Few-shot segmentation (FSS) aims at training a model on base classes with sufficient annotations and then tasking the model with predicting a binary mask to identify novel class pixels with limited labeled images. Mainstream FSS methods adopt a support-query matching paradigm that activates target regions of the query image according to their similarity with a single support class prototype. However, this prototype vector is inclined to overfit the support images, leading to potential under-matching in latent query object regions and incorrect mismatches with base class features in the query image. To address these issues, this study reformulates conventional single foreground prototype matching to a multi-prototype matching paradigm. In this paradigm, query features exhibiting high confidence with non-target prototypes will be categorized as background. Specifically, the target query features are drawn closer to the novel class prototype through a Masked Cross-Image Encoding (MCE) module and a Semantic Multi-prototype Matching (SMM) module is incorporated to collaboratively filter unexpected base class regions on multi-scale features. Furthermore, we devise an adaptive class activation map, termed target-aware class activation map (TCAM) to preserve semantically coherent regions that might be inadvertently suppressed under pixel-wise matching guidance. Experimental results on PASCAL-5$^{i}$and COCO-20$^{i}$datasets demonstrate the advantage of the proposed novel modules, with the holistic approach outperforming compared state-of-the-art methods.

Convolutional Neural Networks (CNNs) have been applied effectively to classify high to medium-resolution imageries, especially for local scale land cover mapping, and attained high accuracy by outperforming the conventional machine learning techniques as the models incorporate spatial information as well as spectral reflectance values to differentiate objects.However, few studies have explored the effectiveness of CNN models for coarse-resolution satellite image classification. In this work, therefore, we applied 1D CNN and 3D CNN for time-series, coarse resolution (1km) FY-3C image classification in extensive area land cover mapping of a part of Eastern and North-East Africa.The result indicates both 1D CNN and 3D CNN models achieved high overall accuracy (OA >=85), although the former outperformed the latter significantly by 2-4%, indicating the superiority of pixel-based classification in time-series coarse resolution image classification.

We propose an integrated lithological classification scheme in this study embedding a squeeze and excitation (SE) attention module in a Long Short-Term Memory (LSTM) recurrent neural network (RNN). Using high-resolution Landsat-9 and ASTER images, we integrate fieldwork and a two-stream multisource feature fusion strategy with dual-tree complex wavelet transform (DTCWT) to consolidate the intrinsic details of target features. We then leverage the synthesized dataset to train the proposed SE-LSTM model, which learns to classify target lithologies based on patterns of their feature representation within the dataset. Evaluation metrics such as Sensitivity, Specificity, Area Under the Curve (AUC), Accuracy and Confusion Matrix are used to assess the model performance. Assessing SE-LSTM’s 0.98 AUC and 84.14% accuracy against ViT, vanilla LSTM, ResNet50, KNN and RF, shows its superior efficiency and robustness in classification. SE-LSTM scores a 2.08% increase in accuracy in identifying lithology in the intricate West African Craton.

In remote sensing, complex spatial layouts and feature interpretation raise concerns in scene classification. Convolutional neural networks (CNNs) do a great job at capturing global features yet, they have a propensity to overlook long-range contextual detail. In contrast, Vision Transformers (ViTs) excel in contextual information extraction with computational complexity and local feature capturing as their downside. This study therefore seeks to strike a balance between CNNs and ViTs with a proposed DenseViT model for an efficient lithological mapping integrating Landsat-9 and ASTER geodata. The proposed model is evaluated against ViT, ResNet50, Random Forest (RF) and KNN, using metrics including area under the curve (AUC), accuracy, sensitivity, specificity and confusion matrices. The result metrics show that DenseViT averages a 1.92% increase in performance relative to the comparative models in this study with an 83.66% accuracy. The proposed DenseViT model demonstrates computational efficiency and encapsulates local and global features remarkably.

Semantic change detection (SCD) supplies not only the change location but also the detailed land cover/land use (LC/LU) categories before and after the change. Vision Foundation Models (VFMs) such as the Segment Anything Model (SAM) allow for zero-shot or reduce the reliance on task-specific modeling expertise, making it possible for them to migrate to new image distributions and tasks. However, due to the special imaging characteristics of Remote Sensing (RS), their direct use in many remote sensing applications is often unsatisfactory. Therefore, our goal is to utilize the powerful visual recognition capability of VFM to improve semantic change detection in high-resolution remote sensing images (RSIs). To make MobileSAM applicable to RS scenarios, we fine-tune its encoder.

Achieving autonomous navigation and positioning for UAV through computer vision technology has emerged as a key focus and hot topic in current research. The precise matching of UAV images is crucial for realizing this functionality. However, the intrinsic difference between satellite images and UAV images resulted in the sub-optimal performance of traditional matching algorithms. Although the depth-local feature matching of linear Transformers has demonstrated superior hierarchical matching capabilities in UAV image matching, the lack of fine local interactions between pixel tokens restricts their ability to extract highly accurate and localized correspondences. To address the limitations of existing linear Transformer matching algorithms, this paper proposes a novel method called MixFormer, a Mixed Attention Matching Transformer for UAV image feature matching. The algorithm comprises two main aspects: firstly, it introduces a hierarchical feature matching attention framework that operates attention at different scales, integrating global attention and local attention to achieve global context awareness and fine-grained matching, thereby enabling efficient and compact implementation. Secondly, it introduces a feature transformation module for transitional Convolutional Neural Network (CNN) to extract features with full receptive fields. Experimental results on benchmark tests confirm the effectiveness and efficiency of the proposed technique.

