS radiation areas and areas covered by different vegetation types to support the calculation of PM2.5 concentration reduction rates. Third, PM2.5 concentration reduction rates by vegetation types were evaluated through masking and regional statistical analysis. Results for Beijing–Tianjin–Hebei (BTH) in 2015 and 2020 show that: (1) the average PM2.5 decreased from 71.70 to 39.60 µg/m3, corresponding to an overall reduction of 44.8%; (2) PM2.5 concentration reduction rates varied substantially among vegetation types; open deciduous broadleaved forest showed the highest reduction rate of 39.08%, while rainfed and irrigated cropland showed negative reduction rates of −9.35% and −6.71%; (3) city-scale and case analyses show denser vegetation in radiation zones generally lowers PM2.5 even under ongoing industrial activity. The study supports vegetation greening, IHS control, regional air quality improvement, and sustainable industrial development strategies.
- 8 June 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (12) , 1890
Open AccessAnalysis of the Effect of Vegetation Types in Industrial Heat Source Radiation Areas on PM2.5 Concentration Reduction in the Beijing–Tianjin–Hebei Region
Industrial heat source (IHS) radiation areas are key accumulation zones for fine particulate matter with an aerodynamic diameter of 2.5 μm or less (PM2.5) in heavily industrialized regions, but PM2.5 concentration reduction rates by vegetation types have not been systematically assessed. A systematic analysis of PM2.5 concentration reduction rates by vegetation types using IHS, PM2.5, land-cover, and digital elevation model (DEM) data was conducted to assess PM2.5 concentration reduction rates by vegetation types within IHS radiation areas. First, this study adopted the published IHS radiation-area dataset developed by Xin Sui et al. to define the spatial extent of industrially influenced areas. Second, PM2.5 concentrations were extracted within IHS radiation areas and areas covered by different vegetation types to support the calculation of PM2.5 concentration reduction rates. Third, PM2.5 concentration reduction rates by vegetation types were evaluated through masking and regional statistical analysis. Results for Beijing–Tianjin–Hebei (BTH) in 2015 and 2020 show that: (1) the average PM2.5 decreased from 71.70 to 39.60 µg/m3, corresponding to an overall reduction of 44.8%; (2) PM2.5 concentration reduction rates varied substantially among vegetation types; open deciduous broadleaved forest showed the highest reduction rate of 39.08%, while rainfed and irrigated cropland showed negative reduction rates of −9.35% and −6.71%; (3) city-scale and case analyses show denser vegetation in radiation zones generally lowers PM2.5 even under ongoing industrial activity. The study supports vegetation greening, IHS control, regional air quality improvement, and sustainable industrial development strategies.
- Open Access
- 20 January 2024
- Published by MDPI AG in Atmosphere
- Vol. 15 (1) , 131
Industrial Heat Source-Related PM2.5 Concentration Estimates and Analysis Using New Three-Stage Model in the Beijing–Tianjin–Hebei Region
The prevalent high-energy, high-pollution and high-emission economic model has led to significant air pollution challenges in recent years. The industrial sector in the Beijing–Tianjin–Hebei (BTH) region is a notable source of atmospheric pollutants, with industrial heat sources (IHSs) being primary contributors to this pollution. Effectively managing emissions from these sources is pivotal for achieving air pollution control goals in the region. A new three-stage model using multi-source long-term data was proposed to estimate atmospheric, delicate particulate matter (PM2.5) concentrations caused by IHS. In the first stage, a region-growing algorithm was used to identify the IHS radiation areas. In the second and third stages, based on a seasonal trend decomposition procedure based on Loess (STL), multiple linear regression, and U-convLSTM models, IHS-related PM2.5 concentrations caused by meteorological and anthropogenic conditions were removed using long-term data from 2012 to 2021. Finally, this study analyzed the spatial and temporal variations in IHS-related PM2.5 concentrations in the BTH region. The findings reveal that PM2.5 concentrations in IHS radiation areas were higher than in background areas, with approximately 33.16% attributable to IHS activities. A decreasing trend in IHS-related PM2.5 concentrations was observed. Seasonal and spatial analyses indicated higher concentrations in the industrially dense southern region, particularly during autumn and winter. Moreover, a case study in Handan’s She County demonstrated dynamic fluctuations in IHS-related PM2.5 concentrations, with notable reductions during periods of industrial inactivity. Our results aligned closely with previous studies and actual IHS operations, showing strong positive correlations with related industrial indices. This study’s outcomes are theoretically and practically significant for understanding and addressing the regional air quality caused by IHSs, contributing positively to regional environmental quality improvement and sustainable industrial development.
