Learning with transductive SVM for semisupervised pixel classification of remote sensing imagery

Aiming at the detection problem of Multiple blockage in urban water supply pipelines and drainage pipelines, also the problem of distinguishing commonly used pipe components such as lateral connection from the actual blocking conditions. A multiple-blocking fault identification method based on support vector machine (SVM) combined with a feature extraction approach for component signal are proposed in this paper. Firstly, the variational mode decomposition (VMD) was applied on the acoustic signals collected in the pipeline to obtain a set of finite bandwidth natural mode functions (IMF), multiple time domain indices and center frequencies were extracted as features, then a feature vector set can be constructed and input into the SVM classifier. The experimental results have shown that the method based on VMD feature fusion and support vector machine can effectively identify the multiple congestion faults of drainage pipelines. In addition, the method was compared with back propagation (BP)neural network and the k-nearest neighbor algorithm (KNN). The results suggest that the proposed method has a better performance on the partial blockage recognition with a small number of training samples.

This paper proposes an automatic framework for land cover classification. In majority of published work by various researchers so far, most of the methods need manually mark the label of land cover types. In the proposed framework, all the information, like land cover types and their features, is defined as prior knowledge achieved from land use maps, topographic data, texture data, vegetation’s growth cycle and field data. The land cover classification is treated as an automatically supervised learning procedure, which can be divided into automatic sample selection and fuzzy supervised classification. Once a series of features were extracted from multi-source datasets, spectral matching method is used to determine the degrees of membership of auto-selected pixels, which indicates the probability of the pixel to be distinguished as a specific land cover type. In order to make full use of this probability, a fuzzy support vector machine (SVM) classification method is used to handle samples with membership degrees. This method is applied to Landsat Thematic Mapper (TM) data of two areas located in Northern China. The automatic classification results are compared with visual interpretation. Experimental results show that the proposed method classifies the remote sensing data with a competitive and stable accuracy, and demonstrate that an objective land cover classification result is achievable by combining several advanced machine learning methods.

Land Use and Land Cover (LULC) classification plays a pivotal role in understanding and managing environmental resources. This study presents a novel methodology utilizing sentinel satellite data in conjunction with two robust machine learning algorithms: Random Forest (RF) and Support Vector machine (SVM) on Google Earth Engine platform. Sentinel data, renowned for its high- resolution multispectral imagery, provides rich information for classification. Google Earth Engine provides access to vast geospatial datasets and computational resource, enabling effective analysis. RF and SVM, distinguished for their ability to handle complex dataset, are employed to optimize classification accuracy. A systematic work flow for preprocessing of Sentinel imagery is outlined, followed by implementation of RF and SVM algorithm with a focus on accurately classifying vegetation, built-up areas, barren land and water bodies. Evaluation metrics including overall accuracy and kappa coefficient demonstrate the efficacy of the proposed methodology. A compelling study demonstrates the utility of RF and SVM within GEE for precise LULC mapping, highlighting their pivotal role in supporting informed decision-making for environmental planning and conservation initiatives. Keywords GEE, SVM, RF, Sentinel Data, LULC

Researchers constantly seek more efficient detection techniques to better utilize enhanced image resolution in accurately detecting and monitoring land cover. Recently, convolutional neural networks (CNNs) have shown high performances comparable to or even better than widely used and adopted machine learning techniques. The aim of this study is to investigate the application of CNNs for land cover classification by using two-dimensional (2-D) spectral curve graphs from multispectral satellite images. The land cover classification was conducted in Concord, New Hampshire, USA, and South Korea by using multispectral images acquired from 30-m Landsat-8 and 500-m Geostationary Ocean Color Imager images. For the construction of input data specific to CNNs, two seasons (winter and summer) of multispectral bands were transformed into 2-D spectral curve graphs for each class. Land cover classification results of CNNs were compared with the results of support vector machines (SVMs) and random forest (RFs). The CNNs model showed higher performance than RFs and SVMs in both study sites. The examination of land cover classification maps demonstrates a good agreement with reference maps, Google Earth images, and existing global scale land cover map, especially for croplands. Using the spectral curve graph could incorporate the phenological cycles on classifying the land cover types. This study shows that the use of a new transformation of spectral bands into a 2-D form for application in CNNs can improve land cover classification performance.