Accurate depiction of high spatial resolution remote sensing images necessitates an understanding of the internal attributes of objects and the external relationships between different entities. Existing image captioning algorithms lack global representational capability, rendering them unsuitable for the summarization of intricate scenes. To address this, we propose a remote sensing image captioning approach based on multi-level feature extraction and an adaptive attention mechanism. Specifically, in the encoder phase, localized and global features of the image are extracted separately, and subsequently, the attention mechanism method integrates the global features with locally extracted features from the target detection algorithm. In the decoder section, a third layer LSTM network is introduced as a contemplation layer, concurrently incorporating an adaptive attention mechanism based on image sentinels, enhancing the precision and delicacy of the text description generated by the decoder. Experimental results on public datasets substantiate the superiority of the proposed method over existing approaches.

Few-shot segmentation (FSS) is a dense prediction task that aims to infer the pixel-wise labels of unseen classes using only a limited number of annotated images. The key challenge in FSS is to classify the labels of query pixels using class prototypes learned from the few labeled support exemplars. Prior approaches to FSS have typically focused on learning class-wise descriptors independently from support images, thereby ignoring the rich contextual information and mutual dependencies among support-query features. To address this limitation, we propose a joint learning method termed Masked Cross-Image Encoding (MCE), which is designed to capture common visual properties that describe object details and to learn bidirectional inter-image dependencies that enhance feature interaction. MCE is more than a visual representation enrichment module; it also considers cross-image mutual dependencies and implicit guidance. Experiments on FSS benchmarks PASCAL-5iand COCO-20idemonstrate the advanced meta-learning ability of the proposed method.

This work analyzes the impacts of training sample size on the performance of supervised classification methods when coarse resolution imageries are employed for regional land cover mapping. We utilized FegnYun-3C composite imageries with 1km spatial resolution and random forest (RF) and support vector machine (SVM) algorithms that were trained and tested with five sets of reference datasets: 66/34, 69/31, 73/27, 76/24 and 79/21.The results show that the performance of the two algorithms increases with increasing the size of the training examples until a certain point, and achieves the maximum accuracy (0.86 for RF and 0.84 for SVM) when the ratio was 76/24. However, considering the 79/21 (train/test) ratio made no change in accuracy, implying increasing a training dataset beyond a certain limit has no effect. Moreover, despite the size of training samples employed, the RF outperformed the SVM in contrary to the claim that SVM yields a better accuracy in case of scarce training data by pervious studies.

The West African Craton hosts economic minerals such as diamonds, gold, and bauxite. Yet, it remains underexplored as poor socio-political and environmental conditions limit traditional exploration in the area. This study assesses the performance of the Landsat-9 OLI-2/TIR-2 in mapping lithologies and highlighting potential metallogenic points using remote sensing techniques. Specifically, we perform classification tasks on preprocessed Landsat-9 dataset to classify the lithological features using a hybrid machine learning (ML) module integrating Local Fisher Discriminant Analysis (LFDA) and Support Vector Machine (SVM) against three (3) baseline ML algorithms. The aim is to enhance computing proficiency and improve classification precision. The accuracy results show that the proposed LFDA and SVM algorithm performs better than Random Forest (RF) and KNN. The results distinguish nine lithological units with a 0.9992 overall accuracy. Additionally, Landsat-9 OLI-2/TIR-2 proves efficient in attaining high accuracy in conducting geological exploration work in terrains under unfavorable conditions.

Monitoring poultry behaviour provides the opportunity to aid egg production and animal welfare. With the current development in machine learning and computer vision, automated content analysis has become a practical way for low-cost and continuous monitoring of animal behaviours. In this demo, we will show a simple yet effective flock monitoring system based on computer vision and machine learning techniques for egg farmers that allows them to reduce labour yet improve performance. This demo shows that it is possible to auto-analyse flock activities thereby providing early warning of welfare issues, by applying object detection, tracking and crowd-counting techniques. Summaries of individual bird activity and their distribution are closely related to the flock behaviour, which in turn reflects the welfare status. Specifically, the density and movement patterns of birds provide reliable information on the welfare status of the flock. For example, the real-time monitoring of density and movement can give early warnings of pile-ups. To observe these and other important flock activities, we developed a low-cost and easy-use system based on recent computer vision techniques to auto-estimate the density and movement of birds on commercial egg farms.

This paper compared multi-temporal composite products of FY-3C VIRR and MODIS for regional land cover (LC) mapping of a part of Africa. LC classification was conducted using a random forest algorithm in the Scikit-Learn library of Python after the model was trained using reference data that were collected by combining three techniques and employed simultaneously i.e. Landsat 8 image interpretation, referring exiting maps, and crosschecking on Google Earth pro/ maps. Based on the overall accuracy (OA) and kappa value (k) the two instruments showed insignificant performance variation although FY-3C VIRR achieved slightly higher OA (.82) and k (.79) which are 1 % higher than MODIS. However, the two instruments exhibited notable performance differences in discerning individual classes. The FY-3C data are generally better for vegetation classification; MODIS, whereas, classified built-up, bare/sparse-vegetation, and water bodies with better accuracy. Moreover, the incorporation of FY-3C thermal bands improved its accuracy significantly, by 3%.

In this work, we compare the impact of two ways of representing the crop growth model uncertainty (the crop growth model was calibrated by Markov Chain Monte Carlo (MCMC)) on the subsequent assimilation of the Sentinel-2 LAI through Ensemble Kalman Filter (EnKF): generating N sets of crop parameters based on the Optimal-posterior parameter value (reference method, we name it OMCMC-EnKF) and Randomly selecting N sets of crop parameters from the most frequent parameters (our proposed method, RMCMC-EnKF). The results show that our proposed method is better than the reference model, when compared with the field measured winter wheat LAI and yield, its performance in the R2, RMSE, and uncertainty estimation is better. Furthermore, our proposed method is more robust to feedback from remote sensing data and more resistant to lower quality observations encountered during assimilation.

