Sea surface temperature (SST) has important practical value in ocean related fields. Numerical prediction is a common method for forecasting SST at present. However, the forecast results produced by ...the numerical forecast models often deviate from the actual observation data, so it is necessary to correct the bias of the numerical forecast products. In this paper, an SST correction approach based on the Convolutional Long Short-Term Memory (ConvLSTM) network with multiple attention mechanisms is proposed, which considers the spatio-temporal relations in SST data. The proposed model is appropriate for correcting SST numerical forecast products by using satellite remote sensing data. The approach is tested in the region of the South China Sea and reduces the root mean squared error (RMSE) to 0.35 °C. Experimental results reveal that the proposed approach is significantly better than existing models, including traditional statistical methods, machine learning based methods, and deep learning methods.
Sea surface temperature (SST) prediction has attracted increasing attention, due to its crucial role in understanding the Earth’s climate and ocean system. Existing SST prediction methods are ...typically based on either physics-based numerical methods or data-driven methods. Physics-based numerical methods rely on marine physics equations and have stable and explicable outputs, while data-driven methods are flexible in adapting to data and are capable of detecting unexpected patterns. We believe that these two types of method are complementary to each other, and their combination can potentially achieve better performances. In this paper, a space-time partial differential equation (PDE) is employed to form a novel physics-based deep learning framework, named the space-time PDE-guided neural network (STPDE-Net), to predict daily SST. Comprehensive experiments for SST prediction were conducted, and the results proved that our method could outperform the traditional finite-difference forecast method and several state-of-the-art deep learning and physics-guided deep learning methods.
In this paper, we study the dynamics property of a stochastic HIV model with Beddington–DeAngelis functional response. It has a unique uninfected steady state. We prove that the model has a unique ...global positive solution. Furthermore, if the basic reproductive number is not larger than 1, the asymptotic behavior of the solution is stochastically stable. Otherwise, it fluctuates randomly around the infected steady state of the corresponding deterministic HIV model. Finally, some numerical simulations are carried out to verify our results.
Genetic factors have a certain proportion in the risk factors of hypertension. The purpose was to investigate the relationship of cytochrome P450 2C19 (CYP2C19) polymorphisms with hypertension in ...Hakka population.
The study included 1,872 hypertensive patients and 1,110 controls. The genotypes of CYP2C19 rs4244285 and rs4986893 of all individuals were detected and analyzed.
The genotype and allele distributions of CYP2C19 rs4244285 were significantly different between hypertension group and control group. The CYP2C19 *1/*1 genotype was the most predominant among the subjects (40.8%), followed by the CYP2C19 *1/*2 genotype (40.5%). The percentage of CYP2C19*1, *2, and *3 allele was 64.2%, 30.8%, and 5.0%, respectively. The proportion of intermediate metabolizers (IM) (49.3% vs. 42.9%), poor metabolizers (PM) (14.3% vs. 8.9%) (P < 0.001), and CYP2C19*2 allele (33.8% vs. 25.7%, P < 0.001) in hypertension group was significantly higher than that in control group. Multivariate logistic regression (adjusted for gender, age, smoking, and drinking) indicated that CYP2C19 *1/*2, *1/*3, and *2/*2 genotypes may increase susceptibility to hypertension. And the CYP2C19 IM genotype (IM vs. EM: OR 1.514, 95% CI: 1.291-1.775, P < 0.001), PM genotype (PM vs. EM: OR 2.120, 95% CI: 1.638-2.743, P < 0.001), IM + PM genotypes (IM + PM vs. EM: OR 1.617, 95% CI: 1.390-1.882, P < 0.001) may increase risk of hypertension.
CYP2C19 loss-of-function (IM, PM genotypes) is independent risk factor for hypertension susceptibility. Specifically, the risk genotypes include CYP2C19 *1/*2, *1/*3, and *2/*2.
Arteriosclerosis in multiple arteries has long been associated with heightened cardiovascular risk. Acetaldehyde dehydrogenase 2 (ALDH2) and methylenetetrahydrofolate reductase (MTHFR) play an ...important role in the pathogenesis of arteriosclerosis by participating in the oxidation and reduction reactions in vascular endothelial cells. The purpose was to investigate the relationship of ALDH2 and MTHFR gene polymorphisms with arteriosclerosis in multiple arteries.