Accurate Land Use and Land Cover (LU/LC) classification is essential for sustainable resource management, urban development, and environmental conservation. The integration of remote sensing data with supervised machine learning algorithms has significantly enhanced classification accuracy and efficiency. This study evaluates the performance of five widely used supervised learning algorithms namely 1) Classification and Regression Tree (CART), 2) Gradient Boost Tree (GB), 3) K-Nearest Neighbours (KNN), 4) Support Vector Machine (SVM) and 5) Random Forest (RF) for LU/LC mapping in study area of East Godavari District, Andhra Pradesh, India over a time period of 2 years between 2023 and 2025. High-resolution Landsat-8 imagery is processed and classified using above algorithms, with model performance assessed based on overall accuracy, Kappa coefficient, precision and F1-score. The findings indicated that Gradient Tree Boost demonstrated superior performance compared to the other classifiers, attaining the highest accuracy of 98.26% along with a Kappa coefficient of 0.9761. Random Forest closely followed, achieving an accuracy of 97.39% and a Kappa value of 0.9642. Additionally, both SVM and KNN exhibited strong classification capabilities, with respective accuracies of 96.52% and Kappa values of 0.9522, highlighting their effectiveness in land cover classification applications. The study also examines the computational efficiency and reliability of each classifier, offering insights into their suitability for LU/LC analysis in diverse landscapes. The findings contribute to the optimization of machine learning techniques for remote sensing applications, aiding in data-driven decision-making for land management. Future research can explore deep learning-based classification models and multi-temporal analysis to further enhance LU/LC mapping accuracy.

In this paper, a graph regularized nonlinear ridge regression (RR) model is proposed for remote sensing data analysis, including hyper-spectral image classification and atmospheric aerosol retrieval. The RR is an efficient linear regression method, especially in handling cases with a small number of training samples or with correlated features. However, large amounts of unlabeled samples exist in remote sensing data analysis. To sufficiently explore the information in unlabeled samples, we propose a graph regularized RR (GRR) method, where the vertices denote labeled or unlabeled samples and the edges represent the similarities among different samples. A natural assumption is that the predict values of neighboring samples are close to each other. To further address the nonlinearly separable problem in remote sensing data caused by the complex acquisition process as well as the impacts of atmospheric and geometric distortions, we extend the proposed GRR into a kernelized nonlinear regression method, namely KGRR. To evaluate the proposed method, we apply it to both classification and regression tasks and compare with representative methods. The experimental results show that KGRR can achieve favorable performance in terms of predictability and computation time.