- 20 January 2024
- Published by MDPI AG in Atmosphere
- Vol. 15 (1) , 131
Open AccessIndustrial Heat Source-Related PM2.5 Concentration Estimates and Analysis Using New Three-Stage Model in the Beijing–Tianjin–Hebei Region
The prevalent high-energy, high-pollution and high-emission economic model has led to significant air pollution challenges in recent years. The industrial sector in the Beijing–Tianjin–Hebei (BTH) region is a notable source of atmospheric pollutants, with industrial heat sources (IHSs) being primary contributors to this pollution. Effectively managing emissions from these sources is pivotal for achieving air pollution control goals in the region. A new three-stage model using multi-source long-term data was proposed to estimate atmospheric, delicate particulate matter (PM2.5) concentrations caused by IHS. In the first stage, a region-growing algorithm was used to identify the IHS radiation areas. In the second and third stages, based on a seasonal trend decomposition procedure based on Loess (STL), multiple linear regression, and U-convLSTM models, IHS-related PM2.5 concentrations caused by meteorological and anthropogenic conditions were removed using long-term data from 2012 to 2021. Finally, this study analyzed the spatial and temporal variations in IHS-related PM2.5 concentrations in the BTH region. The findings reveal that PM2.5 concentrations in IHS radiation areas were higher than in background areas, with approximately 33.16% attributable to IHS activities. A decreasing trend in IHS-related PM2.5 concentrations was observed. Seasonal and spatial analyses indicated higher concentrations in the industrially dense southern region, particularly during autumn and winter. Moreover, a case study in Handan’s She County demonstrated dynamic fluctuations in IHS-related PM2.5 concentrations, with notable reductions during periods of industrial inactivity. Our results aligned closely with previous studies and actual IHS operations, showing strong positive correlations with related industrial indices. This study’s outcomes are theoretically and practically significant for understanding and addressing the regional air quality caused by IHSs, contributing positively to regional environmental quality improvement and sustainable industrial development.
- Open Access
- 9 October 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (19) , 5024
Evaluating Anthropogenic CO2 Bottom-Up Emission Inventories Using Satellite Observations from GOSAT and OCO-2
Anthropogenic carbon dioxide (CO2) emissions from bottom-up inventories have high uncertainties due to the usage of proxy data in creating these inventories. To evaluate bottom-up inventories, satellite observations of atmospheric CO2 with continuously improved accuracies have shown great potential. In this study, we evaluate the consistency and uncertainty of four gridded CO2 emission inventories, including CHRED, PKU, ODIAC, and EDGAR that have been commonly used to study emissions in China, using GOSAT and OCO-2 satellite observations of atmospheric column-averaged dry-air mole fraction of CO2 (XCO2). The evaluation is carried out using two data-driven approaches: (1) quantifying the correlations of the four inventories with XCO2 anomalies derived from the satellite observations; (2) comparing emission inventories with emissions predicted by a machine learning-based model that considers the nonlinearity between emissions and XCO2. The model is trained using long-term datasets of XCO2 and emission inventories from 2010 to 2019. The result shows that the inconsistencies among these four emission inventories are significant, especially in areas of high emissions associated with large XCO2 values. In particular, EDGAR shows a larger difference to CHRED over super-emitting sources in China. The differences for ODIAC and EDGAR, when compared with the machine learning-based model, are higher in Asia than those in the USA and Europe. The predicted emissions in China are generally lower than the inventories, especially in megacities. The biases depend on the magnitude of inventory emissions with strong positive correlations with emissions (R2 is larger than 0.8). On the contrary, the predicted emissions in the USA are slightly higher than the inventories and the biases tend to be random (R2 is from 0.01 to 0.5). These results indicate that the uncertainties of gridded emission inventories of ODIAC and EDGAR are higher in Asian countries than those in European and the USA. This study demonstrates that the top-down approach using satellite observations could be applied to quantify the uncertainty of emission inventories and therefore improve the accuracy in spatially and temporally attributing national/regional totals inventories.
