Pub Date : 2024-11-15DOI: 10.1016/j.jag.2024.104241
Kan Wei , JinKun Dai , Danfeng Hong , Yuanxin Ye
The heterogeneity and complexity of multimodal data in high-resolution remote sensing images significantly challenges existing cross-modal networks in fusing the complementary information of high-resolution optical and synthetic aperture radar (SAR) images for precise semantic segmentation. To address this issue, this paper proposes a multi-layer perceptron (MLP) dominated gate fusion network (MGFNet). MGFNet consists of three modules: a multi-path feature extraction network, an MLP-gate fusion (MGF) module, and a decoder. Initially, MGFNet independently extracts features from high-resolution optical and SAR images while preserving spatial information. Then, the well-designed MGF module combines the multi-modal features through channel attention and gated fusion stages, utilizing MLP as a gate to exploit complementary information and filter redundant data. Additionally, we introduce a novel high-resolution multimodal remote sensing dataset, YESeg-OPT-SAR, with a spatial resolution of 0.5 m. To evaluate MGFNet, we compare it with several state-of-the-art (SOTA) models using YESeg-OPT-SAR and Pohang datasets, both of which are high-resolution multi-modal datasets. The experimental results demonstrate that MGFNet achieves higher evaluation metrics compared to other models, indicating its effectiveness in multi-modal feature fusion for segmentation. The source code and data are available at https://github.com/yeyuanxin110/YESeg-OPT-SAR.
{"title":"MGFNet: An MLP-dominated gated fusion network for semantic segmentation of high-resolution multi-modal remote sensing images","authors":"Kan Wei , JinKun Dai , Danfeng Hong , Yuanxin Ye","doi":"10.1016/j.jag.2024.104241","DOIUrl":"10.1016/j.jag.2024.104241","url":null,"abstract":"<div><div>The heterogeneity and complexity of multimodal data in high-resolution remote sensing images significantly challenges existing cross-modal networks in fusing the complementary information of high-resolution optical and synthetic aperture radar (SAR) images for precise semantic segmentation. To address this issue, this paper proposes a multi-layer perceptron (MLP) dominated gate fusion network (MGFNet). MGFNet consists of three modules: a multi-path feature extraction network, an MLP-gate fusion (MGF) module, and a decoder. Initially, MGFNet independently extracts features from high-resolution optical and SAR images while preserving spatial information. Then, the well-designed MGF module combines the multi-modal features through channel attention and gated fusion stages, utilizing MLP as a gate to exploit complementary information and filter redundant data. Additionally, we introduce a novel high-resolution multimodal remote sensing dataset, YESeg-OPT-SAR, with a spatial resolution of 0.5 m. To evaluate MGFNet, we compare it with several state-of-the-art (SOTA) models using YESeg-OPT-SAR and Pohang datasets, both of which are high-resolution multi-modal datasets. The experimental results demonstrate that MGFNet achieves higher evaluation metrics compared to other models, indicating its effectiveness in multi-modal feature fusion for segmentation. The source code and data are available at <span><span>https://github.com/yeyuanxin110/YESeg-OPT-SAR</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"135 ","pages":"Article 104241"},"PeriodicalIF":7.6,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142651956","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-13DOI: 10.1016/j.jag.2024.104269
Mengjie Wang, Xi Li
Traditional methods for measuring asset wealth face limitations due to data scarcity, making it challenging to apply them on a large scale and over long periods with fine granularity. Publicly available satellite images, such as nighttime light imagery, have become an important alternative data source for estimating asset wealth. This study thoroughly exploited the spatial neighborhood information of nighttime light, combined with other remote sensing features and the cross-national, temporally comparable International Wealth Index (IWI), to construct long-term asset wealth estimation models for African countries with and without sample data. Based on these models, it generates asset wealth estimates for African settlements at a 500 m spatial resolution from 2012 to 2022. The R2 values for the models of countries with and without sample data are 0.85 and 0.76, respectively, with mean absolute errors of 6.08 and 8.35, and root means square errors of 8.52 and 10.81, respectively. Additionally, the accuracy of the temporal variation estimates surpasses previous related studies, achieving an R2 of 0.60. From 2012 to 2022, the overall IWI increased from 28.80 to 30.80, representing an increase of 0.11 standard deviations. In addition to countries with household survey data, the proposed method can also accurately estimate asset wealth for countries without survey data and effectively track asset wealth changes over time.
