Object-based Classification Method Research Articles

Multi-Source Remote Sensing Data for Wetland Information Extraction: A Case Study of the Nanweng River National Wetland Reserve

Wetlands play a vital role in regulating the global carbon cycle, providing biodiversity, and reducing flood risks. These functions maintain ecological balance and ensure human well-being. Timely, accurate monitoring of wetlands is essential, not only for conservation efforts, but also for achieving Sustainable Development Goals (SDGs). In this study, we combined Sentinel-1/2 images, terrain data, and field observation data collected in 2020 to better understand wetland distribution. A total of 22 feature variables were extracted from multi-source data, including spectral bands, spectral indices (especially red edge indices), terrain features, and radar features. To avoid high correlations between variables and reduce data redundancy, we selected a subset of features based on recursive feature elimination (RFE) and Pearson correlation analysis methods. We adopted the random forest (RF) method to construct six wetland delineation schemes and incorporated multiple types of characteristic variables. These variables were based on remote sensing image pixels and objects. Combining red-edge features, terrain data, and radar data significantly improved the accuracy of land cover information extracted in low-mountain and hilly areas. Moreover, the accuracy of object-oriented schemes surpassed that of pixel-level methods when applied to wetland classification. Among the three pixel-based schemes, the addition of terrain and radar data increased the overall classification accuracy by 7.26%. In the object-based schemes, the inclusion of radar and terrain data improved classification accuracy by 4.34%. The object-based classification method achieved the best results for swamps, water bodies, and built-up land, with relative accuracies of 96.00%, 90.91%, and 96.67%, respectively. Even higher accuracies were observed in the pixel-based schemes for marshes, forests, and bare land, with relative accuracies of 98.67%, 97.53%, and 80.00%, respectively. This study’s methodology can provide valuable reference information for wetland data extraction research and can be applied to a wide range of future research studies.

Rockfall mapping and susceptibility evaluation based on UAV high-resolution imagery and support vector machine method

Abstract This study aims to develop a comprehensive method for automated rockfall mapping and susceptibility assessment using unmanned aerial vehicle (UAV) tilt photography and the support vector machine (SVM) algorithm. By employing Jinzhong Town in the mountainous forest landscapes of Southwest China as a case study, we leverage photogrammetry principles and computer vision algorithms to generate high-precision, high-resolution digital surface models (DSMs), and digital orthophoto maps through a UAV remote sensing system. The rockfall inventory is accurately and automatically mapped using the object-based classification method and SVM algorithm. The automated rockfall identification method achieves a 93% accuracy with a Kappa coefficient of 0.7967. Statistical analyses of spatial distribution characteristics reveal a significant correlation between rockfall volume and area with a correlation coefficient (R²) of 0.92316 under logarithmic coordinates. In addition, a power function relationship describes the link between rockfall volume and slope height (R² = 0.87), while the relationship with sliding distance is characterized by a weaker linear correlation (R² = 0.65). Rockfall runout distance also shows a significant linear correlation with slope height (R² = 0.79) but exhibits a less-pronounced association with rockfall volume (R² = 0.58). The SVM model employed to assess rockfall susceptibility indicates high accuracy (area under the curve = 0.896), affirming its efficacy in rockfall susceptibility assessment. Our findings underscore the utility of UAV remote sensing for rockfall information extraction and susceptibility evaluation, particularly in challenging mountainous forest environments characterized by intricate topography and geological complexities.

