Zhanghanshu Han, Yuying Wang, Jialu Xu, Yi Shang, Zhanqing Li, Chunsong Lu, Puning Zhan, Xiaorui Song, Min Lv, Yinshan Yang
In this study, we investigate the planetary boundary layer height (PBLH) using micro-pulse lidar (MPL) and microwave radiometer (MWR) methods, examining its relationship with the mass concentration of particles less than 2.5 µm in aerodynamic diameter (PM2.5) and its chemical compositions. Long-term PBLH retrieval results are presented derived from the MPL and the MWR, including its seasonal and diurnal variations, showing a superior performance regarding the MPL in terms of reliability and consistency with PM2.5. Also examined are the relationships between the two types of PBLHs and PM2.5. Unlike the PBLH derived from the MPL, the PBLH derived from the MWR does not have a negative correlation under severe pollution conditions. Furthermore, this study explores the effects of the PBLH on different aerosol chemical compositions, with the most pronounced impact observed on primary aerosols and relatively minimal influence on secondary aerosols, especially secondary organics during spring. This study underscores disparities in PBLH retrievals by different instruments during long-term observations and unveils distinct relationships between the PBLH and aerosol chemical compositions. Moreover, it highlights the greater influence of the PBLH on primary pollutants, laying the groundwork for future research in this field.
{"title":"Assessment of Multiple Planetary Boundary Layer Height Retrieval Methods and Their Impact on PM2.5 and Its Chemical Compositions throughout a Year in Nanjing","authors":"Zhanghanshu Han, Yuying Wang, Jialu Xu, Yi Shang, Zhanqing Li, Chunsong Lu, Puning Zhan, Xiaorui Song, Min Lv, Yinshan Yang","doi":"10.3390/rs16183464","DOIUrl":"https://doi.org/10.3390/rs16183464","url":null,"abstract":"In this study, we investigate the planetary boundary layer height (PBLH) using micro-pulse lidar (MPL) and microwave radiometer (MWR) methods, examining its relationship with the mass concentration of particles less than 2.5 µm in aerodynamic diameter (PM2.5) and its chemical compositions. Long-term PBLH retrieval results are presented derived from the MPL and the MWR, including its seasonal and diurnal variations, showing a superior performance regarding the MPL in terms of reliability and consistency with PM2.5. Also examined are the relationships between the two types of PBLHs and PM2.5. Unlike the PBLH derived from the MPL, the PBLH derived from the MWR does not have a negative correlation under severe pollution conditions. Furthermore, this study explores the effects of the PBLH on different aerosol chemical compositions, with the most pronounced impact observed on primary aerosols and relatively minimal influence on secondary aerosols, especially secondary organics during spring. This study underscores disparities in PBLH retrievals by different instruments during long-term observations and unveils distinct relationships between the PBLH and aerosol chemical compositions. Moreover, it highlights the greater influence of the PBLH on primary pollutants, laying the groundwork for future research in this field.","PeriodicalId":48993,"journal":{"name":"Remote Sensing","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250914","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yuanling Li, Shengyuan Zou, Tianzhong Zhao, Xiaohui Su
Building change detection (BCD) from remote sensing images is an essential field for urban studies. In this well-developed field, Convolutional Neural Networks (CNNs) and Transformer have been leveraged to empower BCD models in handling multi-scale information. However, it is still challenging to accurately detect subtle changes using current models, which has been the main bottleneck to improving detection accuracy. In this paper, a multi-scale differential feature self-attention network (MDFA-Net) is proposed to effectively integrate CNN and Transformer by balancing the global receptive field from the self-attention mechanism and the local receptive field from convolutions. In MDFA-Net, two innovative modules were designed. Particularly, a hierarchical multi-scale dilated convolution (HMDConv) module was proposed to extract local features with hybrid dilation convolutions, which can ameliorate the effect of CNN’s local bias. In addition, a differential feature self-attention (DFA) module was developed to implement the self-attention mechanism at multi-scale difference feature maps to overcome the problem that local details may be lost in the global receptive field in Transformer. The proposed MDFA-Net achieves state-of-the-art accuracy performance in comparison with related works, e.g., USSFC-Net, in three open datasets: WHU-CD, CDD-CD, and LEVIR-CD. Based on the experimental results, MDFA-Net significantly exceeds other models in F1 score, IoU, and overall accuracy; the F1 score is 93.81%, 95.52%, and 91.21% in WHU-CD, CDD-CD, and LEVIR-CD datasets, respectively. Furthermore, MDFA-Net achieved first or second place in precision and recall in the test in all three datasets, which indicates its better balance in precision and recall than other models. We also found that subtle changes, i.e., small-sized building changes and irregular boundary changes, are better detected thanks to the introduction of HMDConv and DFA. To this end, with its better ability to leverage multi-scale differential information than traditional methods, MDFA-Net provides a novel and effective avenue to integrate CNN and Transformer in BCD. Further studies could focus on improving the model’s insensitivity to hyper-parameters and the model’s generalizability in practical applications.