اهداف: پایش تغییرات کاربری‌ها و درک پویایی آن در یک حوضۀ آبخیز، از جایگاه خاصی در مدیریت پایدار آن حوضه برخوردار است. هدف تحقیق حاضر، استفاده از سنجش از دور و GIS جهت تهیۀ نقشۀ تغییرات و شناسایی انتقالات کاربری اراضی و پوشش زمین با به‌کارگیری ماتریس انتقال و تصاویر ماهوارۀ لندست در حوضۀ آبخیز دریاچۀ ارومیه می‌باشد. روش: جهت انجام تحقیق، از تصاویر ماهوارۀ لندست در دورۀ زمانی 2015 ـ 1988 استفاده گردید. بدین‌منظور پس از انجام پیش‌پردازش‌های موردنظر، جهت انجام طبقه‌بندی از روش‌های ماشین‌بردار پشتیبان و روشیءگرا استفاده و سپس اعتبارسنجی گردیدند. همچنین جهت برآورد میزان انتقالات و دیگر ویژگی‌های حوضۀ آبخیز دریاچۀ ارومیه، ابتدا ماتریس انتقالی استخراج شده و سپس طبقه‌بندی شئ‌گرا بین دوره‌های زمانی 2015ـ1988 ارائه شد. سپس با استفاده از فرمول‌های موردنظر، میزان پایداری، افزایش، کاهش، تغییرات کل، تغییرات خالص و مبادلۀ همزمان کاربری‌های اراضی و پوشش زمین مشخص گردید. یافته‌ها/ نتایج: پس از ارزیابی صحت، صحت کلی برای نقشه‌های حاصل از ماشین بردار پشتیبان و روش شئ‌گرا به‌ترتیب برابر با 94 و 92 درصد و مقدار کاپای آنها به‌ترتیب 92 و 89 برآورد شد که نشان‌دهندۀ برتری روش شئ‌گرا در مقایسه با روش ماشین بردار پشتیبان است. در کل، هر دو روش طبقه‌بندی توانستند صحت قابل‌قبولی برای نقشه‌های کاربری اراضی و پوشش زمین ارائه دهند. نتایج حاصل از انتقالات نشان داد به‌طور میانگین، 59 درصد از چهرۀ زمین در حوضۀ آبخیز دریاچۀ ارومیه در فاصلۀ زمانی 2015ـ 1988 پایداری پوشش داشته است، که بیشترین میزان این تداوم براساس مقدار این کاربری در فاصلۀ زمانی 2015ـ1988 مربوطه به مناطق مسکونی می-باشد. حدود 14 درصد از سطح حوزۀ آبخیز دریاچۀ ارومیه به‌صورت تبادل همزمان بوده است. همچنین سطوح آبی حوضۀ آبخیز دریاچۀ ارومیه در دورۀ زمانی فوق، بیشترین ازدست‌دادگی و کمترین تبادل همزمان را تجربه کرده است. نتیجه‌گیری: حوضۀ آبخیز دریاچۀ ارومیه در این فاصلۀ زمانی (2015ـ1988) تغییرات و انتقالات شدیدی را تجربه کرده است، تاجایی‌که تنها 59 درصد از چهرۀ زمین، ثابت مانده و قسمت‌های دیگر، انواعی از انتقال‌ها را تجربه کرده‌اند. همچنین سطوح آبی و سپس مراتع، بیشترین آسیب-پذیری را تجربه کرده‌اند که نشان از افزایش اراضی فاقد پوشش و اراضی زراعی (کشاورزی) می-باشد. این تجزیه‌وتحلیل ما را به سنجش و تجسم میزان انتقالات عمدۀ LULC درجهت برنامه‌ریزی آیندۀ حوضۀ آبخیز دریاچۀ ارومیه توصیه می‌کند.

Land cover is all types of features that exist on the earth's surface on certain land, either artificial or natural. Information related to monitoring and processing satellite image data to obtain land cover classification can be done in various ways, one of which is machine learning methods. This study aims to apply machine learning methods in monitoring land cover using Landsat-8 imagery, to obtain a technique that has high accuracy and is suitable for monitoring land cover. This study uses machine learning methods, namely Support Vector Machine (SVM) and Random Forest (RF). The classification of land cover in this study consists of five classes, namely, built-up areas, water bodies, vacant land, agriculture, and vegetation, where the determination of this land cover class is based on the type of land cover that exists on the RTRW Map of Mataram City in 2011-2031. match the image used. This study shows that the method with the best accuracy is the Support Vector Machine (SVM) method with overall accuracy and kappa accuracy values of 0.9101 and 0.8748. However, there is a misclassification caused by several factors such as the reflectance value of each pixel which is almost the same, the cropping period, and other factors. These factors need to be considered because they affect the land cover classification results.