An automated sample generation method by integrating phenology domain optical-SAR features in rice cropping pattern mapping

Accurate spatio-temporal information on rice cropping patterns is vital for predicting grain production, managing water resource and assessing greenhouse gas emissions. However, current automated mapping of rice cropping patterns at regional scale is heavily constrained by insufficient training samples and frequent cloudy weathers in major rice-producing areas. To tackle this challenge, we proposed a Phenology domain Optical-SAR feature inTegration method to Automatically generate single (SC-Rice) and double cropping Rice (DC-Rice) sample (POSTAR) for efficient and refined rice mapping. POSTAR includes three major steps: (1) generating a potential rice map using a phenology- and object-based classification method with optical data (Sentinel-2 MSI) to select candidate rice samples; (2) employing K-means to identify SC- and DC-Rice candidate samples according to unique SAR-based (Sentinel-1 SAR) phenological features; (3) implementing a two-step refinement strategy to filter high-confidence SC- and DC-Rice samples, maintaining a balance between intraclass phenological variance and sample purity. Test areas selected for validation include the Dongting Lake plain and Poyang Lake plain in South China, as well as Fujin county located in the Sanjiang plain of North China. POSTAR proved effective in producing reliable SC- and DC-Rice samples, achieving a high spectral correlation similarity (>0.85) and low dynamic time wrapping distance (<8.5) with field samples. Applying POSTAR-derived samples to random forest classifier yielded an overall accuracy of 89.6%, with F1 score of 0.899 for SC-Rice and 0.938 for DC-Rice in the Dongting Lake plain. Owing to the incorporation of knowledge-based optical and SAR phenological features, POSTAR exhibited strong spatial transferability, achieving an overall accuracy of 96.0% in the Poyang Lake plain and 97.8% in the Fujin county. These results demonstrated the effectiveness of the POSTAR method in accurately mapping rice cropping patterns without extensive field visits, providing valuable insights for crop monitoring in large, diverse, and cloudy regions through the integration of optical and SAR data.

Vectorized dataset of silted land formed by check dams on the Chinese Loess Plateau

Check dams on the Chinese Loess Plateau (CLP) have captured billions of tons of eroded sediment, substantially reducing sediment load in the Yellow River. However, uncertainties persist regarding the precise sediment capture and the role of these dams in Yellow River flow and sediment dynamics due to the lack of available spatial distribution datasets. We produced the first vectorized dataset of silted land formed by check dams on the CLP, combining high-resolution and easily accessible Google Earth images with object-based classification methods. The accuracy of the dataset was verified by 1947 collected test samples, and the producer’s accuracy and user’s accuracy of the dam lands were 88.9% and 99.5%, respectively. Our dataset not only provides fundamental information for accurately assessing the ecosystem service functions of check dams, but also helps to interpret current changes in sediment delivery of the Yellow River and plan future soil and water conservation projects.

Object Based Classification in Google Earth Engine Combining SNIC and Machine Learning Methods (Case Study: Lake Köyceğiz)

Köyceğiz Lake is one of our country’s most critical coastal barrier lakes, rich in sulfur, located at the western end of the Mediterranean Region. Köyceğiz Lake, connected to the Mediterranean via the Dalyan Strait, is one of the 7 lakes in the world with this feature. In this study, water change analysis of Köyceğiz Lake was carried out by integrating the Object-Based Image Classification method with CART (Classification and Regression Tree), RF (Random Forest), and SVM (Support Vector Machine) algorithms, which are machine learning algorithms. SNIC (Simple Non-iterative Clustering) segmentation method was used, which allows a detailed analysis at the object level by dividing the image into super pixels. Sentinel 2 Harmonized images of the study area were obtained from the Google Earth Engine (GEE) platform for 2019, 2020, 2021, and 2022,and all calculations were made in GEE. When the classification accuracies of four years were examined, it was seen that the classification accuracies(OA, UA, PA, and Kappa) of the lake water area were above 92%, F-score was above 0.98 for all methods using the object-based classification method obtained by the combination of the SNIC algorithm and CART, RF, and SVM machine learning algorithms. It has been determined that the SVM algorithm has higher evaluation metrics in determining the lake water area than the CART and RF methods.