{"title":"Estimation of long time-series fine-grained asset wealth in Africa using publicly available remote sensing imagery","authors":"Mengjie Wang, Xi Li","doi":"10.1016/j.jag.2024.104269","DOIUrl":"10.1016/j.jag.2024.104269","url":null,"abstract":"<div><div>Traditional methods for measuring asset wealth face limitations due to data scarcity, making it challenging to apply them on a large scale and over long periods with fine granularity. Publicly available satellite images, such as nighttime light imagery, have become an important alternative data source for estimating asset wealth. This study thoroughly exploited the spatial neighborhood information of nighttime light, combined with other remote sensing features and the cross-national, temporally comparable International Wealth Index (IWI), to construct long-term asset wealth estimation models for African countries with and without sample data. Based on these models, it generates asset wealth estimates for African settlements at a 500 m spatial resolution from 2012 to 2022. The R<sup>2</sup> values for the models of countries with and without sample data are 0.85 and 0.76, respectively, with mean absolute errors of 6.08 and 8.35, and root means square errors of 8.52 and 10.81, respectively. Additionally, the accuracy of the temporal variation estimates surpasses previous related studies, achieving an R<sup>2</sup> of 0.60. From 2012 to 2022, the overall IWI increased from 28.80 to 30.80, representing an increase of 0.11 standard deviations. In addition to countries with household survey data, the proposed method can also accurately estimate asset wealth for countries without survey data and effectively track asset wealth changes over time.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"135 ","pages":"Article 104269"},"PeriodicalIF":7.6,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142651763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-13DOI: 10.1016/j.jag.2024.104263
Dan Kong, Yong Pang
Supervised classification methods can distinguish between noise and signal in ice, cloud, and land elevation satellite-2 (ICESat-2) data across various feature perspectives and autonomously optimize parameters. Nevertheless, model generalization remains a significant limitation for practical applications. This study focuses on developing a universal denoising model for ICESat-2 using machine learning algorithms and analyzing its spatial transferability under various forest and terrain conditions. A photon-denoising feature parameter system is developed based on the analysis of the three-dimensional distribution of photons in forested regions. This system reduces the parameters dependent on absolute physical quantities and increases those that are less influenced by terrain and forest features to enhance the model’s transferability. Subsequently, automated machine learning algorithms (AutoML) are used for model selection and parameter optimization across six non-parametric regression models. We evaluate the accuracies of the local, global, and transfer models in estimating canopy height across four representative forested areas in China. Results show that the algorithm can effectively distinguish between signal and noise photons. The estimated canopy heights from signal photons are highly consistent with heights obtained using airborne laser scanning (ALS), exhibiting a Pearson correlation coefficient (r) of 0.89, root mean square errors (RMSE) of 3.75 m, relative root mean square error (rRMSE) of 0.27, relative bias (rBias) of −0.11 and mean Bias of −1.45 m. Notably, the accuracy of canopy height estimation by the global model has increased by an average of 21 % compared to ICESat-2 land-vegetation along-track products (ATL08). Furthermore, the model exhibits significant spatial transfer capabilities, with the accuracies of the transfer model exceeding those of ATL08 by margins ranging from 4 % to 41 %. This study marks a significant advancement in photon-denoising methodologies, providing a robust and transferable solution for large-scale environmental data analysis.
