Graph neural architecture search (NAS) has emerged as a promising approach for autonomously designing graph neural network architectures by leveraging correlations between graphs and architectures. However, existing methods merely rely on correlations, which may be spurious and vary across distributions. This reliance, without considering causal graph-architecture relationships, limits their ability to generalize under distribution shifts that are ubiquitous in real-world graph scenarios. In this paper, we propose to handle the distribution shifts in NAS process by exploiting the causal graph-architecture relationship to search for optimal architectures that can generalize under distribution shifts. Key challenges remain unexplored: discovering causal graph-architecture relationships with stable cross-distribution predictive abilities, and leveraging them to handle distribution shifts. To address these challenges, we propose a novel approach, Causal-aware Graph Neural Architecture Search (CARNAS), which is capable of capturing causal graph-architecture relationship during NAS process and discovering optimal graph architecture under distribution shifts. We propose Disentangled Causal Subgraph Identification to extract causal subgraphs with stable predictive power across distributions, followed by Graph Embedding Intervention to intervene on these subgraphs in latent space by preserving essential features while filtering out non-causal elements, and Invariant Architecture Customization to enhance their causal invariance for optimizing graph architectures. Extensive experiments on synthetic and real-world datasets show that CARNAS enhances out-of-distribution generalization by uncovering causal graph-architecture relationships during NAS.

Accurate and high spatiotemporal resolution water quality data are critical for the effective management of marine and coastal ecosystems. However, accurate atmospheric correction under high solar zenith angles (SZA) remains a challenge, introducing substantial uncertainties in satellite-derived water quality indicators (WQI) under high SZA. With an attempt to fill the gap, this study evaluated three types of strategies for satellite retrieval of suspended particulate matter (SPM) and chlorophyll-a (Chl-a) concentrations from top-of-atmosphere reflectance (ρt), Rayleigh-corrected reflectance (ρrc) and remote sensing reflectance (Rrs), respectively. The models, named XGBWQI, based on three types of remote sensing data were tested with in-situ data and compared with the Geostationary Ocean Color Imager (GOCI) standard algorithms. Results showed that: (i) ρt-based XGBWQI had the best accuracy (R2= 0.90 and MAPD = 14.65% for SPM, R2= 0.85 and MAPD = 5.34% for Chl-a); (ii) model testing results with in-situ data also confirmed the advantage of ρt-based XGBWQI over other models (R2= 0.88, MAPD = 26.9% and MRPD =11.8% for SPM, R2= 0.78, MAPD = 43.3% and MRPD = -15.5% for Chl-a); and (iii) the XGBWQI models obtained more valid WQI values for GOCI images under high SZA and successfully revealed the diurnal variations of a red tide event in the Yellow Sea and the SPM dynamics in the East China Sea. Therefore, ρt-based XGBWQI models were recommended as the best strategy for satellite retrievals of WQI under high SZA. The methods can serve as an effective tool in retrieving WQI in coastal waters under high SZA, and thus contribute to better and high-frequency water quality monitoring.

In the field of Artificial Intelligence for Information Technology Operations, causal discovery is pivotal for operation and maintenance of systems, facilitating downstream industrial tasks such as root cause analysis. Temporal causal discovery, as an emerging method, aims to identify temporal causal relations between variables directly from observations by utilizing interventional data. However, existing methods mainly focus on synthetic datasets with heavy reliance on interventional targets and ignore the textual information hidden in real-world systems, failing to conduct causal discovery for real industrial scenarios. To tackle this problem, in this paper we investigate temporal causal discovery in industrial scenarios, which faces two critical challenges: how to discover causal relations without the interventional targets that are costly to obtain in practice, and how to discover causal relations via leveraging the textual information in systems which can be complex yet abundant in industrial contexts. To address these challenges, we propose the RealTCD framework, which is able to leverage domain knowledge to discover temporal causal relations without interventional targets. We first develop a score-based temporal causal discovery method capable of discovering causal relations without relying on interventional targets through strategic masking and regularization. Then, by employing Large Language Models (LLMs) to handle texts and integrate domain knowledge, we introduce LLM-guided meta-initialization to extract the meta-knowledge from textual information hidden in systems to boost the quality of discovery. We conduct extensive experiments on both simulation datasets and our real-world application scenario to show the superiority of our proposed RealTCD over existing baselines in temporal causal discovery.