- 9 October 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (19) , 5024
Open AccessEvaluating Anthropogenic CO2 Bottom-Up Emission Inventories Using Satellite Observations from GOSAT and OCO-2
Anthropogenic carbon dioxide (CO2) emissions from bottom-up inventories have high uncertainties due to the usage of proxy data in creating these inventories. To evaluate bottom-up inventories, satellite observations of atmospheric CO2 with continuously improved accuracies have shown great potential. In this study, we evaluate the consistency and uncertainty of four gridded CO2 emission inventories, including CHRED, PKU, ODIAC, and EDGAR that have been commonly used to study emissions in China, using GOSAT and OCO-2 satellite observations of atmospheric column-averaged dry-air mole fraction of CO2 (XCO2). The evaluation is carried out using two data-driven approaches: (1) quantifying the correlations of the four inventories with XCO2 anomalies derived from the satellite observations; (2) comparing emission inventories with emissions predicted by a machine learning-based model that considers the nonlinearity between emissions and XCO2. The model is trained using long-term datasets of XCO2 and emission inventories from 2010 to 2019. The result shows that the inconsistencies among these four emission inventories are significant, especially in areas of high emissions associated with large XCO2 values. In particular, EDGAR shows a larger difference to CHRED over super-emitting sources in China. The differences for ODIAC and EDGAR, when compared with the machine learning-based model, are higher in Asia than those in the USA and Europe. The predicted emissions in China are generally lower than the inventories, especially in megacities. The biases depend on the magnitude of inventory emissions with strong positive correlations with emissions (R2 is larger than 0.8). On the contrary, the predicted emissions in the USA are slightly higher than the inventories and the biases tend to be random (R2 is from 0.01 to 0.5). These results indicate that the uncertainties of gridded emission inventories of ODIAC and EDGAR are higher in Asian countries than those in European and the USA. This study demonstrates that the top-down approach using satellite observations could be applied to quantify the uncertainty of emission inventories and therefore improve the accuracy in spatially and temporally attributing national/regional totals inventories.
- Open Access
- 7 September 2022
- Published by MDPI AG in Sustainability
- Vol. 14 (18) , 11228
Classification of Industrial Heat Source Objects Based on Active Fire Point Density Segmentation and Spatial Topological Correlation Analysis in the Beijing–Tianjin–Hebei Region
The development of industrial infrastructure in the Beijing–Tianjin–Hebei(BTH) region has been accompanied by a disorderly expansion of industrial zones and other inappropriate development. Accurate industrial heat source classification data become important to evaluate the policies of industrial restructuring and air quality improvement. In this study, a new classification of industrial heat source objects model based on active fire point density segmentation and spatial topological correlation analysis in the BTH Region was proposed. First, industrial heat source objects were detected with an active fire point density segmentation method using NPP-VIIRS active fire/hotspot data. Then, industrial heat source objects were classified into five categories based on a spatial topological correlation analysis method using POI data. Then, identification and classification results were manually validated based on Google Earth imagery. Finally, we evaluated the factors influencing the number of industrial heat sources based on an OLS regression model. A total of 493 industrial heat source objects were identified in this study with an identification accuracy of 96.14%(474/493). Compared with results for nighttime fires, the number of industrial heat source objects that were identified was higher, and the spatial coverage was greater; the minimum size of the detected objects was also smaller. Based on the function of the identified industrial heat source objects, the objects in the BTH region were then divided into five categories: cement plants (21.73%), steel plants (53.80%), coal and chemical industry (12.66%), oil and gas developments (7.81%), and other (4.01%). An analysis of their operations showed that the number of industrial heat source objects in operation in the BTH region tended to first rise and then decline during the 2012–2021 period, with the peak being reached in 2013. The results of this study will aid the rationalization of industrial infrastructure in the BTH region and, by extension, in China as a whole.