BackgroundAccurate classification of microarray data is critical for successful clinical diagnosis and treatment. The "curse of dimensionality" problem and noise in the data, however, undermines the performance of many algorithms.MethodIn order to obtain a robust classifier, a novel Additive Nonparametric Margin Maximum for Case-Based Reasoning (ANMM4CBR) method is proposed in this article. ANMM4CBR employs a case-based reasoning (CBR) method for classification. CBR is a suitable paradigm for microarray analysis, where the rules that define the domain knowledge are difficult to obtain because usually only a small number of training samples are available. Moreover, in order to select the most informative genes, we propose to perform feature selection via additively optimizing a nonparametric margin maximum criterion, which is defined based on gene pre-selection and sample clustering. Our feature selection method is very robust to noise in the data.ResultsThe effectiveness of our method is demonstrated on both simulated and real data sets. We show that the ANMM4CBR method performs better than some state-of-the-art methods such as support vector machine (SVM) and k nearest neighbor (kNN), especially when the data contains a high level of noise.AvailabilityThe source code is attached as an additional file of this paper.

High spatial resolution (1–5 m) remotely sensed datasets are increasingly being used to map land covers over large geographic areas using supervised machine learning algorithms. Although many studies have compared machine learning classification methods, sample selection methods for acquiring training and validation data for machine learning, and cross-validation techniques for tuning classifier parameters are rarely investigated, particularly on large, high spatial resolution datasets. This work, therefore, examines four sample selection methods—simple random, proportional stratified random, disproportional stratified random, and deliberative sampling—as well as three cross-validation tuning approaches—k-fold, leave-one-out, and Monte Carlo methods. In addition, the effect on the accuracy of localizing sample selections to a small geographic subset of the entire area, an approach that is sometimes used to reduce costs associated with training data collection, is investigated. These methods are investigated in the context of support vector machines (SVM) classification and geographic object-based image analysis (GEOBIA), using high spatial resolution National Agricultural Imagery Program (NAIP) orthoimagery and LIDAR-derived rasters, covering a 2,609 km2 regional-scale area in northeastern West Virginia, USA. Stratified-statistical-based sampling methods were found to generate the highest classification accuracy. Using a small number of training samples collected from only a subset of the study area provided a similar level of overall accuracy to a sample of equivalent size collected in a dispersed manner across the entire regional-scale dataset. There were minimal differences in accuracy for the different cross-validation tuning methods. The processing time for Monte Carlo and leave-one-out cross-validation were high, especially with large training sets. For this reason, k-fold cross-validation appears to be a good choice. Classifications trained with samples collected deliberately (i.e., not randomly) were less accurate than classifiers trained from statistical-based samples. This may be due to the high positive spatial autocorrelation in the deliberative training set. Thus, if possible, samples for training should be selected randomly; deliberative samples should be avoided.

This paper presents a novel and automatic artificial-intelligence (AI) method for grape-bunch detection from RGB images. It mainly consists of a cascade of support vector machine (SVM)-based classifiers that rely on visual contrast-based features that, in turn, are defined according to grape bunch color visual perception. Due to some principles of opponent color theory and proper visual contrast measures, a precise estimate of grape bunches is achieved. Extensive experimental results show that the proposed method is able to accurately segment grapes even in uncontrolled acquisition conditions and with limited computational load. Finally, such an approach requires a very small number of training samples, making it appropriate for onsite and real-time applications that are implementable on smart devices, usable and even set up by winemakers.

Hyperspectral images (HSIs) obtained from remote sensing contain abundant information of ground objects, and precise analysis of landcover depends on effective and efficient classification of HSIs into homogeneous ground regions. While many advanced algorithms have been developed for HSI classification, it is a challenge for an algorithm to achieve a good balance between its effectiveness and efficiency due to the high dimensionality of HSIs and insufficient labeled training samples. By taking both the rich spectral features and the spatially homogeneous property of land cover distributions, in this paper, we propose a simple and efficient yet effective method for HSI classification. First, features are extracted by using a weighted spatial-spectral and global-local discriminant analysis algorithm, which is proposed to reduce the feature dimension. Then, combining the discriminant information of neighboring pixels, we propose a spatial collaboration nearest neighbor (SC-NN) classifier to make reliable class judgment for the central one. In the SC-NN classifier, the spatially homogeneous property of landcover distribution of HSIs is utilized to effectively reduce the probability of misclassification when only a small number of training samples are available. To further address the issue of a small number of training samples, we adopt an incremental learning strategy by adding the samples with high classification confidence to the training set. Experimental results on four public datasets show that our proposed method outperforms several state-of-the-art methods with high classification accuracy.