410 patients with arteriosclerosis in single artery and 472 patients with arteriosclerosis in multiple arteries were included. The relationship between ALDH2 rs671 and MTHFR rs1801133 polymorphisms and arteriosclerosis in single artery and arteriosclerosis in multiple arteries was analyzed.
The proportion of ALDH2 rs671 A allele (35.6% vs. 30.9%, P = 0.038) and MTHFR rs1801133 T allele (32.6% vs. 27.1%, P = 0.012) in patients with arteriosclerosis in multiple arteries was significantly higher than that in arteriosclerosis in single artery, respectively. The proportion of history of alcohol consumption in patients with ALDH2 rs671 G/G genotype was higher than those in ALDH2 rs671 G/A genotype and A/A genotype (P < 0.001). The results of logistic regression analysis indicated that ALDH2 rs671 A/A genotype (A/A vs. G/G: OR 1.996, 95% CI: 1.258-3.166, P = 0.003) and MTHFR rs1801133 T/T genotype (T/T vs. C/C: OR 1.943, 95% CI: 1.179-3.203, P = 0.009) may be independent risk factors for arteriosclerosis in multiple arteries (adjusted for age, sex, smoking, drinking, hypertension, and diabetes).
ALDH2 rs671 A/A and MTHFR rs1801133 T/T genotypes may be independent risk factors for arteriosclerosis in multiple arteries.
Advances in data assimilation (DA) methods and the increasing amount of observations have continuously improved the accuracy of initial fields in numerical weather prediction during the last decades. ...Meanwhile, in order to effectively utilize the rapidly increasing data, Earth scientists must further improve DA methods. Recent studies have introduced machine learning (ML) methods to assist the DA process. In this paper, we explore the potential of a four‐dimensional variational (4DVar) constrained neural network (NN) method for accurate DA. Our NN is trained to approximate the solution of the variational problem, thereby avoiding the need for expensive online optimization when generating the initial fields. In the context that the full‐field system truths are unavailable, our approach embeds the system's kinetic features described by a series of analysis fields into the NN through a 4DVar‐form loss function. Numerical experiments on the Lorenz96 physical model demonstrate that our method can generate better initial fields than most traditional DA methods at a low computational cost, and is robust when assimilating observations with higher error outside of the distributions where it is trained. Furthermore, our NN‐based DA model is effective against Lorenz96 physical models with larger variable numbers. Our approach exemplifies how ML methods can be leveraged to improve both the efficiency and accuracy of DA techniques.
Plain Language Summary
The use of machine learning (ML) to approximate mappings from data has made a significant impact on numerical weather prediction. In the data assimilation (DA) process, several recent studies have applied ML to accelerate or improve the accuracy of DA output. In this paper, we investigate the potential of employing physical constraints based on four‐dimensional variational (4DVar) DA to further enhance the accuracy of an end‐to‐end ML‐based DA model. Our objective is to determine whether the 4DVar‐constrained ML model can perform the DA task more efficiently and produce comparable accuracy to the traditional DA methods. We trained our NN‐based model without true values as labels and tested it on the Lorenz96 physical model. Several experiments have been applied to verify that the 4DVar‐constrained ML model can be used as a potential substitute for the DA process.
Key Points
A physics‐informed neural network trained without ground truths can provide accurate initial fields for numerical predictions
The system's kinetic features are embedded into the model through our four‐dimensional variational form loss function
We show on Lorenz96 that the proposed method can be used directly for accurate data assimilation as a low computational cost
Nowadays, people are usually involved in multiple heterogeneous social networks simultaneously. Discovering the anchor links between the accounts owned by the same users across different social ...networks is crucial for many important inter-network applications, e.g., cross-network link transfer and cross-network recommendation. Many different supervised models have been proposed to predict anchor links so far, but they are effective only when the labeled anchor links are abundant. However, in real scenarios, such a requirement can hardly be met and most anchor links are unlabeled, since manually labeling the inter-network anchor links is quite costly and tedious. To overcome such a problem and utilize the numerous unlabeled anchor links in model building, in this paper, we introduce the active learning based anchor link prediction problem. Different from the traditional active learning problems, due to the
on anchor links, if an unlabeled anchor link a = ( u , v ) is identified as positive (i.e., existing), all the other unlabeled anchor links incident to account
or account
will be negative (i.e., non-existing) automatically. Viewed in such a perspective, asking for the labels of potential positive anchor links in the unlabeled set will be rewarding in the active anchor link prediction problem. Various novel anchor link information gain measures are defined in this paper, based on which several constraint active anchor link prediction methods are introduced. Extensive experiments have been done on real-world social network datasets to compare the performance of these methods with state-of-art anchor link prediction methods. The experimental results show that the proposed
method can outperform other methods with significant advantages.
