Sparse Linear Wind Farm Energy Forecast

Sparse wavelet regression with multiple predictive curves

Genes regulate each other and form a gene regulatory network (GRN) to realise biological functions. Elucidating GRN from experimental data remains a challenging problem in systems biology. Numerous techniques have been developed and sparse linear regression methods become a promising approach to infer accurate GRNs. However, most linear methods are either based on steady-state gene expression data or their statistical properties are not analysed. Here, two sparse penalties, adaptive least absolute shrinkage and selection operator and smoothly clipped absolute deviation, are proposed to infer GRNs from time-course gene expression data based on an auto-regressive model and their Oracle properties are proved under mild conditions. The effectiveness of those methods is demonstrated by applications to in silico and real biological data.

We use sparse regression methods (SRMs) to build accurate and explainable models that predict the stellar mass of central and satellite galaxies as a function of properties of their host dark matter haloes. SRMs are machine learning algorithms that provide a framework for modelling the governing equations of a system from data. In contrast with other machine learning algorithms, the solutions of SRM methods are simple and depend on a relatively small set of adjustable parameters. We collect data from 35 459 galaxies from the EAGLE simulation using 19 redshift slices between z = 0 and z = 4 to parametrize the mass evolution of the host haloes. Using an appropriate formulation of input parameters, our methodology can model satellite and central haloes using a single predictive model that achieves the same accuracy as when predicted separately. This allows us to remove the somewhat arbitrary distinction between those two galaxy types and model them based only on their halo growth history. Our models can accurately reproduce the total galaxy stellar mass function and the stellar mass-dependent galaxy correlation functions (ξ(r)) of EAGLE. We show that our SRM model predictions of ξ(r) is competitive with those from subhalo abundance matching and might be comparable to results from extremely randomized trees. We suggest SRM as an encouraging approach for populating the haloes of dark matter only simulations with galaxies and for generating mock catalogues that can be used to explore galaxy evolution or analyse forthcoming large-scale structure surveys.

Sparse regression methods such as l1-regularized linear regression, or Lasso [18], are commonly used for analysis of high-dimensional, small-sample datasets, due to their good generalization and feature-selection properties. However, predictive accuracy of sparse regression can be further improved by incorporating more realistic data-modeling assumptions (e.g., nonlinearity) and by fully exploiting all available data, as suggested by the transductive approach [6], which makes instance-specific predictions based on both labeled (training) data and unlabeled (test) data, instead of learning a single fixed model from training data. Based on these ideas, we develop a novel method, called Transductive HSIC Lasso, that incorporates transduction into a nonlinear sparse regression approach known as HSIC Lasso [19]. Unlike the existing transductive Lasso algorithm of [1], our approach does not rely on imputation, i.e., on estimation of unknown labels using a predictor built on training data; the latter may sometimes result in poor overall performance due to unreliable label estimates. Instead, our method exploits the structure of the HSIC Lasso, which maximizes the relevance between the selected features and the label, while minimizing the redundancy between the selected features; transduction is achieved by including unlabeled samples into the redundancy computation. Our experiments demonstrate advantages of the proposed method over the state-of-the-art approaches, both on simulated and real-life data, such as prediction of phenotypic traits from genomic data, and prediction of subject’s pain level from his/her functional MRI data.

While functional magnetic resonance imaging (fMRI) is important for healthcare/neuroscience applications, it is challenging to classify or interpret due to its multi-dimensional structure, high dimensionality, and small number of samples available. Recent sparse multilinear regression methods based on tensor are emerging as promising solutions for fMRI, yet existing works rely on unfolding/folding operations and a tensor rank relaxation with limited tightness. The newly proposed tensor singular value decomposition (t-SVD) sheds light on new directions. In this work, we study t-SVD for sparse multilinear regression and propose a Sparse tubal-regularized multilinear regression (Sturm) method for fMRI. Specifically, the Sturm model performs multilinear regression with two regularization terms: a tubal tensor nuclear norm based on t-SVD and a standard L1 norm. We further derive the algorithm under the alternating direction method of multipliers framework. We perform experiments on four classification problems, including both resting-state fMRI for disease diagnosis and task-based fMRI for neural decoding. The results show the superior performance of Sturm in classifying fMRI using just a small number of voxels.

