Change detection (CD) is an essential aspect of urban planning and resource management. Deep learning (DL) has the potential to detect complex changes from massive data more automatically than traditional methods. However, current DL-based CD methods have limited abilities to efficiently extract bi-temporal features, emphasize real changes, detect weak edges, and ultimately integrate multiscale change information in detail. To address these challenges, we propose an edge and flow guided iterative convolutional neural network (EFICNN). Our network introduces an innovative and efficient iterative backbone (IB) as the feature extractor through pretrained fine-tuning. By embedding the IB into a Siamese architecture, it is possible to extract richer bi-temporal features from the input remote sensing (RS) images. On this basis, we design a 3-D difference enhancement module (3D-DEM) that utilizes a parameter-free 3-D attention mechanism to emphasize and connect bi-temporal differential and concatenated change features. Additionally, an edge-guided attention module (EGAM) is developed to enhance weak edges. This module combines reverse attention and edge attention based on the Laplacian pyramid to capture change backgrounds and high-frequency change edges, respectively. Inspired by the optical flow alignment between adjacent frames, we ultimately employ a flow-guided fusion module (FGFM) to promote the propagation of fine-grained features from deep to shallow and dynamically optimize the multiscale fusion process. Qualitative and quantitative experiments on three publicly available datasets demonstrate that our method outperforms 17 SOTA methods in terms of real change recognition and edge refinement. Our code is available athttps://github.com/LYT-work/EFICNN.

Real-time and accurate cropland recognition is conducive to scientific and rational planting management and utilization of agricultural resources. In recent years, deep learning methods have made great progress in recognizing cropland. However, there are still many challenges in experimenting with complex areas based on a single data source. In response to the above, this paper proposes a cropland recognition method based on cooperative spatial attention and edge detection with multi-source remote sensing data. Specifically, the edge extraction module obtains the gradient information of the image and extracts the edge features of the image. Then, through the spatial attention module, the global features are retained while the local texture information is highlighted. It is worth saying that ASPP ensures that features are extracted at the same time without losing information at the lowest resolution. We conducted experiments on the study area of Chengdu Plain, and the results showed that the OA, mIoU and F1 scores of USEA-Net reached 85.21%, 75.08% and 83.1%, respectively, which verified its effectiveness and superiority.

Polarimetric SAR (PolSAR) images have become a crucial data source for change detection in cloud cover and fog regions. Deep learning (DL) enables extract change features form PolSAR images automatically, overcoming the limitations of conventional methods. To address the computational complexity of global attention and inaccurate prediction of changes edges in DL, this study proposes a model integrating matrix factorization and adaptive propagation. The model adopts a Siamese structure, receiving bi-temporal PolSAR images as input. Then, a matrix factorization based attention module replaces traditional attention design, utilizing the low-rank matrix from matrix factorization as global information. Additionally, an adaptive propagation module is introduced to improve edge pixel sampling, calculating central pixel values based on fixed and variable offsets from a local neighborhood. Experimental results on Sentinel-1 dual-pol SAR dataset demonstrate the model's effectiveness in preserving edge integrity and enhancing land change detection accuracy.

The forest canopy is the most active and direct part of vegetation when it interacts with the external environment. Gap fraction (GF) is widely recognized as an accurate characterization of the spatial structure of the canopy and is decisive for the inversion of other important vegetation parameters like leaf area index (LAI). Terrestrial laser scanning (TLS) is a high-precision active remote sensing technology that can quickly acquire 3-D structure information of targets. In previous studies, the process of calculating GF using TLS data has often involved the downscaling of 3-D information, excessive computational complexity, or reduction in spatial resolution. In this work, we aimed to develop a computationally simple GF estimation model that can make full use of the vertical dimensional information of the point cloud data and accurately calculate the canopy GF. By building a quantitative relationship between the distances of point clouds at different locations from the projection surface and the laser point area, a laser point area (LPA) model connecting the point clouds to the leaves can be established and validated as effective. A comparison was made between the GF obtained by the LPA method and the results obtained by the digital hemisphere photography (DHP) and Monte Carlo (MC) methods. The results show that our method gives higher estimates than the DHP method and lower estimates than the MC method. The variation trend of the results of our method is generally in line with the other two methods ($R^{2}$= 0.86 with DHP,$R^{2}$= 0.60 with MC), indicating the validity of the LPA model developed in this letter.