Accurate and timely regional crop yield information, particularly field-level yield estimation, is essential for commodity traders and producers in planning production, growing, harvesting, and other interconnected marketing activities. In this study, we propose a novel data assimilation framework. Firstly, we construct the county-level prior and likelihood constraints for a process-based crop growth model based on the previous year's statistical yield and the current year's field observations. Then, we infer the posterior sets of model-simulated time-series LAI and the final yield of winter wheat with an MCMC (Markov chain Monte Carlo) method for each meteorological data grid of ERA5 (European Centre for Medium-Range Weather Forecasts Reanalysis v5). Finally, we estimate the winter wheat yield at the spatial resolution of 10 m by combining Sentinel-2 LAI and the WOFOST model in Hengshui, the prefecture-level city of Hebei province of China. The results show that the proposed framework can estimate the winter wheat yield with a coefficient of determination R2equal to 0.29 and mean absolute percentage error MAPE equal to 7.20% compared with field measurements. However, agricultural stress that crop growth models cannot quantitatively simulate, such as lodging, can greatly reduce the accuracy. The results also suggest good agreements with county-level statistics of the growing year with a coefficient of determination R2equal to 0.52 and mean absolute percentage error MAPE equal to 7.19%.

Graph-based subspace clustering methods have exhibited promising performance. However, they still suffer some of these drawbacks: they encounter the expensive time overhead, they fail to explore the explicit clusters, and cannot generalize to unseen data points. In this work, we propose a scalable graph learning framework, seeking to address the above three challenges simultaneously. Specifically, it is based on the ideas of anchor points and bipartite graph. Rather than building an n×n graph, where n is the number of samples, we construct a bipartite graph to depict the relationship between samples and anchor points. Meanwhile, a connectivity constraint is employed to ensure that the connected components indicate clusters directly. We further establish the connection between our method and the K -means clustering. Moreover, a model to process multiview data is also proposed, which is linearly scaled with respect to n . Extensive experiments demonstrate the efficiency and effectiveness of our approach with respect to many state-of-the-art clustering methods.

The acquisition of surface water information is of great significance of the study of global change. In this study, the Köppen climate zone was firstly used to select sample data onto different climate zones around the world, and then water and non-water samples were collected for each sample. Get as complete a sample of information as possible worldwide. Deep Neural Networks method is adopted to improve the model building, The features data is FY3D/MERSI, containing 6 bands 250m resolution data, add the NDVI and EVI to enhance characteristic data, use the attention mechanism to enhance the model, to strengthen the adaptability for different regions, the model for predicting data using global standardization process. The results show that this method can effectively extract the information on land surface water, especially for different disturbance conditions such as cloud and shadow under cloud. Water tests for 33 different regions of the world show that the method of sample set and model can adapt to different regions of the world.

An automatic airplane recognition algorithm is proposed in this paper, which sequentially uses an object detection convolutional neural network (CNN) and a semantic segmentation CNN to accomplish the airplane recognition task. Experimental results on a collected airplane dataset demonstrate the effectiveness of the proposed method. Our results demonstrate that about 4 points increase of mIOU can be achieved by even reducing the shrinkage rate (SR) with a factor of 2, and better performance can be achieved by further reducing the SR in CNN. We also observed that post-processing techniques such as CRF could be unnecessary when the SR is relatively low. We also adopted the focal loss function, which was originally proposed for object detection, into the semantic segmentation task, and observed that better segmentation results can be achieved by assigning a larger weight to hard samples than to easy samples in the training procedure.

In obtaining Digital Elevation Model (DEM), most methods of acquiring the tie points are generated automatically by software and then manually screened, which is time-consuming and labor-intensive, and the accuracy cannot be guaranteed. Therefore, this paper proposes an automatic stereo matching method combining Speeded Up Robust Features (SURF) and Rational Function Model (RFM) to reconstruct 3D model of remote sensing generalized image pairs. There are two main tasks: first, apply the SURF algorithm to remote sensing images, and screen the tie points at the same name; second, verify the accuracy and effectiveness of the method through experiments.

Crop yield estimation at the field scale is essential for farmers, crop insurance companies to make informed decisions. Methodologies based on assimilating remote sensing LAI into crop growth models have shown advantages in crop yield estimates. Compared with MODIS and Landsat, Sentinel-2 satellites provide higher spatial and temporal resolution data, which brings revolutionary opportunities for crop monitoring. This study is to evaluate the performance of assimilating Sentinel-2 LAI into the WOFOST model for winter wheat yield estimation using the Ensemble Kalman Filter algorithm. The results showed that assimilating Sentinel-2 LAI improved the yield estimation (R2= 0.45; RMSE = 512 kg/ha) compared to the situation without data assimilation (R2= 0.27; RMSE = 818 kg/ha), which demonstrated the potential usage of the Sentinel-2 LAI for yield estimation at the field scale.

Surface albedo is an important land surface characteristic parameter in the study of radiation an energy balance, which can determine the distribution process of radiant energy between the earth's surface and the atmosphere. In this paper, we propose a direct estimation algorithm based on FY-3D Medium Resolution Spectral Imager -2 (MERSI-2) top of atmosphere reflectivity (TOA). The core of this algorithm is to establish a regression relationship between MERSI-2 TOA and shortwave surface broadband albedo. First, the 6S atmospheric radiation transmission model is used to simulate the TOA of MERIS-2 and MODIS under various atmospheric conditions, multiple observation angles, and various BRDF surface characteristics. Next, a linear regression method is proposed to obtain the conversion coefficient between TOA of MERSI-2 and MODIS. Finally, convert MODIS albedo lookup table into MERSI-2 albedo lookup table. FY-3D MERSI-2 surface albedo can be obtained by calling MERSI-2 lookup table. The cross-validation results show that the proposed algorithm obtains better performance.