{"title":"MDFA-Net: Multi-Scale Differential Feature Self-Attention Network for Building Change Detection in Remote Sensing Images","authors":"Yuanling Li, Shengyuan Zou, Tianzhong Zhao, Xiaohui Su","doi":"10.3390/rs16183466","DOIUrl":"https://doi.org/10.3390/rs16183466","url":null,"abstract":"Building change detection (BCD) from remote sensing images is an essential field for urban studies. In this well-developed field, Convolutional Neural Networks (CNNs) and Transformer have been leveraged to empower BCD models in handling multi-scale information. However, it is still challenging to accurately detect subtle changes using current models, which has been the main bottleneck to improving detection accuracy. In this paper, a multi-scale differential feature self-attention network (MDFA-Net) is proposed to effectively integrate CNN and Transformer by balancing the global receptive field from the self-attention mechanism and the local receptive field from convolutions. In MDFA-Net, two innovative modules were designed. Particularly, a hierarchical multi-scale dilated convolution (HMDConv) module was proposed to extract local features with hybrid dilation convolutions, which can ameliorate the effect of CNN’s local bias. In addition, a differential feature self-attention (DFA) module was developed to implement the self-attention mechanism at multi-scale difference feature maps to overcome the problem that local details may be lost in the global receptive field in Transformer. The proposed MDFA-Net achieves state-of-the-art accuracy performance in comparison with related works, e.g., USSFC-Net, in three open datasets: WHU-CD, CDD-CD, and LEVIR-CD. Based on the experimental results, MDFA-Net significantly exceeds other models in F1 score, IoU, and overall accuracy; the F1 score is 93.81%, 95.52%, and 91.21% in WHU-CD, CDD-CD, and LEVIR-CD datasets, respectively. Furthermore, MDFA-Net achieved first or second place in precision and recall in the test in all three datasets, which indicates its better balance in precision and recall than other models. We also found that subtle changes, i.e., small-sized building changes and irregular boundary changes, are better detected thanks to the introduction of HMDConv and DFA. To this end, with its better ability to leverage multi-scale differential information than traditional methods, MDFA-Net provides a novel and effective avenue to integrate CNN and Transformer in BCD. Further studies could focus on improving the model’s insensitivity to hyper-parameters and the model’s generalizability in practical applications.","PeriodicalId":48993,"journal":{"name":"Remote Sensing","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Dae Wook Park, Han Eung Kim, Kicheol Lee, Jeongjun Park
In the process of using multi-channel ground-penetrating radar (GPR) for underground cavity exploration, the acquired 3D data include reflection data from underground cavities or various underground objects (structures). Reflection data from unspecified structures can interfere with the identification process of underground cavities. This study aims to identify underground cavities using a C-GAN model with an applied ResBlock technique. This deep learning model demonstrates excellent performance in the image domain and can automatically classify the presence of cavities by analyzing 3D GPR data, including reflection waveforms (A-scan), cross-sectional views (B-scan), and plan views (C-scan) measured from the ground under roads. To maximize the performance of the C-GAN model, a background filtering algorithm (BFA) was developed and applied to enhance the visibility and clarity of underground cavities. To verify the performance of the developed BFA, 3D data collected from roads in Seoul, Republic of Korea, using 3D GPR equipment were transformed, and the C-GAN model was applied. As a result, it was confirmed that the recall, an indicator of cavity prediction, improved by approximately 1.15 times compared to when the BFA was not applied. This signifies the verification of the effectiveness of the BFA. This study developed a special algorithm to distinguish underground cavities. This means that in the future, not only the advancement of separate equipment and systems but also the development of specific algorithms can contribute to the cavity exploration process.
