Multisource Remote Sensing Data Research Articles

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.

Habitat Prediction of Northwest Pacific Saury Based on Multi-Source Heterogeneous Remote Sensing Data Fusion

Accurate habitat prediction is important to improve fishing efficiency. Most of the current habitat-prediction studies use the single-source datasets and the sequence model based on single-source datasets, which, to a certain extent, limits the further improvement of prediction accuracy. In this paper, we propose a habitat-prediction method based on the multi-source heterogeneous remote-sensing data fusion, using product-level remote-sensing data and L1B-level original remote-sensing data. We designed a heterogeneous data feature extraction model based on a Convolution Neural Network (CNN) and Long and Short-Term Memory network (LSTM), and we designed a decision-fusion model based on multi-source heterogeneous data feature extraction. In the habitat prediction for the Northwest Pacific Saury, the mean R2 of the model reaches 0.9901 and the RMSE decreases to 0.01588 in the model validation experiment. It is significantly better than the results of other models, with the single datasets as input. Moreover, the model performs well in the generalization experiment because we limited the prediction error to less than 8%. Compared with the single-source sequence network model in the existing literature, the proposed method in this paper solves the problem of ineffective fusion caused by the differences in the structure and size of heterogeneous data through multilevel feature fusion and decision fusion, and it deeply explores the features of remote-sensing fishery data with different data structures and sizes. It can effectively improve the accuracy of fishery prediction, proving the feasibility and advancement of using multi-source remote-sensing data for habitat prediction. It also provides new methods and ideas for future research in the field of habitat prediction.

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.

Retrieval of Live Fuel Moisture Content Based on Multi-Source Remote Sensing Data and Ensemble Deep Learning Model

Live fuel moisture content (LFMC) is an important index used to evaluate the wildfire risk and fire spread rate. In order to further improve the retrieval accuracy, two ensemble models combining deep learning models were proposed. One is a stacking ensemble model based on LSTM, TCN and LSTM-TCN models, and the other is an Adaboost ensemble model based on the LSTM-TCN model. Measured LFMC data, MODIS, Landsat-8, Sentinel-1 remote sensing data and auxiliary data such as canopy height and land cover of the forest-fire-prone areas in the Western United States, were selected for our study, and the retrieval results of different models with different groups of remote sensing data were compared. The results show that using multi-source data can integrate the advantages of different types of remote sensing data, resulting in higher accuracy of LFMC retrieval than that of single-source remote sensing data. The ensemble models can better extract the nonlinear relationship between LFMC and remote sensing data, and the stacking ensemble model with all the MODIS, Landsat-8 and Sentinel-1 remote sensing data achieved the best LFMC retrieval results, with R2 = 0.85, RMSE = 18.88 and ubRMSE = 17.99. The proposed stacking ensemble model is more suitable for LFMC retrieval than the existing method.

A Spatio-Temporal Monitoring Method Based on Multi-Source Remote Sensing Data Applied to the Case of the Temi Landslide

It is challenging to monitor landslides due to their heavy concealment and the extreme destructiveness during the long development of landslides. Many landslide monitoring tools are somewhat onefold. In this paper, a comprehensive landslide monitoring method involving multiple factors from time-series multi-data sources is proposed. We focus on the changes in three aspects consisting of the vegetation condition, the surface deformation information and the landslide susceptibility. Firstly, the fractional vegetation cover of the landslide is extracted from optical remote sensing Gaofen-1 (GF-1) images using the dimidiate pixel model. Next, the surface deformation information of the landslide is derived from SAR remote sensing Sentinel-1A images applying the SBAS-InSAR method. Then, the landslide susceptibility based on GF-1, Sentinel-1A images and DEM data is computed using the analytic hierarchy process method. Finally, the spatio-temporal correlations of the vegetation condition, the surface deformation information and the landslide susceptibility are compared and interpreted. The Temi landslide is located along the Jinsha River and poses a high risk of blocking the river. Taking the Temi landslide as the study area, it is indicated from the results that the fractional vegetation cover, surface deformation information and landslide susceptibility reveal a consistency in the patterns of changes in spatial and temporal terms. As the surface deformation information improves, the status of the landslide vegetation also deteriorates and the landslide susceptibility becomes high, which indicates an increased probability of the creep and even the occurrence of landslides. In contrast, when the surface deformation information drops, the vegetation condition of the landslide becomes superior and the landslide becomes less susceptible, which means the likelihood of sliding declines. This study provides a new idea for a landslide monitoring method and potential way for natural disaster prevention and mitigation.