Recent advances in land use and land cover (LULC) classification with remote sensing imagery are driven by state-of-the-art models such as Convolutional Neural Networks (CNNs). Advanced CNN architecture like ResNet can enhance overall classification performance by incorporating residual skip connections. The integration of 3D feature extraction and ResNet architecture suggests a potential improvement in classification tasks. This paper explores the potential of the 3D ResNet model for LULC classification, comparing it with baseline approaches (Support Vector Machine, Random Forest, XGBoost, 1D CNN, 3D CNN) and state-of-the-art 3D models (3D VGG, 3D DenseNet) using WorldView-2 satellite imagery. The 3D ResNet-18 model, fine-tuned via transfer learning on multispectral images, demonstrates significant improvements in classification performance over machine learning models. It achieves the highest Overall Accuracy (OA) of 99.66% and Kappa Accuracy (KA) of 99.39% on the primary dataset. Despite having slightly lower performance on the external validation dataset (OA:82.89%, KA:80.05%) than 3D DenseNet, it is highly efficient with processing times of 490.2 minutes and 3.6 minutes for both datasets respectively. McNemar’s test results show 3D ResNet and 3D DenseNet have significant differences in classification performance (p<0.05) against other models consistently for both datasets.

This study investigates a new technique for land cover analysis by means of the Support Vector Machines. Intrinsic spatial variability within SAR images, beyond that caused by speckle, is of high interest for land cover characterization and classification. However, its use is still an ongoing issue due to its complex multi-scale nature. On the other hand, classification algorithms based on statistical learning methods such as the supervised Support Vector Machines (SVM) approach are implemented in a wide range of data mining applications. SVM can also be used as a technique for feature selection. In this paper, a new tool using the Recursive Feature Elimination SVM-based process (SVM-RFE) and the textural Haralick's parameters is introduced. The real contribution of textures within the land cover classification can be understood. A small set of textural parameters is determined at local scale while being optimal for the land cover discrimination. In this study, orthorectified 50m resolution data acquired by the L-band PALSAR/ALOS sensor are used.

Landsat-like moderate resolution remote sensing images are widely used in land use and land cover (LULC) classification. Limited by coarser resolutions, most of the traditional LULC classifications that are based on moderate resolution remote sensing images focus on the spectral features of a single pixel. Inspired by the spatial evaluation methods in landscape ecology, this study proposed a new method to extract neighborhood characteristics around a pixel for moderate resolution images. 3 landscape-metric-like indexes, i.e., mean index, standard deviation index, and distance weighted value index, were defined as adjacent region features to include the surrounding environmental characteristics. The effects of the adjacent region features and the different feature set configurations on improving the LULC classification were evaluated by a series of well-controlled LULC classification experiments using K nearest neighbor (KNN) and support vector machine (SVM) classifiers on a Landsat 8 Operational Land Imager (OLI) image. When the adjacent region features were added, the overall accuracies of both the classifiers were higher than when only spectral features were used. For the KNN and SVM classifiers that used only spectral features, the overall accuracies of the LULC classification were 85.45% and 88.87%, respectively, and the accuracies were improved to 94.52% and 96.97%. The classification accuracies of all the LULC types improved. Highly heterogeneous LULC types that are easily misclassified achieved greater improvements. As comparisons, the grey-level co-occurrence matrix (GLCM) and convolutional neural network (CNN) approaches were also implemented on the same dataset. The results revealed that the new method outperformed GLCM and CNN approaches and can significantly improve the classification performance that is based on moderate resolution data.