Rice-crop intensity is the annual number of rice growth cycles in a field. Monitoring the intensity on a large scale is vital in evaluating grain production and its ecological impact. Synthetic Aperture Radar (SAR) has an all-weather imaging capability. However, the existing SAR-based rice-crop intensity mapping methods mostly focus on small regions due to the diversity of rice backscatter patterns, the inefficiency of the time-series feature extraction, and the unavailability of rice phenological information on a large scale. In this study, a harmonic-based method is proposed to identify the essential backscatter periodicities. It also suppresses short-term disturbance in time-series Sentinel-1 SAR data without setting filtering windows or assuming profile shapes. The method detects backscatter troughs, eliminating the requirement for point-by-point traversal mathematical operations. Annual temperature profiles are derived from time-series ERA5-Land data to identify troughs related to rice growth cycles under various agro-climatic conditions. Then, the single (135,537 km2), double (19,036 km2), and triple (259 km2) rice-crop intensities covering the entire Southern China in 2020 are mapped in a 10m resolution, without relying on region-specific prior phenological information. The method achieves an overall accuracy of 82.26%, and can potentially support the continental or global mapping task.

This paper aims at improving the individual tree segmentation method proposed by Liu et al. (2019), which is based on the 3-D distribution of point cloud without any prior knowledge or manual threshold setting. The improved algorithm has been applied to 22 plots of single-layered coniferous forest, single-layered broad-leaved forest, single-layered coniferous broad-leaved mixed forest, multi-layered coniferous forest and multi-layered coniferous broad-leaved mixed forest. The results showed that the algorithm can segment trees effectively, with an overall root mean square extraction rate of 0.95, and a root mean square F_Score of 0.73. It was found that the algorithm performed better in coniferous forest and single forest type of single layer with a stand density less than 300 plants/ha.

LiDAR is an active remote sensing technology, which have been used in forest monitoring over twenty years. The separation of branches and leaves is a key prerequisite for estimating some forest parameters. At present, branch and leaf separation algorithms based on terrestrial laser scanning (TLS) point cloud data are matured and numerous. However, they are unable to meet the requirements of large-scale forest inventory and research using UAV-LiDAR data. This study proposed a novel branch and leaf separation method mainly utilizing the near-infrared intensity information of UAV-LiDAR data, as the reflectance of branch and leaf is quite different. This method enabled branch and leaf separation over large scene areas with a straightforward, efficient, and less interactive way. Our study would improve the ability of forest resource investigation, management, and ecological research over large scales.

Canopy gaps affect the spatial distribution of radiation in the canopy. The estimation of gap fraction (GF) is important for the study of leaf area index (LAI). Terrestrial laser scanning (TLS) has been widely used for retrieving canopy structure parameters through massive high-resolution spatial samples in the form of 3-D point cloud data sets. Monte Carlo simulations can be used to obtain approximate solutions to quantitative problems through a large number of random sampling while avoiding complicated mathematical calculations. Monte Carlo simulations are suitable for analyzing TLS data and could help overcome resolution reductions inherent to current point cloud processing approaches. However, few studies have applied the Monte Carlo method to capture the canopy structure features implicit in high-resolution point clouds. This letter proposes a method for estimating the GF based on Monte Carlo simulations. A large number of randomly simulated laser beams were emitted to identify the canopy and gaps according to the discrimination distance, and the results were compared with the GFs derived from digital hemispherical photography (DHP). In general, the proposed TLS method estimated smaller GFs than the DHP method since DHP was vulnerable to exposure conditions and complex canopy structure. The GF estimated by the two methods is consistent ($R^{2} =0.7522$), indicating the effectiveness of the Monte Carlo method.