{"title":"Development of a Background Filtering Algorithm to Improve the Accuracy of Determining Underground Cavities Using Multi-Channel Ground-Penetrating Radar and Deep Learning","authors":"Dae Wook Park, Han Eung Kim, Kicheol Lee, Jeongjun Park","doi":"10.3390/rs16183454","DOIUrl":"https://doi.org/10.3390/rs16183454","url":null,"abstract":"In the process of using multi-channel ground-penetrating radar (GPR) for underground cavity exploration, the acquired 3D data include reflection data from underground cavities or various underground objects (structures). Reflection data from unspecified structures can interfere with the identification process of underground cavities. This study aims to identify underground cavities using a C-GAN model with an applied ResBlock technique. This deep learning model demonstrates excellent performance in the image domain and can automatically classify the presence of cavities by analyzing 3D GPR data, including reflection waveforms (A-scan), cross-sectional views (B-scan), and plan views (C-scan) measured from the ground under roads. To maximize the performance of the C-GAN model, a background filtering algorithm (BFA) was developed and applied to enhance the visibility and clarity of underground cavities. To verify the performance of the developed BFA, 3D data collected from roads in Seoul, Republic of Korea, using 3D GPR equipment were transformed, and the C-GAN model was applied. As a result, it was confirmed that the recall, an indicator of cavity prediction, improved by approximately 1.15 times compared to when the BFA was not applied. This signifies the verification of the effectiveness of the BFA. This study developed a special algorithm to distinguish underground cavities. This means that in the future, not only the advancement of separate equipment and systems but also the development of specific algorithms can contribute to the cavity exploration process.","PeriodicalId":48993,"journal":{"name":"Remote Sensing","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250878","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The accurate and timely prediction of Napa cabbage fresh weight is essential for optimizing harvest timing, crop management, and supply chain logistics, which ultimately contributes to food security and price stabilization. Traditional manual sampling methods are labor-intensive and lack precision. This study introduces an artificial intelligence (AI)-powered model that utilizes unmanned aerial systems (UAS)-based multi-sensor data to predict Napa cabbage fresh weight. The model was developed using high-resolution RGB, multispectral (MSP), and thermal infrared (TIR) imagery collected throughout the 2020 growing season. The imagery was used to extract various vegetation indices, crop features (vegetation fraction, crop height model), and a water stress indicator (CWSI). The deep neural network (DNN) model consistently outperformed support vector machine (SVM) and random forest (RF) models, achieving the highest accuracy (R2 = 0.82, RMSE = 0.47 kg) during the mid-to-late rosette growth stage (35–42 days after planting, DAP). The model’s accuracy improved with cabbage maturity, emphasizing the importance of the heading stage for fresh weight estimation. The model slightly underestimated the weight of Napa cabbages exceeding 5 kg, potentially due to limited samples and saturation effects of vegetation indices. The overall error rate was less than 5%, demonstrating the feasibility of this approach. Spatial analysis further revealed that the model accurately captured variability in Napa cabbage growth across different soil types and irrigation conditions, particularly reflecting the positive impact of drip irrigation. This study highlights the potential of UAS-based multi-sensor data and AI for accurate and non-invasive prediction of Napa cabbage fresh weight, providing a valuable tool for optimizing harvest timing and crop management. Future research should focus on refining the model for specific weight ranges and diverse environmental conditions, and extending its application to other crops.