In estuarine-coastal-shelf seas, particulate organic carbon (POC) shows the highest turnover rates of any organic carbon pool on the planet, playing a key role in the biological carbon pump. Compared with open ocean, estuarine and coastal waters are affected by large river inputs and show high hydrodynamic variability, which results in a mixture of diverse particles that includes inorganic mineral particles, living algal particles, and organic detritus. The highly complex and variable particle compositions in estuarine-coastal-shelf waters pose significant challenges in assessing their distinct roles in the carbon cycle and total POC. To overcome challenges, we collected biogeochemical and optical in situ data from 2014 to 2020 in estuarine-coastal-shelf waters of eastern China, which is one of the largest estuarine-coastal-shelf systems in the world, to develop an algorithm that can optically discriminate particle composition and estimate their respective contributions to POC. The algorithm combines the quasi-analytical algorithm and the semi-empirical radiative transfer algorithm to estimate total suspended particle concentrations and the mass fraction of organic particles from which both phytoplankton- and detritus-related POC fractions are derived. Compared to existing POC algorithms, this algorithm shows improved retrievals compared to in situ counterparts, with$r^{2}$and root mean squared error (RMSE) values of 0.84 and$16.57~\mu \text{g}~\text{L}^{-1}$, respectively. The algorithm is also applied to Sentinel-3/ocean and land color instrument (OLCI) images for the year of 2020. Applying the particle component discrimination method can enhance our understanding of the roles of different particle compositions in coastal carbon cycling affected by strong land-sea exchange.

Causal learning from observational data has garnered attention as controlled experiments can be costly. To enhance identifiability, incorporating intervention data has become a mainstream approach. However, these methods have yet to be explored in the context of time series data, despite their success in static data. To address this research gap, this paper presents a novel contribution. Firstly, a temporal interventional dataset with causal labels is introduced, derived from a data center IT room of a cloud service company. Secondly, this paper introduces TECDI, a novel approach for temporal causal discovery. TECDI leverages the smooth, algebraic characterization of acyclicity in causal graphs to efficiently uncover causal relationships. Experimental results on simulated and proposed real-world datasets validate the effectiveness of TECDI in accurately uncovering temporal causal relationships. The introduction of the temporal interventional dataset and the superior performance of TECDI contribute to advancing research in temporal causal discovery. Our datasets and codes have released at~\hrefhttps://github.com/lpwpower/TECDI https://github.com/lpwpower/TECDI.

The problem of reconstructing nonlinear and complex dynamical systems from available data or time series is prominent in many fields, including engineering, physical, computer, biological, and social sciences. Many methods have been proposed to address this problem and their performance is satisfactory. However, none of them can reconstruct network structure from large-scale real-time streaming data, which leads to the failure of real-time and online analysis or control of complex systems. In this article, to overcome the limitations of current methods, we first extend the network reconstruction problem (NRP) to online settings, and then develop a follow-the-regularized-leader (FTRL)-Proximal style method to address the online complex NRP; we refer to it as Online-NR. The performance of Online-NR is validated on synthetic evolutionary game network reconstruction datasets and eight real-world networks. The experimental results demonstrate that Online-NR can effectively solve the problem of online network reconstruction with large-scale real-time streaming data. Moreover, Online-NR outperforms or matches nine state-of-the-art network reconstruction methods.