- 7 September 2022
- Published by MDPI AG in Sustainability
- Vol. 14 (18) , 11228
Open AccessClassification of Industrial Heat Source Objects Based on Active Fire Point Density Segmentation and Spatial Topological Correlation Analysis in the Beijing–Tianjin–Hebei Region
The development of industrial infrastructure in the Beijing–Tianjin–Hebei(BTH) region has been accompanied by a disorderly expansion of industrial zones and other inappropriate development. Accurate industrial heat source classification data become important to evaluate the policies of industrial restructuring and air quality improvement. In this study, a new classification of industrial heat source objects model based on active fire point density segmentation and spatial topological correlation analysis in the BTH Region was proposed. First, industrial heat source objects were detected with an active fire point density segmentation method using NPP-VIIRS active fire/hotspot data. Then, industrial heat source objects were classified into five categories based on a spatial topological correlation analysis method using POI data. Then, identification and classification results were manually validated based on Google Earth imagery. Finally, we evaluated the factors influencing the number of industrial heat sources based on an OLS regression model. A total of 493 industrial heat source objects were identified in this study with an identification accuracy of 96.14%(474/493). Compared with results for nighttime fires, the number of industrial heat source objects that were identified was higher, and the spatial coverage was greater; the minimum size of the detected objects was also smaller. Based on the function of the identified industrial heat source objects, the objects in the BTH region were then divided into five categories: cement plants (21.73%), steel plants (53.80%), coal and chemical industry (12.66%), oil and gas developments (7.81%), and other (4.01%). An analysis of their operations showed that the number of industrial heat source objects in operation in the BTH region tended to first rise and then decline during the 2012–2021 period, with the peak being reached in 2013. The results of this study will aid the rationalization of industrial infrastructure in the BTH region and, by extension, in China as a whole.
- Open Access
- 16 December 2021
- Published by MDPI AG in Remote Sensing
- Vol. 13 (24) , 5116
Landslide Extraction from High-Resolution Remote Sensing Imagery Using Fully Convolutional Spectral–Topographic Fusion Network
Considering the complexity of landslide hazards, their manual investigation lacks efficiency and is time-consuming, especially in high-altitude plateau areas. Therefore, extracting landslide information using remote sensing technology has great advantages. In this study, comprehensive research was carried out on the landslide features of high-resolution remote sensing images on the Mangkam dataset. Based on the idea of feature-driven classification, the landslide extraction model of a fully convolutional spectral–topographic fusion network (FSTF-Net) based on a deep convolutional neural network of multi-source data fusion is proposed, which takes into account the topographic factor (slope and aspect) and the normalized difference vegetation index (NDVI) as multi-source data input by which to train the model. In this paper, a high-resolution remote sensing image classification method based on a fully convolutional network was used to extract the landslide information, thereby realizing the accurate extraction of the landslide and surrounding ground-object information. With Mangkam County in the southeast of the Qinghai–Tibet Plateau China as the study area, the proposed method was evaluated based on the high-precision digital elevation model (DEM) generated from stereoscopic images of Resources Satellite-3 and multi-source high-resolution remote sensing image data (Beijing-2, Worldview-3, and SuperView-1). Results show that our method had a landslide detection precision of 0.85 and an overall classification accuracy of 0.89. Compared with the latest DeepLab_v3+, our model increases the landslide detection precision by 5%. Thus, the proposed FSTF-Net model has high reliability and robustness.