Sentinel-2 image based smallholder crops classification and accuracy assessment by UAV data

Timely and accurate extraction of crop planting units plays a critical role in crop yield estimation, soil management, food supplies, and disaster warnings. However, precisely mapping crop types is challenging in smallholder farming systems due to heterogeneous and mixed pixels, where field sizes are small, and crop types are very diverse. In this paper, the crop type system of Huocheng County in northwest China as an example area, crop classification feature variables are constructed using Sentinel-2 remote sensing images, and combining the ReliefF algorithm, three feature selection classification models are established by 3092 crop type sampling points data. The crop planting units are extracted using pixel-based and object-based classification methods, respectively, and unmanned aerial vehicle (UAV) data assess the accuracy as ground truth. The Sentinel-2 image based smallholder crops classification results indicate that: The effective combination of optimal input feature variables selection and classification models significantly improves crop classification accuracy. This is particularly evident when integrating this approach into pixel-based classification, addressing challenges such as low pixel classification accuracy in regions of this type. The validation results from UAV data also confirm these findings. At validation points 2, 3, and 4, pixel-based classification demonstrates significantly higher accuracy compared to object-based classification, with pixel-based classification accuracy improving by 9.16%, 7.83%, and 31.83%, respectively. Although the UAV validation accuracy does not reach a high level, pixel-based classification remains the optimal choice for smallholder crop classification. This method offers new insights and references for research related to the classification of smallholder crops with complex planting structures.

Spatial Change Analysis Using Object Based Classification Method for Sustainable Lake Basin Management in Adaptation to Climate Change in Marmara Lake

Akdeniz Havzası’nda yer alan Türkiye coğrafi konumu itibariyle iklim değişikliğinden en fazla etkilenen ülkelerden birisidir. İklim değişikliği başta su kaynakları olmak üzere birçok doğal ve beşerî sistemi olumsuz yönde etkilemektedir. Bunlar içerisinde sulak alanlar sahip oldukları zengin biyolojik çeşitlilik nedeni ile dünyanın en önemli ekosistemlerinden biridir. Son yıllarda gerek kuraklık gerekse sulak alanların bilinçsiz kullanımı ve yönetimi sulak alanların yok olma sürecini hızlandırmaktadır. Bu çalışmada iklim değişikliğinin Türkiye’nin önemli sulak alanlarıdan birisi olan Marmara Gölü’nde mekânsal değişime etkisi 2013-2023 yılları arasında uzaktan algılama veri ve metotları kullanılarak ve arazi çalışmalarından elde edilen bulgularla analiz edilecektir. Çalışmada veri olarak Landsat 8 OLI ve Sentinel 2 uydu görüntüleri; metot olarak ise Arc GIS Pro yazılımında Nesne Tabanlı Sınıflandırma Yöntemi uygulanacaktır. Çalışmanın sürdürülebilir kalkınma ilkeleri doğrultusunda “İklim Eylemi”, “Sudaki Yaşam” ve “Sürdürülebilir Şehirler ve Topluluklar” hedeflerine uygun sürdürülebilir göl havzası yönetimine güncel ve farklı bir bakış açısı sunarak literatüre katkı sağlaması amaçlanmaktadır.

Perturbed peer model with joint confidence for semi-supervised object-based classification in urban area

ABSTRACT The application of deep learning (DL) improves the accuracy of object-based classification in urban area, but the huge numbers of labelled samples required for training DL models are difficult to obtain. To address that, we propose a novel semi-supervised object-based classification method that combines pseudo-labelling method and consistency regularization method, named as perturbed peer model (PPM). To evaluate the quality of unlabelled object samples, a new object-level joint confidence is designed to assess the confidence of the samples’ prediction, which provides guidance for selecting unlabelled object samples in semi-supervised object-based classification. Instead of only using the high-confidence samples as usual, both the high-confidence samples with discriminative power and the low-confidence samples with a large range of structural features are exploited using pseudo-labelling method and consistency regularization method, respectively, facilitating the fusion of the two methods in the proposed PPM. In addition, two types of perturbations, dropout and difference augmentation, are integrated into the model to drive the consistency regularization method as well as to enhance the difference to facilitate the pseudo-labelling method. Experimental results show that the classification accuracy of PPM is better than the widely-used self-training, co-training, noisy-student, unsupervised data augmentation for consistency training, and FreeMatch methods in urban area.