{"title":"Development of a UAS-Based Multi-Sensor Deep Learning Model for Predicting Napa Cabbage Fresh Weight and Determining Optimal Harvest Time","authors":"Dong-Ho Lee, Jong-Hwa Park","doi":"10.3390/rs16183455","DOIUrl":"https://doi.org/10.3390/rs16183455","url":null,"abstract":"The accurate and timely prediction of Napa cabbage fresh weight is essential for optimizing harvest timing, crop management, and supply chain logistics, which ultimately contributes to food security and price stabilization. Traditional manual sampling methods are labor-intensive and lack precision. This study introduces an artificial intelligence (AI)-powered model that utilizes unmanned aerial systems (UAS)-based multi-sensor data to predict Napa cabbage fresh weight. The model was developed using high-resolution RGB, multispectral (MSP), and thermal infrared (TIR) imagery collected throughout the 2020 growing season. The imagery was used to extract various vegetation indices, crop features (vegetation fraction, crop height model), and a water stress indicator (CWSI). The deep neural network (DNN) model consistently outperformed support vector machine (SVM) and random forest (RF) models, achieving the highest accuracy (R2 = 0.82, RMSE = 0.47 kg) during the mid-to-late rosette growth stage (35–42 days after planting, DAP). The model’s accuracy improved with cabbage maturity, emphasizing the importance of the heading stage for fresh weight estimation. The model slightly underestimated the weight of Napa cabbages exceeding 5 kg, potentially due to limited samples and saturation effects of vegetation indices. The overall error rate was less than 5%, demonstrating the feasibility of this approach. Spatial analysis further revealed that the model accurately captured variability in Napa cabbage growth across different soil types and irrigation conditions, particularly reflecting the positive impact of drip irrigation. This study highlights the potential of UAS-based multi-sensor data and AI for accurate and non-invasive prediction of Napa cabbage fresh weight, providing a valuable tool for optimizing harvest timing and crop management. Future research should focus on refining the model for specific weight ranges and diverse environmental conditions, and extending its application to other crops.","PeriodicalId":48993,"journal":{"name":"Remote Sensing","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shashank Karki, Thomas J. Pingel, Timothy D. Baird, Addison Flack, Todd Ogle
Digitals twins, used to represent dynamic environments, require accurate tracking of human movement to enhance their real-world application. This paper contributes to the field by systematically evaluating and comparing pre-existing tracking methods to identify strengths, weaknesses and practical applications within digital twin frameworks. The purpose of this study is to assess the efficacy of existing human movement tracking techniques for digital twins in real world environments, with the goal of improving spatial analysis and interaction within these virtual modes. We compare three approaches using indoor-mounted lidar sensors: (1) a frame-by-frame method deep learning model with convolutional neural networks (CNNs), (2) custom algorithms developed using OpenCV, and (3) the off-the-shelf lidar perception software package Percept version 1.6.3. Of these, the deep learning method performed best (F1 = 0.88), followed by Percept (F1 = 0.61), and finally the custom algorithms using OpenCV (F1 = 0.58). Each method had particular strengths and weaknesses, with OpenCV-based approaches that use frame comparison vulnerable to signal instability that is manifested as “flickering” in the dataset. Subsequent analysis of the spatial distribution of error revealed that both the custom algorithms and Percept took longer to acquire an identification, resulting in increased error near doorways. Percept software excelled in scenarios involving stationary individuals. These findings highlight the importance of selecting appropriate tracking methods for specific use. Future work will focus on model optimization, alternative data logging techniques, and innovative approaches to mitigate computational challenges, paving the way for more sophisticated and accessible spatial analysis tools. Integrating complementary sensor types and strategies, such as radar, audio levels, indoor positioning systems (IPSs), and wi-fi data, could further improve detection accuracy and validation while maintaining privacy.
