Chengzu Bai

National University of Defense Technology | NUDT · College of Meteorology and Oceanography

High-resolution synthetic aperture radars (SARs) are becoming an indispensable environmental monitoring system to capture the important geophysical phenomena on the earth and sea surface. However, there is a lack of comprehensive models that can orchestrate such large-scale datasets from numerous satellite missions such as GaoFen-3 and Sentinel-1....

Previously the interannual variability of tropical cyclone genesis (TCG) in the Australian region has mainly been attributed to the climate variability in the Pacific and Indian Oceans. In this study, we found that the influence from climate variability in the Atlantic is of equal importance. Application of a state-of-the-art causality analysis rev...

The ability of synthetic aperture radar (SAR) to capture maritime phenomena is widely acknowledged. However, ocean SAR scene automatic classification remains challenging due to speckle noise interference, the nonlinearities and poor distinguishability of different geophysical phenomena. Kernel entropy component analysis (KECA) was recently proposed...

Sea surface temperature (SST) fronts are important for fisheries and marine ecology, as well as upper ocean dynamics, weather forecasting and climate monitoring. In this paper, we propose a new approach to detect SST fronts from RADARSAT-2 ScanSAR images, based on the correlation of SAR-derived wind speeds using the gray level co-occurrence matrix...

Multivariate hydrological frequency analysis is important when designing hydraulic and civil infrastructures. However, hydrologic data scarcity and insufficiency are common. By studying the relationship between copula entropy and total correlation estimated by the matrix-based Renyi's α-order entropy functional, a new estimation method (total corre...

Assimilation systems absorb both satellite measurements and Argo observations. This assimilation is essential to diagnose and evaluate the contribution from each type of data to the reconstructed analysis, allowing for better configuration of assimilation parameters. To achieve this, two comparative reconstruction schemes were designed under the op...

The algorithms based on Surface Quasi-Geostrophic (SQG) dynamics have been developed and validated by many researchers through model products, however it is still doubtful whether these SQG-based algorithms are worth using in terms of observed data. This paper analyzes the factors impeding the practical application of SQG and makes amends by a simp...

It is necessary to evaluate satellite sea surface salinity (SSS) L3 products prior to using them to analyze SSS variability. Instead of performing comparison analysis on the accuracy of products (e.g., Root Mean Square Deviation (RMSD)), two new evaluation methods, information entropy and local variance, are introduced to assess the performance of...

Multivariate hydrological series become nonstationary under the changing environment. In this paper, a new method is proposed to study the change in the dependence structure between runoff and sediment sequences. First, a moving cut transfer entropy is proposed to detect the sudden change point in the dependence structure between runoff and sedimen...

The North Pacific sea surface salinity (SSS) decadal variation (NPSDV) plays key roles in tracing ocean circulation and hydrological cycle, and its contributing climate modes need to be identified. Three data sets, ORAS4, EN4.2.1, and GODAS, were first evaluated. An autoregressive lag 1 (AR‐1) process model, along with spectrum and correlation anal...

Principal component analysis (PCA) and its variations are still the primary tool for feature extraction (FE) in remote sensing community. This is unfortunate, as there has been strong argument against using PCA for this purpose due to its inherent linear properties and uninformative principal components. Therefore, several critical issues still sho...

Kernel Low-Rank Entropic Component Analysis for Hyperspectral Image Classification

The ability to predict the risk of water shortage is critical, and therefore it is important to develop methods of parameter estimation for statistical models in situations when insufficient data are available. Based on the maximum entropy principle, this paper proposes an alternative method of parameter estimation for a logistic regression model i...

Kernel entropy component analysis (KECA) is a recently proposed dimensionality reduction approach, which has showed superiority in many pattern analysis algorithms previously based on principal component analysis (PCA). The optimized KECA (OKECA) is a state-of-the-art extension of KECA and can return projections retaining more expressive power than...

The ordered clustering problem in the context of multicriteria decision aid has been increasingly examined in management science and operational research during the past few years. However, the existing clustering algorithms may not provide an exact suggestion for a partition number for decision makers by using the diagram method. In addition, thes...

An improved scoring search algorithm based on information flow is proposed for Bayesian network structure learning. Firstly, the 0/1 optimization problem is constructed based on the information flow for global causal analysis, and the optimal initial network structure is obtained. Then, the search space is generated based on the initial structure,...

In drought years, it is important to have an estimate or prediction of the probability that a water shortage risk will occur to enable risk mitigation. This study developed an improved logistic probability prediction model for water shortage risk in situations when there is insufficient data. First, information flow was applied to select water shor...

How to extract the causal relations in climate-cyclone interactions is an important problem in atmospheric science. Traditionally, the most commonly used research methodology in this field is time-delayed correlation analysis. This may be not appropriate, since a correlation cannot imply causality, as it lacks the needed asymmetry or directedness b...

Software defect prediction plays a significant part in identifying the most defect-prone modules before software testing. Quite a number of researchers have made great efforts to improve prediction accuracy. However, the problem of insufficient historical data available for within- or cross- project still remains unresolved. Further, it is common p...

A formal Bayesian approach that uses the Markov Chain Monte Carlo method to estimate the uncertainties of natural hazards has attracted significant attention in recent years, and a fuzzy graph can be considered an estimation of the relationship that we want to know in risk systems. However, the challenge with such approaches is to sufficiently cons...

The theory of probabilistic linguistic term sets (PLTSs) is very useful in dealing with the multi-criteria decision making (MCDM) problems in which there is hesitancy in providing linguistic assessments; and PLTSs allow experts to express their preferences on one linguistic term over another. The existing approaches associated with PLTSs are limite...

Determining OWA (ordered weighted averaging) weights has received more and more attention since the appearance of the OWA operator. Based on the principle of least mean squared errors, a new parametric OWA operator is proposed to obtain its associated weights. In coordination with fuzzy inference and a few of judgments on weights provided by decisi...

In this paper, to naturally fill the gap in incomplete data, a new algorithm is proposed for estimating the risk of natural disasters based on the information diffusion theory and the equation of the vibrating string. Two experiments are performed with small samples to investigate its effectiveness. Furthermore, to demonstrate the practicality of t...

Abnormal Western Pacific subtropical high (WPSH) activities often lead to extreme weather events in East Asia in some years. The relationship between the WPSH and the members of the East Asian summer monsoon (EASM) system is unknown, however. So the forecasting of abnormal WPSH activities is still difficult. Because of adaptive learning and nonline...

With the objective of tackling the problem of inaccurate long-term western pacific subtropical high (WPSH) forecasts, based on the concept of dynamical model reconstruction and improved self-memorization principle, a new dynamical forecasting model of WPSH area (SI) index is developed. To overcome the problem of single initial prediction value, the...

The identification of the rainfall-runoff relationship is a significant precondition for surface-atmosphere process research and operational flood forecasting, especially in inadequately monitored basins. Based on an information diffusion model (IDM) improved by a genetic algorithm, a new algorithm (GIDM) is established for interpolating and foreca...

Aiming at tackling the difficulty in establishing a sea surface temperature (SST) dynamical model, this study develops a non-linear dynamical–statistical model of SST fields and their correlative factors based on Genetic Algorithms (GA) and the dynamical system reconstruction idea, which greatly improves the El Niño–Southern Oscillation (ENSO) fore...