Aboveground biomass estimation of wetland vegetation at the species level using unoccupied aerial vehicle RGB imagery.

Wetland vegetation biomass is an essential indicator of wetland health, and its estimation has become an active area of research. Zizania latifolia (Z. latifolia) is the dominant species of emergent vegetation in Honghu Wetland, and monitoring its aboveground biomass (AGB) can provide a scientific basis for the protection and restoration of this and other wetlands along the Yangtze River. This study aimed to develop a method for the AGB estimation of Z. latifolia in Honghu Wetland using high-resolution RGB imagery acquired from an unoccupied aerial vehicle (UAV). The spatial distribution of Z. latifolia was first extracted through an object-based classification method using the field survey data and UAV RGB imagery. Linear, quadratic, exponential and back propagation neural network (BPNN) models were constructed based on 17 vegetation indices calculated from RGB images to invert the AGB. The results showed that: (1) The visible vegetation indices were significantly correlated with the AGB of Z. latifolia. The absolute value of the correlation coefficient between the AGB and CIVE was 0.87, followed by ExG (0.866) and COM2 (0.837). (2) Among the linear, quadratic, and exponential models, the quadric model based on CIVE had the highest inversion accuracy, with a validation R2 of 0.37, RMSE and MAE of 853.76 g/m2 and 671.28 g/m2, respectively. (3) The BPNN model constructed with eight factors correlated with the AGB had the best inversion effect, with a validation R2 of 0.68, RMSE and MAE of 732.88 g/m2 and 583.18 g/m2, respectively. ​Compared to the quadratic model constructed by CIVE, the BPNN model achieved better results, with a reduction of 120.88 g/m2 in RMSE and 88.10 g/m2 in MAE. This study indicates that using UAV-based RGB images and the BPNN model provides an effective and accurate technique for the AGB estimation of dominant wetland species, making it possible to efficiently and dynamically monitor wetland vegetation cost-effectively.

Integrated Method for Classifying Medium Resolution Satellite Remotely Sensed Imagery into Land Use Map

There are several remotely sensed images of varied resolutions available. As a result, several classification techniques exist, which are roughly classified as pixel-based and object-based classification methods. Based on the foregoing, this study provided an integrated method of deriving land use from a coarse satellite image. Location coordinates of the land uses were acquired with a handheld Global Positioning System (GPS) instrument as primary data. The study classified the image quantitatively (pixel-based) into built-up, water, riparian, cultivated, and uncultivated land cover classes with no mixed pixels, and then qualitatively into educational, commercial, health, residential, and security land use classes that were conflicting due to spectral similarity. The total accuracy and kappa coefficient of the pixel-based land cover classification were 92.5% and 94% respectively. The results showed that residential land use occupied an area of 5500.01ha, followed by educational (2800.69ha); security (411.27ha); health (133.88ha); and commercial (109.01ha) respectively. The integrated method produces a crisp-appearance like the object-based image classification method. It eliminates the "salt and pepper" appearance that a traditional pixel-based classification would have. The output can be a vector or raster model depending on the purpose for which it is created.

Land Cover Classification Assessment Using Decision Trees and Maximum Likelihood Classification Algorithms on Landsat 8 Data

&lt;p&gt;&lt;em&gt;Classification technique on remote sensing images is an effort taken to identify the class of each pixel based on the spectral characteristics of various channels. Traditional classifications such as Maximum Likelihood are based on statistical parameters such as standard deviation and mean, which have a probability model of each pixel in each class. While the object-based classification method, one of which is the Decision Trees, is based on rules for each class with mathematical functions. This study compares the Decision Trees and Maximum Likelihood algorithms for land cover classification in the Surabaya and Bangkalan areas using Landsat 8 data. This research begins with creating Regions of Interest (ROIs) and Rules on images with greater than and less than functions for Decision Trees. The ROIs test was carried out using the Separability Index and matching each class using the Confusion Matrix. The experimental results show that the accuracy value resulting from the Confusion Matrix calculation is 90.48%, with a Kappa Coefficient Value of 0.87. The Decision Trees method produces land cover nigher to the actual condition than the Maximum Likelihood method. The difference in the class distribution of the two ways is not significant. This study is limited because the validation uses manual interpretation results. Future research is expected to use the large-scale classification results from the relevant agencies to verify the classification results and use field data, larger samples of ROIs, and the use of high-resolution imagery in order to improve the classification results.&lt;/em&gt;&lt;/p&gt;

