Multi-source Remote Sensing Research Articles

Deep Multimodal Fusion Model for Building Structural Type Recognition Using Multisource Remote Sensing Images and Building-Related Knowledge

Deep Multimodal Fusion Model for Building Structural Type Recognition Using Multisource Remote Sensing Images and Building-Related Knowledge

Forest Canopy Height Mapping Based on Multi-source Remote Sensing Data

Forest Canopy Height Mapping Based on Multi-source Remote Sensing Data

57-Year Ice Velocity Dynamics in Byrd Glacier Based on Multisource Remote Sensing Data

Long time series glacier ice velocity reflects the local climate changes and can be used to estimate mass balance (MB) changes, which is a critical parameter for understanding of glacier-climate interactions and prediction of sea level rise. However, due to the difficulty in image matching caused by the poor-quality of historical satellite images, there was insufficient glacier ice velocity data before 1999. Here, we proposed a multiple-constraint dense image matching approach for mapping historical ice velocity based on the early poor-quality images from ARGON, Landsat-1, Landsat-4/5. We successfully applied this method to Byrd Glacier to generate its historical ice velocity maps from 1963 to 1999. Additionally, ice velocity maps of Byrd Glacier from 2000 to 2014 were generated by IMCORR software using Landsat-7, Landsat-8 images. Combining with the ice velocity maps from the Global Land Ice Velocity Extraction from Landsat-8 (GoLIVE) dataset since 2014, we obtained the ice velocity of Byrd Glacier for 57 years. Our results showed that the glacier experienced slight fluctuations in ice velocity, which may not be due to the calving events in the studied portion of the Ross Ice Shelf (RIS) or the air temperature changes, but by the activity of subglacial drainage systems. Furthermore, Byrd Glacier showed a positive MB (average rate of 2.6 ± 2.0 Gt/y) from 1963 to 2020, indicating that global climate change may have a limited impact on it.

Consistency Center-Based Deep Cross-Modal Hashing for Multisource Remote Sensing Image Retrieval

Consistency Center-Based Deep Cross-Modal Hashing for Multisource Remote Sensing Image Retrieval

Mapping Urban Functional Areas Using Multisource Remote Sensing Images and Open Big Data

Mapping Urban Functional Areas Using Multisource Remote Sensing Images and Open Big Data

A Local–Global Framework for Semantic Segmentation of Multisource Remote Sensing Images

Recently, deep learning has been widely used in the segmentation tasks of remote sensing images. However, the existing deep learning method most focus on local contextual information and has limited field of perception, which makes it difficult to capture the long-range contextual feature of objects at large scales form very-high-resolution (VHR) images. In this paper, we present a novel Local–global Framework consisting of the dual-source fusion network and local–global transformer modules, which efficiently utilize features extracted from multiple sources and fully capture features of local and global regions. The dual-source fusion network is an encoder designed to extract features from multiple sources such as spectra, synthetic aperture radar, and elevations, which selective fuse features from multiple sources and reduce the interference of redundant features. The local–global transformer module is proposed to capture fine-grained local features and coarse-grained global features, which enables the framework to focus on recognizing multiple-scale objects from the local and global regions. Moreover, we propose a pixelwise contrastive loss, which could encourage that the prediction is pulled closer to the ground truth. The Local–global Framework achieves state-of-the-art performance with 90.45% mean f1 score on the ISPRS Vaihingen dataset and 93.20% mean f1 score on the ISPRS Potsdam dataset.

Drought Monitoring and Performance Evaluation Based on Machine Learning Fusion of Multi-Source Remote Sensing Drought Factors

Drought is an extremely dangerous natural hazard that causes water crises, crop yield reduction, and ecosystem fires. Researchers have developed many drought indices based on ground-based climate data and various remote sensing data. Ground-based drought indices are more accurate but limited in coverage; while the remote sensing drought indices cover larger areas but have poor accuracy. Applying data-driven models to fuse multi-source remote sensing data for reproducing composite drought index may help fill this gap and better monitor drought in terms of spatial resolution. Machine learning methods can effectively analyze the hierarchical and non-linear relationships between the independent and dependent variables, resulting in better performance compared with traditional linear regression models. In this study, seven drought impact factors from the Moderate Resolution Imaging Spectroradiometer (MODIS) satellite sensor, Global Precipitation Measurement Mission (GPM), and Global Land Data Assimilation System (GLDAS) were used to reproduce the standard precipitation evapotranspiration index (SPEI) for Shandong province, China, from 2002 to 2020. Three machine learning methods, namely bias-corrected random forest (BRF), extreme gradient boosting (XGBoost), and support vector machines (SVM) were applied as regression models. Then, the best model was used to construct the spatial distribution of SPEI. The results show that the BRF outperforms XGBoost and SVM in SPEI estimation. The BRF model can effectively monitor drought conditions in areas without ground observation data. The BRF model provides comprehensive drought information by producing a spatial distribution of SPEI, which provides reliability for the BRF model to be applied in drought monitoring.