Predicting individual apple tree yield using UAV multi-source remote sensing data and ensemble learning

As one of the world’s most popular fruit, apple tree yield prediction before harvest plays an important role in optimizing orchard nutrition management, especially at the individual tree level. However, few studies focus on fruit-tree yield prediction with remote-sensing technology whereas most of them aim at field crops. Current fruits identifying and counting methods often fail to produce the expected result due to light and occlusion in complex orchard conditions. Since both the spectral and morphological characteristics of tree canopy can reflect the growth and development of fruit trees and are directly related to its potential yield. In this study, we develop a channel for automatic extraction of spectral and morphological features of apple trees using light detection and ranging (LiDAR) and multispectral imagery data from unmanned aerial vehicles. The contribution of spectral and morphological characteristics to the yield prediction of individual apple trees is discussed. With the combination of spectral and morphological features, an ensemble machine learning yield prediction model was developed by combining two widely used basic learners: support vector regression (SVR) and K-nearest neighbor (KNN). Then through extrapolating the ensemble model, the yield map was produced at the orchard level and individual tree level, respectively. The results show that the data processing channels developed in this study can accurately extract the morphological and spectral features of individual apple trees. Three features (Crown Volume 1, Ratio Vegetation Index, and CPA1) contribute most in apple tree yield prediction. The ensemble learning model outperforms all base learners with R2 = 0.813 for the validation and 0.758 for the test when using the selected three features. This study thus provides a practical example of predicting the yield of individual apple trees based on multi-source remote-sensing data and ensemble learning.

Monitoring and Analysis of Water Level–Water Storage Capacity Changes in Ngoring Lake Based on Multisource Remote Sensing Data

Mastering the fluctuation of water levels and the water storage capacity of plateau lakes is greatly important for monitoring the water balance of the Tibetan Plateau and predicting regional and global climate change. The water level of plateau lakes is difficult to measure, and the ground measured data of long-time series are difficult to obtain. Ngoring Lake is considered in this study, using spaceborne single-photon lidar ICESat-2/ATL13 inland lake standard data products, the water level values provided by Hydroweb laboratory, and the image data of an optical remote sensing satellite. A new method is proposed in the absence of measured data. The method uses multisource remote sensing data to estimate the long-term changes in the water levels, surface area, and water storage capacity of Ngoring Lake in the past three decades. The results show that the water level values of ICESat-2 and Hydroweb on overlapping observation days are highly correlated, with R2 = 0.9776, MAE = 0.420 m, RMSE = 0.077 m, and the average absolute height difference is 0.049 m. The fusion of multiple altimetry data can obtain more continuous long-time series water-level observation results. From 1992 to 2021, the water body information of Ngoring Lake basin fluctuated greatly and showed different variation characteristics in different time periods. The lowest water level in January 1997 was approximately 4268.49 m, and it rose to its highest in October 2009, approximately 4272.44 m. The change in the water level in the basin was mainly affected by natural factors, such as precipitation, air temperature, and human activities. The analysis shows that ICESat-2 can be combined with other remote sensing data to realize the long-time series dynamic monitoring of plateau lakes, showing great advantages in the comprehensive observation of plateau lakes in no man’s land.

Temporal and Spatial Changes in Vegetation Ecological Quality and Driving Mechanism in Kökyar Project Area from 2000 to 2021

The “Kökyar Greening Project” in the suburb of Aksu, Xinjiang, is a model of large-area artificial afforestation in an environment of drought and water scarcity. As an important part of the “3-North Shelter Forest Program”, it plays an important role in promoting the economic development and the environmentally friendly construction of Aksu and even of the whole Xinjiang region. Based on multisource remote-sensing data and meteorological observation data, this study explored the temporal and spatial changes in the vegetation parameters (FVC, NPP, and VEQI) and the ecological parameters (RSEI and LULC) in the Kökyar Project Area from 2000 to 2021. Based on the Theil–Sen median and TSS-RESTREND, this study investigated the path of mutual influence among the FVC, NPP, VEQI, and RSEI, as well as their responses to climate change and human activities. The results show that: (1) from 2000 to 2021, the FVC, NPP, VEQI, and RSEI in the Kökyar Project Area showed a significant upward trend and showed the distribution characteristics of “high in the south and low in the north”. (2) Over the past 22 years, the RSEI has shown a significant increase with the FVC, NPP and VEQI (p < 0.001), indicating that the “Kökyar Greening Project” has achieved significant ecological benefits. (3) The changes in the vegetation parameters and RSEI in the Kökyar Project Area were dominated by human activities. (4) The Kökyar Project Area has caused great changes to the ecosystem pattern of the region, and the vegetation parameters and RSEI in the Kökyar Project Area have increased, mainly in the form of cropland and grassland expansion over the past 22 years.