- 16 December 2021
- Published by MDPI AG in Remote Sensing
- Vol. 13 (24) , 5116
Open AccessLandslide Extraction from High-Resolution Remote Sensing Imagery Using Fully Convolutional Spectral–Topographic Fusion Network
Considering the complexity of landslide hazards, their manual investigation lacks efficiency and is time-consuming, especially in high-altitude plateau areas. Therefore, extracting landslide information using remote sensing technology has great advantages. In this study, comprehensive research was carried out on the landslide features of high-resolution remote sensing images on the Mangkam dataset. Based on the idea of feature-driven classification, the landslide extraction model of a fully convolutional spectral–topographic fusion network (FSTF-Net) based on a deep convolutional neural network of multi-source data fusion is proposed, which takes into account the topographic factor (slope and aspect) and the normalized difference vegetation index (NDVI) as multi-source data input by which to train the model. In this paper, a high-resolution remote sensing image classification method based on a fully convolutional network was used to extract the landslide information, thereby realizing the accurate extraction of the landslide and surrounding ground-object information. With Mangkam County in the southeast of the Qinghai–Tibet Plateau China as the study area, the proposed method was evaluated based on the high-precision digital elevation model (DEM) generated from stereoscopic images of Resources Satellite-3 and multi-source high-resolution remote sensing image data (Beijing-2, Worldview-3, and SuperView-1). Results show that our method had a landslide detection precision of 0.85 and an overall classification accuracy of 0.89. Compared with the latest DeepLab_v3+, our model increases the landslide detection precision by 5%. Thus, the proposed FSTF-Net model has high reliability and robustness.
- Open Access
- 10 December 2019
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 8 (12) , 568
Assessing the Distribution of Heavy Industrial Heat Sources in India between 2012 and 2018
The heavy industry in India has witnessed rapid development in the past decades. This has increased the pressures and load on the Indian environment, and has also had a great impact on the world economy. In this study, the Preparatory Project Visible Infrared Imaging Radiometer (NPP VIIRS) 375-m active fire product (VNP14IMG) and night-time light (NTL) data were used to study the spatiotemporal patterns of heavy industrial development in India. We employed an improved adaptive K-means algorithm to realize the spatial segmentation of long-term VNP14IMG data and artificial heat-source objects. Next, the initial heavy industry heat sources were distinguished from normal heat sources using a threshold recognition model. Finally, the maximum night-time light data were used to delineate the final heavy industry heat sources. The results suggest, that this modified method is a much more accurate and effective way of monitoring heavy industrial heat sources, and the accuracy of this detection model was higher than 92.7%. The number of main findings were concluded from the study: (1) the heavy industry heat sources are mainly concentrated in the north-east Assam state, east-central Jharkhand state, north Chhattisgarh and Odisha states, and the coastal areas of Gujarat and Maharashtra. Many heavy industrial heat sources were also found around a line from Kolkata on the Eastern Indian Ocean to Mumbai on the Western Indian Ocean. (2) The number of working heavy industry heat sources (NWH) and, particularly, the total number of fire hotspots for each working heavy industry heat source area (NFHWH) are continuing to increase in India. These trends mirror those for the Gross Domestic Product (GDP) and total population of India between 2012 and 2017. (3) The largest values of NWH and NFHWH were in Jharkhand, Chhattisgarh, and Odisha whereas the smallest negative values, the in Jharkhand and Chhattisgarh were also the two largest values in the whole country. The smallest negative values of and were in Haryana. The in the mainland Gujarat had the second most negative value, while the value of the was the third-highest positive value.- 10 December 2019