Analysis of the Green Development Effects of High-Speed Railways Based on Eco-Efficiency: Evidence from Multisource Remote Sensing and Statistical Data of Urban Agglomerations in the Middle Reaches of the Yangtze River, China

As part of the modern transport infrastructure, high-speed railways (HSRs) have been considered an important factor affecting eco-efficiency (EE). This study used multisource remote sensing and statistical data from 185 counties representing urban agglomerations in the middle reaches of the Yangtze River (UAMRYR) in China from 2009 to 2018. The study integrated ArcGIS analysis, the Super-SBM (super slack-based measure) model, and the DSPDM (dynamic spatial panel Durbin model) to explore the spatial effects of HSRs on EE. The results showed that the coordinates of the interannual centers of gravity for EE and HSRs both fell in the same county, possessing similar parameter values for the standard deviation elliptical, a negative spatial mismatch index, and obvious spatial mismatch characteristics. In different spatially dislocated areas, the spatial effects of HSRs on EE are variable. Overall, the short-term effects are more intense than the long-term effects, and both the long-term and short-term effects are dominated by the effects of spatial spillover. A new perspective is proposed to explore the green development effects of HSRs, with a view to providing policy implications for the enhancement of EE and the planning of HSRs.

All-Weather and Superpixel Water Extraction Methods Based on Multisource Remote Sensing Data Fusion

The high spatial and temporal resolution of water body data offers valuable guidance for disaster monitoring and assessment. These data can be employed to quickly identify water bodies, especially small water bodies, and to accurately locate affected areas, which is significant for protecting people’s lives and property. However, the application of optical remote sensing is often limited by clouds and fog during actual floods. In this paper, water extraction methods of the multisource data fusion model (MDFM) and superpixel water extraction model (SWEM) are proposed, in which the MDFM fuses optical and synthetic aperture radar (SAR) images, and all-weather water extraction is achieved by using spectral information of optical images, texture information and the good penetration performance of SAR images. The SWEM further improves the accuracy of the water boundary with superpixel decomposition for extracted water boundaries using the fully constrained least squares (FCLS) method. The results show that the correlation coefficient (r) and area accuracy (Parea) of the MDFM and SWEM are improved by 2.22% and 9.20% (without clouds), respectively, and 3.61% and 18.99% (with clouds), respectively, compared with the MDFM, and 41.54% and 85.09% (without clouds), respectively, and 32.31% and 84.31% (with clouds), respectively, compared with the global surface water product of the European Commission Joint Research Centre’s Global Surface Water Explorer (JRC-GSWE). The MDFM and SWEM can extract water bodies with all weather and superpixel and improve the temporal and spatial resolution of water extraction, which has obvious advantages.

WITHDRAWN: Sensitivity evaluation of landslide geological hazards based on Multi-source Remote Sensing Data

The landslide geological disaster caused by heavy rainfall has the characteristics of sudden and rain and slide. Due to the limitations of weather, terrain and other conditions during the disaster period, the traditional manual survey is difficult to carry out at the first time and can not meet the needs of disaster relief. Multi source remote sensing data makes up for the defects of a single sensor. Relying on its advantages of large-scale, long time series and all-weather real-time imaging, using multi-source remote sensing data technology, various evaluation elements in the survey area can be quickly extracted to investigate the sensitivity evaluation of landslide geological hazards. Landslide is one of the natural disasters that cause great losses and casualties in the world. This is a serious geological disaster second only to earthquake, which poses a great threat to people's life, property safety and economic construction. Considering the serious situation of landslide disaster and the huge losses caused by it, effectively investigating and monitoring the distribution and activities of landslide, predicting and evaluating landslide are not only the urgent requirements of the affected areas, but also the mission of landslide scientists, so as to provide a scientific basis for the prevention and management of landslide disaster. This paper will study the landslide sensitivity evaluation, which is the central problem of landslide disaster research. Landslide sensitivity, also known as landslide susceptibility, belongs to the category of landslide spatial prediction. In this paper, GIS, RS, data mining and landslide sensitivity evaluation are combined to solve the problems of low efficiency, low precision, time and labor consumption in the previous landslide sensitivity evaluation, and realize the informatization and scientization of landslide geology.

