With the increase in population and the growing demand for timber, especially fuelwood, Kenya's forests are facing the threat of serious deforestation and illegal logging activities. At present, remote sensing has become an important means of monitoring the dynamic changes of forest resources with its advantages of wide monitoring range, fast speed and low cost. This paper selected Mount Kenya National Forest Park as the study area, employing domestic 2-meter resolution satellite images (Gaofen-1 satellite constellation, Gaofen-6 and the Ziyuan-3 satellites) to conduct dynamic forest change monitoring from 2019 to 2023. The optimized semantic segmentation model DeepLabv3+, which is based on the Pytorch deep learning framework, was used to achieve fine segmentation of forest element boundaries via a spatial pyramid pooling module and an encoder-decoder architecture. The method of manual annotation was used to mark the forest changes and their causes from 2019 to 2023. The newly added forest was mainly restored by artificial planting, covering an area of 3078.71 ha. The total area of forest reduction was 2,425.91 ha. There were 542 patches of forest land occupied by new arable land, covering an area of 1,613.41 ha. It was the most important cause for the forest reduction. 327 patches of forest reduction were due to artificial logging, covering an area of 408.34 ha, which was the secondary cause of forest loss. Human activities were more constrained at higher altitudes, hence, the most of planting and lost forest patches usually occurred below 2,600 meters above sea level. Effective implementation of environmental protection policies was an important reason for the emergence of large areas of new plantation while the occupation of arable land and logging were main factors for the forest reduction in Mount Kenya.

When given two similar images, humans identify their differences by comparing the appearance (e.g., color and texture) with the help of semantics (e.g., objects and relations). However, mainstream binary change detection models adopt a supervised training paradigm, where the annotated binary change map is the main constraint. Thus, such methods primarily emphasize difference-aware features between bitemporal images, and the semantic understanding of changed landscapes is undermined, resulting in limited accuracy in the face of noise and illumination variations. To this end, this article explores incorporating semantic priors from visual foundation models to improve the ability to detect changes. First, we propose a semantic-aware change detection network (SA-CDNet), which transfers the knowledge of visual foundation models (i.e., FastSAM) to change detection. Inspired by the human visual paradigm, a novel dual-stream feature decoder is derived to distinguish changes by combining semantic-aware features and difference-aware features. Second, we explore a single-temporal pretraining strategy for better adaptation of visual foundation models. With pseudo-change data constructed from single-temporal segmentation datasets, we employ an extra branch of the proxy semantic segmentation task for pretraining. We explore various settings like dataset combinations and landscape types, thus providing valuable insights. Experimental results on five challenging benchmarks demonstrate the superiority of our method over the existing state-of-the-art methods. The code is available at https://github.com/DREAMXFAR/SA-CDNet

In order to give full play to the application efficiency of land remote sensing satellites for natural resources and strengthen the protection of cultivated land in China, this paper introduces a two-stage intelligent extraction strategy for erosion gullies. This strategy integrates deep learning object detection with interactive semantic segmentation.Initially, an iterative optimization method of object detection samples and models based on incremental learning and confidence filtering is proposed, achieving automatic identification of erosion gullies. Then, an interactive semantic segmentation method based on edge constraint is adopted to extract the precise contours of erosion gullies semi-automatically. An erosion gully extraction experiment was conducted in Heilongjiang Province of China, utilizing satellite images with a spatial resolution of 2 meters. Accuracy assessment was performed using GF-7 satellite imagery and verified through field verification. The results indicate that the Precision of erosion gully extraction in test area was 95.4%, the Recall was 93.0%, and the F1_score was 94.2%. The feasibility and accuracy of the proposed method has been verified by the experiments.

Change Detection is a crucial but extremely challenging task of remote sensing image analysis, and much progress has been made with the rapid development of deep learning. However, most existing deep learning-based change detection methods mainly focus on intricate feature extraction and multi-scale feature fusion, while ignoring the insufficient utilization of features in the intermediate stages, thus resulting in sub-optimal results. To this end, we propose a novel framework, named RFL-CDNet, that utilizes richer feature learning to boost change detection performance. Specifically, we first introduce deep multiple supervision to enhance intermediate representations, thus unleashing the potential of backbone feature extractor at each stage. Furthermore, we design the Coarse-To-Fine Guiding (C2FG) module and the Learnable Fusion (LF) module to further improve feature learning and obtain more discriminative feature representations. The C2FG module aims to seamlessly integrate the side prediction from previous coarse-scale into the current fine-scale prediction in a coarse-to-fine manner, while LF module assumes that the contribution of each stage and each spatial location is independent, thus designing a learnable module to fuse multiple predictions. Experiments on several benchmark datasets show that our proposed RFL-CDNet achieves state-of-the-art performance on WHU cultivated land dataset and CDD dataset, and the second best performance on WHU building dataset. The source code and models are publicly available at https://github.com/Hhaizee/RFL-CDNet.