Several existing shadow detection methods cannot keep the balance between accuracy and automaticity well. To overcome the weakness, we present a novel method to detect shadow in very high spatial resolution satellite images. First, a new shadow detection index is developed to obtain the shadow ratio map. The initial shadow mask map is then obtained by utilizing the Gaussian mixture mode and the Otsu's method automatically. Finally, the initial shadow mask map is refined by jointly using the object spectral characteristics and the spatial-correlation relationship between objects. The experimental results performed on different images show that the accuracy and automation of the proposed method are over several state-of-the-art methods.

FPAR is one of the key climate parameters for the Global Climate Observing System (GCOS) and the Global Terrestrial Observing System (GTOS). An accurate assessment to FPAR is particularly important to understand the global climate change. In this paper, the FY-3C Medium Resolution Imaging Spectrometer (MERIS) data combined with the improved PROSAIL model and look-up table algorithm to retrieve the FPAR at the Hulunber Grassland. The cross-validation results show that FPAR retrieved from FY-3C data has good consistency with the FPAR products of MODIS, GEOV1 and GLASS, with 0.6654, 0.6893 and 0.6192 at overall Pearson’s correlation coefficients (R), respectively. This study provides the potential for the generating the large-area and long-term sequence FPAR products from FengYun-3C (FY-3C) data.

Snow albedo plays an important role in the global climate system due to its climatic feedback effects. Due to the limitations of remote sensing methods, the remotely sensed snow albedo products have significant data loss and error uncertainty. In view of the limitation of retrieval methods, this research utilizing SNICAR model to study the forward simulation of snow albedo. We verify and optimize the SNICAR forward simulation model at the plot scale, based on field measurements of the input variables of forward model such as snow grain size, snow density, water content and solar zenith angle, and combined with the snow grain size evolution model driven by meteorological elements. The results indicate that the MAE (mean absolute error), RMSE (root mean square error), R (Pearson correlation coefficient), and NSE (Nash-Sutcliffe efficiency coefficient) of the observed and simulated snow albedo by the optimized SNICAR model are 0.04, 0.05, 0.86 and 0.67, respectively. Our research validates and optimizes the snow albedo forward simulation model, which provides an effective simulation means acquiring the snow albedo data of continuous time series in alpine mountain regions.

The surface albedo indicates the ability of the Earth's surface to reflect solar radiation, and it is an important land surface characteristic parameter that affects the radiation and energy balance of the Earth system. This paper presents a surface albedo inversion method for FY-3C MERSI. First, we estimated the narrow-band surface albedo for different surface cover types by using constrained least squares and the RossThick-LiTransit model. Then, we calculated the conversion coefficient of the FY-3C MERSI narrow-band surface albedo to the broad-band surface albedo conversion by using the FY-3C MERSI spectral response function, the 6S radiation transmission model and the USGS spectral library. Finally, we obtained the surface black and white albedo of the four narrow-band and visible-light bands of the FY-3C MERSI, and the spatial resolution of the data is 250m. In the comparative verification experiment, we cross-validated the surface albedo of FY-3C with the surface albedo of MODIS (moderate-resolution imaging spectroradiometer), CGLS (Copernicus Global Land Service) and GLASS (Global LAnd Surface Satellite). The results show that the correlation coefficient is mostly above 0.75, the overall absolute deviation is 0.068 on average and the minimum root mean square error is 0.02 between the albedo products obtained in this paper and the above three products. Therefore, FY-3C MERSI surface albedo products and MODIS, CGLS, GLASS surface albedo products have good consistency in four narrowband and visible light bands.

Land surface water is one of the most important components of surface cover and global water cycle. In this study, the standard water spectrum selected from FY/MERSI image was firstly used to calculate the water probability. Then, based on water probability, the image was roughly classified into four classes: homogeneous ground, junction of land cover, minor tributaries and other. To extract land surface water from small tributaries, the Duda's Road Operator (DRO) was introduced to enhance the linear features, while Discrete Particle Swarm Optimization (DPSO) was applied to extract land surface water from other three classes. The results show that the method could effectively extract land surface water, especially from small tributaries, and overall accuracy (OA) and Kappa coefficient are improved compared to DPSO algorithm based on spectral matching (SMDPSO).

Few studies have studied the impact of different rural reference selections on the study of urban heat island intensity (SUHII) from the perspective of land surface temperature (LST) gradient changes. The purpose of this study was to analyze the gradients of land surface temperature in rural areas of 32 cities in China and to explain the causes of gradient changes through biophysical effects (Albedo and ET). The main findings include: (1) As the distance from the urban increases, there is a gradient change in the land surface temperature, and the gradient changes in different cities are different. According to the trend, 32 cities can be divided into the following three categories: the land surface temperature shows a decreasing trend with increasing distance. It decreases first and then flats with increasing distance and it shows an increasing trend with increasing distance. And the land surface temperature gradient changes in the same city are different between the day and night. (2) Albedo and ET have significant effects on land surface temperature gradient changes. From the results of variance partitioning, the explanatory ability of ET is slightly stronger than that of Albedo. But for most cities, the two jointly have a stronger ability to interpret. And the effects of both at night are stronger than during the day. This study reveals the gradient of land surface temperature and its causes more comprehensively, thus providing a valuable scientific reference for the selection of rural areas when studying urban heat island intensity .