{"title":"ICESat-2 data denoising and forest canopy height estimation using Machine Learning","authors":"Dan Kong, Yong Pang","doi":"10.1016/j.jag.2024.104263","DOIUrl":"10.1016/j.jag.2024.104263","url":null,"abstract":"<div><div>Supervised classification methods can distinguish between noise and signal in ice, cloud, and land elevation satellite-2 (ICESat-2) data across various feature perspectives and autonomously optimize parameters. Nevertheless, model generalization remains a significant limitation for practical applications. This study focuses on developing a universal denoising model for ICESat-2 using machine learning algorithms and analyzing its spatial transferability under various forest and terrain conditions. A photon-denoising feature parameter system is developed based on the analysis of the three-dimensional distribution of photons in forested regions. This system reduces the parameters dependent on absolute physical quantities and increases those that are less influenced by terrain and forest features to enhance the model’s transferability. Subsequently, automated machine learning algorithms (AutoML) are used for model selection and parameter optimization across six non-parametric regression models. We evaluate the accuracies of the local, global, and transfer models in estimating canopy height across four representative forested areas in China. Results show that the algorithm can effectively distinguish between signal and noise photons. The estimated canopy heights from signal photons are highly consistent with heights obtained using airborne laser scanning (ALS), exhibiting a Pearson correlation coefficient (r) of 0.89, root mean square errors (RMSE) of 3.75 m, relative root mean square error (rRMSE) of 0.27, relative bias (rBias) of −0.11 and mean Bias of −1.45 m. Notably, the accuracy of canopy height estimation by the global model has increased by an average of 21 % compared to ICESat-2 land-vegetation along-track products (ATL08). Furthermore, the model exhibits significant spatial transfer capabilities, with the accuracies of the transfer model exceeding those of ATL08 by margins ranging from 4 % to 41 %. This study marks a significant advancement in photon-denoising methodologies, providing a robust and transferable solution for large-scale environmental data analysis.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"135 ","pages":"Article 104263"},"PeriodicalIF":7.6,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142651865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-12DOI: 10.1016/j.jag.2024.104247
Jiwei Hu , Tianhao Wang , Qiwen Jin , Chengli Peng , Quan Liu
Hyperspectral unmixing is of vital importance within the realm of hyperspectral analysis, which is aimed to decide the fractional proportion (abundances) of fundamental spectral signatures (endmembers) at a subpixel level. Unsupervised unmixing techniques that employ autoencoder (AE) network have gained significant attention for its exceptional feature extraction capabilities. However, traditional AE-based methods lean towards focusing excessively on the information of spectral dimension in the data, resulting in limited ability to extract endmembers with meaningful physical interpretations, and achieve uncompetitive performance. In this paper, we propose a novel multi-domain dual-stream network, called MdsNet, which enhances performance by incorporating high-rank spatial information to guide the unmixing process. This approach allows us to uncover pure endmember data that is hidden within the original hyperspectral image (HSI). We first apply superpixel segmentation and smoothing operations as preprocessing steps to transform the HSI into a coarse domain. Then, MdsNet efficiently handles multi-domain data and employs attention generated from the approximate domain to learn meaningful information about the endmembers’ physical characteristic. Experimental results and ablation studies conducted on Synthetic and real datasets (Samson, Japser, Urban) outperform state-of-the-art techniques by more than 10% in terms of root mean squared error and spectral angle distance, illustrating the effectiveness and superiority of our proposed method. The source code is available at https://github.com/qiwenjjin/JAG-MdsNet.
{"title":"A multi-domain dual-stream network for hyperspectral unmixing","authors":"Jiwei Hu , Tianhao Wang , Qiwen Jin , Chengli Peng , Quan Liu","doi":"10.1016/j.jag.2024.104247","DOIUrl":"10.1016/j.jag.2024.104247","url":null,"abstract":"<div><div>Hyperspectral unmixing is of vital importance within the realm of hyperspectral analysis, which is aimed to decide the fractional proportion (abundances) of fundamental spectral signatures (endmembers) at a subpixel level. Unsupervised unmixing techniques that employ autoencoder (AE) network have gained significant attention for its exceptional feature extraction capabilities. However, traditional AE-based methods lean towards focusing excessively on the information of spectral dimension in the data, resulting in limited ability to extract endmembers with meaningful physical interpretations, and achieve uncompetitive performance. In this paper, we propose a novel multi-domain dual-stream network, called MdsNet, which enhances performance by incorporating high-rank spatial information to guide the unmixing process. This approach allows us to uncover pure endmember data that is hidden within the original hyperspectral image (HSI). We first apply superpixel segmentation and smoothing operations as preprocessing steps to transform the HSI into a coarse domain. Then, MdsNet efficiently handles multi-domain data and employs attention generated from the approximate domain to learn meaningful information about the endmembers’ physical characteristic. Experimental results and ablation studies conducted on Synthetic and real datasets (Samson, Japser, Urban) outperform state-of-the-art techniques by more than 10% in terms of root mean squared error and spectral angle distance, illustrating the effectiveness and superiority of our proposed method. The source code is available at <span><span>https://github.com/qiwenjjin/JAG-MdsNet</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"135 ","pages":"Article 104247"},"PeriodicalIF":7.6,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142651758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-11DOI: 10.1016/j.jag.2024.104223
Ma. Flordeliza P. Del Castillo , Toshio Fujimi , Hirokazu Tatano
Economic impact estimates of the initial lockdowns due to the COVID-19 pandemic showed a significant reduction in economic activities globally. However, the succeeding impacts and their spatiotemporal distribution within countries remain unknown. Studies showed that nighttime light data (NTL) has effectively revealed the spatiotemporal dimensions of the economic effects of COVID-19. Thus, this study used NTL data to determine the medium-term regional monthly economic impacts of the pandemic in the Philippines in terms of the Economic Activity Reduction (EAR) index. We generated a spatial error model, regressing pre-pandemic NTL on mean temperature, maximum rainfall, and built-up area. This model explained 81.6% of the pre-pandemic NTL and was used to estimate the counterfactual NTL. We subtracted the actual from the counterfactual to compute the EAR. Then, the EAR was regressed on regional factors to determine which ones influence the impacts. Results showed uneven distribution of EAR across space and time. The EAR was generally higher in urban regions than in rural ones. Overall, more regions in the south had higher EAR. Temporally, the EAR showed a dynamic pattern, increasing in less urban regions and decreasing in highly urbanized regions. Regional analysis showed that urbanization level, population density, and poverty incidence had a significant positive relationship with the EAR. Beyond the immediate impacts, NTL effectively revealed spatiotemporal dimensions of the economic effects of a long-term global hazard.
