El Niño Southern Oscillation (ENSO) event is characterized by sea surface temperature (SST) anomalies in the tropical Pacific and mainly identified with Oceanic Index (ONI). ENSO forecasting very challenging owing to existence of predictability barrier chaos climate variability. Recently, machine learning approaches have received considerable attention besides conventional numerical models for this task. However, these existing works mostly focus on investigating single ONI data, neglecting...

Abstract Continuing the tropical Pacific multivariate air‐sea coupler proposed by us before, we design Global spatial‐temporal Teleconnection Coupler (GTC), which is modeled to discover latent teleconnections among global sea surface temperature (SST). To this end, Pacific, Indian, and Atlantic oceans are divided into small ocean patches that compose a dynamics graph, in adjacent relationships artificially constructed prior knowledge non‐adjacent learned from data deep learning methods....

Focuses on modeling, parameter estimation, and control for a heavy-duty electrohydraulic manipulator of harvester machine. The linear-graph method is implemented in deriving mathematical models the swing, boom stick subsystems. Actuation dynamics are subsequently integrated with to result complete machine model. Identification procedures employed estimating physical parameters discussed detail key results supplied. Model validation studies show good agreement between model predictions...

In this paper, a Physics-Informed Red Tide forecast model (PIRT) considering causal-inferred predictors selection is proposed. Specifically, the directed acyclic graph-graph neural network (DAG-GNN) method first applied to quantify causality among multiple ocean-atmosphere-biology variables for selecting most significant of red tides (or other chlorophyll variations). Then, encoder-decoder consisting an Energy Attention Module (EAM) built daily tide forecasting. The multi-sourced...

QoS prediction has become an important step in service recommending and selecting. Most approaches are using collaborative filtering as a technique. But may suffer from data sparsity problem which degrade the accuracy. In order to alleviate of filtering, we presented hybrid approach by applying clustering on web services before (named prediction, SCQP). The process cluster clusters have same physical environment. Then similarity between users is calculated based these instead individual...

The North Atlantic Oscillation (NAO) is a major climatic phenomenon in the Northern Hemisphere, but underlying air–sea interaction and physical mechanisms remain elusive. Despite successful short-term forecasts using physics-based numerical models, longer-term of NAO continue to pose challenge. In this study, we employ advanced data-driven causal discovery techniques explore causality between multiple ocean–atmosphere processes NAO. We identify best predictors based on analysis develop...

Abstract DBSCAN is a popular tool to analyse datasets which can effectively discover clusters with arbitrary shapes. However, it requires two input parameters are difficult be determined, according the fact that performance of clustering result depends heavily on user-specified parameters. In addition, uses global not appropriate those multi-density datasets. Aiming at these problems, we propose parameter-free algorithm perform different density-level We select some classical and TLC taxi...

This paper aims to get initial trust value of direct and recommender trust. Firstly, we gives domain representations for information structure; then defines purpose as class with properties, computes subordinate degree each property rank based on fuzzy sets. For evaluating trust, calculate correlation coefficient; establish a reasonable basic probability assignment property; merge functions all properties using evidence combination rule function the value. The calculation is similar value;...

Climate downscaling is a way to provide finer resolution data at local scales, which has been widely used in meteorological research. The two main approaches for climate are dynamical and statistical. traditional methods quite time- resource-consuming based on general circulation models (GCMs). Recently, more researchers construct statistical deep learning model motivated by the single-image superresolution (SISR) process computer vision (CV). This an approach that uses historical...

Conditional nonlinear optimal perturbation (CNOP) is an initial evolving into the largest evolution at prediction time. It has become a useful tool in meteorology and oceanography. The common method for solving CNOP adjoint-based which always referred to as benchmark. Unfortunately, many numerical models have no corresponding adjoint models, developing new one usually huge engineering, consequently limits application of CNOP. In order avoid we propose principal components-based great deluge...

Abstract. Due to global warming, the Arctic sea ice extent (SIE) is rapidly decreasing each year. According Intergovernmental Panel on Climate Change (IPCC) climate model projections, summer will be nearly sea-ice-free in 2050s of 21st century, which have a great impact change. As result, accurate predictions are significant interest. In most current studies, majority deep-learning-based SIE prediction models focus one-step prediction, and they not only short lead times but also limited...

Double-gyre ocean circulation is a typical phenomenon in the northern mid-latitude basins. Its low-frequency variability significantly influences on both and climate. To enhance its predictability, finding of optimal initial perturbation which can trigger double-gyre variation important. CNOP method adopted to calculate this has already been widely applied. Previous studies show that intelligent algorithms are effective methods solve ENSO event ZC model. In paper, it first time algorithm...

This paper focuses on modeling and parameter estimation for the electrohydraulic actuation system of an articulated forestry machine. The linear graph method is implemented in deriving mathematical models swing, boom stick subsystems. Actuation dynamics are subsequently integrated with manipulator to result a complete machine model. Identification procedures employed estimating physical parameters discussed. Model validation studies show good agreement between model predictions experiments....

By combining data-driven and keyword-driven technologies using XML format to store testing data, this paper shows how design implement a GUI automated framework with strong reusability, expandability robustness. The separation of scripts, data business logic divides personnel into developers testers. In case, testers could concentrate on the test case development file, helping improve quality simplifying skills required for testing. Furthermore, detailed description about use express revert...

Mining valuable information from taxi trip data to recommend drivers hotspot pickup areas become a hot research problem since taxis cruising in the city causes large energy waste every day. In existing methods, many methods are just cluster pick-up by various clustering algorithm without further analysis of differences between hotspots. this paper, we propose novel recommendation model analyzing according different factors based on an improved DBSCAN algorithm. We conduct several experiments...