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 8 (12) , 568
Open AccessAssessing the Distribution of Heavy Industrial Heat Sources in India between 2012 and 2018
The heavy industry in India has witnessed rapid development in the past decades. This has increased the pressures and load on the Indian environment, and has also had a great impact on the world economy. In this study, the Preparatory Project Visible Infrared Imaging Radiometer (NPP VIIRS) 375-m active fire product (VNP14IMG) and night-time light (NTL) data were used to study the spatiotemporal patterns of heavy industrial development in India. We employed an improved adaptive K-means algorithm to realize the spatial segmentation of long-term VNP14IMG data and artificial heat-source objects. Next, the initial heavy industry heat sources were distinguished from normal heat sources using a threshold recognition model. Finally, the maximum night-time light data were used to delineate the final heavy industry heat sources. The results suggest, that this modified method is a much more accurate and effective way of monitoring heavy industrial heat sources, and the accuracy of this detection model was higher than 92.7%. The number of main findings were concluded from the study: (1) the heavy industry heat sources are mainly concentrated in the north-east Assam state, east-central Jharkhand state, north Chhattisgarh and Odisha states, and the coastal areas of Gujarat and Maharashtra. Many heavy industrial heat sources were also found around a line from Kolkata on the Eastern Indian Ocean to Mumbai on the Western Indian Ocean. (2) The number of working heavy industry heat sources (NWH) and, particularly, the total number of fire hotspots for each working heavy industry heat source area (NFHWH) are continuing to increase in India. These trends mirror those for the Gross Domestic Product (GDP) and total population of India between 2012 and 2017. (3) The largest values of NWH and NFHWH were in Jharkhand, Chhattisgarh, and Odisha whereas the smallest negative values, the in Jharkhand and Chhattisgarh were also the two largest values in the whole country. The smallest negative values of and were in Haryana. The in the mainland Gujarat had the second most negative value, while the value of the was the third-highest positive value. - Open Access
- 28 October 2019
- Published by MDPI AG in Remote Sensing
- Vol. 11 (21) , 2523
High-Resolution Remote Sensing Imagery Classification of Imbalanced Data Using Multistage Sampling Method and Deep Neural Networks
Class imbalance is a key issue for the application of deep learning for remote sensing image classification because a model generated by imbalanced samples training has low classification accuracy for minority classes. In this study, an accurate classification approach using the multistage sampling method and deep neural networks was proposed to classify imbalanced data. We first balance samples by multistage sampling to obtain the training sets. Then, a state-of-the-art model is adopted by combining the advantages of atrous spatial pyramid pooling (ASPP) and Encoder-Decoder for pixel-wise classification, which are two different types of fully convolutional networks (FCNs) that can obtain contextual information of multiple levels in the Encoder stage. The details and spatial dimensions of targets are restored using such information during the Decoder stage. We employ four deep learning-based classification algorithms (basic FCN, FCN-8S, ASPP, and Encoder-Decoder with ASPP of our approach) on multistage training sets (original, MUS1, and MUS2) of WorldView-3 images in southeastern Qinghai-Tibet Plateau and GF-2 images in northeastern Beijing for comparison. The experiments show that, compared with existing sets (original, MUS1, and identical) and existing method (cost weighting), the MUS2 training set of multistage sampling significantly enhance the classification performance for minority classes. Our approach shows distinct advantages for imbalanced data.