Most conventional Leaf Area Index (LAI) retrieval methods using Terrestrial Laser Scanning (TLS) data are based on Beer’s law and are severely affected by the effects of leaf occlusion and aggregation. Moreover, the correction of LAI using the Clumping Index (CI) relies on assumptions and is generally not robust. This paper exploits the high spatial resolution and penetration capability of TLS to explore the physical meaning of point cloud data sampling and then model the leaf cluster envelope by the Alpha-shape algorithm. Subsequently, canopy LAI is obtained by counting the surface area of the envelope of each leaf cluster within the canopy and combining it with the projected area of the canopy. The entire process is physically based and introduces a new LAI inversion approach based on TLS. We tested the approach by simulating the TLS data of 25 synthetic trees with different leaf areas and morphologies to evaluate its robustness. Four strategies were adopted for parameter selection in the envelope modeling step to automate the process of finding the optimal envelope radius and improve the inversion accuracy of LAI. In comparison with the traditional LAI retrieval method based on Beer’s law (RMSE% is 47.3%), we found that the method proposed in this letter has a higher inversion accuracy with a minimum RMSE% of 27.7%. Our method also is significantly more robust for high LAI scenes and performs well in scenes with high occlusion and aggregation.

Terrestrial lidar is capable of resolving trees at the branch/leaf level with accurate and dense point clouds. The separation of leaf and wood components is a prerequisite for the estimation of branch/leaf-scale biophysical properties and realistic tree model reconstruction. Most existing methods have been tested on trees with similar structures; their robustness for trees of different species and sizes remains relatively unexplored. This study proposed a new graph-based leaf–wood separation (GBS) method for individual trees purely using the xyz-information of the point cloud. The GBS method fully utilized the shortest path-based features, as the shortest path can effectively reflect the structures for trees of different species and sizes. Ten types of tree data—covering tropical, temperate, and boreal species—with heights ranging from 5.4 to 43.7 m, were used to test the method performance. The mean accuracy and kappa coefficient at the point level were 94% and 0.78, respectively, and our method outperformed two other state-of-the-art methods. Through further analysis and testing, the GBS method exhibited a strong ability for detecting small and leaf-surrounded branches, and was also sufficiently robust in terms of data subsampling. Our research further demonstrated the potential of the shortest path-based features in leaf–wood separation. The entire framework was provided for use as an open-source Python package, along with our labeled validation data.

Microwave remote sensing is an important substitute for rice growth monitoring in cloudy area. Fields identification is the most basic task for tracking rice crop cultivation. A series of sophisticated classification methods such as machine learning techniques have been applied to mapping crop planting area. However, these methods are weak in interpreting the physical mechanism of identifying crop fields, and hardly illustrate the backscattering difference between rice fields and other ground objects. Besides, enormous training samples and computational expense are demanded to achieve high recognition accuracy, which limited their application to rapid and large-area agricultural monitoring. In this study, C-band quad-pol backscattering coefficients of different land cover types were extracted from RADARSAT-2 PolSAR (Polarimetric Synthetic Aperture Radar) data during the reproductive period of rice fields. The backscatter statistical characteristics of rice fields and other ground types in different polarimetric bands were visualized and analyzed using boxplots. Based on the scatter performance of the five interested ground objects, a simple decision tree scheme was proposed to identify rice paddy fields. The overall accuracy is 88.65% and Kappa coefficient is 0.77. Meanwhile, a land cover classification map of the study area was obtained though the hierarchical judgement of decision tree strategy.

The information about tree canopy structure is crucial for better understanding the process of radiation propagation. Clumping index (CI) describes the nonrandom distribution of foliage in canopy. Terrestrial laser scanning (TLS) has great advantages in obtaining high spatial resolution point cloud. In this paper, a point cloud projection and slicing algorithm was developed to retrieve CI from TLS data. The results were in good consistency with the CI derived from digital hemispherical photography (DHP). The TLS-based CIs had the highest correlation with the DHP-based CIs when the slice size is 0.1° × 0.2°.

