Lithological information extraction and classification in hyperspectral remote sensing data using Backpropagation Neural Network.
Ontology highlight
ABSTRACT:
SUBMITTER: Wang Z
PROVIDER: S-EPMC8516202 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:ProblemWith the rapid advancement of remote sensing technology is that the need for efficient and accurate crop classification methods has become increasingly important. This is due to the ever-growing demand for food security and environmental monitoring. Traditional crop classification methods have limitations in terms of accuracy and scalability, especially when dealing with large datasets of high-resolution remote sensing images. This study aims to develop a novel crop classification technique, named Dipper Throated Optimization with Deep Convolutional Neural Networks based Crop Classification (DTODCNN-CC) for analyzing remote sensing images. The objective is to achieve high classification accuracy for various food crops.MethodsThe proposed DTODCNN-CC approach consists of the following key components. Deep convolutional neural network (DCNN) a GoogleNet architecture is employed to extract robust feature vectors from the remote sensing images. The Dipper throated optimization (DTO) optimizer is used for hyper parameter tuning of the GoogleNet model to achieve optimal feature extraction performance. Extreme Learning Machine (ELM): This machine learning algorithm is utilized for the classification of different food crops based on the extracted features. The modified sine cosine algorithm (MSCA) optimization technique is used to fine-tune the parameters of ELM for improved classification accuracy.ResultsExtensive experimental analyses are conducted to evaluate the performance of the proposed DTODCNN-CC approach. The results demonstrate that DTODCNN-CC can achieve significantly higher crop classification accuracy compared to other state-of-the-art deep learning methods.ConclusionThe proposed DTODCNN-CC technique provides a promising solution for efficient and accurate crop classification using remote sensing images. This approach has the potential to be a valuable tool for various applications in agriculture, food security, and environmental monitoring.
| S-EPMC10909238 | biostudies-literature
Project description:A strong positive correlation between vegetation canopy bidirectional reflectance factor (BRF) in the near infrared (NIR) spectral region and foliar mass-based nitrogen concentration (%N) has been reported in some temperate and boreal forests. This relationship, if true, would indicate an additional role for nitrogen in the climate system via its influence on surface albedo and may offer a simple approach for monitoring foliar nitrogen using satellite data. We report, however, that the previously reported correlation is an artifact--it is a consequence of variations in canopy structure, rather than of %N. The data underlying this relationship were collected at sites with varying proportions of foliar nitrogen-poor needleleaf and nitrogen-rich broadleaf species, whose canopy structure differs considerably. When the BRF data are corrected for canopy-structure effects, the residual reflectance variations are negatively related to %N at all wavelengths in the interval 423-855 nm. This suggests that the observed positive correlation between BRF and %N conveys no information about %N. We find that to infer leaf biochemical constituents, e.g., N content, from remotely sensed data, BRF spectra in the interval 710-790 nm provide critical information for correction of structural influences. Our analysis also suggests that surface characteristics of leaves impact remote sensing of its internal constituents. This further decreases the ability to remotely sense canopy foliar nitrogen. Finally, the analysis presented here is generic to the problem of remote sensing of leaf-tissue constituents and is therefore not a specific critique of articles espousing remote sensing of foliar %N.
| S-EPMC3549131 | biostudies-other
Project description:The development of state-of-the-art convolutional neural networks (CNN) has allowed researchers to perform plant classification tasks previously thought impossible and rely on human judgment. Researchers often develop complex CNN models to achieve better performances, introducing over-parameterization and forcing the model to overfit on a training dataset. The most popular process for evaluating overfitting in a deep learning model is using accuracy and loss curves. Train and loss curves may help understand the performance of a model but do not provide guidance on how the model could be modified to attain better performance. In this article, we analyzed the relation between the features learned by a model and its capacity and showed that a model with higher representational capacity might learn many subtle features that may negatively affect its performance. Next, we showed that the shallow layers of a deep learning model learn more diverse features than the ones learned by the deeper layers. Finally, we propose SSIM cut curve, a new way to select the depth of a CNN model by using the pairwise similarity matrix between the visualization of the features learned at different depths by using Guided Backpropagation. We showed that our proposed method could potentially pave a new way to select a better CNN model.