The accurate and frequent extraction of information regarding new construction land is essential in natural resource monitoring and land law enforcement supervision.To fulfill these practical demands,this study constructed a technical framework for the intelligent monitoring of new construction land via satellite remote sensing.The framework includes a"spatial-temporal-spectral-classified"monitoring hypercube,a base map generation for monitoring,a sample annotation iteration,component-based artificial intelligence(AI)change detection model establishment,parcel information filtering,and post-processing.To meet the demand for accurate applications in large areas and complex scenes,this study fully combined different AI algorithms and network structures,such as attention mechanism,domain adaptation,and visual transformers,to develop a component-based AI change detection model for improving the accuracy and reliability of the algorithm.Meanwhile,to address issues,such as misidentification during the automatic extraction of new construction land parcels,parcel fragmentation,and edge inaccuracy,geomorphological principles were comprehensively utilized to set constraints and investigate post-processing parcel refinement methods.Experiments by region and time were conducted on large-scale remote sensing monitoring of new construction land to verify the feasibility of the proposed concept of the"spatial-temporal-spectral-classified"monitoring hypercube.Moreover,through ablation analysis of the component-based AI change detection model,the advantages and disadvantages of the algorithms were compared and analyzed.In particular,the visual transformer module exhibits evident advantages in terms of the feature completeness,edge accuracy,and recall rate of new construction land extraction.On the basis of certain operational data of satellite image-based law enforcement and supervision,cloud cover filtering was conducted.Wrongly extracted parcels accounted for about 0.84％.In addition,after the post-processing parcel refinement method proposed in this study was adopted,the accuracy and practicability of the monitoring results were further enhanced.The satellite remote sensing-based technologies and methods for the intelligent monitoring of new construction land proposed in this study have been applied to natural resource monitoring,such as land law enforcement and supervision.

一、引言 红树林是在热带亚热带地区、海岸潮间带滩涂上生长的木本植物群落,是兼具陆地和海洋特性的复杂生态系统.红树林在防浪护堤、海湾改善、污染净化和湿地多样性保护等方面发挥着不可替代的作用,具备重要的生态系统服务功能以及社会经济价值 [1].红树林生态系统具有开放性、脆弱性和复杂性等特点,因其位于人为干扰强度大的沿海地区,人类活动对其分布产生直接影响.据联合国粮农组织(FAO)调查,全球红树林生态系统仍处于高度受威胁状态,针对红树林生态系统开展长期监测具有重要意义.

To meet the demands of natural resource monitoring, land development supervision, and other applications for high-precision and high-frequency information extraction from constructed land change, this paper focused on automatic feature extraction and data processing optimization methods for newly constructed bare land based on remote sensing images. A generalized deep convolutional neural network change detection model framework integrating multi-scale information was developed for the automatic extraction of change information. To resolve the problems in the automatic extraction of new bare land parcels, such as mis-extractions and parcel fragmentation, a proximity evaluation model that integrates the confidence-based semantic distance and spatial distance between parcels and their overlapping area is proposed to perform parcel aggregation. Additionally, we propose a complete set of optimized processing techniques from pixel pre-processing to vector post-processing. The results demonstrated that the aggregation method developed in this study is more targeted and effective than ArcGIS for the automatically extracted land change parcels. Additionally, compared with the initial parcels, the total number of optimized parcels decreased by more than 50% and the false detection rate decreased by approximately 30%. These results indicate that this method can markedly reduce the overall data volume and false detection rate of automatically extracted parcels through post-processing under certain conditions of the model and samples and provide technical support for applying the results of automatic feature extraction in engineering practices.