{"title":"Enhancing Digital Twins with Human Movement Data: A Comparative Study of Lidar-Based Tracking Methods","authors":"Shashank Karki, Thomas J. Pingel, Timothy D. Baird, Addison Flack, Todd Ogle","doi":"10.3390/rs16183453","DOIUrl":"https://doi.org/10.3390/rs16183453","url":null,"abstract":"Digitals twins, used to represent dynamic environments, require accurate tracking of human movement to enhance their real-world application. This paper contributes to the field by systematically evaluating and comparing pre-existing tracking methods to identify strengths, weaknesses and practical applications within digital twin frameworks. The purpose of this study is to assess the efficacy of existing human movement tracking techniques for digital twins in real world environments, with the goal of improving spatial analysis and interaction within these virtual modes. We compare three approaches using indoor-mounted lidar sensors: (1) a frame-by-frame method deep learning model with convolutional neural networks (CNNs), (2) custom algorithms developed using OpenCV, and (3) the off-the-shelf lidar perception software package Percept version 1.6.3. Of these, the deep learning method performed best (F1 = 0.88), followed by Percept (F1 = 0.61), and finally the custom algorithms using OpenCV (F1 = 0.58). Each method had particular strengths and weaknesses, with OpenCV-based approaches that use frame comparison vulnerable to signal instability that is manifested as “flickering” in the dataset. Subsequent analysis of the spatial distribution of error revealed that both the custom algorithms and Percept took longer to acquire an identification, resulting in increased error near doorways. Percept software excelled in scenarios involving stationary individuals. These findings highlight the importance of selecting appropriate tracking methods for specific use. Future work will focus on model optimization, alternative data logging techniques, and innovative approaches to mitigate computational challenges, paving the way for more sophisticated and accessible spatial analysis tools. Integrating complementary sensor types and strategies, such as radar, audio levels, indoor positioning systems (IPSs), and wi-fi data, could further improve detection accuracy and validation while maintaining privacy.","PeriodicalId":48993,"journal":{"name":"Remote Sensing","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xiang Gao, Ronghao Yang, Xuewen Chen, Junxiang Tan, Yan Liu, Zhaohua Wang, Jiahao Tan, Huan Liu
Three-dimensional indoor models have wide applications in fields such as indoor navigation, civil engineering, virtual reality, and so on. With the development of LiDAR technology, automatic reconstruction of indoor models from point clouds has gained significant attention. We propose a new framework for generating indoor 3D digital models from point clouds. The proposed method first generates a room instance map of an indoor scene. Walls are detected and projected onto a horizontal plane to form line segments. These segments are extended, intersected, and, by solving an integer programming problem, line segments are selected to create room polygons. The polygons are converted into a raster image, and image connectivity detection is used to generate a room instance map. Then the roofs of the point cloud are extracted and used to perform an overlap analysis with the generated room instance map to segment the entire roof point cloud, obtaining the roof for each room. Room boundaries are defined by extracting and regularizing the roof point cloud boundaries. Finally, by detecting doors and windows in the scene in two steps, we generate the floor plans and 3D models separately. Experiments with the Giblayout dataset show that our method is robust to clutter and furniture point clouds, achieving high-accuracy models that match real scenes. The mean precision and recall for the floorplans are both 0.93, and the Point–Surface Distance (PSD) and standard deviation of the PSD for the 3D models are 0.044 m and 0.066 m, respectively.
{"title":"A New Framework for Generating Indoor 3D Digital Models from Point Clouds","authors":"Xiang Gao, Ronghao Yang, Xuewen Chen, Junxiang Tan, Yan Liu, Zhaohua Wang, Jiahao Tan, Huan Liu","doi":"10.3390/rs16183462","DOIUrl":"https://doi.org/10.3390/rs16183462","url":null,"abstract":"Three-dimensional indoor models have wide applications in fields such as indoor navigation, civil engineering, virtual reality, and so on. With the development of LiDAR technology, automatic reconstruction of indoor models from point clouds has gained significant attention. We propose a new framework for generating indoor 3D digital models from point clouds. The proposed method first generates a room instance map of an indoor scene. Walls are detected and projected onto a horizontal plane to form line segments. These segments are extended, intersected, and, by solving an integer programming problem, line segments are selected to create room polygons. The polygons are converted into a raster image, and image connectivity detection is used to generate a room instance map. Then the roofs of the point cloud are extracted and used to perform an overlap analysis with the generated room instance map to segment the entire roof point cloud, obtaining the roof for each room. Room boundaries are defined by extracting and regularizing the roof point cloud boundaries. Finally, by detecting doors and windows in the scene in two steps, we generate the floor plans and 3D models separately. Experiments with the Giblayout dataset show that our method is robust to clutter and furniture point clouds, achieving high-accuracy models that match real scenes. The mean precision and recall for the floorplans are both 0.93, and the Point–Surface Distance (PSD) and standard deviation of the PSD for the 3D models are 0.044 m and 0.066 m, respectively.","PeriodicalId":48993,"journal":{"name":"Remote Sensing","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Andrew Du, Anh-Dzung Doan, Yee Wei Law, Tat-Jun Chin
