An Unsupervised Aspect-Aware Recommendation Model with Explanation Text Generation

Review based recommendation utilizes both users’ rating records and the associated reviews for recommendation. Recently, with the rapid demand for explanations of recommendation results, reviews are used to train the encoder–decoder models for explanation text generation. As most of the reviews are general text without detailed evaluation, some researchers leveraged auxiliary information of users or items to enrich the generated explanation text. Nevertheless, the auxiliary data is not available in most scenarios and may suffer from data privacy problems. In this article, we argue that the reviews contain abundant semantic information to express the users’ feelings for various aspects of items, while these information are not fully explored in current explanation text generation task. To this end, we study how to generate more fine-grained explanation text in review based recommendation without any auxiliary data. Though the idea is simple, it is non-trivial since the aspect is hidden and unlabeled. Besides, it is also very challenging to inject aspect information for generating explanation text with noisy review input. To solve these challenges, we first leverage an advanced unsupervised neural aspect extraction model to learn the aspect-aware representation of each review sentence. Thus, users and items can be represented in the aspect space based on their historical associated reviews. After that, we detail how to better predict ratings and generate explanation text with the user and item representations in the aspect space. We further dynamically assign review sentences which contain larger proportion of aspect words with larger weights to control the text generation process, and jointly optimize rating prediction accuracy and explanation text generation quality with a multi-task learning framework. Finally, extensive experimental results on three real-world datasets demonstrate the superiority of our proposed model for both recommendation accuracy and explainability.

KRAN: Knowledge Refining Attention Network for Recommendation

Recommender algorithms combining knowledge graph and graph convolutional network are becoming more and more popular recently. Specifically, attributes describing the items to be recommended are often used as additional information. These attributes along with items are highly interconnected, intrinsically forming a Knowledge Graph (KG). These algorithms use KGs as an auxiliary data source to alleviate the negative impact of data sparsity. However, these graph convolutional network based algorithms do not distinguish the importance of different neighbors of entities in the KG, and according to Pareto’s principle, the important neighbors only account for a small proportion. These traditional algorithms can not fully mine the useful information in the KG. To fully release the power of KGs for building recommender systems, we propose in this article KRAN, a Knowledge Refining Attention Network, which can subtly capture the characteristics of the KG and thus boost recommendation performance. We first introduce a traditional attention mechanism into the KG processing, making the knowledge extraction more targeted, and then propose a refining mechanism to improve the traditional attention mechanism to extract the knowledge in the KG more effectively. More precisely, KRAN is designed to use our proposed knowledge-refining attention mechanism to aggregate and obtain the representations of the entities (both attributes and items) in the KG. Our knowledge-refining attention mechanism first measures the relevance between an entity and it’s neighbors in the KG by attention coefficients, and then further refines the attention coefficients using a “richer-get-richer” principle, in order to focus on highly relevant neighbors while eliminating less relevant neighbors for noise reduction. In addition, for the item cold start problem, we propose KRAN-CD, a variant of KRAN, which further incorporates pre-trained KG embeddings to handle cold start items. Experiments show that KRAN and KRAN-CD consistently outperform state-of-the-art baselines across different settings.

Augmented Sample-Based Real-Time Spatiotemporal Spectral Unmixing

Recently, the method of spatiotemporal spectral unmixing (STSU ) was developed to fully explore multi-scale temporal information (e.g., MODIS –Landsat image pairs) for spectral unmixing of coarse time series (e.g., MODIS data). To further enhance the application for timely monitoring, the real-time STSU( RSTSU) method was developed for real-time data. In RSTSU, we usually choose a spatially complete MODIS–Landsat image pair as auxiliary data. Due to cloud contamination, the temporal distance between the required effective auxiliary data and the real-time data to be unmixed can be large, causing great land cover changes and uncertainty in the extracted unchanged pixels (i.e., training samples). In this article, to extract more reliable training samples, we propose choosing the auxiliary MODIS–Landsat data temporally closest to the prediction time. To deal with the cloud contamination in the auxiliary data, we propose an augmented sample-based RSTSU( ARSTSU) method. ARSTSU selects and augments the training samples extracted from the valid (i.e., non-cloud) area to synthesize more training samples, and then trains an effective learning model to predict the proportions. ARSTSU was validated using two MODIS data sets in the experiments. ARSTSU expands the applicability of RSTSU by solving the problem of cloud contamination in temporal neighbors in actual situations.

