For more than a decade, the remote sensing community has called for longwave spectral measurements of the Earth system to facilitate closing the radiation budget. In an effort to address this large gap in Earth-observing capability, NASA has supported the development and implementation of the Polar Radiant Energy in the Far-Infrared (FIR) Experiment (PREFIRE), which realizes two miniaturized thermal IR spectrometers (TIRSs), one on each of two polar orbiting small satellites with different ascending node crossing times. The spectral radiances measured by the TIRS instruments are utilized to extract cloud presence, atmospheric state, surface properties, and the associated top-of-atmosphere (TOA) spectral fluxes at both poles. This article describes the major system and algorithm components and introduces the geophysical products. PREFIRE data will be used to inform and improve ice-sheet and coupled-Earth system models to better predict the future state of the Earth’s poles.

Surface emissivity (ϵ) plays a critical role in Earth’s radiation budget and climate. The Polar Radiant Energy in the Far-InfraRed Experiment (PREFIRE) and the Far-Infrared Outgoing Radiation Understanding and Monitoring (FORUM) satellite missions aim to estimate surface spectral emissivities in mid-IR and far-IR regions. This study presents a neural network (NN)-based surface spectral emissivity retrieval algorithm under clear-sky that offers comparable performance to optimal-estimation (OE)-based methods but reduces computation time by a factor of 105. The NN-based method has achieved a mean relative retrieval error (|∆ϵ|) of 0.0028 with a standard deviation of 0.0013. Shapley values are employed to interpret the algorithm’s results and assess the relative importance of input features. The results derived from the Shapley values analysis are in good agreement with the physical understanding. The study highlights the effectiveness of the proposed neural network approach for surface emissivity estimation in forthcoming satellite missions.

Abstract The sparse matrix regression (SMR) model for the feature selection method has attracted much attention. However, most existing models do not consider the globality and adaptively preserve the local structure of the image data in projection space. To settle such issues, an adaptive non‐negative low‐rank preserving SMR model for supervised image feature selection is proposed. It first uses the low‐rank representation with non‐negative constraint to capture the globality and more discriminative information of image data and makes the error matrix in self‐representation of training data sparse. Next, the non‐negative low‐rank representation coefficients are used to establish a graph matrix learning model to reveal the local manifold structure of the image data. Thus, the proposed model enhances the discriminative ability as well as performs feature selection by the obtained transformation matrix. Finally, an alternating iterative algorithm for solving this model is developed and its convergence and complexity are also analyzed. Experimental results on some image data sets show that the proposed algorithm is effective for images and its recognition ability is obviously superior to other existing methods. In addition, the proposed method is also applied to two scene image classifications to further verify its effectiveness.

Abstract Unsupervised feature selection is a dimensionality reduction method and has been widely used as an important and indispensable preprocessing step in many tasks. However, real‐world data are not only high‐dimensional, but also have intrinsic correlations between data points, which are not fully utilized in feature selection. Furthermore, real‐world data usually inevitably contain noise or outliers. In order to select features from data more effectively, a sparse regression model based on latent low‐rank representation with the symmetric constraint for unsupervised feature selection is proposed. With the coefficient matrix of non‐negative symmetric low‐rank representation, an affinity matrix characterized by the correlation relationship between data points is adaptively obtained, which reveals the intrinsic geometric relationship, global structure, and discrimination of data points. A latent representation of all data points obtained from this affinity matrix is employed as a pseudo‐label, and feature selection is carried out by sparse linear regression. This method performs feature selection in the learned latent space instead of the original data space. An alternating iteration algorithm is designed to solve the proposed model, and its effectiveness and efficiency are verified on several benchmark data sets.