The advent of satellite-borne machine learning hardware accelerators has enabled the onboard processing of payload data using machine learning techniques such as convolutional neural networks (CNNs). A notable example is using a CNN to detect the presence of clouds in the multispectral data captured on Earth observation (EO) missions, whereby only clear sky data are downlinked to conserve bandwidth. However, prior to deployment, new missions that employ new sensors will not have enough representative datasets to train a CNN model, while a model trained solely on data from previous missions will underperform when deployed to process the data on the new missions. This underperformance stems from the domain gap, i.e., differences in the underlying distributions of the data generated by the different sensors in previous and future missions. In this paper, we address the domain gap problem in the context of onboard multispectral cloud detection. Our main contributions lie in formulating new domain adaptation tasks that are motivated by a concrete EO mission, developing a novel algorithm for bandwidth-efficient supervised domain adaptation, and demonstrating test-time adaptation algorithms on space deployable neural network accelerators. Our contributions enable minimal data transmission to be invoked (e.g., only 1% of the weights in ResNet50) to achieve domain adaptation, thereby allowing more sophisticated CNN models to be deployed and updated on satellites without being hampered by domain gap and bandwidth limitations.
{"title":"Domain Adaptation for Satellite-Borne Multispectral Cloud Detection","authors":"Andrew Du, Anh-Dzung Doan, Yee Wei Law, Tat-Jun Chin","doi":"10.3390/rs16183469","DOIUrl":"https://doi.org/10.3390/rs16183469","url":null,"abstract":"The advent of satellite-borne machine learning hardware accelerators has enabled the onboard processing of payload data using machine learning techniques such as convolutional neural networks (CNNs). A notable example is using a CNN to detect the presence of clouds in the multispectral data captured on Earth observation (EO) missions, whereby only clear sky data are downlinked to conserve bandwidth. However, prior to deployment, new missions that employ new sensors will not have enough representative datasets to train a CNN model, while a model trained solely on data from previous missions will underperform when deployed to process the data on the new missions. This underperformance stems from the domain gap, i.e., differences in the underlying distributions of the data generated by the different sensors in previous and future missions. In this paper, we address the domain gap problem in the context of onboard multispectral cloud detection. Our main contributions lie in formulating new domain adaptation tasks that are motivated by a concrete EO mission, developing a novel algorithm for bandwidth-efficient supervised domain adaptation, and demonstrating test-time adaptation algorithms on space deployable neural network accelerators. Our contributions enable minimal data transmission to be invoked (e.g., only 1% of the weights in ResNet50) to achieve domain adaptation, thereby allowing more sophisticated CNN models to be deployed and updated on satellites without being hampered by domain gap and bandwidth limitations.","PeriodicalId":48993,"journal":{"name":"Remote Sensing","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142268639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Gislayne Farias Valente, Gabriel Araújo e Silva Ferraz, Felipe Schwerz, Rafael de Oliveira Faria, Felipe Augusto Fernandes, Diego Bedin Marin
An accurate assessment of frost damage in coffee plantations can help develop effective agronomic practices to cope with extreme weather events. Remotely piloted aircrafts (RPA) have emerged as promising tools to evaluate the impacts caused by frost on coffee production. The objective was to evaluate the impact of frost on coffee plants, using vegetation indices, in plantations of different ages and areas of climatic risks. We evaluated two coffee plantations located in Brazil, aged one and two years on the date of frost occurrence. Multispectral images were collected by a remotely piloted aircraft, three days after the occurrence of frost in July 2021. The relationship between frost damage and these vegetation indices was estimated by Pearson’s correlation using simple and multiple linear regression. The results showed that variations in frost damage were observed based on planting age and topography conditions. The use of PRA was efficient in evaluating frost damage in both young and adult plants, indicating its potential and application in different situations. The vegetation index MSR and MCARI2 indices were effective in assessing damage in one-year-old coffee plantations, whereas the SAVI, MCARI1, and MCARI2 indices were more suitable for visualizing frost damage in two-year-old coffee plantations.