Estimation of Aboveground Carbon Density of Forests Using Deep Learning and Multisource Remote Sensing

Forests are crucial in carbon sequestration and oxygen release. An accurate assessment of forest carbon storage is meaningful for Chinese cities to achieve carbon peak and carbon neutrality. For an accurate estimation of regional-scale forest aboveground carbon density, this study applied a Sentinel-2 multispectral instrument (MSI), Advanced Land Observing Satellite 2 (ALOS-2) L-band, and Sentinel-1 C-band synthetic aperture radar (SAR) to estimate and map the forest carbon density. Considering the forest field-inventory data of eastern China from 2018 as an experimental sample, we explored the potential of the deep-learning algorithms convolutional neural network (CNN) and Keras. The results showed that vegetation indices from Sentinel-2, backscatter and texture characters from ALOS-2, and coherence from Sentinel-1 were principal contributors to the forest carbon-density estimation. Furthermore, the CNN model was found to perform better than traditional models. Results of forest carbon-density estimation validated the improvements effectively by combining the optical and radar data. Compared with traditional regression methods, deep learning has a higher potential for accurately estimating forest carbon density using multisource remote-sensing data.

Surface Environmental Evolution Monitoring in Coal Mining Subsidence Area Based on Multi-Source Remote Sensing Data

The exploitation of mineral resources is crucial for cost-effective construction but has also led to severe damage to the ecological environment in mining areas. Therefore, it is particularly important to effectively monitor surface environmental problems in the mining subsidence area caused by the exploitation of mineral resources. Herein, the Huinong coal mining subsidence area, Shizuishan city, Ningxia, China, was taken as the study area. The remote sensing image features of various environmental elements were investigated through field investigations, the measured spectra, and image spectrum contrast analysis. On this basis, an object-oriented random forest classification method was used to classify images from different time phases and sources in coal mining subsidence areas. Next, the man–machine interactive interpretation was confirmed by referring to the pre-classification results. By overlaying the interpretation result map and analyzing the land-use class changes, the spatial–temporal evolution monitoring of the surface environment in the coal mining subsidence area from 1979 to 2018 was carried out. The results show that the surface environment in the coal mining subsidence area has undergone significant changes over the past 40 years, among which—from 1979 to 2003—the environment of the coal mining area was severely damaged by the intensive mining activities. The area of cultivated land and vegetation coverage decreased sharply, while the area of other land-use classes, such as coal heaps, water bodies, and coal gangue, exhibited a trend of rapid growth. From 2003 to 2018, after more than 10 years of mine geological environment renovation and management, the surface environment of the coal mining subsidence area greatly improved, among which the vegetation coverage has shown the fastest growth rate, while the area of coal gangue, badlands, and other land-use classes have significantly reduced. The hidden dangers of geological disasters have been drastically mitigated. In addition, the residential area continued to decrease in the early stages and then rebounded to a certain extent, indicating that urbanization was carried out at the same time as the ecological environment began to improve. The surface environment before and after the renovation is consistent with the results from remote sensing monitoring.

Agroecological Efficiency Evaluation Based on Multi-Source Remote Sensing Data in a Typical County of the Tibetan Plateau

Evaluating agricultural ecology can help us to understand regional environmental status and contribute to the sustainable development of agricultural ecosystems. Furthermore, the results of eco-environmental assessment can provide data support for policy-making and agricultural production. The application of multi-source remote-sensing technology has the advantages of being fast, accurate and wide ranging. It can reveal the status of regional ecological environments, and is of great significance to monitoring their quality. In this paper, an agroecological efficiency evaluation model was constructed by combining remote sensing data and ecological index (EI). Multi-source remote-sensing data were used to obtain the evaluation index. Indicators collected from satellites, such as biological richness, vegetation cover, water network density, land stress, and pollution load, were used to quantitatively evaluate the agroecological efficiency of Rangtang County in the Tibetan Plateau. The results showed that the EI of Rangtang County increased from 61.77 to 65.10 during 2000–2020, which means that the eco-environmental quality of this area was good, and it has shown an obviously improving trend over the past 20 years. Rangtang County has converted more than 30 km²of grassland into woodland over the past 20 years. Climate change and human activities have had combined effects on the ecological environment of this area. The change in ecological environment quality is greatly affected by human disturbance. Policymakers should continue setting up nature reserves and should implement the policy of returning farmland to forests. Unreasonable grazing and rational allocation of land resources are still critical points of concern for future ecological environment construction. EI, combined with remote sensing and statistical data, is proven to be able to reasonably represent changes in ecological environment in Rangtang County, thus providing more possibilities for ecological evaluation on the Tibetan Plateau, and even the whole world.