Few studies have compared the effects of different urban-rural selection methods on estimating urban heat island intensity (SUHII) spatial variation. This study aims to analyze the influence of different urban and rural selection methods (Whether water and elevation should be excluded, whether rural areas should be restricted, and whether urban-rural fringe should be considered) on the spatial variation of SUHII, to take 32 cities in China as an example. The main findings include: (1) Comparison of different methods, the SUHII calculated by these methods that include water bodies and elevations, unrestricted rural areas, and rural areas that exclude urban-rural fringe will be larger.(2) Estimates of SUHII in 32 cities are affected by different methods differently.(3)When using different methods to analyze SUHII in four types of humid and dry areas. The order of the large and small SUHII in the four regions obtained is different. Except for the arid regions, the other three regions showed the same regular characteristics as the conclusion (1). However, in the arid regions, SUHII obtained by these methods that unrestricted rural areas and excluded urban-rural fringe is smaller.(4)In the analysis of the seven geographical divisions. The relative size of SUHII in different geographical regions is different by the influence of the method, and the difference is obvious. This study compares the six urban and rural selection methods to find that different methods have an important impact on the spatial variation of SUHII. Therefore, in the study of SUHII, the emphasis on the selection of urban and rural partition methods should be improved.

Accurate mapping of urban land cover is still a fundamental challenge in remote sensing communities due to the great spectral variability of urban environments. This study presents an application of multiple criteria spectral mixture analysis (MCSMA) approach to map vegetation, impervious surfaces, and soil (V-I-S) components in a highly urbanized city of Chengdu, China, using the Landsat-8 Operational Land Imager (OLI) surface reflectance product. Unlike its counterparts which rely on single indicator in the mapping process, MCSMA uses multiple indicators to better address the problem of spectral variability. Our results showed that MCSMA produced accurate V-I-S maps that well matched the actual distributions. The vegetation map presented higher accuracies than impervious surfaces and soil maps in root mean square error, mean absolute error and systematic error. Results of this study demonstrate the potential of MCSMA in accurate urban land cover mapping.

Forests are at risk of extinction due to increased competition for land in urban areas due to expansion of cities. Forests are important as they act as heat and carbon sinks hence the need to monitor their spatial and temporal changes. We investigated the link between forest cover changes and land surface temperature dynamics in Freetown and Bo town Sierra Leone between 1998 and 2015 using Landsat data. Results showed that forests are expanding in Freetown while diminishing in Bo town. As a result, land surface temperatures warmed faster in Bo town than in Freetown where the land surface temperature moderation value of dense forest increased with time. Surface temperature increased by 4°C in Bo town while it increased by less than 2°C in Freetown due to differences in forest changes between the cities. The results showed that increasing tree density in forests is strong land surface temperature moderation measure. Future urban growth must consider impact of forest cover in order to ensure sustainability.

Snow albedo plays an important role in the global climate system. There are notable missing data and error uncertainties in the current remote sensing snow albedo products that are attributed to the limits of remote-sensing technology. Due to the uncertainties of meteorological factors and the differences in various forward model simulation methods, snow albedo forward simulations also have considerable uncertainties. This paper suggests a long-time-series reconstruction of snow albedo utilizing a forward radiation-transferring model and a remote-sensing retrieval model together with multisource remotely sensed data and meteorological data. The key to this paper is to estimate snow information for areas lacking data utilizing a forward model for snow albedo with clear physical mechanisms. The estimated snow information can be used as reliable data for snow albedo reconstructions. The results indicate that the long time series of snow albedo data obtained by coupling the snow albedo retrieval model and forward simulation model is highly accurate. The mean absolute error, root mean square error, Pearson's correlation coefficient (R), and Nash-Sutcliffe efficiency coefficient of the observed and reconstructed snow albedos are 0.11, 0.14, 0.79, and 0.69, respectively. The reconstructed snow albedo data are underestimated by only 11% relative to the in situ snow surface albedo measurements. In the alpine mountain regions, the proposed method has a simulation accuracy that is 6% greater than that of the MOD10A1 SAD. This paper provides an effective reconstruction solution that improves the accuracy of estimations of snow albedo and fills gaps in the data.

The classification and mapping method is vital for many fields of research and has important societal and economic meaning. In this study, we applied QuickBird image to discuss a Multi-scale segmentation method about orchard in Taolin region, Ningxia province in China. Meanwhile, eCognition , as the leading object-oriented software in the world , was used to achieve the goal of classification and mapping. Then, based on the image object's attributes, relationship of each other etc, we formulated a orchard classification system, set a suit of remote sensing interpretation standard, and put forward a Multi-scale segmentation idea to realize sophisticated classification and get satisfied classification result.

In this paper, we focus on winter wheat yield assessment in Hebei province in china. The method take two procedures: first, we extract phenological transition dates from MODIS-LAI. Then, using SCE_UA algorithm, we assimilated the phenology information into crop growth model SWAP. The results shown that an improved accuracy of crop yield can be achieved compared to the method with no assimilation algorithm.

In this paper, the Kuusk-Nilson forest reflectance and transmittance (FRT) model was inverted to retrieve the overstory and understory leaf area index (LAI) of forest stands in the Longmenhe Nature Reserve (Xingshan County, Hubei province, China). Atmospherically and topographically corrected hyperspectral Hyperion imagery and field data had been input to retrieve the overstory and understory LAI simultaneously using FRT inverted model. An uncertainty and sensitivity matrix was used to analyze the sensitivity of the FRT model parameters based on field data. Twenty-one Hyperion bands were selected based on principal-components analysis and band importance from total Hyperion bands. Eight different Hyperion band combinations from 21 Hyperion bands were tested to evaluate the accuracy of the inversion of overstory and understory LAI. Our study showed that the overstory LAI of stands can be better retrieved when considering the understory LAI compared to only use total LAI.