| S-EPMC9132261 | biostudies-literature
Project description:Multi-scale image segmentation and the selection of optimal segmentation parameters are the key processes in the object-oriented information extraction of high-resolution remote sensing images. The accuracy of remote sensing special subject information depends on this extraction. On the basis of WorldView-2 high-resolution data, the optimal segmentation parameters methodof object-oriented image segmentation and high-resolution image information extraction, the following processes were conducted in this study. Firstly, the best combination of the bands and weights was determined for the information extraction of high-resolution remote sensing image. An improved weighted mean-variance method was proposed andused to calculatethe optimal segmentation scale. Thereafter, the best shape factor parameter and compact factor parameters were computed with the use of the control variables and the combination of the heterogeneity and homogeneity indexes. Different types of image segmentation parameters were obtained according to the surface features. The high-resolution remote sensing images were multi-scale segmented with the optimal segmentation parameters. Ahierarchical network structure was established by setting the information extraction rules to achieve object-oriented information extraction. This study presents an effective and practical method that can explain expert input judgment by reproducible quantitative measurements. Furthermore the results of this procedure may be incorporated into a classification scheme.
| S-EPMC4928919 | biostudies-literature
Project description:This paper describes the concept of the hyperspectral Earth-observing thermal infrared (TIR) satellite mission HiTeSEM (High-resolution Temperature and Spectral Emissivity Mapping). The scientific goal is to measure specific key variables from the biosphere, hydrosphere, pedosphere, and geosphere related to two global problems of significant societal relevance: food security and human health. The key variables comprise land and sea surface radiation temperature and emissivity, surface moisture, thermal inertia, evapotranspiration, soil minerals and grain size components, soil organic carbon, plant physiological variables, and heat fluxes. The retrieval of this information requires a TIR imaging system with adequate spatial and spectral resolutions and with day-night following observation capability. Another challenge is the monitoring of temporally high dynamic features like energy fluxes, which require adequate revisit time. The suggested solution is a sensor pointing concept to allow high revisit times for selected target regions (1-5 days at off-nadir). At the same time, global observations in the nadir direction are guaranteed with a lower temporal repeat cycle (>1 month). To account for the demand of a high spatial resolution for complex targets, it is suggested to combine in one optic (1) a hyperspectral TIR system with ~75 bands at 7.2-12.5 µm (instrument NEDT 0.05 K-0.1 K) and a ground sampling distance (GSD) of 60 m, and (2) a panchromatic high-resolution TIR-imager with two channels (8.0-10.25 µm and 10.25-12.5 µm) and a GSD of 20 m. The identified science case requires a good correlation of the instrument orbit with Sentinel-2 (maximum delay of 1-3 days) to combine data from the visible and near infrared (VNIR), the shortwave infrared (SWIR) and TIR spectral regions and to refine parameter retrieval.
| S-EPMC5539530 | biostudies-other
Project description:The amount of information involved in hyperspectral imaging is large. Hyperspectral band selection is a popular method for reducing dimensionality. Several information based measures such as mutual information have been proposed to reduce information redundancy among spectral bands. Unfortunately, mutual information does not take into account the spatial dependency between adjacent pixels in images thus reducing its robustness as a similarity measure. In this paper, we propose a new band selection method based on spatial mutual information. As validation criteria, a supervised classification method using support vector machine (SVM) is used. Experimental results of the classification of hyperspectral datasets show that the proposed method can achieve more accurate results.
| S-EPMC4396555 | biostudies-other
Project description:This paper addresses the problem of semi-supervised transfer learning with limited cross-modality data in remote sensing. A large amount of multi-modal earth observation images, such as multispectral imagery (MSI) or synthetic aperture radar (SAR) data, are openly available on a global scale, enabling parsing global urban scenes through remote sensing imagery. However, their ability in identifying materials (pixel-wise classification) remains limited, due to the noisy collection environment and poor discriminative information as well as limited number of well-annotated training images. To this end, we propose a novel cross-modal deep-learning framework, called X-ModalNet, with three well-designed modules: self-adversarial module, interactive learning module, and label propagation module, by learning to transfer more discriminative information from a small-scale hyperspectral image (HSI) into the classification task using a large-scale MSI or SAR data. Significantly, X-ModalNet generalizes well, owing to propagating labels on an updatable graph constructed by high-level features on the top of the network, yielding semi-supervised cross-modality learning. We evaluate X-ModalNet on two multi-modal remote sensing datasets (HSI-MSI and HSI-SAR) and achieve a significant improvement in comparison with several state-of-the-art methods.