准确评估咖啡种植园的霜冻损失有助于制定有效的农艺措施，以应对极端天气事件。遥控飞机（RPA）已成为评估霜冻对咖啡生产影响的理想工具。我们的目标是利用植被指数评估霜冻对不同树龄和气候风险地区的咖啡种植园的影响。我们对位于巴西的两个咖啡种植园进行了评估，这两个种植园在霜冻发生当日的树龄分别为一年和两年。2021 年 7 月霜冻发生三天后，我们用遥控飞机采集了多光谱图像。利用简单和多元线性回归，通过皮尔逊相关性估算了霜冻损害与这些植被指数之间的关系。结果表明，冻害因种植年龄和地形条件而异。使用 PRA 可以有效评估幼苗和成株的冻害情况，这表明 PRA 在不同情况下都具有应用潜力。植被指数 MSR 和 MCARI2 指数可有效评估一龄咖啡种植园的冻害情况，而 SAVI、MCARI1 和 MCARI2 指数则更适用于观察二龄咖啡种植园的冻害情况。
{"title":"Remotely Piloted Aircraft for Evaluating the Impact of Frost in Coffee Plants: Interactions between Plant Age and Topography","authors":"Gislayne Farias Valente, Gabriel Araújo e Silva Ferraz, Felipe Schwerz, Rafael de Oliveira Faria, Felipe Augusto Fernandes, Diego Bedin Marin","doi":"10.3390/rs16183467","DOIUrl":"https://doi.org/10.3390/rs16183467","url":null,"abstract":"An accurate assessment of frost damage in coffee plantations can help develop effective agronomic practices to cope with extreme weather events. Remotely piloted aircrafts (RPA) have emerged as promising tools to evaluate the impacts caused by frost on coffee production. The objective was to evaluate the impact of frost on coffee plants, using vegetation indices, in plantations of different ages and areas of climatic risks. We evaluated two coffee plantations located in Brazil, aged one and two years on the date of frost occurrence. Multispectral images were collected by a remotely piloted aircraft, three days after the occurrence of frost in July 2021. The relationship between frost damage and these vegetation indices was estimated by Pearson’s correlation using simple and multiple linear regression. The results showed that variations in frost damage were observed based on planting age and topography conditions. The use of PRA was efficient in evaluating frost damage in both young and adult plants, indicating its potential and application in different situations. The vegetation index MSR and MCARI2 indices were effective in assessing damage in one-year-old coffee plantations, whereas the SAVI, MCARI1, and MCARI2 indices were more suitable for visualizing frost damage in two-year-old coffee plantations.","PeriodicalId":48993,"journal":{"name":"Remote Sensing","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142268638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zhenxiong Zhou, Boheng Duan, Kaijun Ren, Weicheng Ni, Ruixin Cao
Significant Wave Height (SWH) is a crucial parameter in oceanographic research, essential for understanding various marine and atmospheric processes. Traditional methods for obtaining SWH, such as ship-based and buoy measurements, face limitations like limited spatial coverage and high operational costs. With the advancement of Global Navigation Satellite Systems reflectometry (GNSS-R) technology, a new method for retrieving SWH has emerged, demonstrating promising results. This study utilizes Radio occultation sounder (GNOS) data from the FY-3E satellite and incorporates the latest Vision Transformer (ViT) technology to investigate GNSS-R-based SWH retrieval. We designed and evaluated various deep learning models, including ANN-Wave, CNN-Wave, Hybrid-Wave, Trans-Wave, and ViT-Wave. Through comparative training using ERA5 data, the ViT-Wave model was identified as the optimal retrieval model. The ViT-Wave model achieved a Root Mean Square Error (RMSE) accuracy of 0.4052 m and Mean Absolute Error (MAE) accuracy of 0.2700 m, significantly outperforming both traditional methods and newer deep learning approaches utilizing Cyclone Global Navigation Satellite Systems (CYGNSS) data. These results underscore the potential of integrating GNSS-R technology with advanced deep-learning models to enhance SWH retrieval accuracy and reliability in oceanographic research.