- 28 October 2019
- Published by MDPI AG in Remote Sensing
- Vol. 11 (21) , 2523
Open AccessHigh-Resolution Remote Sensing Imagery Classification of Imbalanced Data Using Multistage Sampling Method and Deep Neural Networks
Class imbalance is a key issue for the application of deep learning for remote sensing image classification because a model generated by imbalanced samples training has low classification accuracy for minority classes. In this study, an accurate classification approach using the multistage sampling method and deep neural networks was proposed to classify imbalanced data. We first balance samples by multistage sampling to obtain the training sets. Then, a state-of-the-art model is adopted by combining the advantages of atrous spatial pyramid pooling (ASPP) and Encoder-Decoder for pixel-wise classification, which are two different types of fully convolutional networks (FCNs) that can obtain contextual information of multiple levels in the Encoder stage. The details and spatial dimensions of targets are restored using such information during the Decoder stage. We employ four deep learning-based classification algorithms (basic FCN, FCN-8S, ASPP, and Encoder-Decoder with ASPP of our approach) on multistage training sets (original, MUS1, and MUS2) of WorldView-3 images in southeastern Qinghai-Tibet Plateau and GF-2 images in northeastern Beijing for comparison. The experiments show that, compared with existing sets (original, MUS1, and identical) and existing method (cost weighting), the MUS2 training set of multistage sampling significantly enhance the classification performance for minority classes. Our approach shows distinct advantages for imbalanced data.
- Open Access
- 26 November 2018
- Published by MDPI AG in Sustainability
- Vol. 10 (12) , 4419
Assessing Heavy Industrial Heat Source Distribution in China Using Real-Time VIIRS Active Fire/Hotspot Data
Rapid urbanization and economic development have led to the development of heavy industry and structural re-equalization in mainland China. This has resulted in scattered and disorderly layouts becoming prominent in the region. Furthermore, economic development has exacerbated pressures on regional resources and the environment and has threatened sustainable and coordinated development in the region. The NASA Land Science Investigator Processing System (Land-SIPS) Visible Infrared Imaging Radiometer (VIIRS) 375-m active fire product (VNP14IMG) was selected from the Fire Information for Resource Management System (FIRMS) to study the spatiotemporal patterns of heavy industry development. Furthermore, we employed an improved adaptive K-means algorithm to realize the spatial segmentation of long-order VNP14IMG and constructed heat source objects. Lastly, we used a threshold recognition model to identify heavy industry objects from normal heat source objects. Results suggest that the method is an accurate and effective way to monitor heat sources generated from heavy industry. Moreover, some conclusions about heavy industrial heat source distribution in mainland China at different scales were obtained. Those can be beneficial for policy-makers and heavy industry regulation.
- 26 November 2018
- Published by MDPI AG in Sustainability
- Vol. 10 (12) , 4419
Open AccessAssessing Heavy Industrial Heat Source Distribution in China Using Real-Time VIIRS Active Fire/Hotspot Data
Rapid urbanization and economic development have led to the development of heavy industry and structural re-equalization in mainland China. This has resulted in scattered and disorderly layouts becoming prominent in the region. Furthermore, economic development has exacerbated pressures on regional resources and the environment and has threatened sustainable and coordinated development in the region. The NASA Land Science Investigator Processing System (Land-SIPS) Visible Infrared Imaging Radiometer (VIIRS) 375-m active fire product (VNP14IMG) was selected from the Fire Information for Resource Management System (FIRMS) to study the spatiotemporal patterns of heavy industry development. Furthermore, we employed an improved adaptive K-means algorithm to realize the spatial segmentation of long-order VNP14IMG and constructed heat source objects. Lastly, we used a threshold recognition model to identify heavy industry objects from normal heat source objects. Results suggest that the method is an accurate and effective way to monitor heat sources generated from heavy industry. Moreover, some conclusions about heavy industrial heat source distribution in mainland China at different scales were obtained. Those can be beneficial for policy-makers and heavy industry regulation.