Land cover change has largely resulted in deforestation, biodiversity loss, global warming and reduction of environmental services, so many countries and organizations establish land cover data through multiform methods. Despite its importance, accurate statistics on land cover change data is not available in most countries, the detection and monitoring of land cover dynamics is highly desirable. With increasing frequency, remotely sensed data sets have been used to classify global land cover. The objective of this paper is to construct an operational system to update land cover dataset based on CBERS-02B image and outdated land cover data.

It is important to inventory and monitor wetlands and their adjacent environment. People can't go to somewhere of wetlands. Satellite remote sensing has several advantages for monitoring wetland resources, especially for large geographic areas and no man's land This paper uses multi-temporal Landsat TM and ETM+ data to study the degradation of wetlands. The simple method to classify wetlands is unsupervised classification or clustering. Wetland classification is difficult because of spectral confusion with other landcover classes and among different types of wetlands. However, multi-temporal remote sensing data and ancillary data such as soil data, elevation or topography data usually improves the classification of wetlands. Change detection studies have taken advantage of the repeat coverage and archival data available with satellite remote sensing. The result of multi-temporal monitoring indicates the degradation of Ruoergai Wetland.

The ability to extract the special land use type of environment, and associated temporal changes, has important societal and economic meaning. This paper uses the high spatial resolution of the image---QuickBird to extract greenhouse in agriculture of Hexian region, ANHUI province in China. The paper uses software package eCognition to process data and extract information. The software adopted object-oriented image segmentation and classification which is based on fuzzy logic. In this study the greenhouse is a special land cover type in agricultural land, we use not only image object's attributes, but also the relationship between networked image objects; it can perform sophisticated classification and get satisfied classification result, allows the integration of a broad spectrum of different object features, such as spectral values, shape and texture. The aim of this work was to develop an object-oriented segmentation and classification approach for extracting special land cover type.

Vegetation cover is of great significance in understanding climate change process due to its vital role in controlling water and carbon cycles. The properties of vegetation's surfaces are usually estimated by remotely sensed data through regression models or physical-based models, which simulates the interactions of solar radiation with the vegetation medium. In real domain, the spectral responses measured by the sensor in forested area are strongly influenced by the different understory natural conditions that limit the possibility of applying both retrieval methods to predict overstory vegetation parameters. Understory information is therefore needed for estimating trees' parameters; moreover from a biodiversity point of view and perspective of forest management, understory represents a critical component of forest ecosystem that needs a better characterization. An experiment has been conducted using hyperion and panchromatic QuickBird data to explore the status of different vegetation's understory under a sparse forest in the Longmenhe Nature Reserve, China. Understory vegetation information of study area is classified into five classes. The novel aspect of the method is the integration of spectral (hyperspectral) domain fusion and spatial domain fusion techniques within a multi-layer perceptron artificial neural network model. Real data from the experiment on a limited ground as well as hyperion and QuickBird data are used as input dataset. A nonlinear artificial neural network achieved a classification accuracy of 80% despite the presence of co-occurring mid-story and understory vegetation. The achieved results show that this method is able to identify the different vegetation information under the tree canopy. Our studies suggest that it is necessary to incorporate the geographic and vegetation community prior information to further improve the accuracy in order to monitor understory vegetation.

Soil erosion is a major environmental problem worldwide, threatening the human sustainable development. Global water erosion and wind erosion affect 1094 and 549 Mha, respectively. Soil erosion concerns multi factors, for example, land cover, climate, vegetation cover, topographic factors. Soil erosion is also different in different spatial and temporal scales. To monitor and assess the extent of soil erosion, multi data concerning these influencing elements need to be considered by combined use. Among these factors that influent the process of soil erosion, vegetation cover and slope steepness are selected. The vegetation cover data in the Chengdu plain have been estimated from normalized difference vegetation index derived from Landsat-7 ETM+ image acquired at 2000-11-02. Slope steepness is computed based on the pixels of DEM (Digital Elevation Model), the pixels of DEM are transformed from the 1:100000 terrain map. Vegetation cover and topographic factor can be combined as a cross tab model. A soil erosion risk map with six grades can be drawn. Using the method the probability and the extent of soil erosion can be measured. Remote sensing data provide a significant information source for mapping, monitoring and predicting current rapid soil erosion. In the analysis process of soil erosion monitoring geography information system takes very important roll. It can fuse different thematic data and different formats of data. This paper gives a brief synthesis of the information obtainable from remote-sensing data and DEM data, and assesses the status of soil erosion in Chengdu plain.

Based on the uncertainty and fuzziness of remote sensing images, a dot density function weighted fuzzy C-means (WFCM) clustering algorithm is proposed to carry out the fuzzy classification or the hard classification of remote sensing images. First, the algorithm considering data spatial distribution information and classification fuzziness is described. The fuzzy C-means algorithm is an unsupervised fuzzy classification method. Clustering precision of the algorithm is affected by its equal partition trend for data sets, which leads to the optimal solution of the algorithm may not be the correct partition in the data set of which cluster sample numbers are difference greatly. In order to overcome this drawback, a dot density function WFCM algorithm is proposed in this paper. The method has not only overcome the limitation of FCM to certain extent, but also been favorable convergence. Then the WFCM algorithm would be compared with the K-means algorithms by experiments in LANDSAT TM image. Finally classification result of the algorithms is analyzed systematically, and the experiment result shows the WFCM algorithm can improve classification accuracy for remote sensing images.