Vectorized dataset of check dams on the Chinese Loess Plateau using object-based classification method from Google Earth images

Vectorized dataset of check dams on the Chinese Loess Plateau using object-based classification method from Google Earth images

Vectorized dataset of check dams on the Chinese Loess Plateau using object-based classification method from Google Earth images

Vectorized dataset of check dams on the Chinese Loess Plateau using object-based classification method from Google Earth images

Https://journals.scholarpublishing.org/index.php/AIVP/article/view/13922

Land use system is the interface between society and the biophysical environment; it is concern how humans use ecosystems services provide by natural resources.&nbsp; Land-use and land-cover changes have great effects for the environmental and socioeconomic sustainability of rural communities. A capacity for detecting and reporting land use change is critical to evaluating and monitoring trends in natural resource conditions and the effectiveness of public investment in their management. In Mexico, despite ongoing mapping land use - land cover efforts; there remains a need for development of basic datasets providing quantitative and spatial land use/land cover information, mainly a detailed scale. Recent availability of high-resolution satellite remote-sensing images coupling with advances digital image processing techniques offers an improved opportunity to map in a more detailed scale the land use&nbsp; and land cover, which will be an important tool to monitor the environment at local scales. It is the objective of this study, conduct a detailed mapping of land use-land cover in&nbsp; Usumacinta watershed, using high-resolution satellite images and analyze&nbsp; changes occurred when&nbsp; is compared with&nbsp; National Institute of Statistic and geography map - Series VII,2016. The basis for the land use and vegetation cover presented in this study is the digital land cover and land use classification elaborated with SPOT imagery, spatial resolution 1.5 meters, using &nbsp;an object-based classification method&nbsp; in combination with an image classification based on expert knowledge. The resulting map was &nbsp;updated using Sentinel images&nbsp; 2021 and 2022 , by means of on screen digital interpretation. The result is a detail map of land use land cover, where new classes were generated as association and consociation units. As a conclusion is established that the resulting map is more stable in time, and it can be used as indicative to implement restoration measures on natural vegetation and as input to calculate a more precise estimations of agriculture statistic’s. All of this aspects can guide the design and implementation of public policies about land use.

Pemetaan Perubahan Penggunaan Lahan Wilayah Pesisir di Kecamatan Bulak, Surabaya Tahun 2014 dan 2020

The coastal area is an intersection between mainland and ocean. The tourism potential in the coastal area of Bulak District in Surabaya is expanded. It is shown by the construction of Surabaya Bridge in 2015. This construction will affect land use change. Remote sensing technology is one of the acquisitions to monitor land use change. This research focuses on identifying the land use change in the coastal area in Bulak District, Surabaya, in 2014 and 2020, as well as to determine the accuracy of classification method applied for mapping the land use change in 2020. The application of 2014 acquisitions data was used as the bridge construction plan, while the application of 2020 acquisitions data was used as the premise for the land classification system in the previous year. There are two methods used to classify land use in coastal areas, that is pixel-based classification (maximum likelihood algorithm) and object-based classification (nearest neighbor algorithm). The research shows that there are 6 land use classes in study area: built-up land, rice fields, forests, shrubs, non-built-up land, and ocean. By applying these two methods, the result shows different area changes. The conversion of the highest mainland by applying a pixel-based classification was found in built-up land (+23.03 ha) and rice fields (-24.84 ha), while the area changes by applying object-based classification method were found in built-up land (+32.75 ha) and rice fields (-26.91 ha), respectively. The accuracy by applying the pixel and object-based method is 89% and 92%, respectively, from the percentage indicates good interpretation.