Large-Scale Automated Sustainability Assessment of Infrastructure Projects Using Machine Learning Algorithms with Multisource Remote Sensing Data

Large-Scale Automated Sustainability Assessment of Infrastructure Projects Using Machine Learning Algorithms with Multisource Remote Sensing Data

The Coupling of Glacier Melt Module in SWAT+ Model Based on Multi-Source Remote Sensing Data: A Case Study in the Upper Yarkant River Basin

Glaciers have proven to be a particularly sensitive indicator of climate change, and the impacts of glacier melting on downstream water supplies are becoming increasingly important as the world’s population expands and global warming continues. Data scarcity in mountainous catchments, on the other hand, has been a substantial impediment to hydrological simulation. Therefore, an enhanced glacier hydrological model combined with multi-source remote sensing data was introduced in this study and was performed in the Upper Yarkant River (UYR) Basin. A simple yet efficient degree-day glacier melt algorithm considering solar radiation effects has been introduced for the Soil and Water Assessment Tool Plus model (SWAT+), sensitivity analysis and auto calibration/validation processes were integrated into this enhanced model as well. The results indicate that (i) including glacio-hydrological processes and multi-source remote sensing data considerably improved the simulation precision, with a Nash–Sutcliffe efficiency coefficient (NSE) promotion of 1.9 times and correlated coefficient (R2) of 1.6 times greater than the original model; (ii) it is an efficient and feasible way to simulate glacio-hydrological processes with SWAT+Glacier and calibrate it using observed discharge data in data-scarce and glacier-melt-dominated catchments; and (iii) glacier runoff is intensively distributed throughout the summer season, accounting for about 78.5% of the annual glacier runoff, and glacier meltwater provides approximately 52.5% (4.4 × 109 m3) of total runoff in the study area. This research can serve the runoff simulation in glacierized regions and help in understanding the interactions between streamflow components and climate change on basin scale.

An Advanced Data Fusion Method to Improve Wetland Classification Using Multi-Source Remotely Sensed Data.

The goal of this research was to improve wetland classification by fully exploiting multi-source remotely sensed data. Three distinct classifiers were designed to distinguish individual or compound wetland categories using random forest (RF) classification. They were determined, in part, to best use the available remotely sensed features in order to maximize that information and to maximize classification accuracy. The results from these classifiers were integrated according to Dempster-Shafer theory (D-S theory). The developed method was tested on data collected from a study area in Northern Alberta, Canada. The data utilized were Landsat-8 and Sentinel-2 (multi-spectral), Sentinel-1 (synthetic aperture radar-SAR), and digital elevation model (DEM). Classification of fen, bog, marsh, swamps, and upland resulted in an overall accuracy of 0.93 using the proposed methodology, an improvement of 5% when compared to a traditional classification method based on the aggregated features from these data sources. It was noted that, with the traditional method, some pixels were misclassified with a high level of confidence (>85%). Such misclassification was significantly reduced (by ~10%) by the proposed method. Results also showed that some features important in separating compound wetland classes were not considered important using the traditional method based on the RF feature selection mechanism. When used in the proposed method, these features increased the classification accuracy, which demonstrated that the proposed method provided an effective means to fully employ available data to improve wetland classification.

Large-Scale Rice Mapping Based on Google Earth Engine and Multi-Source Remote Sensing Images

Large-Scale Rice Mapping Based on Google Earth Engine and Multi-Source Remote Sensing Images

Multisource Remote Sensing Data-Based Flood Monitoring and Crop Damage Assessment: A Case Study on the 20 July 2021 Extraordinary Rainfall Event in Henan, China

