Classification Of Remote Sensing Data Research Articles

IFF-Net: Irregular Feature Fusion Network for Multimodal Remote Sensing Image Classification

In recent years, classification and identification of Earth’s surface materials has been a challenging research topic in the field of earth science and remote sensing (RS). Although deep learning techniques have achieved some results in remote sensing image classification, there are still some challenges for multimodal remote sensing data classification, such as information redundancy between multimodal remote sensing images. In this paper, we propose a multimodal remote sensing data classification method IFF-Net based on irregular feature fusion, called IFF-Net. The IFF-Net architecture utilizes weight-shared residual blocks for feature extraction while maintaining the independent batch normalization (BN) layer. During the training phase, the redundancy of the current channel is determined by evaluating the judgement factor of the BN layer. If this judgment factor falls below a predefined threshold, it indicates that the current channel information is redundant and should be substituted with another channel. Sparse constraints are imposed on some of the judgment factors in order to remove extra channels and enhance generalization. Furthermore, a module for feature normalization and calibration has been devised to leverage the spatial interdependence of multimodal features in order to achieve improved discrimination. Two standard datasets are used in the experiments to validate the effectiveness of the proposed method. The experimental results show that the IFF-NET method proposed in this paper exhibits significantly superior performance compared to the state-of-the-art methods.

Causal Meta-Reinforcement Learning for Multimodal Remote Sensing Data Classification

Multimodal remote sensing data classification can enhance a model’s ability to distinguish land features through multimodal data fusion. In this context, how to help models understand the relationship between multimodal data and target tasks has become the focus of researchers. Inspired by the human feedback learning mechanism, causal reasoning mechanism, and knowledge induction mechanism, this paper integrates causal learning, reinforcement learning, and meta learning into a unified remote sensing data classification framework and proposes causal meta-reinforcement learning (CMRL). First, based on the feedback learning mechanism, we overcame the limitations of traditional implicit optimization of fusion features and customized a reinforcement learning environment for multimodal remote sensing data classification tasks. Through feedback interactive learning between agents and the environment, we helped the agents understand the complex relationships between multimodal data and labels, thereby achieving full mining of multimodal complementary information.Second, based on the causal inference mechanism, we designed causal distribution prediction actions, classification rewards, and causal intervention rewards, capturing pure causal factors in multimodal data and preventing false statistical associations between non-causal factors and class labels. Finally, based on the knowledge induction mechanism, we designed a bi-layer optimization mechanism based on meta-learning. By constructing a meta training task and meta validation task simulation model in the generalization scenario of unseen data, we helped the model induce cross-task shared knowledge, thereby improving its generalization ability for unseen multimodal data. The experimental results on multiple sets of multimodal datasets showed that the proposed method achieved state-of-the-art performance in multimodal remote sensing data classification tasks.

Random Forest Classifier Algorithm of Geographic Resources Analysis Support System Geographic Information System for Satellite Image Processing: Case Study of Bight of Sofala, Mozambique

Mapping coastal regions is important for environmental assessment and for monitoring spatio-temporal changes. Although traditional cartographic methods using a geographic information system (GIS) are applicable in image classification, machine learning (ML) methods present more advantageous solutions for pattern-finding tasks such as the automated detection of landscape patches in heterogeneous landscapes. This study aimed to discriminate landscape patterns along the eastern coasts of Mozambique using the ML modules of a Geographic Resources Analysis Support System (GRASS) GIS. The random forest (RF) algorithm of the module ‘r.learn.train’ was used to map the coastal landscapes of the eastern shoreline of the Bight of Sofala, using remote sensing (RS) data at multiple temporal scales. The dataset included Landsat 8-9 OLI/TIRS imagery collected in the dry period during 2015, 2018, and 2023, which enabled the evaluation of temporal dynamics. The supervised classification of RS rasters was supported by the Scikit-Learn ML package of Python embedded in the GRASS GIS. The Bight of Sofala is characterized by diverse marine ecosystems dominated by swamp wetlands and mangrove forests located in the mixed saline–fresh waters along the eastern coast of Mozambique. This paper demonstrates the advantages of using ML for RS data classification in the environmental monitoring of coastal areas. The integration of Earth Observation data, processed using a decision tree classifier by ML methods and land cover characteristics enabled the detection of recent changes in the coastal ecosystem of Mozambique, East Africa.