Recent satellite missions have provided a variety of high spatial resolution, multi-spectral, and high-frequency revisit remote sensing datasets. The collaborative use of optical and synthetic aperture radar (SAR) imagery in remote sensing applications attracts considerable attention. The purpose of this paper is to investigate the contribution of both data to the rice planting area mapping. In particular, the red-edge band was introduced to construct a red-edge vegetation index based on Sentinel-2 data. C-band quad-pol Radarsat-2 data was also used. We finally used the random forest algorithm, collaborating with optical and radar data to map rice planting area. We found that the red-edge band and red-edge vegetation index can improve the classification accuracy compared to the classifier using NIR (near-infrared) band and NDVI (Normalized Difference Vegetation Index). The result shows that the jointly use of optical and radar data is feasible to map rice planting area. The overall accuracy, recall and F-measure are 0.9441, 0.9598 and 0.9680, respectively. Index Terms - red edge, SAR, rice mapping, random forest, Sentinel-2, Radarsat-2

Accurate mapping of paddy rice planting area is important for rice yield prediction. Polarimetric synthetic aperture radar (PolSAR) data is suitable for rice growth monitoring in cloudy and foggy weather. The potential of using quad-pol PolSAR parameters for rice area mapping needs exploration in detail. In this study, multi-temporal C-band quad-pol RADARSAT-2 datasets and random forest classification algorithm were used to identify the rice planting area in Meishan City, China in 2016. The backscatter coefficients, polarimetric variables and decomposition parameters were extracted and divided into groups as the inputs of random forest classifier. The decomposition parameters derived from single-day PolSAR data during the rice reproductive period were found the most practicable for rice area mapping, with the overall accuracy of 95.94% and kappa coefficient of 0.92.

The objective of this paper aims to propose a new individual tree segmentation algorithm using airborne light detection and ranging (A-LiDAR) point cloud according to the trend of tree crown shape without any priori-knowledges. First, the method of crown profile points extraction was used to remove redundant data to improve the computational efficiency and to make higher accuracy. Then a segmentation method based on trend discrimination was proposed, which used the vertical profile and spatial distribution characteristics of tree crown point cloud to segment individual trees. This algorithm was applied to six experimental plots and was appraised using recall, precision, and F-score, which reached 98%, 94% and 0.96, respectively. The results indicated that this algorithm can accurately segment individual trees with low computational cost.

Rice is one of the most important crops in the world. Rice usually grows in tropical and subtropical areas where are usually rainy and cloudy. Under this weather condition, optical remote sensing has a great limitation, but the synthetic aperture radar (SAR) runs well. This paper utilized C band multi-temporal Radarsat-2 data, which is acquired in 2016, to extract quad-polarized backscattering coefficients, Cloude-Pottier and Freeman-Durden decomposition parameters for establishing classification features. Random forest (RF) algorithm was employed as the classifier. The Overall Accuracy (OA) is 82.9% when only the data on May 15thwas used. After adding the data on July 26th, the OA increased to 88.8%. Then, the variable importance was estimated by using out-of-bag (OOB) data. The results indicate that using RF would effectively identify the ground objects in the rice planting area.

The tree skeleton is one of the important parameters for building 3D model of the tree. The accurate extraction of tree skeleton is of great significance for tree visualization. This paper proposed an effective method for extracting tree skeleton of individual trees. The complexity of canopy structure was reduced by slicing. The leaf and wood components were separated by combining classification and segmentation methods. L1-median algorithm was used to extract the tree skeleton points accurately. The results show that the method can accurately extract the tree skeleton from terrestrial LiDAR data. The extracted skeleton had a good conformance with the point cloud of the tree in morphology.

Fraction of absorbed photosynthetically active radiation (FPAR) refers to the ratio of photosynthetically active radiation (PAR) absorbed by the green part of the vegetation canopy to the total PAR. Accurate and quantitative monitoring of rice FPAR is of great significance for cultivation management and yield estimation. High spatial and temporal resolution optical images, and all-time all-weather radar images are widely used in crop monitoring. In this study, a rice FPAR synergistic inversion model was established using a combination of optical and radar remote sensing dataset. The results suggest that the estimated FPAR is more approximate to the measured values, compared with the commonly used MODIS FPAR product. The FPAR spatiotemporal distribution maps are generated based on the synergistic inversion model.