On 20 July 2021, an extraordinary rainfall event occurred in Henan Province, China, resulting in heavy waterlogging, flooding, and hundreds of fatalities and causing considerable property damage. Because the damaged region was a major grain-producing region of China, assessing crop food production losses following this event is very important. Because the crop rotation production system is utilized in the region to accommodate two crops per year, it is very valuable to accurately identify the types of crops affected by the event and to assess the crop production losses separately; however, the results obtained using these methods are still inadequate. In this study, we used China’s first commercial synthetic aperture radar (SAR) data source, named Hisea-1, together with other open-source and widely used remote sensing data (Sentinel-1 and Sentinel 2), to monitor this catastrophic flood. Both the modified normalized difference water index (MNDWI) and Sentinel-1 dual-polarized water index (SDWI) were calculated, and an unsupervised classification (k-means) method was adopted for rapid water body extraction. Based on time-series datasets synthesized from multiple sources, we obtained four flooding characteristics, including the flooded area, flood duration, and start and end times of flooding. Then, according to these characteristics, we conducted a more precise analysis of the damages to flooded farmlands. We used the Google Earth Engine (GEE) platform to obtain normalized difference vegetation index (NDVI) time-series data for the disaster year and normal years and overlaid the flooded areas to extract the effects of flooding on crop species. According to the statistics from previous years, we calculated the areas and types of damaged crops and the yield reduction amounts. Our results showed that (1) the study area endured two floods in July and September of 2021; (2) the maximum areas affected by these two flooding events were 380.2 km2 and 215.6 km2, respectively; (3) the floods significantly affected winter wheat and summer grain (maize or soybean), affecting areas of 106.4 km2 and 263.3 km2, respectively; and (4) the crop production reductions in the affected area were 18,708 t for winter wheat and 160,000 t for maize or soybean. These findings indicate that the temporal-dimension information, as opposed to the traditional use of the affected area and the yield per unit area when estimating food losses, is very important for accurately estimating damaged crop types and yield reductions. Time-series remote sensing data, especially SAR remote sensing data, which have the advantage of penetrating clouds and rain, play an important role in remotely sensed disaster monitoring. Hisea-1 data, with a high spatial resolution and first flood-monitoring capabilities, show their value in this study and have the potential for increased usage in further studies, such as urban flooding research. As such, the approach proposed herein is worth expanding to other applications, such as studies of water resource management and lake/wetland hydrological changes.

Estimation of National Forest Aboveground Biomass from Multi-Source Remotely Sensed Dataset with Machine Learning Algorithms in China

Forests are the largest terrestrial ecosystem carbon pool and provide the most important nature-based climate mitigation pathway. Compared with belowground biomass (BGB) and soil carbon, aboveground biomass (AGB) is more sensitive to human disturbance and climate change. Therefore, accurate forest AGB mapping will help us better assess the mitigation potential of forests against climate change. Here, we developed six models to estimate national forest AGB using six machine learning algorithms based on 52,415 spaceborne Light Detection and Ranging (LiDAR) footprints and 22 environmental features for China in 2007. The results showed that the ensemble model generated by the stacking algorithm performed best with a determination coefficient (R2) of 0.76 and a root mean square error (RMSE) of 22.40 Mg/ha. The verifications at pixel level (R2 = 0.78, RMSE = 16.08 Mg/ha) and provincial level (R2 = 0.53, RMSE = 14.05 Mg/ha) indicated the accuracy of the estimated forest AGB map is satisfactory. The forest AGB density of China was estimated to be 53.16 ± 1.63 Mg/ha, with a total of 11.00 ± 0.34 Pg. Net primary productivity (NPP), normalized difference vegetation index (NDVI), enhanced vegetation index (EVI), average annual rainfall, and annual temperature anomaly are the five most important environmental factors for forest AGB estimation. The forest AGB map we produced is expected to reduce the uncertainty of forest carbon source and sink estimations.

Characterizing Forest Cover and Landscape Pattern Using Multi-Source Remote Sensing Data with Ensemble Learning

Accurate information on forest distribution is an essential basis for the protection of forest resources. Recent advances in remote sensing and machine learning have contributed to the monitoring of forest-cover distribution cost-effectively, but reliable methods for rapid forest-cover mapping over mountainous areas are still lacking. In addition, the forest landscape pattern has proven to be closely related to the functioning of forest ecosystems, yet few studies have explicitly measured the forest landscape pattern or revealed its driving forces in mountainous areas. To address these challenges, we developed a framework for forest-cover mapping with multi-source remote sensing data (Sentinel-1, Sentinel-2) and an automated ensemble learning method. We also designed a scheme for forest landscape pattern evaluation and driver attribution based on landscape metrics and random forest regression. Results in the Qilian Mountains showed that the proposed framework and scheme could accurately depict the distribution and pattern of forest cover. The overall accuracy of the obtained level-1 and level-2 forest-cover maps reached 95.49% and 78.05%, respectively. The multi-classifier comparison revealed that for forest classification, the ensemble learning method outperformed base classifiers such as LightGBM, random forests, CatBoost, XGBoost, and neural networks. Integrating multi-dimensional features, including spectral, phenological, topographic, and geographic information, helped distinguish forest cover. Compared with other land-cover products, our mapping results demonstrated high quality and rich spatial details. Furthermore, we found that forest patches in the Qilian Mountains were concentrated in the eastern regions with low-to-medium elevations and shady aspects. We also identified that climate was the critical environmental determent of the forest landscape pattern in the Qilian Mountains. Overall, the proposed framework and scheme have strong application potential for characterizing forest cover and landscape patterns. The mapping and evaluation results can further support forest resource management, ecological assessment, and regional sustainable development.