- Open Access
- 14 March 2018
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 7 (3) , 110
Pixel-Wise Classification Method for High Resolution Remote Sensing Imagery Using Deep Neural Networks
Considering the classification of high spatial resolution remote sensing imagery, this paper presents a novel classification method for such imagery using deep neural networks. Deep learning methods, such as a fully convolutional network (FCN) model, achieve state-of-the-art performance in natural image semantic segmentation when provided with large-scale datasets and respective labels. To use data efficiently in the training stage, we first pre-segment training images and their labels into small patches as supplements of training data using graph-based segmentation and the selective search method. Subsequently, FCN with atrous convolution is used to perform pixel-wise classification. In the testing stage, post-processing with fully connected conditional random fields (CRFs) is used to refine results. Extensive experiments based on the Vaihingen dataset demonstrate that our method performs better than the reference state-of-the-art networks when applied to high-resolution remote sensing imagery classification.
- 14 March 2018
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 7 (3) , 110
Open AccessPixel-Wise Classification Method for High Resolution Remote Sensing Imagery Using Deep Neural Networks
Considering the classification of high spatial resolution remote sensing imagery, this paper presents a novel classification method for such imagery using deep neural networks. Deep learning methods, such as a fully convolutional network (FCN) model, achieve state-of-the-art performance in natural image semantic segmentation when provided with large-scale datasets and respective labels. To use data efficiently in the training stage, we first pre-segment training images and their labels into small patches as supplements of training data using graph-based segmentation and the selective search method. Subsequently, FCN with atrous convolution is used to perform pixel-wise classification. In the testing stage, post-processing with fully connected conditional random fields (CRFs) is used to refine results. Extensive experiments based on the Vaihingen dataset demonstrate that our method performs better than the reference state-of-the-art networks when applied to high-resolution remote sensing imagery classification.
- Open Access
- 18 October 2017
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 6 (10) , 310
A Content-Based Remote Sensing Image Change Information Retrieval Model
With the rapid development of satellite remote sensing technology, the size of image datasets in many application areas is growing exponentially and the demand for Land-Cover and Land-Use change remote sensing data is growing rapidly. It is thus becoming hard to efficiently and intelligently retrieve the change information that users need from massive image databases. In this paper, content-based image retrieval is successfully applied to change detection, and a content-based remote sensing image change information retrieval model is introduced. First, the construction of a new model framework for change information retrieval from a remote sensing database is described. Then, as the target content cannot be expressed by one kind of feature alone, a multiple-feature, integrated retrieval model is proposed. Thirdly, an experimental prototype system that was set up to demonstrate the validity and practicability of the model is described. The proposed model is a new method of acquiring change detection information from remote sensing imagery and so can reduce the need for image pre-processing and also deal with problems related to seasonal changes, as well as other problems encountered in the field of change detection. Meanwhile, the new model has important implications for improving remote sensing image management and autonomous information retrieval. The experiment results obtained using a Landsat data set show that the use of the new model can produce promising results. A coverage rate and mean average precision of 71% and 89%, respectively, were achieved for the top 20 returned pairs of images.
- 18 October 2017
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 6 (10) , 310
Open AccessA Content-Based Remote Sensing Image Change Information Retrieval Model
With the rapid development of satellite remote sensing technology, the size of image datasets in many application areas is growing exponentially and the demand for Land-Cover and Land-Use change remote sensing data is growing rapidly. It is thus becoming hard to efficiently and intelligently retrieve the change information that users need from massive image databases. In this paper, content-based image retrieval is successfully applied to change detection, and a content-based remote sensing image change information retrieval model is introduced. First, the construction of a new model framework for change information retrieval from a remote sensing database is described. Then, as the target content cannot be expressed by one kind of feature alone, a multiple-feature, integrated retrieval model is proposed. Thirdly, an experimental prototype system that was set up to demonstrate the validity and practicability of the model is described. The proposed model is a new method of acquiring change detection information from remote sensing imagery and so can reduce the need for image pre-processing and also deal with problems related to seasonal changes, as well as other problems encountered in the field of change detection. Meanwhile, the new model has important implications for improving remote sensing image management and autonomous information retrieval. The experiment results obtained using a Landsat data set show that the use of the new model can produce promising results. A coverage rate and mean average precision of 71% and 89%, respectively, were achieved for the top 20 returned pairs of images.