{"title":"Estimating medium-term regional monthly economic activity reductions during the COVID-19 pandemic using nighttime light data","authors":"Ma. Flordeliza P. Del Castillo , Toshio Fujimi , Hirokazu Tatano","doi":"10.1016/j.jag.2024.104223","DOIUrl":"10.1016/j.jag.2024.104223","url":null,"abstract":"<div><div>Economic impact estimates of the initial lockdowns due to the COVID-19 pandemic showed a significant reduction in economic activities globally. However, the succeeding impacts and their spatiotemporal distribution within countries remain unknown. Studies showed that nighttime light data (NTL) has effectively revealed the spatiotemporal dimensions of the economic effects of COVID-19. Thus, this study used NTL data to determine the medium-term regional monthly economic impacts of the pandemic in the Philippines in terms of the Economic Activity Reduction (EAR) index. We generated a spatial error model, regressing pre-pandemic NTL on mean temperature, maximum rainfall, and built-up area. This model explained 81.6% of the pre-pandemic NTL and was used to estimate the counterfactual NTL. We subtracted the actual from the counterfactual to compute the EAR. Then, the EAR was regressed on regional factors to determine which ones influence the impacts. Results showed uneven distribution of EAR across space and time. The EAR was generally higher in urban regions than in rural ones. Overall, more regions in the south had higher EAR. Temporally, the EAR showed a dynamic pattern, increasing in less urban regions and decreasing in highly urbanized regions. Regional analysis showed that urbanization level, population density, and poverty incidence had a significant positive relationship with the EAR. Beyond the immediate impacts, NTL effectively revealed spatiotemporal dimensions of the economic effects of a long-term global hazard.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"135 ","pages":"Article 104223"},"PeriodicalIF":7.6,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142651872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-11DOI: 10.1016/j.jag.2024.104252
Fabian Sittaro , Michael Vohland
Invasive alien plant species (IPS) are one of the major threats to biodiversity and ecosystem services. As the dynamics of biological invasions by non-native plant species are expected to intensify with climate change, there is an increasing need to provide accessible information on the distribution of IPS to improve environmental management programmes. Monitoring the probability of occurrence of IPS is therefore essential to limit their spread, as control measures are most effective in the early stages of invasion. This article presents IPS Monitor, a tool developed to monitor habitat suitability for IPS in Germany under current and projected climate conditions. Developed from previous research on IPS impacts and habitat modelling, the tool facilitates the visualisation of habitat suitability for 45 IPS through digital web maps and fact sheets. IPS Monitor acts as a bridge between scientific research and its application, aiming to support decision-making by conservationists, policy-makers and other stakeholders. It provides a scientific basis for developing targeted strategies against the spread of IPS and enables integrated management approaches by providing access to synthesised research and predictive modelling.