Nowadays, people are overwhelmingly exposed to various kinds of information from different information networks. In order to recommend users with the information entities that match their interests, ...many recommendation methods have been proposed so far. And some of these methods have explored different ways to utilize different kinds of auxiliary information to deal with the information sparsity problem of user feedbacks. However, as a special kind of information sparsity problem, the "cold start" problem is still a big challenge not well-solved yet in the recommendation problem. In order to tackle the "cold start" challenge, in this paper, we propose a novel recommendation model, which integrates the auxiliary information in multiple heterogeneous information networks (HINs), namely the Cross-HIN Recommendation System (CHRS) . By utilizing the rich heterogeneous information from meta-paths, the CHRS is able to calculate the similarities of information entities and apply the calculated similarity scores in the recommendation process. For the information entities shared among multiple information networks, CHRS transfers item latent information from other networks to help the recommendation task in a given network. During the information transfer process, CHRS applies a domain adaptation matrix to tackle the domain difference problem. We conduct experiments to compare our CHRS method with several widely employed or the state-of-art recommendation models, and the experimental results demonstrate that our method outperforms the baseline methods in addressing the "cold start" recommendation problem.
Evaporation ducts are a particular type of atmospheric stratification that frequently appears on the sea surface. The accurate and timely prediction of the evaporation duct height (EDH) is ...significant for the practical application of electromagnetic communication equipment. Due to the typical time-series (TS) characteristics of the measured evaporation duct data, we construct an EDH prediction model based on a long short-term memory network (LSTM-EDH model) for the first time. The experimental results show that the LSTM-EDH model's root-mean-square error (RMSE) is dramatically reduced and can achieve a better fit of the measured EDH compared with the Babin-Young-Carton (BYC), Naval-Postgraduate-School (NPS), and eXtreme Gradient Boosting (XGB) EDH models. Compared with the XGB model, the generalization ability is also greatly improved.
•We propose a general-purpose nonlinear dimensionality reduction method named Vec2vec by extending the representation learning of words to numeric matrices, which has lower computational complexity ...than most existing dimensionality reduction methods on high-dimensional data.•We design a tailored objective function to preserve the pairwise similarities of data points and define the contexts of data points as random walk sequences in the neighborhood similarity graph, which serve as samples for model training.•We propose a more lightweight adaption of Vec2vec, which is referred to as AVec2vec. AVec2vec further reduces the computational complexity of Vec2vec with marginal loss in structural information.•We conduct extensive experiments for data classification and clustering on nine popular real-world image and text datasets to evaluate the performance of our method. The results show that Vec2vec outperforms several state-of-the-art dimensionality reduction methods in statistical hypothesis tests, and is more efficient than UMAP on high-dimensional data. The results also show that AVec2vec needs less computational time than Vec2vec with little performance loss in data classification and clustering tasks.
Dimensionality reduction has many applications in data visualization and machine learning. Existing methods can be classified into global ones and local ones. The global methods usually learn the linear relationship in data, while the local ones learn the manifold intrinsic geometry structure, which has a significant impact on pattern recognition. However, most of existing local methods obtain an embedding with eigenvalue or singular value decomposition, where the computational complexities are very high in a large amount of high-dimensional data. In this paper, we propose a local nonlinear dimensionality reduction method named Vec2vec, which employs a neural network with only one hidden layer to reduce the computational complexity. We first build a neighborhood similarity graph from the input matrix, and then define the context of data points with the random walk properties in the graph. Finally, we train the neural network with the context of data points to learn the embedding of the matrix. We conduct extensive experiments of data classification and clustering on nine image and text datasets to evaluate the performance of our method. Experimental results show that Vec2vec is better than several state-of-the-art dimensionality reduction methods, except that it is equivalent to UMAP on data clustering tasks in the statistical hypothesis tests, but Vec2vec needs less computational time than UMAP in high-dimensional data. Furthermore, we propose a more lightweight method named Approximate Vec2vec (AVec2vec) with little performance degradation, which employs an approximate method to build the neighborhood similarity graph. AVec2vec is still better than some state-of-the-art local dimensionality reduction methods and competitive with UMAP on data classification and clustering tasks in the statistical hypothesis tests.
PDF