Kernel functions embed into the autoencoder to identify the sparse models of nonlinear dynamics

This article is addressed to the layman with a science education. It is thus not addressed specifically to the meteorologist, but it contains certain information about the weather services, and the impact of numerical weather prediction on them, that I believe will interest those in the meteorological community who have not had close associations with the service side of our house. The weather services are principally concerned with weather and river forecasting and serve virtually all of the general public and the entire economy of our nation. Numerical weather prediction is at the core of the complex set of forecast services, and more accurate forecasts depend on progress in numerical weather prediction more than on anything else. This is as true now as it has been during the 20-odd years since operational numerical weather prediction began. Progress has been, and still is, paced by advances in computer power. Numerical weather prediction has seen a succession of four generations of computer ha...

Wind power forecasting is significant for the security and economy of the power system. For the better robustness and accuracy, various clustering-based forecasting methods have been proposed. However, most of them utilize clustering on a daily sample basis usually called day clustering, which mainly exploits daily features of numerical weather prediction (NWP) and meets some limitations. In this paper, a single point clustering method is proposed to enhance the performance of day-ahead forecasting, which is conducted on a point sample basis through K-means algorithm. First, the extraction of clustering features is optimized. Being different from the commonly used clustering features, the high-order features extracted from NWP is used for the proposed method based on stacked denoising autoencoder (SDAE). Then, both the compactness within the single group and the separation among the multiple groups are enhanced, which is realized through choosing the number of clusters to maximize silhouette. In the case study, the proposed method is compared to the conventional day clustering method with two types of features and the single point clustering with the commonly used clustering features of NWP. Through the results, it is shown that the proposed method performs better than the other comparative methods.

In case of an unplanned emission event from a nuclear power plant, the local population can be protected more efficiently when valid atmospheric dispersion model results are available. Atmospheric dispersion models use local meteorological variables as inputs. When atmospheric dispersion in the future is being predicted, a forecast of the local meteorological variables is needed. The most important variable in atmospheric dispersion modelling is wind, and accurately predicting ground level winds presents a challenge to numerical weather prediction models. We therefore develop hybrid models for forecasting local ground level wind at a single location where the terrain is complex and the average wind is weak and fluctuating. Wind speed and direction are modelled as west-east and south-north wind components. Each model is composed of a numerical weather prediction model and a Gaussian process statistical model that uses numerical weather predictions as some of its inputs and is trained on historical data to predict the output component. The most advanced Gaussian process models studied are of Gaussian process nonlinear autoregressive model with exogenous input (GPNARX) type. In addition to numerical weather predictions, they also use local meteorological variables, including the output variable, as their inputs. Numerical weather prediction results based on large scale information and fundamental knowledge of the system are thus supplemented by local measurements that better reflect the effects of local topography and land use. The models are tested by prediction and simulation. The wind components predicted by more advanced models are more accurate than raw or post-processed numerical weather prediction results. As an example, a model predicting 2D wind vector 1.5 h in advance achieves a NRMSE of 0.214 if it uses all the immediately available information. This is better than both the persistence model with NRMSE of 0.188 and post-processed NWP with NRMSE of 0.164. This demonstrates that hybrid modelling provides the best weather information for short-term and medium-term atmospheric dispersion forecasting. While the method is motivated by nuclear emission sources, it could also be applied to other pollution.