Comparing Machine Learning Algorithms for Pixel/Object-Based Classifications of Semi-Arid Grassland in Northern China Using Multisource Medium Resolution Imageries

Knowledge of grassland classification in a timely and accurate manner is essential for grassland resource management and utilization. Although remote sensing imagery analysis technology is widely applied for land cover classification, few studies have systematically compared the performance of commonly used methods on semi-arid native grasslands in northern China. This renders the grassland classification work in this region devoid of applicable technical references. In this study, the central Xilingol (China) was selected as the study area, and the performances of four widely used machine learning algorithms for mapping semi-arid grassland under pixel-based and object-based classification methods were compared: random forest (RF), support vector machine (SVM), k-nearest neighbor (KNN), and naive Bayes (NB). The features were composed of the Landsat OLI multispectral data, spectral indices, Sentinel SAR C bands, topographic, position (coordinates), geometric, and grey-level co-occurrence matrix (GLCM) texture variables. The findings demonstrated that (1) the object-based methods depicted a more realistic land cover distribution and had greater accuracy than the pixel-based methods; (2) in the pixel-based classification, RF performed the best, with OA and Kappa values of 96.32% and 0.95, respectively. In object-based classification, RF and SVM presented no statistically different predictions, with OA and Kappa exceeding 97.5% and 0.97, respectively, and both performed significantly better than other algorithms. (3) In pixel-based classification, multispectral bands, spectral indices, and geographic features significantly distinguished grassland, whereas, in object-based classification, multispectral bands, spectral indices, elevation, and position features were more prominent. Despite the fact that Sentinel 1 SAR variables were chosen as an effective variable in object-based classification, they made no significant contribution to the grassland distinction.

Spatial and Temporal Dynamics of Wetlands in Guangdong-Hong Kong-Macao Greater Bay Area from 1976 to 2019

Wetland ecosystems contain rich natural resources and vital ecological functions, and the investigation of spatial and temporal evolution characteristics of wetlands and their driving factors is critical for the management and conservation of wetlands. This study aimed to explore the spatial and temporal dynamics of wetlands in the Guangdong–Hong Kong–Macao Greater Bay Area (GBA) from 1976 to 2019 using multi-source remote sensing data (DISP KH-9, Landsat, and GaoFen-1), combing with the object-based classification method and landscape invasion index, and further analyze the driving forces affecting the spatial and temporal evolution of wetlands. The results showed that: (1) The total area of wetlands in the GBA showed a trend to first increase and then stabilize from 1976 to 2019. (2) The rapid development of aquaculture led to a continuous increase in aquaculture ponds and offshore aquaculture and a flat change in the middle and late stages, the area of mangroves declined substantially before 2000 and has gradually recovered since then, the invasion of various types of wetlands by built-up land is increasing, and wetlands are becoming increasingly fragmented. (3) The wetland changes in the GBA are the result of a combination of natural factors and human activities. Environmental conditions represent the basis for wetland dynamics, while the population, socio-economics, and policies are important drivers of wetland evolution. The findings will be beneficial to the understanding of wetland dynamic changes in the GBA over the past 40 years, and helpful to the scientific management and sustainable development of wetlands.

Using high-resolution imagery from 2013 and 2020 to establish baseline vegetation in oil-damaged mangrove habitat prior to large-scale post-remediation planting in Bodo, Eastern Niger Delta, Nigeria