Cognitive land cover mapping: A three-layer deep learning architecture for remote sensing data classification

In many application domains, remotely sensed (RS) data are essential for disaster monitoring, climate forecasting, and remote surveillance. It perceives and gathers environmental, sociological, and transitional data on its own, from a distance, in increasing amounts of spatial and temporal details. While urbanization has been continued to be a worldwide phenomenon, the urban management and planning are needed to satisfy the needs of the Earth system. The operations associated with land management, urban planning, and transportation on Earth have been connected to digital maps and geographic databases. Knowledge of land cover is also significant for managing, conserving, and formulating environmental and urban development policies. Therefore, highly accurate Land Use Land Cover (LULC) assessment and monitoring are of the utmost significance for empirical studies and organizational accomplishment. In this study, we leverage remotely sensed data to formulate a sophisticated deep learning system for comprehensive Earth observation. The core of our approach involves the development of a three-layered Convolution-Convolution-Maxpooling Convolutional Neural Network (CCMCNN) model, preceded by a meticulous pre-processing stage. In the pre-processing stage, images extracted from the NWPU-RESISC dataset undergo resizing, division, and augmentation procedures before being fed into the three-layered CCMCNN architecture for the purpose of classifying them into five different LULC categories. The effectiveness of our proposed model undergoes thorough validation through a comparative examination against various pre-trained deep learning models outlined in existing literature. Presenting performance metrics, our model attains a remarkable accuracy rate of 98.4%. This advancement holds significant promise in the realm of Earth surveillance, offering a valuable tool for enhancing situational awareness and environmental monitoring.

Foundation Model-Based Multimodal Remote Sensing Data Classification

Foundation Model-Based Multimodal Remote Sensing Data Classification

Multiscale Spectral–Spatial Attention Residual Fusion Network for Multisource Remote Sensing Data Classification

Multiscale Spectral–Spatial Attention Residual Fusion Network for Multisource Remote Sensing Data Classification

Multimodal Remote Sensing Data Classification Based on Gaussian Mixture Variational Dynamic Fusion Network

Multimodal Remote Sensing Data Classification Based on Gaussian Mixture Variational Dynamic Fusion Network

Multifrequency Graph Convolutional Network With Cross-Modality Mutual Enhancement for Multisource Remote Sensing Data Classification

Multifrequency Graph Convolutional Network With Cross-Modality Mutual Enhancement for Multisource Remote Sensing Data Classification

Urban tourism expansion monitoring by remote sensing and random forest

Tourism and urban areas experienced rapid development at the beginning of the 21st century. This condition is caused by natural, cultural, and artificial tourist destinations and adequate infrastructure support. Tourist destinations in urban areas add to urbanization because apart from being the center of government, trade, and industry, it is also a tourist destination that can attract tourists. Monitoring the development of urban tourism is carried out in the cities of Denpasar and Bali, as well-known destinations at the world level. The development of the urban area can be detected through multi-temporal and multispectral remote sensing imagery in combination with machine learning technology. This study aims to determine the spatial distribution of urban tourism development from 2013 to 2021. This study uses remote sensing and machine learning methods with the Random Forest (RF) algorithm on Google Earth Engine (GEE) cloud computing. The RF algorithm is one of the non-parametric classification algorithms which is widely applied in remote sensing data classification because of its insensitivity to excessive noise and training data and its good performance. The material used is Landsat 8, especially on the Operational Land Imager (OLI) sensor. The result showed that integrating remote sensing, GEE cloud computing, and machine learning, especially the RF algorithm, effectively monitors urban tourism expansion. The overall accuracy of the RF model with simple training data is above 90%. We found that within nine years, vegetated land was changed into an urban area of 20.23 km2. For this reason, special attention is needed from the government to make regulations on spatial planning and control over land conversion so that there will still be green open spaces in the future.

Cross-Scale Mixing Attention for Multisource Remote Sensing Data Fusion and Classification

Hyperspectral and multispectral images (HS/MS) fusion and classification as an important branch of data quality improvement and interpretation, has attracted increasing attention in recent years. However, the unavailable sensor prior still limits the performance of many traditional fusion methods, consequently deteriorating the classification results. Despite the unsupervised methods based on convolutional neural network (CNN) making a lot of attempts to mitigate the limitations, challenges with extracting the long-range dependencies hamper the performance. To address these impediments, a transformer-based baseline constructed by the cross-scale mixing attention (CSMFormer) is designed for HS/MS fusion and classification. Especially, the spatial-spectral mixer (SSMixer) is utilized to extract the long-range dependencies at large scale. Simultaneously, cross-scale feature calibration is achieved by combining information from the original scale. After that, nonlinear enhancement module (NLEM) is designed to encourage feature discrimination. Note that the spatial and spectral mixers can be replaced by any spatial-spectral feature extractors. Therefore, the proposed CSMFormer is flexible in data fusion, land-covers classification, segmentation, etc. Experiments about data fusion and land-covers classification on two HS/MS wetland remote sensing scenes demonstrate the superiority of the proposed CSMFormer baseline, improving the data quality and classification precision.