{"title":"Enhancing Significant Wave Height Retrieval with FY-3E GNSS-R Data: A Comparative Analysis of Deep Learning Models","authors":"Zhenxiong Zhou, Boheng Duan, Kaijun Ren, Weicheng Ni, Ruixin Cao","doi":"10.3390/rs16183468","DOIUrl":"https://doi.org/10.3390/rs16183468","url":null,"abstract":"Significant Wave Height (SWH) is a crucial parameter in oceanographic research, essential for understanding various marine and atmospheric processes. Traditional methods for obtaining SWH, such as ship-based and buoy measurements, face limitations like limited spatial coverage and high operational costs. With the advancement of Global Navigation Satellite Systems reflectometry (GNSS-R) technology, a new method for retrieving SWH has emerged, demonstrating promising results. This study utilizes Radio occultation sounder (GNOS) data from the FY-3E satellite and incorporates the latest Vision Transformer (ViT) technology to investigate GNSS-R-based SWH retrieval. We designed and evaluated various deep learning models, including ANN-Wave, CNN-Wave, Hybrid-Wave, Trans-Wave, and ViT-Wave. Through comparative training using ERA5 data, the ViT-Wave model was identified as the optimal retrieval model. The ViT-Wave model achieved a Root Mean Square Error (RMSE) accuracy of 0.4052 m and Mean Absolute Error (MAE) accuracy of 0.2700 m, significantly outperforming both traditional methods and newer deep learning approaches utilizing Cyclone Global Navigation Satellite Systems (CYGNSS) data. These results underscore the potential of integrating GNSS-R technology with advanced deep-learning models to enhance SWH retrieval accuracy and reliability in oceanographic research.","PeriodicalId":48993,"journal":{"name":"Remote Sensing","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142268692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zachary Mondschein, Ambica Paliwal, Tesfaye Shiferaw Sida, Jordan Chamberlin, Runzi Wang, Meha Jain
Remote sensing offers a low-cost method for estimating yields at large spatio-temporal scales. Here, we examined the ability of Sentinel-2 satellite imagery to map field-level maize yields across smallholder farms in two regions in Oromia district, Ethiopia. We evaluated how effectively different indices, the MTCI, GCVI, and NDVI, and different models, linear regression and random forest regression, can be used to map field-level yields. We also examined if models improved by adding weather and soil data and how generalizable our models were if trained in one region and applied to another region, where no data were used for model calibration. We found that random forest regression models that used monthly MTCI composites led to the highest yield prediction accuracies (R2 up to 0.63), particularly when using only localized data for training the model. These models were not very generalizable, especially when applied to regions that had significant haze remaining in the imagery. We also found that adding soil and weather data did little to improve model fit. Our results highlight the ability of Sentinel-2 imagery to map field-level yields in smallholder systems, though accuracies are limited in regions with high cloud cover and haze.
{"title":"Mapping Field-Level Maize Yields in Ethiopian Smallholder Systems Using Sentinel-2 Imagery","authors":"Zachary Mondschein, Ambica Paliwal, Tesfaye Shiferaw Sida, Jordan Chamberlin, Runzi Wang, Meha Jain","doi":"10.3390/rs16183451","DOIUrl":"https://doi.org/10.3390/rs16183451","url":null,"abstract":"Remote sensing offers a low-cost method for estimating yields at large spatio-temporal scales. Here, we examined the ability of Sentinel-2 satellite imagery to map field-level maize yields across smallholder farms in two regions in Oromia district, Ethiopia. We evaluated how effectively different indices, the MTCI, GCVI, and NDVI, and different models, linear regression and random forest regression, can be used to map field-level yields. We also examined if models improved by adding weather and soil data and how generalizable our models were if trained in one region and applied to another region, where no data were used for model calibration. We found that random forest regression models that used monthly MTCI composites led to the highest yield prediction accuracies (R2 up to 0.63), particularly when using only localized data for training the model. These models were not very generalizable, especially when applied to regions that had significant haze remaining in the imagery. We also found that adding soil and weather data did little to improve model fit. Our results highlight the ability of Sentinel-2 imagery to map field-level yields in smallholder systems, though accuracies are limited in regions with high cloud cover and haze.","PeriodicalId":48993,"journal":{"name":"Remote Sensing","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：