Since 1990s, Airborne Hyperspectral imagers have been developed in China. The Pushbroom Hyperspectral Imager (PHI) was designed with fully adjustable integration time and scan rate, low readout noise, and high high-speed frame-shifted surface array CCD, covering the visible and near-infrared spectra with spectral resolution of 5 nm (Li et al., 2006). The Operational Modular Imaging Spectrometer (OMIS) was a whiskbroom imager, covering wide domain, including near-infrared, short-wave infrared, mid-wave infrared, and thermal infrared spectra. In 2008, HyperSpectral Imager (HSI) was first equipped on satellites HJ-1A for environment and disaster monitoring, which has 110-128 spectral bands covering the 450-950 nm, with the spatial resolution of 100 m, the spectral resolution of 4.5 nm, and the swath width of 50 km. Recently, the Advanced Hyperspectral Imager (AHSI) equipped on GaoFen-5 (GF-5) was launched in May 2018, with wide coverage and spectral band (i.e., 60 km swath width and 30 m spatial resolution). The GF-5/AHSI has 150 bands in the visible and near-infrared range (400-1000 nm) with spectral resolution of 5 nm and signal-to-noise ratio between 150 and 700, and 180 bands in the short-wave infrared range (1000-2500 nm) with spectral resolution of 10 nm and signal-to-noise ratio between 150 and 500 (Liu et al. 2020).

The problem of inferring nonlinear and complex dynamical systems from available data is prominent in many fields, including engineering, biological, social, physical, and computer sciences. Many evolutionary algorithm (EA)-based network reconstruction methods have been proposed to address this problem, but they ignore several useful information of network structure, such as community structure, which widely exists in various complex networks. Inspired by the community structure, this article develops a community-based evolutionary multiobjective network reconstruction framework to promote the reconstruction performance of EA-based network reconstruction methods due to their good performance; we refer this framework as CEMO-NR. CEMO-NR is a generic framework and any population-based multiobjective metaheuristic algorithm can be employed as the base optimizer. CEMO-NR employs the community structure of networks to divide the original decision space into multiple small decision spaces, and then any multiobjective EA (MOEA) can be used to search for improved solutions in the reduced decision space. To verify the performance of CEMO-NR, this article also designs a test suite for complex network reconstruction problems. Three representative MOEAs are embedded into CEMO-NR and compared with their original versions, respectively. The experimental results have demonstrated the significant improvement benefiting from the proposed CEMO-NR in 30 multiobjective network reconstruction problems (MONRPs).

Fuzzy cognitive maps (FCMs) have been successfully applied to time series forecasting. However, it still remains challenging to handle multivariate long nonstationary time series, such as EEG data, which may change rapidly and have patterns of trend. To overcome this limitation, in this article, we propose a fast prediction model to deal with multivariate long nonstationary time series based on the combination of elastic net and high order fuzzy cognitive map (HFCM), which is termed as ElasticNetHFCM. The designed FCM models each variable by one node and the high-order FCM helps to capture the patterns of trend. A case study on predicting human actions through the Electroencephalogram (EEG) data in the form of multichannel long nonstationary time series is investigated based on the proposed prediction model. Specifically, we first predict EEG signals based on the historical data, then a 1D-convolutionary neural network (1D-CNN) is developed to classify the predicted time series. The experimental results on the Grasp-and-Lift dataset show that the proposal can predict the EEG data with lower prediction error compared with the other regression methods. The area under the curve scores obtained on the Grasp-and-Lift dataset by 1D-CNN are higher than those obtained by state-of-the-art classification methods for EEG data in most cases. These results illustrate that the proposal can predict and classify multivariate long nonstationary time series with high accuracy and efficiency.

The fuzzy cognitive map (FCM) is an effective tool for modeling and simulating complex dynamic systems. The research on the problem of learning FCM from the available time series is outstanding. Many batch FCM learning methods have been proposed to address this issue and the performance of these methods is satisfactory. However, these batch-learning methods are difficult to cope with large-scale data sets (for example, the memory in computers is not enough to store all instances) and real-time streaming data, leading to the failure of real-time and online analysis of complex systems. In this article, unlike the existing batch learning methods, such as evolutionary and regression-based methods, we first extend the FCM learning to an online setting, and then develop an effective algorithm based on a follow-the-regularized-leader (FTRL)-proximal style learning algorithm to address the online FCM learning problem, termed as OFCM. The performance of OFCM is validated on constructed benchmark data sets, including synthetic data sets, and gene regulatory network reconstruction data sets. The experimental results demonstrate the merits of OFCM, which can effectively solve online FCM learning problems.