Adversarial Complementary Learning for Multisource Remote Sensing Classification

Convolutional neural networks (CNN) have attracted increasing attention in the field of multimodal cooperation. Recently, the adoption of CNN-based methods has achieved remarkable performance in multisource remote sensing data classification. However, it is still confronted with challenges in the aspect of complementarity extraction. In this paper, the adversarial complementary learning strategy is embedded into the CNN model called ACL-CNN, which is employed to extract the complementary information of the multisource data. The proposed ACL-CNN is able to filter out the common patterns and specific patterns from multisource data by conducting the adversarial max-min game. Especially, the modality-independent common patterns constitute the basic representation of the land-covers, while the specific patterns that are linearly independent of the common patterns that provide the supplementary representation. Therefore, the complementary information is mapped to a compact and discriminative representation. To eliminate the singularity noise, a learnable pattern sampling module (PSM) is designed to extract the mutual-exclusion relationship between specific patterns. Extensive experiments over three datasets demonstrate the superiority of the proposed ACL-CNN compared with several classification technologies.

Mixing Self-Attention and Convolution: A Unified Framework for Multisource Remote Sensing Data Classification

Mixing Self-Attention and Convolution: A Unified Framework for Multisource Remote Sensing Data Classification

Quaternion Convolutional Neural Network With EMAP Representation for Multisource Remote-Sensing Data Classification

Quaternion Convolutional Neural Network With EMAP Representation for Multisource Remote-Sensing Data Classification

R Libraries for Remote Sensing Data Classification by k-means Clustering and NDVI Computation in Congo River Basin, DRC

R Libraries for Remote Sensing Data Classification by k-means Clustering and NDVI Computation in Congo River Basin, DRC

R Libraries for Remote Sensing Data Classification by k-means Clustering and NDVI Computation in Congo River Basin, DRC

R Libraries for Remote Sensing Data Classification by k-means Clustering and NDVI Computation in Congo River Basin, DRC

R Libraries for Remote Sensing Data Classification by K-Means Clustering and NDVI Computation in Congo River Basin, DRC

In this paper, an image analysis framework is formulated for Landsat-8 Operational Land Imager and Thermal Infrared Sensor (OLI/TIRS) scenes using the R programming language. The libraries of R are shown to be effective in remote sensing data processing tasks, such as classification using k-means clustering and computing the Normalized Difference Vegetation Index (NDVI). The data are processed using an integration of the RStoolbox, terra, raster, rgdal and auxiliary packages of R. The proposed approach to image processing using R is designed to exploit the parameters of image bands as cues to detect land cover types and vegetation parameters corresponding to the spectral reflectance of the objects represented on the Earth’s surface. Our method is effective at processing the time series of the images taken at various periods to monitor the landscape dynamics in the middle part of the Congo River basin, Democratic Republic of the Congo (DRC). Whereas previous approaches primarily used Geographic Information System (GIS) software, we proposed to explicitly use the scripting methods for satellite image analysis by applying the extended functionality of R. The application of scripts for geospatial data is an effective and robust method compared with the traditional approaches due to its high automation and machine-based graphical processing. The algorithms of the R libraries are adjusted to spatial operations, such as projections and transformations, object topology, classification and map algebra. The data include Landsat-8 OLI-TIRS covering the three regions along the Congo river, Bumba, Basoko and Kisangani, for the years 2013, 2015 and 2022. We also validate the performance of graphical data handling for cartographic visualization using R libraries for visualising changes in land cover types by k-means clustering and calculation of the NDVI for vegetation analysis.