North piedmont of Yinshan mountain is a typical ecological fragile zone and an important eco-shelter in north China. It is very important to study impact of global change in this area in order to monitor and analyze dynamics of vegetation cover. This paper illustrates the application of a local variance technique to assess vegetation cover change in Yinshan Mountain using integrated growing season NDVI measurements. The paper calculated seasonal integrated normalized difference vegetation index (NDVI) for each of 8 years using a time-series of 1-km data from SPOT Vegetation (1998-2005) sensors. Based on the data, we can construct the smoothed NDVI time-series to locate the onset and end of the growing season of vegetation. Then we can calculate the integrated NDVI (iNDVI) as the area under the NDVI curve from the start of season to the end of season. The paper uses a local variance method to detect local spatial anomalies of iNDVI for study area. We summarized the number of years that a given pixel was identified as an anomaly. The resulting anomaly maps were analyzed using Landsat ETM+ imagery and extensive ground knowledge to assess the results. The local variance analysis is a reliable method for assessing vegetation cover change from human pressures or increased land productivity from natural resource management practices. The result provides a good support for analyzing relation between vegetation change and climatic factors.

Leaf area index (LAI) is an important parameter for describing vegetation canopy structure in the terrestrial ecosystem on the global, continental and regional scales. In this paper, a simple data assimilation method for improving estimation of MODIS LAI time-series data products based on a new 2-D LMS (two-dimensional least mean square) adaptive filter was proposed. Firstly, The new 2-D LMS adaptive filter algorithm is introduced and analyzed. Secondly, A simple data assimilation method for improving estimation of MODIS LAI time-series data products based on the new 2-D LMS adaptive filter and quality control data of MODIS LAI is proposed. Finally, the experiments are performed based on the simple data assimilation method using MODIS LAI data products from 2000 to 2005 of southwestern China.

Crop growth monitoring is very important in agriculture resource management. Crop growth monitoring could provide crop state information for the decisive maker and reflect variety information of crop yield in time. The index of crop growth monitoring has closely relation with crop yield, which could as early as forecast large-scale food state that possibility missing or surplus. Therefore, there are important meanings to the macro control for food. Traditionally, the monitoring of crop growth and yield forecasts are made on the basis of samples by field visits or written inquiries. On national scale, the processing of these sample data is an expensive and time-consuming procedure. Recent developments in remote sensing technologies have created promising opportunities for monitoring agricultural crop growth. The moderate resolution imaging spectroradiometer (MODIS) is one detector board on Terra's (EOS-AMI), which was lunched on December 18, 1999 by NASA. It offers a unique combination of spectral, temporal, and spatial resolution compared to previous global sensors, making it a good candidate for large-scale crop growth monitoring. The paper studied the method of crop growth monitoring based on data of MODIS/TERRA vegetation indices. Results from the study not only monitor the crop growth in investigation area, but also illustrate the powerful potential to provide information about crop growth based MODIS VI data.

Crop acreage monitoring is basic information necessary for wise management of plant natural resources. Recent developments in remote sensing technologies have created promising opportunities for improving agricultural statistics systems. The Moderate Resolution Imaging Spectroradiometer (MODIS) is one detector board on Terra's (EOS-AM1), which was lunched on December 18, 1999 by NASA. It offers a unique combination of spectral, temporal, and spatial resolution compared to previous global sensors, making it a good candidate for large-scale crop acreage estimating. However, because of subpixel heterogeneity, the application of traditional hard classification approaches to MODIS data may result in significant errors in crop area estimation, especially in China. This paper developed and tested an unmixing approach with MODIS data that estimates subpixel fractions of crop area based on the temporal signature of reflectance throughout the growing season. A zone that can get LANDSAT/TM data was chosen to be train dataset in this method. The paper assumes that the crop area estimating from LANDSAT/TM data is correct; in the training zone the crop area based on MODIS data can get from the classification result of LANDSAT/TM data. Then we can extend the result to a large-scale; finally we compare the result to national statistic data. The results of this study demonstrate the importance of subpixel heterogeneity in cropland systems, and the potential of temporal unmixing to provide accurate and rapid assessments of crop distributions using MODIS data. I INTRODUCTION

Miyun reservoir is an important water supplier of Beijing, China, therefore soil erosion of this area is very critical and must be paid sufficient attention. To monitor and manage soil erosion information in Miyun reservoir area, a monitoring information system that is dynamic, interactive and Internet-based was developed. The paper describes how the WebGIS application was developed, implemented and used. The overall monitoring information system is multi-scale, multi-source, flexible and geographically organized. It uses an Internet-based GIS ("WebGIS") technology, and has obtained information about soil erosion in Miyun reservoir area through four methods: RUSLE model, TM images visual interpretation, model based on vegetation cover and slope, and data fusion of three results. The decision-making officers can access and analyze these data more effectively and conveniently via the Internet.

Drought is one of the major environmental disasters in north China, and it is very important to detect and monitor drought periodically at large scale for decision making. The Normalized Difference Vegetation Index (NDVI) has been widely used to monitor moisture-related vegetation condition. To better understand the relationship between vegetation vigor and moisture availability, the Normalized Difference Water Index (NDWI) was calculated in addition to the NDVI. In this study, the analysis was conducted on time series compositing NDVI and NDWI of the period of ten days. With the support of land use map and soil humidity of crop for the growing season, we build the simple model of northern China for crop drought monitoring. The results of July 2002 show that the large scale temporal and spatial characteristics of drought in Northern China can be effectively detected by this way. Based on this method, we have developed a operational crop drought monitoring system for whole China land areas.