Estimation of Soil Organic Carbon Content in the Ebinur Lake Wetland, Xinjiang, China, Based on Multisource Remote Sensing Data and Ensemble Learning Algorithms.

Soil organic carbon (SOC), as the largest carbon pool on the land surface, plays an important role in soil quality, ecological security and the global carbon cycle. Multisource remote sensing data-driven modeling strategies are not well understood for accurately mapping soil organic carbon. Here, we hypothesized that the Sentinel-2 Multispectral Sensor Instrument (MSI) data-driven modeling strategy produced superior outcomes compared to modeling based on Landsat 8 Operational Land Imager (OLI) data due to the finer spatial and spectral resolutions of the Sentinel-2A MSI data. To test this hypothesis, the Ebinur Lake wetland in Xinjiang was selected as the study area. In this study, SOC estimation was carried out using Sentinel-2A and Landsat 8 data, combining climatic variables, topographic factors, index variables and Sentinel-1A data to construct a common variable model for Sentinel-2A data and Landsat 8 data, and a full variable model for Sentinel-2A data, respectively. We utilized ensemble learning algorithms to assess the prediction performance of modeling strategies, including random forest (RF), gradient boosted decision tree (GBDT) and extreme gradient boosting (XGBoost) algorithms. The results show that: (1) The Sentinel-2A model outperformed the Landsat 8 model in the prediction of SOC contents, and the Sentinel-2A full variable model under the XGBoost algorithm achieved the best results R2 = 0.804, RMSE = 1.771, RPIQ = 2.687). (2) The full variable model of Sentinel-2A with the addition of the red-edge band and red-edge index improved R2 by 6% and 3.2% over the common variable Landsat 8 and Sentinel-2A models, respectively. (3) In the SOC mapping of the Ebinur Lake wetland, the areas with higher SOC content were mainly concentrated in the oasis, while the mountainous and lakeside areas had lower SOC contents. Our results provide a program to monitor the sustainability of terrestrial ecosystems through a satellite perspective.

Automated Delineation of Supraglacial Debris Cover Using Deep Learning and Multisource Remote Sensing Data

High-mountain glaciers can be covered with varying degrees of debris. Debris over glaciers (supraglacial debris) significantly alter glacier melt, velocity, ice geometry, and, thus, the overall response of glaciers towards climate change. The accumulated supraglacial debris impedes the automated delineation of glacier extent owing to its similar reflectance properties with surrounding periglacial debris (debris aside the glaciated area). Here, we propose an automated scheme for supraglacial debris mapping using a synergistic approach of deep learning and multisource remote sensing data. A combination of multisource remote sensing data (visible, near-infrared, shortwave infrared, thermal infrared, microwave, elevation, and surface slope) is used as input to a fully connected feed-forward deep neural network (i.e., deep artificial neural network). The presented deep neural network is designed by choosing the optimum number and size of hidden layers using the hit and trial method. The deep neural network is trained over eight sites spread across the Himalayas and tested over three sites in the Karakoram region. Our results show 96.3% accuracy of the model over test data. The robustness of the proposed scheme is tested over 900 km2 and 1710 km2 of glacierized regions, representing a high degree of landscape heterogeneity. The study provides proof of the concept that deep neural networks can potentially automate the debris-covered glacier mapping using multisource remote sensing data.