| S-EPMC7453915 | biostudies-literature
Project description:Advances in remote sensing technology can help estimate biodiversity at large spatial extents. To assess whether we could use hyperspectral visible near-infrared (VNIR) spectra to estimate species diversity, we examined the correlations between species diversity and spectral diversity in early-successional abandoned agricultural fields in the Ridge and Valley ecoregion of north-central Virginia at the Blandy Experimental Farm. We established plant community plots and collected vegetation surveys and ground-level hyperspectral data from 350 to 1,025 nm wavelengths. We related spectral diversity (standard deviations across spectra) with species diversity (Shannon-Weiner index) and evaluated whether these correlations differed among spectral regions throughout the visible and near-infrared wavelength regions, and across different spectral transformation techniques. We found positive correlations in the visible regions using band depth data, positive correlations in the near-infrared region using first derivatives of spectra, and weak to no correlations in the red-edge region using either of the two spectral transformation techniques. To investigate the role of pigment variability in these correlations, we estimated chlorophyll, carotenoid, and anthocyanin concentrations of five dominant species in the plots using spectral vegetation indices. Although interspecific variability in pigment levels exceeded intraspecific variability, chlorophyll was more varied within species than carotenoids and anthocyanins, contributing to the lack of correlation between species diversity and spectral diversity in the red-edge region. Interspecific differences in pigment levels, however, made it possible to differentiate these species remotely, contributing to the species-spectral diversity correlations. VNIR spectra can be used to estimate species diversity, but the relationships depend on the spectral region examined and the spectral transformation technique used.
| S-EPMC5433985 | biostudies-literature
Project description:Chlorophyll content is an important indicator of the growth status of japonica rice. The objective of this paper is to develop an inversion model that can predict japonica rice chlorophyll content by using hyperspectral image of rice canopy collected with unmanned aerial vehicle (UAV). UAV-based hyperspectral remote sensing can provide timely and cost-effective monitoring of chlorophyll content over a large region. The study was based on hyperspectral data collected at the Shenyang Agricultural College Academician Japonica Rice Experimental Base in 2018 and 2019. In order to extract the salient information embedded in the high-dimensional hyperspectral data, we first perform dimension reduction by using a successive projection algorithm (SPA). The SPA extracts the characteristic hyperspectral bands that are used as input to the inversion model. The characteristic bands extracted by SPA are 410 nm, 481 nm, 533 nm, 702 nm, and 798 nm, respectively. The inversion model is developed by using an extreme learning machine (ELM), the parameters of which are optimized by using particle swarm optimization (PSO). The PSO-ELM algorithm can accurately model the nonlinear relationship between hyperspectral data and chlorophyll content. The model achieves a coefficient of determination R2 = 0.791 and a root mean square error of RMSE = 8.215 mg/L. The model exhibits good predictive ability and can provide data support and model reference for research on nutrient diagnosis of japonica rice.
| S-EPMC7485794 | biostudies-literature
Project description:Addressing the challenges in effectively extracting multi-scale features and preserving pose information during hyperspectral image (HSI) classification, a Multi-Scale Depthwise Separable Capsule Network (MDSC-Net) is proposed in this article for HSI classification. Initially, hierarchical features are extracted by MDSC-Net through the employment of parallel multi-scale convolutional kernels, while computational complexity is reduced via depthwise separable convolutions, thus reducing the overall computational load and achieving efficient feature extraction. Subsequently, to enhance the translational invariance of features and reduce the loss of pose information, features of various scales are processed in parallel by independent capsule networks, with improvements in max pooling achieved through dynamic routing. Lastly, features of different scales are concatenated and integrated through the concatenate operation, thereby facilitating precise analysis of multi-level information in the hyperspectral image classification process. Experimental comparisons demonstrate that MDSC-Net achieves average accuracies of 94%, 98%, and 99% on the Kennedy Space Center, University of Pavia, and Salinas datasets, respectively, indicating a significant performance advantage over recent HSI classification models and validating the effectiveness of the proposed model.
| S-EPMC11357079 | biostudies-literature