{"title":"IPS Monitor – A habitat suitability monitoring tool for invasive alien plant species in Germany","authors":"Fabian Sittaro , Michael Vohland","doi":"10.1016/j.jag.2024.104252","DOIUrl":"10.1016/j.jag.2024.104252","url":null,"abstract":"<div><div>Invasive alien plant species (IPS) are one of the major threats to biodiversity and ecosystem services. As the dynamics of biological invasions by non-native plant species are expected to intensify with climate change, there is an increasing need to provide accessible information on the distribution of IPS to improve environmental management programmes. Monitoring the probability of occurrence of IPS is therefore essential to limit their spread, as control measures are most effective in the early stages of invasion. This article presents IPS Monitor, a tool developed to monitor habitat suitability for IPS in Germany under current and projected climate conditions. Developed from previous research on IPS impacts and habitat modelling, the tool facilitates the visualisation of habitat suitability for 45 IPS through digital web maps and fact sheets. IPS Monitor acts as a bridge between scientific research and its application, aiming to support decision-making by conservationists, policy-makers and other stakeholders. It provides a scientific basis for developing targeted strategies against the spread of IPS and enables integrated management approaches by providing access to synthesised research and predictive modelling.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"135 ","pages":"Article 104252"},"PeriodicalIF":7.6,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142651757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-11DOI: 10.1016/j.jag.2024.104253
Yinqing Zhen, Qingyun Yan
The escalating water pollution in many lakes has led to more frequent occurrences of algal bloom disasters in recent decades. The severity of these disasters can be assessed through remote sensing techniques, specifically using the Normalized Difference Vegetation Index (NDVI) for measurement. However, NDVI observations using optical sensors are often affected by cloud and fog in areas with numerous water bodies, such as Taihu Lake. Sensors operating in the microwave band can effectively mitigate this issue, particularly the emerging Global Navigation Satellite System Reflectometry (GNSS-R), which offers high temporal resolution and cost-effectiveness. In this paper, we propose a new method to recover lake-surface NDVI on cloudy days, utilizing GNSS-R observables and auxiliary meteorological data in conjunction with a machine learning regression algorithm called Bagging Tree. We also examine the effective range of GNSS-R data within this application scenario. Meanwhile, the Weighted Linear Regression-Laplacian Prior Regulation Method (WLR-LPRM) image gap-filling algorithm is used as a benchmark to evaluate recovery accuracy. The regression coefficient of NDVI retrieved using the proposed method is 0.95, with a root mean square error (RMSE) of 0.021 and a mean absolute error (MAE) of 0.010. Compared to the previous work on GNSS-R algal bloom detection with overall accuracy of 0.82, this work shows significant improvement in both accuracy and utility. The recovery of lake surface NDVI provides detailed insights into algal blooms, including quantifiable metrics such as the amount and spatial distribution, which are crucial for effective monitoring and management. Additionally, the recovered image textures exhibit high clarity and closely resemble the reference NDVI images. Experimental evaluation using simulated and actual cloud blocks indicates the model’s robustness to recover NDVI under varying cloud cover conditions. In summary, this study demonstrates the capability of GNSS-R aided by supplementary data for recovering missing NDVI values on lake surfaces when optical observations are absent for the first time.
{"title":"Recovering NDVI over lake surfaces: Initial insights from CYGNSS data enhanced by ERA-5 inputs","authors":"Yinqing Zhen, Qingyun Yan","doi":"10.1016/j.jag.2024.104253","DOIUrl":"10.1016/j.jag.2024.104253","url":null,"abstract":"<div><div>The escalating water pollution in many lakes has led to more frequent occurrences of algal bloom disasters in recent decades. The severity of these disasters can be assessed through remote sensing techniques, specifically using the Normalized Difference Vegetation Index (NDVI) for measurement. However, NDVI observations using optical sensors are often affected by cloud and fog in areas with numerous water bodies, such as Taihu Lake. Sensors operating in the microwave band can effectively mitigate this issue, particularly the emerging Global Navigation Satellite System Reflectometry (GNSS-R), which offers high temporal resolution and cost-effectiveness. In this paper, we propose a new method to recover lake-surface NDVI on cloudy days, utilizing GNSS-R observables and auxiliary meteorological data in conjunction with a machine learning regression algorithm called Bagging Tree. We also examine the effective range of GNSS-R data within this application scenario. Meanwhile, the Weighted Linear Regression-Laplacian Prior Regulation Method (WLR-LPRM) image gap-filling algorithm is used as a benchmark to evaluate recovery accuracy. The regression coefficient of NDVI retrieved using the proposed method is 0.95, with a root mean square error (RMSE) of 0.021 and a mean absolute error (MAE) of 0.010. Compared to the previous work on GNSS-R algal bloom detection with overall accuracy of 0.82, this work shows significant improvement in both accuracy and utility. The recovery of lake surface NDVI provides detailed insights into algal blooms, including quantifiable metrics such as the amount and spatial distribution, which are crucial for effective monitoring and management. Additionally, the recovered image textures exhibit high clarity and closely resemble the reference NDVI images. Experimental evaluation using simulated and actual cloud blocks indicates the model’s robustness to recover NDVI under varying cloud cover conditions. In summary, this study demonstrates the capability of GNSS-R aided by supplementary data for recovering missing NDVI values on lake surfaces when optical observations are absent for the first time.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"135 ","pages":"Article 104253"},"PeriodicalIF":7.6,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142651873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-11DOI: 10.1016/j.jag.2024.104243