Study of the Buried Basin C-H, Based on the Multi-Source Remote Sensing Data

We use multi-source remote sensing data to identify the details of a mascon south-east of the lunar Copernicus crater. Studies of the topography, gravity, geochronology and mineral are combined to prove that the mascon is a buried peak-ring basin with diameters of about 130 km and 260 km. The underground structure is covered by 890 m thick mare basalts, as determined by analyzing the spectral features of the impact crater, Copernicus H. The determination of the crater size–frequency distribution (CSFD) suggests that the impact that created the C-H basin occurred earlier than 3.9 Ga. Then, a Hawaiian-style eruption in the late Imbrian period formed the Sinus Aestuum-I dark mantling deposit (DMD). Soon, mare basalts covered the basin several times from 3.8 Ga. Finally, the ejecta from the Copernicus impact event at about 800 Ma, and the weathering processes caused the disappearance of the C-H basin rim from the lunar surface.

Activity and Kinematics of Two Adjacent Freeze–Thaw-Related Landslides Revealed by Multisource Remote Sensing of Qilian Mountain

The increase in temperatures and changing precipitation patterns resulting from climate change are accelerating the occurrence and development of landslides in cold regions, especially in permafrost environments. Although the boundary regions between permafrost and seasonally frozen ground are very sensitive to climate warming, slope failures and their kinematics remain barely characterized or understood in these regions. Here, we apply multisource remote sensing and field investigation to study the activity and kinematics of two adjacent landslides (hereafter referred to as “twin landslides”) along the Datong River in the Qilian Mountains of the Qinghai-Tibet Plateau. After failure, there is no obvious change in the area corresponding to the twin landslides. Based on InSAR measurements derived from ALOS PALSAR-1 and -2, we observe significant downslope movements of up to 15 mm/day within the twin landslides and up to 5 mm/day in their surrounding slopes. We show that the downslope movements exhibit distinct seasonality; during the late thaw and early freeze season, a mean velocity of about 4 mm/day is observed, while during the late freeze and early thaw season the downslope velocity is nearly inactive. The pronounced seasonality of downslope movements during both pre- and post-failure stages suggest that the occurrence and development of the twin landslide are strongly influenced by freeze–thaw processes. Based on meteorological data, we infer that the occurrence of twin landslides are related to extensive precipitation and warm winters. Based on risk assessment, InSAR measurements, and field investigation, we infer that new slope failure or collapse may occur in the near future, which will probably block the Datong River and cause catastrophic disasters. Our study provides new insight into the failure mechanisms of slopes at the boundaries of permafrost and seasonally frozen ground.

A Random Forest Model for Drought: Monitoring and Validation for Grassland Drought Based on Multi-Source Remote Sensing Data

The accuracy of drought monitoring models is crucial for drought monitoring and early warning. Random forest (RF) is being used widely in the field of artificial intelligence. Nonetheless, the application of a random forest model in grassland drought monitoring research is yet to be further explored. In this study, various drought hazard factors were integrated based on remote sensing data, including from the Moderate Resolution Imaging Spectroradiometer (MODIS) and Global Precipitation Measurement (GPM), as multisource remote sensing data. Based on the RF, a comprehensive grassland drought monitoring model was constructed and tested in Inner Mongolia, China, as an example. The critical issue addressed is the construction of a grassland drought disaster monitoring model based on meteorological data and multisource remote sensing data by using an RF model, and the verification of the accuracy and reliability of its monitoring results. The results show that the grassland drought monitoring model could quantitatively monitor the drought situation in Inner Mongolia grasslands. There was a significantly positive correlation between the drought indicators output by the model and the standardized precipitation evapotranspiration index (SPEI) measured in the field. The correlation coefficients (R) between the drought degree were 0.9706 and 0.6387 for the training set and test set, respectively. The consistent rate between the model drought index and the SPEI reached 87.90%. Drought events in Inner Mongolia were monitored from April to September in wet years, normal years, and dry years using the constructed model. The monitoring results of the model constructed in this study were in accordance with the actual drought conditions, reflecting the development and spatial evolution of drought conditions. This study provides a new application method for the comprehensive assessment of grassland drought.