The wood structure is an important parameter that represents the geometrical and topological characteristics of trees. Accurate extraction of the wood component of a tree is of great importance in visualizing trees. Light detection and ranging (LiDAR) has been applied to obtain the 3-D structural properties of vegetation. However, it is difficult to separate the wood and leaf components from point clouds data in situations where wood and leaves are mixed and overlapping. This letter proposes an effective method for extracting wood point cloud of individual trees based on different geometric features of leaves and wood by combining classification and segmentation methods. Magnolia grandiflora and Cinnamomum camphor trees were scanned using a high-resolution terrestrial LiDAR. The complexity of the structure of the canopy was reduced using a slicing method. The wood and/or leaf components were classified using the K-means and random sampling consistency (RANSAC) algorithm. The cylindrical segmentation method based on the RANSAC algorithm was used for the precise extraction of the wood component in wood and leaf mixed point clouds. The trunk under the canopy was extracted completely. The average recall and precision in extracting canopy wood point clouds of the Magnolia grandiflora and Cinnamomum camphor achieved 94.60%, 92.02% and 93.62%, 91.46%, respectively. The results indicate that the proposed method has the potential for accurately extracting the wood point cloud from terrestrial LiDAR data.

The leaf area density (LAD) plays an important role in describing the vertical canopy structure. Light Detection and Ranging (LiDAR) is an active remote-sensing technology that has already been applied to canopy measurements. In this paper, the vertical profiles of the LAD of three different size plots (15 x 15 m, 10 x 10m, and 5 x 5 m) of forest canopy were estimated and compared based on a voxel-based model using airborne LiDAR data and terrestrial LiDAR data, respectively. The LAD profiles retrieved from airborne LiDAR data were different from those obtained by terrestrial LiDAR data. The height of the maximum LAD estimated from the airborne LiDAR data was significantly higher than that estimated from the terrestrial LiDAR data. In addition, the middle and lower parts of the forest canopy LAD were underestimated by airborne LiDAR while the upper part of the forest canopy LAD were underestimated by terrestrial LiDAR compared with the actual canopy vertical structure.

The target decomposition of polarimetric synthetic aperture radar (PolSAR) data was widely used to study the electromagnetic scattering properties of rice paddies. Many studies used eigenvectors-based decomposition like Cloude-Pottier decomposition to monitor rice growth but the potential of model-based decomposition like Freeman-Durden decomposition for rice phenology monitoring was not fully explored. Therefore, a rice phenology inversion method was presented in this paper using Freeman-Durden decomposition parameters acquired from multi-temporal, quad-polarization RADARSAT-2 data over rice fields in Meishan, China. A decision tree approach was employed for the retrieval algorithm. Results show that joint use of logarithmic power scattered by the surface scattering component and double-bounce scattering component of the covariance matrix provides a good performance and obtains a total accuracy of 89.7% when four phenological stages (i.e., transplanting, vegetative, reproductive, and maturation) are considered. Most of the errors occurred in the vegetative and reproductive stages. The corresponding errors were both 16.7%.

The objective of this paper was to develop a new algorithm to segment individual trees directly by using the three-dimensional space characteristic of airborne light detection and ranging point cloud data. The local maximum method was used in the initial segmentation and the error identification tree exclusion. On the basis of the point cloud spatial distribution of individual trees and the adjacent relationship with the other trees, a point cloud clustering method was developed to decide the points belonging to the individual trees. This algorithm was tested by 6 forest plots in the Genhe forestry reserve. The results showed that this algorithm could segment individual trees quickly and accurately, and the overall accuracy of this algorithm was 96.3%.

The terrestrial LiDAR technology can provide canopy structural information implicitly contained within point clouds data and it is a popular tool, particularly in forestry applications. Clumping index characterizes the spatial distribution of the canopy and quantifies the degree of the real distribution deviate from the random case. In this paper, a new method was proposed to estimate the clumping index with terrestrial LiDAR data. The canopy clumping index of each zenith angle was estimated by the logarithmic gap averaging method after establishing voxel-based model, Conversing coordinate system and calculating the gap fraction. In addition, the digital hemispherical photographs (DHP) technology was used for verifying the effectiveness of the proposed approach. The results showed that the correlation coefficient R2between DHP and LiDAR is 0.62 when the voxel size is 0.2m*0.2m*0.2m. For a certain zenith angle, the smaller the voxel size is, the larger the clumping index is, and the converse is also true.