Yuan Wang , Pei Sun , Wenbo Chu , Yuhao Li , Yiping Chen , Hui Lin , Zhen Dong , Bisheng Yang , Chao He
Quick and high-precision semantic segmentation from Mobile Laser Scanning (MLS) point clouds faces huge challenges such as large amounts of data, occlusion in complex scenes, and the high annotation cost associated with 3D point clouds. To tackle these challenges, this paper proposes a novel efficient and high-precision semantic segmentation method Mapping Considering Semantic Segmentation (MCSS) for MLS point clouds by leveraging the 2D-3D mapping relationship, which is not only without the need for labeling 3D samples but also complements missing information using multimodal data. According to the results of semantic segmentation on panoramic images by a neural network, a multi-frame mapping strategy and a local spatial similarity optimization method are proposed to project the panoramic image semantic predictions onto point clouds, thereby establishing coarse semantic information in the 3D domain. Then, a hierarchical geometric constraint model (HGCM) is designed to refine high-precision point cloud semantic segmentation. Comprehensive experimental evaluations demonstrate the effect and efficiency of our method in segmenting challenging large-scale MLS two datasets, achieving improvement by 16.8 % and 16.3 % compared with SPT. Furthermore, the proposed method takes an average of 8 s to process 1 million points and does not require annotation and training, surpassing previous methods in terms of efficiency.
{"title":"Efficient multi-modal high-precision semantic segmentation from MLS point cloud without 3D annotation","authors":"Yuan Wang , Pei Sun , Wenbo Chu , Yuhao Li , Yiping Chen , Hui Lin , Zhen Dong , Bisheng Yang , Chao He","doi":"10.1016/j.jag.2024.104243","DOIUrl":"10.1016/j.jag.2024.104243","url":null,"abstract":"<div><div>Quick and high-precision semantic segmentation from Mobile Laser Scanning (MLS) point clouds faces huge challenges such as large amounts of data, occlusion in complex scenes, and the high annotation cost associated with 3D point clouds. To tackle these challenges, this paper proposes a novel efficient and high-precision semantic segmentation method Mapping Considering Semantic Segmentation (MCSS) for MLS point clouds by leveraging the 2D-3D mapping relationship, which is not only without the need for labeling 3D samples but also complements missing information using multimodal data. According to the results of semantic segmentation on panoramic images by a neural network, a multi-frame mapping strategy and a local spatial similarity optimization method are proposed to project the panoramic image semantic predictions onto point clouds, thereby establishing coarse semantic information in the 3D domain. Then, a hierarchical geometric constraint model (HGCM) is designed to refine high-precision point cloud semantic segmentation. Comprehensive experimental evaluations demonstrate the effect and efficiency of our method in segmenting challenging large-scale MLS two datasets, achieving improvement by 16.8 % and 16.3 % compared with SPT. Furthermore, the proposed method takes an average of 8 s to process 1 million points and does not require annotation and training, surpassing previous methods in terms of efficiency.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"135 ","pages":"Article 104243"},"PeriodicalIF":7.6,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142651871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-11DOI: 10.1016/j.jag.2024.104251
Qi Zhang , Xiangyun Hu
Highly destructive flood disasters have occurred frequently recently. Related to this, accurate mapping of flood areas is a necessary undertaking that helps to understand the temporal and spatial evolution patterns of floods. Thus, this paper proposes a novel, unsupervised multi-scale machine learning (ML) approach for urban flood mapping with SAR images from the perspective of information mining and fusion. Considering the complexity of surface objects in urban scenes, the proposed approach first extracts and fuses multiple types of features, such as polarization, pseudo-color, and spatial features, from pre-flood and post-flood SAR images to enhance distinguishability of water bodies. In particular, some new pseudo-color features are constructed here for SAR images through pseudo-color synthesis and color space transformation. On this basis, a flood probability map (FPM) is generated, and multi-scale superpixel segmentation is performed on it. Then, an ML-based unsupervised classification model assisted by uncertainty analysis based on the Gaussian mixture model is designed and implemented for flood mapping at different segmentation scales. Finally, guided by the minimum uncertainty, an adaptive fusion strategy of multi-scale information is proposed to integrate the flood mapping results at different scales for producing the final flood map. The proposed approach is unsupervised, and can minimize the mapping uncertainty to improve mapping accuracy and reliability. These characteristics of the proposed approach make it practical. The results of comparative experiments demonstrate that the proposed approach is effective and has certain advantages over existing methods, especially in reducing false detections and correctly identifying the categories of uncertain pixels in flood mapping. Furthermore, the experimental results also indicate that the pseudo-color features constructed here also help enhance flood mapping accuracy.