The study area encompasses the largest remedial effort ever undertaken in oil-contaminated mangrove habitats (∼1000 ha) and includes planting of ∼2 million mangrove seedlings to initiate the restoration process. To establish a reference point for both the initial planting and long-term monitoring, and to investigate the longer-term effects of numerous oil spills, mangrove distribution (with minor quantities of nipa palm) was determined using 0.1 and 0.5 m resolution imagery from 2013 and from 2020, supported by numerous ground surveys and low-altitude overflights. A review of pre-spill mangrove location and elimination of pipeline and road corridors determined that 829 ha of former mangrove habitat was suitable for restorative planting.After testing each method, existing vegetation was classified using a supervised object-based classification method (Support Vector Machine) and mean shift segmentation, trained with ten manually classified plots of 1 ha and validated against seven additional plots. Initial classification errors occurred due to false positives caused by surface algae, which were manually removed. The accuracy assessment to determine overall mangrove cover (ha) and ability to encounter mangroves at a specific location within randomly selected 0.785 m2 circles increased to ≥95% within validation plots. In contrast to losses found in other areas of the Niger Delta, vegetation increased in the core area of study (15.6 ha–40.2 ha) but represented only 4.8% of the total 829 ha to be planted. To the west, a 10% vegetation gain was found; to the east where oil theft activities were common, there was a 16% loss. A comparison to a West Africa 20-m data set shows comparative values within 5%, with notable differences when reviewed in detail. Monitoring of the area as it is replanted is expected to continue to 2027 and will use these results as a comparison. This study serves as guidance for analysis and monitoring of future mangrove restorations in the Niger Delta.

WHO SPEAKS FOR THE FOREST? LOCAL KNOWLEDGE, PARTICIPATORY MAPPING AND COLLABORATIVE EVALUATION FOR GIS ANALYSIS IN THE TROPICS OF CENTRAL BALI, INDONESIA

Abstract. This paper describes a land survey of the Bedugul area in Central Bali that was constructed using multi-temporal and multi-spectral data collected from a new class of commercially available satellites to produce detailed land cover mappings. The paper discusses the significance of the land area under investigation, including difficulties in reading land cover features in the tropics. It describes participatory field mapping efforts set in place in order to complement the reading of remote sensing assets and our attempts to represent land use features of particular interest to a local NGO. We further discuss the challenges and opportunities of representing land cover and use scenarios that satellite assets can only partially capture. We use band operations and object-based classification methods to represent change in settlement activity in the area under observation. We also describe a collaborative cloud-based analysis and evaluation pipeline that facilitates the processing of different sources of remote sensing data as well as the representation of various types of land use scenarios defined with the assistance of local knowledge.

Alpine Wetland Evolution and Their Response to Climate Change in the Yellow-River-Source National Park from 2000 to 2020

Clarifying the response of wetland changes to climate change can improve the scientific conservation and utilization capabilities of wetland ecosystems, which is vital for their sustainable development. In this study, the spatial distribution and area changes of the different types of wetlands in the Yellow-River-Source National Park (YRSNP) were obtained using the object-based classification method for the years 2000, 2010, and 2020. The relationship between wetland change and climate factors was investigated by combining grey relation analysis and correlation analysis. The response of wetland change to different climatic factors was consequently clarified. The results showed that the river wetlands and lake wetlands increased significantly from the year 2000 to 2010 (4.04% and 4.21%, respectively). However, the total wetland area demonstrated a decreasing trend (7.08%), primarily due to the significant decrease in the marsh wetlands (6.81%). The total wetland area demonstrated a slightly increasing trend from the year 2010 to 2020 (0.14%), in which river wetlands and lake wetlands increased by 3.25% and 2.09%, respectively, while the marsh wetlands demonstrated a tendency to be stable. From the year 2000 to 2010, 75.53% of precipitation and 27.68% of temperature demonstrated a significant increase and an obvious warm–humid climate trend. However, from the year 2010 to 2020, the trend of increasing precipitation weakened, the temperature decreased slightly, and the warm–humid climate trend was not significant. From the year 2000 to 2020, the YRSNP river wetlands and lake wetlands were significantly and positively correlated with temperature and precipitation, while the marsh wetlands were most affected by climate warming, especially the warm-season temperatures. The spatial–temporal difference was not obvious in the correlation coefficient between marsh wetlands area change and the precipitation and temperature. The results of the study can provide a theoretical basis and technical support for the conservation of wetland ecosystems in the Three-River-Source National Park.