As an important part of the renewable energy, photovoltaic power generation industry has developed rapidly all around China in recent years, however some land use problems have also emerged. Therefore it is of great significance to monitor the number and distribution of photovoltaic power stations timely and accurately with high-resolution satellite images for the healthy development of photovoltaic industry. Combined with the improved DeepLab V3+ model and the ResNeSt-50 backbone network, the paper designs an effective photovoltaics extraction semantic segmentation algorithm and trains the new extraction model iteratively by making full use of big and various photovoltaic land samples. Photovoltaics are extracted accurately all over China with Chinese high-resolution satellite images, following a series of post-processing algorithms, such as binarizing, small and pseudo targets automatic removing, etc. Results show that the accuracy rate of photovoltaic land extraction is about 72.36% and the recall rate is about 91.06%. This precision is good enough for photovoltaic land extraction nationwide annually and the proposed deep learning model is efficient, small and can widely be used with other natural resources target extraction.

Surface water is an irreplaceable strategic resource for human survival and social development. It is of great significance to fully grasp the quantity, spatial distribution and dynamic changes of surface water in China accurately, quickly and timely. With the rapid development of Chinese remote sensing satellite industry, monitoring surface water in whole China quarterly has become a task of challenge but achievable. This paper analyzes and compares the advantages and disadvantages of existing algorithms for surface water extraction. And a practical and useful algorithm workflow is proposed. Based on 2-meter resolution multi-spectral satellite images, the paper adopts the regional fast-growing water extraction algorithm combined with water element buffers. 1,265 above level 3 rivers, their associated 2,128 reservoirs and 2,953 above-1-km2 natural lakes in China have been fast extracted quarterly with high-precision. Practice has shown that the automatic extraction algorithm is one of the most effective algorithms for realizing the automatic monitoring of large-scale surface water.

At present, the Synthetic Aperture Radar (SAR) is one of the few remote sensing methods that can realize rapid all-day and all-weather mapping in difficult areas of surveying and mapping, and has unique advantages incomparable with traditional optical remote sensing technology. And SAR polarimetric scattering mechanism provides important theoretical basis for surface radar target recognition. The paper adopts the P-band polarization data acquired by Chinese Academy of Surveying and Mapping SAR system (CASMSAR) as well as the C-band polarization data from Radarsat-2 and use the Freeman-Durden decomposition method to analyze and compare the difference of six typical terrain targets' scattering characteristics of different band SAR images. Results are as follows: (1) the volume scattering values of vegetation at different height are relatively high in C-band SAR image, which can be distinguished from non-vegetation, but the scattering characteristics between vegetations are confusing. (2) For P-band SAR image, there is a great difference in the volume scattering characteristics between vegetations at different height, while little difference in the odd scattering characteristics among bare soil, water area, and burnt wheat fields. (3) The volume scattering characteristics of vegetations at high height are obvious in P-band SAR image, while those at low height are obvious in C-band SAR image.

The timely and accurate acquisition of greenhouse information is crucial for strategically planning modern agriculture. However, existing methods are affected by the close spacing between agricultural greenhouses, intra-class diversity, and inter-class similarity, resulting in missed and incorrect extraction phenomena. Here, we propose a model for agricultural greenhouse extraction (i.e., EAGNet), which includes a residual block improvement module (RBIM) and boundary segmentation module (BSM) that solve the problem of densely distributed agricultural greenhouse-boundary adhesion. We constructed a class attention module (CAM) to address the leakage extraction phenomenon in agricultural greenhouses caused by intra-class diversity and introduced an object contextual representation module (OCRM) to address the incorrect extraction of agricultural greenhouses caused by the similarity between classes. Experiments on a self-made agricultural greenhouse dataset showed that EAGNet achieved the best extraction results among all compared methods.

Building extraction with deep learning requires a large amount of samples used as train data. Small differences in building features and big differences between building and background features are important for qualified samples. However, in practice, it is difficult to obtain the required massive samples with good quality which restricts the application of building extraction from remote sensing images based on deep learning seriously. To tackle the problem, this paper proposed a fast verification method of small building samples using deep learning extraction with remote sensing images. The main steps include: firstly, combine the morphological building index (MBI) feature with their original bands to be new input images for deep learning network. Secondly, customize network model parameters based on the U-series semantic segmentation framework, use the mini-batch gradient descent method to achieve training parameters and then obtain a suitable deep learning model. Finally, carry out verification of building samples based on model training and accuracy evaluation. Experiments showed that, compared with the traditional U-Net deep learning building sample verification, the proposed method has the advantages of less sample demand, low cost, high accuracy and stable effect.