3DUNetGSFormer: A deep learning pipeline for complex wetland mapping using generative adversarial networks and Swin transformer

Many ecosystems, particularly wetlands, are significantly degraded or lost as a result of climate change and anthropogenic activities. Simultaneously, developments in machine learning, particularly deep learning methods, have greatly improved wetland mapping, which is a critical step in ecosystem monitoring. Yet, present deep and very deep models necessitate a greater number of training data, which are costly, logistically challenging, and time-consuming to acquire. Thus, we explore and address the potential and possible limitations caused by the availability of limited ground-truth data for large-scale wetland mapping. To overcome this persistent problem for remote sensing data classification using deep learning models, we propose 3D UNet Generative Adversarial Network Swin Transformer (3DUNetGSFormer) to adaptively synthesize wetland training data based on each class's data availability. Both real and synthesized training data are then imported to a novel deep learning architecture consisting of cutting-edge Convolutional Neural Networks and vision transformers for wetland mapping. Results demonstrated that the developed wetland classifier obtained a high level of kappa coefficient, average accuracy, and overall accuracy of 96.99%, 97.13%, and 97.39%, respectively, for the data in three pilot sites in and around Grand Falls-Windsor, Avalon, and Gros Morne National Park located in Canada. The results show that the proposed methodology opens a new window for future high-quality wetland data generation and classification. The developed codes are available at https://github.com/aj1365/3DUNetGSFormer.

Analysis of support vector machine and maximum likelihood classifiers in land cover classification using Sentinel-2 images

Remote sensing data has been widely applied to classify the land cover more frequently and on a near real-time basis for updating as it is more economic, less time consuming compared to ground based survey. Accurate classification of the land use/cover classes such as water body, cropland, built-up area, scrub land, fallow land, forest etc., is one of the biggest challenges in natural resource inventory, management and monitoring. As accuracy of remote sensing data classification is affected by many parameters which include type of data, presence of heterogeneous landscapes in study area, classification approaches etc., as satellite imagery is complex in nature. Many classifiers have been developed and tested on remotely sensed data for better classification. Classification of remote sensing data is mainly divided into two categories such as supervised and unsupervised. In supervised classification, the decision boundaries in feature space are determined by training the samples. Two supervised classifiers namely maximum likelihood (ML) classifier, which is a parametric classifier that assumes data to be normally distributed, and support vector machine classifier (SVM) which is a non-parametric classifier are used in classification. In the present study, the accuracy of these two classifiers is studied on five different data sets of Sentinel-2 satellite image of different years and sessions to accommodate intra and inter annual variations of the datasets. Sentinel-2 satellite images covering part of Nagpur, located in Maharashtra, India were used for the classification. Classifier accuracy has been calculated using overall accuracy and kappa statistics based on ground truth information. The result obtained were carefully examined by comparing classification accuracies and then by visual analysis. The result shows that SVM classifiers gives better overall accuracy and kappa coefficients and its average value for intra and inter annual classification outputs were 91.78% and 0.89 in that order which is far better than ML classifier which gave 87.07% and 0.83 respectively. The experimental results obtained from the present study, it is clear that SVM classifier produced better accuracy than ML classifier in classifying Sentinel-2 optical image and have significant potential in classifying various land cover classes in the heterogeneous land use/land cover conditions of the tropical regime.

Dimensionality Reduction for the Feature System in Classification of Hyperspectral Earth Remote Sensing Data by Use of Neural Networks

Dimensionality Reduction for the Feature System in Classification of Hyperspectral Earth Remote Sensing Data by Use of Neural Networks

A3 CLNN: Spatial, Spectral and Multiscale Attention ConvLSTM Neural Network for Multisource Remote Sensing Data Classification.

The problem of effectively exploiting the information multiple data sources has become a relevant but challenging research topic in remote sensing. In this article, we propose a new approach to exploit the complementarity of two data sources: hyperspectral images (HSIs) and light detection and ranging (LiDAR) data. Specifically, we develop a new dual-channel spatial, spectral and multiscale attention convolutional long short-term memory neural network (called dual-channel A3 CLNN) for feature extraction and classification of multisource remote sensing data. Spatial, spectral, and multiscale attention mechanisms are first designed for HSI and LiDAR data in order to learn spectral- and spatial-enhanced feature representations and to represent multiscale information for different classes. In the designed fusion network, a novel composite attention learning mechanism (combined with a three-level fusion strategy) is used to fully integrate the features in these two data sources. Finally, inspired by the idea of transfer learning, a novel stepwise training strategy is designed to yield a final classification result. Our experimental results, conducted on several multisource remote sensing data sets, demonstrate that the newly proposed dual-channel A 3 CLNN exhibits better feature representation ability (leading to more competitive classification performance) than other state-of-the-art methods.