近来,破坏性极大的洪水灾害频繁发生。与此相关,准确绘制洪水区域地图是一项必要的工作,有助于了解洪水的时空演变规律。因此,本文从信息挖掘与融合的角度出发,提出了一种利用合成孔径雷达图像绘制城市洪水地图的新型无监督多尺度机器学习(ML)方法。考虑到城市场景中地表物体的复杂性,本文首先从洪水前和洪水后的合成孔径雷达图像中提取并融合多种类型的特征,如偏振、伪彩色和空间特征,以提高水体的可分辨性。其中,通过伪色合成和色彩空间变换,为 SAR 图像构建了一些新的伪色特征。在此基础上生成洪水概率图(FPM),并对其进行多尺度超像素分割。然后,在高斯混合物模型的基础上,设计并实现了一个基于 ML 的无监督分类模型,并辅以不确定性分析,用于不同分割尺度的洪水测绘。最后,在最小不确定性的指导下,提出了一种多尺度信息的自适应融合策略,以整合不同尺度的洪水绘图结果,生成最终的洪水地图。所提出的方法是无监督的,可以最大限度地减少绘图的不确定性,从而提高绘图的准确性和可靠性。拟议方法的这些特点使其具有实用性。对比实验结果表明,所提出的方法是有效的,与现有方法相比具有一定的优势,特别是在减少误检和正确识别洪水绘图中不确定像素的类别方面。此外,实验结果还表明,本文构建的伪彩色特征也有助于提高洪水测绘的准确性。
{"title":"Urban flood mapping by fully mining and adaptive fusion of the polarimetric and spatial information of Sentinel-1 images","authors":"Qi Zhang , Xiangyun Hu","doi":"10.1016/j.jag.2024.104251","DOIUrl":"10.1016/j.jag.2024.104251","url":null,"abstract":"<div><div>Highly destructive flood disasters have occurred frequently recently. Related to this, accurate mapping of flood areas is a necessary undertaking that helps to understand the temporal and spatial evolution patterns of floods. Thus, this paper proposes a novel, unsupervised multi-scale machine learning (ML) approach for urban flood mapping with SAR images from the perspective of information mining and fusion. Considering the complexity of surface objects in urban scenes, the proposed approach first extracts and fuses multiple types of features, such as polarization, pseudo-color, and spatial features, from pre-flood and post-flood SAR images to enhance distinguishability of water bodies. In particular, some new pseudo-color features are constructed here for SAR images through pseudo-color synthesis and color space transformation. On this basis, a flood probability map (FPM) is generated, and multi-scale superpixel segmentation is performed on it. Then, an ML-based unsupervised classification model assisted by uncertainty analysis based on the Gaussian mixture model is designed and implemented for flood mapping at different segmentation scales. Finally, guided by the minimum uncertainty, an adaptive fusion strategy of multi-scale information is proposed to integrate the flood mapping results at different scales for producing the final flood map. The proposed approach is unsupervised, and can minimize the mapping uncertainty to improve mapping accuracy and reliability. These characteristics of the proposed approach make it practical. The results of comparative experiments demonstrate that the proposed approach is effective and has certain advantages over existing methods, especially in reducing false detections and correctly identifying the categories of uncertain pixels in flood mapping. Furthermore, the experimental results also indicate that the pseudo-color features constructed here also help enhance flood mapping accuracy.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"135 ","pages":"Article 104251"},"PeriodicalIF":7.6,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142651866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-10DOI: 10.1016/j.jag.2024.104257
Simon Ecke , Florian Stehr , Jan Dempewolf , Julian Frey , Hans-Joachim Klemmt , Thomas Seifert , Dirk Tiede
Exploring the capabilities of remote sensing technologies for identifying stress responses in trees due to environmental pressures is crucial for comprehension, management, and maintenance of forests that are productive, healthy, and resilient. In recent decades, research on forest health monitoring has been predominantly focused on data obtained remotely, either from satellites or crewed aircraft. During the last few years, Uncrewed Aerial Vehicles (UAVs) have gained prominence as invaluable remote sensing platforms, increasingly being employed for forest surveying. As intermediary between traditional remote sensing methods and ground-level observations, UAVs can capture high-resolution imagery from low altitudes, even below cloud cover, in unprecedented detail. This ability allows for the precise detection of stress responses at the individual tree scale. In our study, we have acquired a highly heterogenous, multispectral time-series dataset from the International Co-operative Programme on Assessment and Monitoring of Air Pollution Effects on Forests (ICP Forests) inventory plots across Bavaria, Germany, focusing on the main tree species. The data was recorded over three consecutive years from a UAV with the objective of monitoring tree physiological stress responses. Concurrently, with