Mapping Forest Aboveground Biomass Using Multisource Remotely Sensed Data

The majority of the aboveground biomass on the Earth’s land surface is stored in forests. Thus, forest biomass plays a critical role in the global carbon cycle. Yet accurate estimate of forest aboveground biomass (FAGB) remains elusive. This study proposed a new conceptual model to map FAGB using remotely sensed data from multiple sensors. The conceptual model, which provides guidance for selecting remotely sensed data, is based on the principle of estimating FAGB on the ground using allometry, which needs species, diameter at breast height (DBH), and tree height as inputs. Based on the conceptual model, we used multiseasonal Landsat images to provide information about species composition for the forests in the study area, LiDAR data for canopy height, and the image texture and image texture ratio at two spatial resolutions for tree crown size, which is related to DBH. Moreover, we added RaDAR data to provide canopy volume information to the model. All the data layers were fed to a Random Forest (RF) regression model. The study was carried out in eastern North Carolina. We used biomass from the USFS Forest Inventory and Analysis plots to train and test the model performance. The best model achieved an R2 of 0.625 with a root mean squared error (RMSE) of 18.8 Mg/ha (47.6%) with the “out-of-bag” samples at 30 × 30 m spatial resolution. The top five most important variables include the 95th, 85th, 75th, and 50th percentile heights of the LiDAR points and their standard deviations of 85th heights. Numerous features from multiseasonal Sentinel-1 C-Band SAR, multiseasonal Landsat 8 imagery along with image texture features from very high-resolution imagery were selected. But the importance of the height metrics dwarfed all other variables. More tests of the conceptual model in places with a broader range of biomass and more diverse species composition are needed to evaluate the importance of other input variables.

Comparison of the Vegetation Index of Reclamation Mining Areas Calculated by Multi-Source Remote Sensing Data

Following vegetation reclamation in mining areas, secondary damage may occur at any time, especially in locations that have been mined for decades or even hundreds of years. Effective monitoring strategies are required to accurately assess plant growth and to detect the ecological effects of reclamation. Single satellite monitoring is often difficult to ensure vegetation monitoring needs, therefore multi-source remote sensing is preferred. Different sensor parameters and variation in spectral bands can lead to differences in the type of data obtained, and subsequently, methods for evaluating these differences are required for simultaneous sensor/band use. In this study, NDVI was selected to characterize the vegetation growth of the Antaibao Open-pit Coal Mine Dump by analyzing the correlation between different types of sensors (Landsat 8, HJ, Sentinel-2) and vegetation greenness in order to facilitate satellites’ replacement and supplement. Results show that: (1) Landsat 8 and Sentinel-2 satellite have a high relevance for monitoring the vegetation, but the correlation between these two sensors and HJ is relatively low, (2) the correlation between NDVI values varied by vegetation type, tree (R = 0.8698) > combined grass, shrub and tree (R = 0.7788) > grass (R = 0.7619) > shrub (R = 0.7282), and (3) the phenomenon of “Low value is high, high value is low” in the NDVI value with HJ satellite monitoring may have been caused by a weak signal strength and low sensitivity of the HJ sensor. Comparing the correlation of multi-source sensors to monitor the vegetation in the mining areas can be helpful to determine the alternative supplement of sensors through conversion formulas, which are helpful in realizing the long-term monitoring of dumps and detecting reclamation response in mining areas.

An Object-Based Approach to Map Young Forest and Shrubland Vegetation Based on Multi-Source Remote Sensing Data

Many remote sensing studies have individually addressed afforestation, forest disturbance and forest regeneration, and considered land use history. However, no single study has simultaneously addressed all of these components that collectively constitute successional stages and pathways of young forest and shrubland at large spatial extents. Our goal was to develop a multi-source, object-based approach that utilized the strengths of Landsat (large spatial extent with good temporal coverage), LiDAR (vegetation height and vertical structure), and aerial imagery (high resolution) to map young forest and shrubland vegetation in a temperate forest. Further, we defined young forest and shrubland vegetation types in terms of vegetation height and structure, to better distinguish them in remote sensing for ecological studies. The multi-source, object-based approach provided an area-adjusted estimate of 42,945 ha of young forest and shrubland vegetation in Connecticut with overall map accuracy of 88.2% (95% CI 2.3%), of which 20,953 ha occurred in complexes ≥2 ha in size. Young forest and shrubland vegetation constituted 3.3% of Connecticut’s total land cover and 6.3% of forest cover as of 2018. Although the 2018 estimates are consistent with those of the past 20 years, concerted efforts are needed to restore, maintain, or manage young forest and shrubland vegetation in Connecticut.

A3 CLNN: Spatial, Spectral and Multiscale Attention ConvLSTM Neural Network for Multisource Remote Sensing Data Classification.