Groundwater Radon Precursor Anomalies Identification by EMD-LSTM Model

Groundwater radon concentrations can reflect the changes of crustal stress and strain. Scholars and scientific institutions have also recorded groundwater radon precursor anomalies before earthquakes. Therefore, groundwater radon monitoring is an effective means of predicting seismic activities. However, the variation of radon concentrations within groundwater is not only affected by structural factors, but also by environmental factors, such as air pressure, temperature, and rainfall. This causes difficulty in identifying the possible precursor anomalies. Therefore, the EMD-LSTM model is proposed to identify the radon anomalies. This study investigated the time series data of groundwater radon from well #32 located in Sichuan province. Three models (including the LSTM (Long Short-Term Memory) model with auxiliary data, the EMD-LSTM (Empirical Mode Decomposition Long Short-Term Memory) model with auxiliary data, and the EMD-LSTM model without auxiliary data) were developed in order to predict groundwater radon variations. The results indicated that the prediction accuracy of the EMD-LSTM model was much higher than that of the LSTM model, and the EMD-LSTM model without auxiliary data also can obtain an ideal prediction result. Furthermore, the different durations of seismic activities T (T = ±10, ±30, ±50, and ±100) were also investigated by comparing the identification results. The identification rate of the precursor anomalies was the highest when T = ±30. The EMD-LSTM model identified five possible radon anomalies among the seven selected earthquakes. Taking well #32 as an example, we provided a promising method, that was the EMD-LSTM model, to detect the groundwater radon anomalies. It also suggested that the EMD-LSTM model can be used to identify the possible precursor anomalies within future studies.

Evaluation of Surface Reflectance Products Based on Optimized 6S Model Using Synchronous In Situ Measurements

Surface reflectance (SR) estimation is the most essential preprocessing step for multi-sensor remote sensing inversion of geophysical parameters. Therefore, accurate and stable atmospheric correction is particularly important, which is the premise and basis of the quantitative application of remote sensing. It can also be used to directly compare different images and sensors. The Landsat-8 Operational Land Imager (OLI) and Sentinel-2 Multi-Spectral Instrument (MSI) surface reflectance products are publicly available and demonstrate high accuracy. However, there is not enough validation using synchronous spectral measurements over China’s land surface. In this study, we utilized Moderate Resolution Imaging Spectroradiometer (MODIS) atmospheric products reconstructed by Categorical Boosting (CatBoost) and 30 m ASTER Global Digital Elevation Model (ASTER GDEM) data to adjust the relevant parameters to optimize the Second Simulation of Satellite Signal in the Solar Spectrum (6S) model. The accuracy of surface reflectance products obtained from the optimized 6S model was compared with that of the original 6S model and the most commonly used Fast Line-of-sight Atmospheric Analysis of Spectral Hypercubes (FLAASH) model. Surface reflectance products were validated and evaluated with synchronous in situ measurements from 16 sites located in five provinces of China: Fujian, Gansu, Jiangxi, Hunan, and Guangdong. Through the indirect and direct validation across two sensors and three methods, it provides evidence that the synchronous measurements have the higher and more reliable validation accuracy. The results of the validation indicated that, for Landsat-8 OLI and Sentinel-2 MSI SR products, the overall root mean square error (RMSE) calculated results of optimized 6S, original 6S and FLAASH across all spectral bands were 0.0295, 0.0378, 0.0345, and 0.0313, 0.0450, 0.0380, respectively. R2 values reached 0.9513, 0.9254, 0.9316 and 0.9377, 0.8822, 0.9122 respectively. Compared with the original 6S model and FLAASH model, the mean percent absolute error (MPAE) of the optimized 6S model was reduced by 32.20% and 15.86% for Landsat-8 OLI, respectively. On the other, for the Sentinel-2 MSI SR product, the MPAE value was reduced by 33.56% and 33.32%. For the two kinds of data, the accuracy of each band was improved to varying extents by the optimized 6S model with the auxiliary data. These findings support the hypothesis that reliable auxiliary data are helpful in reducing the influence of the atmosphere on images and restoring reality as much as is feasible.