Abstract. Solar radiation is the ultimate source of energy flowing through the atmosphere; it fuels all atmospheric motions. The visible-wavelength range of solar radiation represents a significant contribution to the earth's energy budget, and visible light is a vital indicator for the composition and thermodynamic processes of the atmosphere from the smallest weather scales to the largest climate scales. The accurate and fast description of light propagation in the atmosphere and its lower-boundary environment is therefore of critical importance for the simulation and prediction of weather and climate. Simulated Weather Imagery (SWIm) is a new, fast, and physically based visible-wavelength three-dimensional radiative transfer model. Given the location and intensity of the sources of light (natural or artificial) and the composition (e.g., clear or turbid air with aerosols, liquid or ice clouds, precipitating rain, snow, and ice hydrometeors) of the atmosphere, it describes the propagation of light and produces visually and physically realistic hemispheric or 360∘ spherical panoramic color images of the atmosphere and the underlying terrain from any specified vantage point either on or above the earth's surface. Applications of SWIm include the visualization of atmospheric and land surface conditions simulated or forecast by numerical weather or climate analysis and prediction systems for either scientific or lay audiences. Simulated SWIm imagery can also be generated for and compared with observed camera images to (i) assess the fidelity and (ii) improve the performance of numerical atmospheric and land surface models. Through the use of the latter in a data assimilation scheme, it can also (iii) improve the estimate of the state of atmospheric and land surface initial conditions for situational awareness and numerical weather prediction forecast initialization purposes.

Association analysis of gene expression traits with genomic features is crucial to identify the molecular mechanisms underlying cancer. In this study, we employ sparse regression methods of Lasso and GFLasso to discover ge-nomic associations. Lasso penalizes a least squares regression by the sum of the absolute values of the coefficients, which in turn leads to sparse solutions. GFLasso, an extension of Lasso, fuses regression coefficients across correlated outcome variables, which is especially suitable for the analysis of gene expres-sion traits having inherent network structure as output traits. Our study is about considering combined benefits of these computational methods and investigat-ing the identified genomic associations. Real genomic datasets from breast can-cer and ovarian cancer patients are analyzed by the proposed approach. We show that the combined effect of both the methods has a significant impact in identifying the crucial cancer causing genomic features with both weaker and stronger associations.

Complex orography is still a big challenge for all numerical weather prediction (NWP) models. Orography is an important factor that affects the NWP results. The orography in NWP mainly affects the main accuracy of the results through two aspects: orographic representation in models dynamics and orography-related parameterization schemes in the physical processes. To ensure the accuracy of NWP results, it is necessary to have a comprehensive understanding of the application of orographic data in NWP. This paper summarized the influence of orography on weather, the influence of orographic representation on prediction accuracy, and the parametrization of orography-related drag in NWP models. Finally, this paper elaborates the problems of the application of orographic data in NWP and looks forward to future directions in this field, hoping to improve the performance of NWP in complex orographic areas and provide a reference for better application in NWP.

Improving the Turbulence Coupling between High Resolution Numerical Weather Prediction Models and Lagrangian Particle Dispersion Models

The increasing amount of side information associated with the items in E-commerce applications has provided a very rich source of information that, once properly exploited and incorporated, can significantly improve the performance of the conventional recommender systems. This paper focuses on developing effective algorithms that utilize item side information for top-N recommender systems. A set of sparse linear methods with side information (SSLIM) is proposed, which involve a regularized optimization process to learn a sparse aggregation coefficient matrix based on both user-item purchase profiles and item side information. This aggregation coefficient matrix is used within an item-based recommendation framework to generate recommendations for the users. Our experimental results demonstrate that SSLIM outperforms other methods in effectively utilizing side information and achieving performance improvement.

To satisfy the grid operation scheduling requirements for wind power forecasting model accuracy, the measured wind speed near the height of the wind turbine hub is added to the wind power combined forecasting model. First, the relationship between the numerical weather prediction wind speed and the measured wind speed at different heights are analysed, and the correlation between each wind speed and the wind power is compared. Second, the random forest algorithm combined with the cumulative contribution rate is used to select several meteorological types of numerical weather prediction data as the input of the long short‐term memory network to predict wind speed. Third, while inputting the meteorological data provided by numerical weather prediction, which is highly related to wind power, the wind power prediction network also uses the predicted wind speed of the upper network as input to predict wind power. Finally, the entropy method is used to dynamically determine the combined weights of each forecasting model and improve the adaptability of the model. Research and analysis using measured data from two wind farms located in northeast China have verified the effectiveness of the method.