the drone flights, the ground-based forest condition surveying (Level-1 monitoring) was conducted, serving as ground-truth validation, and providing detailed information on tree health indicators, such as defoliation and discoloration. Our findings revealed that multispectral imagery obtained from a UAV closely aligns with field data, proving effective detection of physiological stress in trees. Remarkably, in conjunction to the red, red edge, and near-infrared band, the inclusion of the blue band emerged as a critical indicator of tree stress when incorporated into the Blue Normalized Difference Vegetation Index (BNDVI), depending on factors such as tree species, class division, and atmospheric conditions. Furthermore, the averaged values per sample tree over three years, alongside the 5th and 25th percentile of the data distribution, have proven to be of key importance. Based on spectral indices, we achieved good classification accuracies by training species-specific gradient boosting models (macro F1-scores ranging from 0.492 to 0.769). These models can assist in quantifying tree stress responses, thereby supporting the objectives of the ICP Forests program, potentially leading to substantial cost savings or increased coverage in the future.
{"title":"Species-specific machine learning models for UAV-based forest health monitoring: Revealing the importance of the BNDVI","authors":"Simon Ecke , Florian Stehr , Jan Dempewolf , Julian Frey , Hans-Joachim Klemmt , Thomas Seifert , Dirk Tiede","doi":"10.1016/j.jag.2024.104257","DOIUrl":"10.1016/j.jag.2024.104257","url":null,"abstract":"<div><div>Exploring the capabilities of remote sensing technologies for identifying stress responses in trees due to environmental pressures is crucial for comprehension, management, and maintenance of forests that are productive, healthy, and resilient. In recent decades, research on forest health monitoring has been predominantly focused on data obtained remotely, either from satellites or crewed aircraft. During the last few years, Uncrewed Aerial Vehicles (UAVs) have gained prominence as invaluable remote sensing platforms, increasingly being employed for forest surveying. As intermediary between traditional remote sensing methods and ground-level observations, UAVs can capture high-resolution imagery from low altitudes, even below cloud cover, in unprecedented detail. This ability allows for the precise detection of stress responses at the individual tree scale. In our study, we have acquired a highly heterogenous, multispectral time-series dataset from the International Co-operative Programme on Assessment and Monitoring of Air Pollution Effects on Forests (ICP Forests) inventory plots across Bavaria, Germany, focusing on the main tree species. The data was recorded over three consecutive years from a UAV with the objective of monitoring tree physiological stress responses. Concurrently, with the drone flights, the ground-based forest condition surveying (Level-1 monitoring) was conducted, serving as ground-truth validation, and providing detailed information on tree health indicators, such as defoliation and discoloration. Our findings revealed that multispectral imagery obtained from a UAV closely aligns with field data, proving effective detection of physiological stress in trees. Remarkably, in conjunction to the red, red edge, and near-infrared band, the inclusion of the blue band emerged as a critical indicator of tree stress when incorporated into the Blue Normalized Difference Vegetation Index (BNDVI), depending on factors such as tree species, class division, and atmospheric conditions. Furthermore, the averaged values per sample tree over three years, alongside the 5th and 25th percentile of the data distribution, have proven to be of key importance. Based on spectral indices, we achieved good classification accuracies by training species-specific gradient boosting models (macro F1-scores ranging from 0.492 to 0.769). These models can assist in quantifying tree stress responses, thereby supporting the objectives of the ICP Forests program, potentially leading to substantial cost savings or increased coverage in the future.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"135 ","pages":"Article 104257"},"PeriodicalIF":7.6,"publicationDate":"2024-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142651870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}