The problem of effectively exploiting the information multiple data sources has become a relevant but challenging research topic in remote sensing. In this article, we propose a new approach to exploit the complementarity of two data sources: hyperspectral images (HSIs) and light detection and ranging (LiDAR) data. Specifically, we develop a new dual-channel spatial, spectral and multiscale attention convolutional long short-term memory neural network (called dual-channel A3 CLNN) for feature extraction and classification of multisource remote sensing data. Spatial, spectral, and multiscale attention mechanisms are first designed for HSI and LiDAR data in order to learn spectral- and spatial-enhanced feature representations and to represent multiscale information for different classes. In the designed fusion network, a novel composite attention learning mechanism (combined with a three-level fusion strategy) is used to fully integrate the features in these two data sources. Finally, inspired by the idea of transfer learning, a novel stepwise training strategy is designed to yield a final classification result. Our experimental results, conducted on several multisource remote sensing data sets, demonstrate that the newly proposed dual-channel A 3 CLNN exhibits better feature representation ability (leading to more competitive classification performance) than other state-of-the-art methods.

Inversion of Soil Salinity Using Multisource Remote Sensing Data and Particle Swarm Machine Learning Models in Keriya Oasis, Northwestern China

Soil salinization is a global problem that damages soil ecology and affects agricultural development. Timely management and monitoring of soil salinity are essential to achieve the most sustainable development goals in arid and semi-arid regions. It has been demonstrated that Polarimetric Synthetic Aperture Radar (PolSAR) data have a high sensitivity to the soil dielectric constant and soil surface roughness, thus having great potential for the detection of soil salinity. However, studies combining PALSAR-2 data and Landsat 8 data to invert soil salinity information are less common. The particle swarm optimization (PSO) algorithm is characterized by simple operation, fast computation, and good adaptability, but there are relatively few studies applying it to soil salinity as well. This paper takes the Keriya Oasis as an example, proposing the PSO-SVR and PSO-BPNN models by combining PSO with support vector machine regression (SVR) and back-propagation neural network (BPNN) models. Then, PALSAR-2 data, Landsat 8 data, evapotranspiration data, groundwater burial depth data, and DEM data were combined to conduct the inversion study of soil salinity in the study area. The results showed that the introduction of PSO generated a satisfactory estimating performance. The SVR model accuracy (R2) improved by 0.07 (PALSAR-2 data), 0.20 (Landsat 8 data), and 0.19 (PALSAR + Landsat data); the BP model accuracy (R2) improved by 0.03 (PALSAR-2 data), 0.24 (Landsat 8 data), and 0.12 (PALSAR + Landsat data), and then combined with the model inversion plots, we found that PALSAR + Landsat data combined with the PSO-SVR model could achieve better inversion results. The fine texture information of PALSAR-2 data can be used to better invert the soil salinity in the study area by combining it with the rich spectral information of Landsat 8 data. This study complements the research ideas and methods for soil salinization using multi-source remote sensing data to provide scientific support for salinity monitoring in the study area.

Understanding the Relationship between China’s Eco-Environmental Quality and Urbanization Using Multisource Remote Sensing Data

The rapid development of urbanization and population growth in China has posed a major threat to the green sustainable development of the ecological environment. However, the impact of urbanization on the eco-environmental quality (EEQ) in China remains to be developed. Understanding their interactive coupling mechanism is of great significance to achieve the urban sustainable development goals. By using multi-source remote sensing data and the coupling coordination degree model (CCDM), we intended to answer the question “What are the temporal and spatial characteristics of urbanization and EEQ in China on the pixel scale during 2000–2013, and what is the coupling mechanism between the urbanization and the EEQ?”. To answer these questions, we explored the coupling mechanism between urbanization and the EEQ in China with a combined mathematical and graphics model. The results show that the urbanization and the coupling coordination degree (CCD) of the whole region continually increased from 2000 to 2013, especially in the three major urban agglomerations, with a spatial distribution pattern that was “high in the east and low in the west”. Most importantly, from 2000 to 2013, the CCD type of cities in China gradually evolved from uncoordinated cities to coordinated cities. Additionally, the decisive factor affecting the CCD from 2000 to 2013 was the development of urbanization, and the degree at which urbanization had an impact on CCD was about 8.4 times larger than that of the EEQ. At the same time, the rapid urbanization that has occurred in some areas has led to a significant decline in the EEQ, thus indicating that China needs to increase its protection of the ecological environment while pursuing social and economic development in the future. This study makes up for the deficiencies in the existing literature and investigates the long-term coupling of the EEQ and urbanization in China, thereby providing a new research perspective for the sustainable development of China and even the world in the future.