The light detection and ranging (LiDAR) technology plays an important role in obtaining the three-dimensional information. A large number of point cloud data of the objects can be obtained through the LiDAR technology. The Iterative Closest Point (ICP) algorithm was widely used for registering the point cloud data, which typically only scan an object from one direction at a time. However, massive point cloud data has brought a great number of troubles to this registration method. The k-d tree is similar to the general tree structure and it can store, manage and search data efficiently. Therefore, an improved ICP algorithm which based on k-d tree was presented for tree point cloud data registration in this paper. The results showed that the improved ICP algorithm can improve the speed of registration about 10 times higher, and it also has obvious advantages in accuracy of registration.

Xiangtan Stream basin, a typical hilly country in the Sichuan Basin, is adversely affected by overuse of chemical fertilizer on the slope farmland and pig manure produced by intensive pig breeding farm located in the upper watershed. The nitrogen and phosphorus compounds in the runoff, sediment and manure contaminate the soil and water bodies. SWAT (Soil Water and Assessment Tool) was applied to characterize hydrologic processes in the watershed and to evaluate the reduction effect of non-point source pollution (NPSP). Field data including flow and concentration (total phosphorus (TP), total nitrogen (TN) and nitrate-nitrogen (NO3-N)) were measured for the time period from March 2012 to March 2013. The result of comparison showed that SWAT model performed satisfactorily for simulating runoff and water quality in the study area. TN and TP load was found to be concentrated in the upper parts of the watershed, critical areas with the pig breeding farm. Contribution rate analysis suggested that livestock was the major contributor for TN and TP load, which should be the key factor for NSPS. Temporal analysis showed, monthly output of TN and TP was higher in June and July.

In this study, we plot a 3D aerosol map over China mainland based on CALIPSO and MODIS aerosol product combined, which is height-resolved. We can see there are several hot spots in terms of aerosol loadings across China, such as Pearl River Delta, Yangtze River Delta. Also, the maximum height that aerosol can reach were figured out based on the aerosol vertical profiles. Generally, this height is consistent with the planetary boundary layer height, less than 2km. Meanwhile, we attempted to sort out the aerosol indirect effect on cloud, by plotting Contoured Frequency by Altitude Diagram (CFAD) of cloud reflectivity from Cloudsat. It demonstrated that cloud tended to be restrained under heavy aerosol conditions.

Timely and accurate acquisition of land surface information in urban area is essential in monitoring the process of urbanization, it is critical for urban planning and management. Aims to investigate urban land cover classification using high resolution remote sensing data, this study proposed an object-oriented image analysis based approach for urban land cover mapping using LiDAR and CCD images. The proposed approach based on the analytic hierarchy process, the optimal scale for image segmentation and methods of image classification are investigated. The main land cover types are determined as low built-up, high built-up, tree, grassland and road, with the multi-scale image segmentation, the corresponding feature spaces are adopted for fuzzy classification. The experiment was carried out in Zhangye city, Gansu province. The results show that the overall accuracy is 93.42, and the Kappa is 0.91.

Photosynthetically active radiation (PAR) is a key parameter for almost all terrestrial ecosystem models. However, the usefulness of the currently available PAR products is constricted by their limited spatial and temporal resolution. In this paper, the processes of PAR in Heihe River Basin are thoroughly studied by improved Eck and Dye model during the period 2000-2008. 8-day composite and annual PAR are calculated using TOMS (Total Ozone Mapping Spectrometer) and OMI (Ozone Monitoring Instrument) reflectance data during 9 years. The results indicate that that the changes of estimated PAR in study area are totally fluctuating over the past several years. Annual total PAR increases from upstream to downstream. Meanwhiles, four representative sites with different landscape types in study area are selected for analyzing seasonal dynamics and interannual variations. Further, because of the remotely sensed data with higher resolutions in 2005-2008, the discrepancies of total annual PAR between these study sites are more obvious over last 4 years.