Abstract Matrix regression has attracted much attention due to directly select some meaningful features from matrix data. However, most existing matrix regressions do not consider the global and local structure of the matrix data simultaneously. To this end, we propose a low‐rank nonnegative sparse representation and local preserving matrix regression (LNSRLP‐MR) model for image feature selection. Here, the loss function is defined by the left and right regression matrices. To capture the global structure and discriminative information of the training images and reduce the effect of heterogeneous data and noises, we impose the low‐rank constraint on the self‐representation error matrix and the nonnegative sparse constraint on the coefficient vector. The graph matrix can be learned adaptively through representation coefficients, so that accurate local structure information in samples can be revealed. Feature selection is performed by obtained row sparse transformation matrix. An optimization procedure and its performance are also present. Experimental results on several image datasets show that compared with the‐state‐of‐the‐art method, the average classification accuracy of the proposed method is improved by at least 1.2% and up to 3.3%. For images with noise or occlusion, the accuracy is improved significantly, up to 4%, which indicates that this method has strong robustness.

Bilinear matrix regression based on matrix data can directly select the features from matrix data by deploying several couples of left and right regression matrices. However, the existing matrix regression methods do not consider the local geometric structure of the samples, which results in poor classification performance. This study proposes a robust graph regularised sparse matrix regression method for two‐dimensional supervised feature selection, where the intra‐class compactness graph based on the manifold learning is used as the regularisation item, and the ‐norm as loss functions to establish the authors’ matrix regression model. An alternating optimisation algorithm is also devised to solve it and give its closed‐form solutions in each iteration. The proposed method not only can learn the left and right regression matrices, but also can preserve the intrinsic geometry structure by using the label information. Extensive experiments on several data sets demonstrate the superiority of the proposed method.

Principal component analysis (PCA) is the most widely used unsupervised dimensionality reduction approach. A number of variants of PCA have been proposed to improve the robustness of the algorithm. However, the existing methods either cannot select the useful features consistently or is still sensitive to outliers. In order to reveal the intrinsic manifold structure and preserve the global structure of data, it is needed to learn more efficient optimal projection matrix for sample sets with outliers. To this end, the authors propose a novel PCA, named low‐rank project embedding and optimal mean principal component analysis (abbreviated as LRPE‐OMPCA), which can learn the optimal mean and the optimal projection matrix and preserve the global geometric information and discriminative structure captured by the self‐representation coefficient weight matrix into the low‐dimensional embedding subspace. Thus, not only can the proposed method further reduce the influence of outliers but also can discard the useless features, which effectively improve the robustness of the method. An effective iterative algorithm to solve the LRPE‐OMPCA is designed. Experimental results on several image databases illustrate the robustness and effectiveness of the proposed method.

Principal component analysis (PCA) is the most widely used unsupervised dimensionality reduction approach. However, most PCA based on the squared reconstruction errors assume that all training samples have been centred, which make them not robust to outliers or noises in the samples and will depress their performance of classification accuracy. On the other hand, when there are various correlations in the training samples, the l 1 ‐norm regularisation encounters instability problems. To address the above problems, the authors propose a novel L 2,1 ‐norm‐based sparse PCA with the trace norm regularised term (abbreviated to OMSPCA‐L21‐TN) to learn the optimal projection matrix and optimal mean simultaneously, where the objective function in model consists of the L 2,1 ‐norm‐based reconstruction error and the trace‐norm‐based regularised term of the projection vectors involved the sample matrix. Thus, not only can the authors’ method obtain the sparse features and reduce the effect of noise and outliers but also be adaptive to the correlation of the training samples. An effective optimisation solution is also given. The experimental results on some publicly available datasets demonstrate that the proposed approach is feasible and effective.

Complex information resources interoperability is becoming an important issue for information resources reuse and aggregation in Semantic Web services. Current registration standards are relatively weak in the description of complex logic relationship between information resources. This paper proposes a complex information resources registry method based on deeply semantic interoperability. The mothod builds complex information registry attribute model, defines complex information registry attribute reference, local and application ontologies and evolution rules of them in the model. The method builds a complex information registry knowledge base on the OWL commitment for ontology and its reasoning capability. At last, we take software component (a type of complex information resources) as an example to realize a type of complex information resources registry based on ontology. The preliminary experimental results show that above method is quite feasible for solving problems with real world sizes.