With the great agriculture population and limited cropland, it is very important to estimate the output of grain produce in China by remote sensing technology. However, the smallholders of cropland can plant what they like, thus it is difficult to monitor the crop planting proportion with only RS images, even with IKONOS/QUICKBIRD data. In GVG agro-status sampling system, the video camera connected with a notebook by a video capture card and GPS receive card are integrated into the GIS environment. GVG is fixed on a motor and restore the crop pictures and their GPS data when the car is moving along the country road derived from the linear sampling frame in a plantation division unit. A great many of crop pictures along the sample lines are obtained on the field in a limited time, and then all pictures with geographical data are interpreted to calculate the ratio of each type of crop plantation. The crop proportion of plantation division unit is estimated by all picture's plantation ratio of sample line due to this unit. This literature review has demonstrated the GVG systems hardware's constitute, working principle and the case studies. GVG agro-status sampling system not only can be acquire every crop's planting proportion of large areas in short time, but also can check up the results, which get from remote sensing crop classification.

Miyun Reservoir is located in the northeast of Beijing and it is the most important drinking water resource of the city. Soil and water loss in this area directly affects local eco-environment and people's life. The soil and water conservation project has been launched out to combat the degrading environment in the upper reach of Miyun Reservoir basin. A ruled-based approach based on the objective of catchments, which is the unit of most soil conservation project, was applied to evaluate soil loss. For each heterogeneous hilly valley in the study area, a set of knowledge-based rules was formulated with remotely sensed images, land use map, DEM and ground investigated data. The relevant parameters, such as slope, vegetation fraction, ravine density, and rainfall distribution, which are also the input parameters of the widely applied universal soil loss equation (USLE), were scaling to the object properties to count this ruled-based model. Finally, all catchments were grouped into four grades according to the soil loss intensity, namely very severe, severe, moderate and slight, the result of the study was practicable to support to make the soil conservation planning.

The global version of the 1km spatial resolution land cover map have been finished at the end of 2003, which is initiated by the European Commission's Joint Research Center, named Global Land Cover 2000 Project (GLC-2000). As a part of GLC2000, the China window has been developed with the 10-day composite SPOT VGT NDVI data over a period of 01 January 2000 to 31 December 2000, DEM and the Meteorological data (Multi-annual average temperature, multi-annual average precipitation data) collected from 313 weather stations distributed over the China from 1971 to 2000. In order to remove cloud contamination and interpolate the missing data masked by cloud, the Harmonic Analysis of Time Series (HANTS) was applied to NDVI data. With the assistance of Erdas ISODATA algorithm, the classification has been carried out, and 22 types of land cover has labeled in the whole China by interpreting according to the Land Cover Classification System (LCCS) developed by the UN Food and Agriculture Organization (FAO) in the framework of the AFRICOVER project. Preliminary comparisons with the statistic data from Chinese Statistics Bureau and TM data show very promising results, and the accuracv assessment of the GLC-2000 is underway.

The China Brazil Earth Resources Satellite (CBERS)-2 CCD has 4 bands of 19.5m spatial resolutions in the visible/near-infrared wavelength regions and 1 pan band of 19.5m spatial resolutions. These bands (except pan) have the same spectral zones as Landsat7 ETM+ multispectral bands. We compared the performance of CCD image with ETM image from 4 key aspects in order to accelerate its application for agriculture monitoring. These 4 key aspects are geometric correction, typical surface features identification, land target area measurement, image classification and interpretation. The results show that CCD image can be geometrically corrected with high accuracy, is better than ETM+ image for typical surface features identification, records the small land targets in detail, can be more suit for recognition by eyes, can be used for measuring land targets area with high accuracy, has the same good performance as ETM image for image classification and interpretation. CBERS-2 CCD shows great potential for the applications of agricultural monitoring.

The ability to map and monitor the spatial extent of the built environment, and associated temporal changes, has important societal and economic meaning. In This work, the high spatial resolution of the image - Quick Bird was used to create a detailed land cover maps of Taigu region, Shanxi province, China. Adopting object-oriented image segmentation and classification which is based on fuzzy logic allows the integration of a broad spectrum of different object features, such as spectral values, shape and texture. In this study we use not only image object's attributes, but also the relationship between networked image objects, it can perform sophisticated classification and get satisfied classification result. The aim of this work was to develop an object-oriented segmentation and classification approach for operational land cover mapping.

In China, crop structure adjustment policy has brought great change of different breed's planting area in different years. Government managers of agricultural industry need timely crop structure information to monitor the performance of the crop structure adjustment policy. The objective of this research was to evaluate the synergistic effects of multitemporal RADAR SAT synthetic aperture radar (SAR) and Land sat ETM+ data for extracting agricultural crops structure using an object-oriented classification approach. This work instructs and analyses the crop structure near the Kaifeng city area in 2002. Four crop types were extracted: corn, soybean, cotton, and peanut. With the object-oriented classification approach, the overall accuracy of crop structure extracting from two-date F5 mode's SAR data (mid- to last-season) and two-date Land sat ETM+ is over 90%.

The land desertification is one of the major environmental problems in the Source Region of the Yangtze River, Qinghai Province. With the Three Gorges Dam construction, more and more attention is paid to restoring the degraded eco-environment of the region. In this study, the sandy land was classified into three types, and the desertified land was also inventoried correspondingly into three levels. Through interpreting TM images in 1986 and 2000, the databases of sandy land at two times had been established, respectively. And then the desertified land data was derived through overlaying the databases of sandy land. The result shows that there is 1,459,365 ha of sandy land in the region in 2000, accounting for 9.89% of all study area. There is 11,877 ha of newly sandy land resulted from land desertification, and sandy land has increased by 7.35% during about 14 years in the end of the 20th century.