Learning large-scale fuzzy cognitive maps (FCMs) with the sparse attribute automatically from time series without prior knowledge remains a challenging problem. Most existing automated learning methods were applied to learn small-scale FCMs, and the learned FCMs are much denser than the maps constructed by human experts. Learning FCMs is the procedure of judging whether there are connecting edges and determining the weights of connecting edges. Thus, we transform the problem of learning FCMs into a biobjective optimization problem with two objects of minimizing the measure error and the number of nonzero entries, respectively. To solve this optimization problem, a preference-based iterative thresholding evolutionary biobjective optimization algorithm for learning FCMs is proposed. The strategy focuses on the knee area of the Pareto front (PF) with preference on the solutions near the true sparsity. Moreover, an initialization operator based on random forest is proposed to increase the speed of convergence toward the PF. The experiments on large-scale synthetic data with varying sizes and densities and the application to the gene regulatory network reconstruction problem have been conducted to demonstrate that our proposal matches or exceeds the existing state-of-the-art FCM learning approaches in most cases in terms of four measures, namely, Data_Error, Out_of_Sample_Error, Model Error, and SS_Mean. The Data_Error obtained by the proposed method can achieve 3.07E-06 even when the number of nodes reaches 200. We also demonstrate the effectiveness of the proposed initialization operator and the preference-based strategy, which can result in a fast convergence speed and higher accuracy.

How to build a generic deep one-class (DeepOC) model to solve one-class classification problems for anomaly detection, such as anomalous event detection in complex scenes? The characteristics of existing one-class labels lead to a dilemma: it is hard to directly use a multiple classifier based on deep neural networks to solve one-class classification problems. Therefore, in this article, we propose a novel DeepOC neural network, termed as DeepOC, which can simultaneously learn compact feature representations and train a DeepOC classifier. Only with the given normal samples, we use the stacked convolutional encoder to generate their low-dimensional high-level features and train a one-class classifier to make these features as compact as possible. Meanwhile, for the sake of the correct mapping relation and the feature representations' diversity, we utilize a decoder in order to reconstruct raw samples from these low-dimensional feature representations. This structure is gradually established using an adversarial mechanism during the training stage. This mechanism is the key to our model. It organically combines two seemingly contradictory components and allows them to take advantage of each other, thus making the model robust and effective. Unlike methods that use handcrafted features or those that are separated into two stages (extracting features and training classifiers), DeepOC is a one-stage model using reliable features that are automatically extracted by neural networks. Experiments on various benchmark data sets show that DeepOC is feasible and achieves the state-of-the-art anomaly detection results compared with a dozen existing methods.

Although the obtained accuracy on some lab-controlled facial expression datasets has been very high, the recognition of facial expressions in wild environments is still a challenging problem. Local Binary Patterns (LBP) is a widely used operator in facial expression recognition. However, there are few variations of LBP operators specifically designed for facial expression recognition. In this paper, we propose a novel representation approach called the Double Complete d-LBP (Double Cd-LBP) according to the characteristics of facial expressions. Two d-LBP are employed to represent details and the contour of faces separately, and complete LBP is used to take sign and magnitude components into account. Moreover, multi-scale LBP is exploited to obtain local texture and global information. We then use the extreme learning machine auto-encoder (ELM-AE) as the feature selection approach to learn the discriminative feature. Cascade forest is employed as the final decision classifier. Experiments conducted on the six facial expression databases, including both lab-controlled and wild environments databases, show that our method outperforms or on par with state-of-the-arts.