Existing deep learning-based change detection methods try to elaborately design complicated neural networks with powerful feature representations, but ignore the universal domain shift induced by time-varying land cover changes, including luminance fluctuations and season changes between pre-event and post-event images, thereby producing sub-optimal results. In this paper, we propose an end-to-end Supervised Domain Adaptation framework for cross-domain Change Detection, namely SDACD, to effectively alleviate the domain shift between bi-temporal images for better change predictions. Specifically, our SDACD presents collaborative adaptations from both image and feature perspectives with supervised learning. Image adaptation exploits generative adversarial learning with cycle-consistency constraints to perform cross-domain style transformation, effectively narrowing the domain gap in a two-side generation fashion. As to feature adaptation, we extract domain-invariant features to align different feature distributions in the feature space, which could further reduce the domain gap of cross-domain images. To further improve the performance, we combine three types of bi-temporal images for the final change prediction, including the initial input bi-temporal images and two generated bi-temporal images from the pre-event and post-event domains. Extensive experiments and analyses on two benchmarks demonstrate the effectiveness and universality of our proposed framework. Notably, our framework pushes several representative baseline models up to new State-Of-The-Art records, achieving 97.34% and 92.36% on the CDD and WHU building datasets, respectively. The source code and models are publicly available at https://github.com/Perfect-You/SDACD.

一、前言 地表水是人类赖以生存和社会发展中不可替代的战略资源,全面掌握其空间分布特征,定期跟踪其动态变化情况,对于提升水资源管理与保护水平,促进水资源合理开发利用,深化水循环和水平衡研究具有重要意义. 卫星遥感具有客观、宏观、快速、及时等特点,在地表水调查与监测方面具有重要优势,国外在利用卫星遥感开展水资源调查与监测方面开展了大量的研究和应用工作,特别是利用美国陆地卫星(Landsat),欧洲哨兵卫星(Sentinel),美国冰、云和陆地高程卫星(ICESat-1)数据在全球或区域尺度上的湖泊、河流、水库、湿地等水资源调查监测方面发布了很多成果,如Global Surface Water、THU Surface Water、THU FROM-GLC10、Global Lakes and Wetlands Database(GLWD)等[1-3].国内利用卫星遥感在水资源调查监测方面开展了很多研究及部分专题性或区域性应用工作,但之前受限于国产卫星数量和能力限制,全国性、大区域的卫星遥感地表水资源调查及监测业务化应用还不多.

Remote sensing derived water area and volume have been widely used in large lakes monitoring. The seed point method was used to monitor the water area and volume of Poyang Lake, as an important international wetland and the largest fresh water lake in China, from 2019 to the flood season in 2020 using ZY3, GF-1, GF-3, GF-6, and BJ-2 data. Furthermore, historical water area and water volume changes of Poyang Lake were analyzed utilizing public data set. The results showed that the water area and water volume of Poyang Lake changed significantly in recent sixty years. It also fluctuated violently during the high water and low water seasons from 2019 to 2020. In the past sixty years, the minimum and maximum water area was 1190.73 km 2 in 1960 and 31 79.31 km 2 in 2019, respectively, and the water volume increased by 1853.62 million cubic meters. The water area difference of Poyang Lake between the high water season and the low water season was more than quadruple, which varied from 3179.21 km 2 in the third quarter in 2019 to 674.01 km 2 in the first quarter in 2020, and the water volume decreased by 489.95 million cubic meters. The flood in 2020 inundated 7834.15 hectares of planting land, 2300.81 hectares of forest and grass coverage, 906.51 hectares of desert and bare land, 2170.87 hectares of water area, 101.78 hectares of housing construction area, and 73.15 hectares of railway and highway. The relevant results provide a scientific basis for the construction of Poyang Lake ecological economic zone and the ecological protection of Poyang Lake wetland and a decision-making reference for flood control and disaster relief in Poyang Lake area.

Danjiangkou Reservoir is the water source of the Middle Route Project of South-To-North Water Diversion. Monitoring cage culture conditions is of great significance to guarantee the quality of the delivered water. The high-resolution remote sensing images from ZY3 and GF-2 satellites from 2013 to 2017 were used to extract cage culture information and analyze its dynamic characteristics. Moreover, suggestions for monitoring cage culture in Danjiangkou Reservoir were proposed. Our research showed that: (1) In general, the total area of cage culture in the reservoir area decreased year by year. The total area reduced to about a quarter in 2017 compared with that in 2013. (2) Taking 2014 as the key time node, the cage culture area increased slightly before 2014 and continued to decrease after 2014. It was related to the enhancement of water quality management because of the water supply of the South-to-North Water Diversion Project at the end of 2014. (3) It was recommended to monitor the water source protection area once a year. Cage culture should be monitored at least twice a year in the key protection area.