A Convolutional Neural Network for Spatial Downscaling of Satellite-Based Solar-Induced Chlorophyll Fluorescence (SIFnet)

Gross primary productivity (GPP) is the sum of leaf photosynthesis and represents a crucial component of the global carbon cycle. Space-borne estimates of GPP typically rely on observable quantities that co-vary with GPP such as vegetation indices using reflectance measurements (e.g., NDVI, NIRv, and kNDVI). Recent work has also utilized measurements of solar-induced chlorophyll fluorescence (SIF) as a proxy for GPP. However, these SIF measurements are typically coarse resolution while many processes influencing GPP occur at fine spatial scales. Here, we develop a Convolutional Neural Network (CNN), named SIFnet, that increases the resolution of SIF from the TROPOspheric Monitoring Instrument (TROPOMI) on board of the satellite Sentinel-5P by a factor of 10 to a spatial resolution of 500 m. SIFnet utilizes coarse SIF observations together with high resolution auxiliary data. The auxiliary data used here may carry information related to GPP and SIF. We use training data from non-US regions between April 2018 until March 2021 and evaluate our CNN over the conterminous United States (CONUS). We show that SIFnet is able to increase the resolution of TROPOMI SIF by a factor of 10 with a r2 and RMSE metrics of 0.92 and 0.17 mW m−2 sr−1 nm−1, respectively. We further compare SIFnet against a recently developed downscaling approach and evaluate both methods against independent SIF measurements from Orbiting Carbon Observatory 2 and 3 (OCO-2/3). SIFnet performs systematically better than the downscaling approach (r = 0.78 for SIFnet, r = 0.72 for downscaling), indicating that it is picking up on key features related to SIF and GPP. Examination of the feature importance in the neural network indicates a few key parameters and the spatial regions these parameters matter. Namely, the CNN finds low resolution SIF data to be the most significant parameter with the NIRv vegetation index as the second most important parameter. NIRv consistently outperforms the recently proposed kNDVI vegetation index. Advantages and limitations of SIFnet are investigated and presented through a series of case studies across the United States. SIFnet represents a robust method to infer continuous, high spatial resolution SIF data.

Incorporating Auxiliary Data of Different Spatial Scales for Spatial Prediction of Soil Nitrogen Using Robust Residual Cokriging (RRCoK)

Auxiliary data has usually been incorporated into geostatistics for high-accuracy spatial prediction. Due to the different spatial scales, category and point auxiliary data have rarely been incorporated into prediction models together. Moreover, traditionally used geostatistical models are usually sensitive to outliers. This study first quantified the land-use type (LUT) effect on soil total nitrogen (TN) in Hanchuan County, China. Next, the relationship between soil TN and the auxiliary soil organic matter (SOM) was explored. Then, robust residual cokriging (RRCoK) with LUTs was proposed for the spatial prediction of soil TN. Finally, its spatial prediction accuracy was compared with that of ordinary kriging (OK), robust cokriging (RCoK), and robust residual kriging (RRK). Results show that: (i) both LUT and SOM are closely related to soil TN; (ii) by incorporating SOM, the relative improvement accuracy of RCoK over OK was 29.41%; (iii) by incorporating LUTs, the relative improvement accuracy of RRK over OK was 33.33%; (iv) RRCoK obtained the highest spatial prediction accuracy (RI = 43.14%). It is concluded that the recommended method, RRCoK, can effectively incorporate category and point auxiliary data together for the high-accuracy spatial prediction of soil properties.

Analysis of the Role of Female Hormones During Infection by COVID-19

Women have metabolic, immunological, and genetic variables that ensure more protection from coronavirus infection. However, the indication of treatment for several pathologies and contraception is determined by hormones that have adverse effects and raise doubts about their use during the COVID-19 pandemic. Therefore, the present study searches women specificities and the relation between female sexual hormones and COVID-19, and reports the main recommendations in this background. To this end, a review of the literature was conducted in the main databases, auxiliary data sources, and official websites. Therefore, considering the hypercoagulability status of COVID-19, the debate about the use of contraceptives due to the relative risk of thromboembolic effects that they impose arises. However, the current available evidence, as well as the recommendations of main health organs around the world, demonstrate that the use of hormonal contraceptives must be maintained during the pandemic.