Mangrove forests are important ecosystems in the coastal intertidal zone, but China’s mangroves have experienced a large reduction in area from the 1950s, and the remaining mangrove forests are exhibiting increased fragmentation. A detailed mangrove dataset of China is crucial for mangrove ecosystem management and protection, but the fragmented mangrove patches are hardly mapped by medium resolution satellite imagery. To overcome these difficulties, we presented a fine-scale mangrove map for 2018 using the 2-meter resolution Gaofen-1 and Ziyuan-3 satellite imagery together with field data. We employed a hybrid method of object-based image analysis (OBIA), interpreter editing, and field surveying for mangrove mapping. The field survey route reached 9500 km, and 2650 patches were verified during the field work. Accuracy assessment by confusion matrix showed that the kappa coefficient reached 0.98, indicating a highly thematic accuracy of the mangrove dataset. Results showed the total area of mangrove forest in China for 2018 was 25,683.88 hectares, and approximately 91% of mangroves were found in the three provinces of Guangdong, Guangxi, and Hainan. About 64% of mangroves were distributed in or near the nature reserves established by national or local governments, which indicated that China’s mangroves were well protected in recent years. The new fine-scale mangrove dataset was freely shared together with this paper, and it can be used by local authorities and research groups for mangrove management and ecological planning.

构建及时、有效的卫星遥感应急监测信息服务框架,是开展自然灾害应急救援能力建设的重要内容。本文以数据统筹管理、多源数据处理、应灾信息分析及信息服务快速发布等关键技术为核心,依托高效互联机制和高速数据通道,构建了卫星遥感应急监测信息服务框架。通过在四川木里森林火灾应急遥感监测中的具体应用,实现了对灾前灾后数据的实时推送,以及灾区遥感解译图、三维地形、救援通达性及火灾变化等综合信息服务的及时发布,为四川省火灾一线救援工作提供了科学指导,为新时期国家应急能力建设提供了探索性技术途径。

The environmental health and green development of the water source area of Mid-Route of the South-North Water Diversion Project (SNWDP) is not only essential for ensuring that "The clear water is sent to Beijing", but also an important prerequisite for sustainable development of society and economy in the water source area. Based on national geographic survey data, basic surveying and mapping data and statistical yearbook data, this paper used the model of relative carrying capacity of resources to estimate and analyze the carrying capacity of relative natural resources (CCRNR), carrying capacity of relative economic resources (CCRER) and carrying capacity of relative resources (CCRR) and their spatial-temporal changes in the Danjiangkou Reservoir area of the water source area of the Mid-Route of SNWDP from 2009 to 2015 by Geographic Information System (GIS) technologies. The results were shown that: (1) CCRR increased significantly compared with that in 2009. However, CCRR in the study area was still overloaded in 2015. (2) CCRNR was rich, but decreased from 2009 to 2015. (3) CCRER was in a overloading state, which increased obviously from 2009 to 2015. The improvement of CCRER was the main reason for the sustainable growth of carrying capacity in the study area. Therefore, the countermeasures including making rational use of natural resources, developing economic resources and controlling population quantity were proposed to promote the sustainable development of society, economy and ecology in the study area.

Mangroves provide a variety of irreplaceable functions such as coastline protection, bay improvement, water purification and wetland diversity protection. However, mangroves are fragile ecosystems and are affected by human activities and climate change. Long-term monitoring on mangroves is of great significance. This paper selected Tongming Bay located in southern China coast as a study case because of its high variation of mangrove extent. Satellite remote sensing images from 1978 to 2018 were used for mangrove extent interpretation, and to obtain the distribution, changes, and main driving factors of changes in the Tongming Bay area in the past 40 years. The results showed that the area of mangrove extent in Tongming Bay continued to shrink from 1978 to 2013, and the area gradually increased after 2013. The main driving factor for the reduction of mangroves was the artificial aquaculture occupation of mangrove habitats, and mangrove area growth was mainly caused by artificial planting. The results of this study can provide references for local government on mangrove management and ecological restoration.