Spatio-temporal estimation of wind speed and wind power using extreme learning machines: predictions, uncertainty and technical potential.

With wind power providing an increasing amount of electricity worldwide, the quantification of its spatio-temporal variations and the related uncertainty is crucial for energy planners and policy-makers. Here, we propose a methodological framework which (1) uses machine learning to reconstruct a spatio-temporal field of wind speed on a regular grid from spatially irregularly distributed measurements and (2) transforms the wind speed to wind power estimates. Estimates of both model and prediction uncertainties, and of their propagation after transforming wind speed to power, are provided without any assumptions on data distributions. The methodology is applied to study hourly wind power potential on a grid of 250 × 250  m 2 for turbines of 100 m hub height in Switzerland, generating the first dataset of its type for the country. We show that the average annual power generation per turbine is 4.4 GWh. Results suggest that around 12,000 wind turbines could be installed on all 19,617 km 2 of available area in Switzerland resulting in a maximum technical wind potential of 53 TWh. To achieve the Swiss expansion goals of wind power for 2050, around 1000 turbines would be sufficient, corresponding to only 8% of the maximum estimated potential. Supplementary Information: The online version contains supplementary material available at 10.1007/s00477-022-02219-w.

Unsupervised learning of Swiss population spatial distribution.

The paper deals with the analysis of spatial distribution of Swiss population using fractal concepts and unsupervised learning algorithms. The research methodology is based on the development of a high dimensional feature space by calculating local growth curves, widely used in fractal dimension estimation and on the application of clustering algorithms in order to reveal the patterns of spatial population distribution. The notion "unsupervised" also means, that only some general criteria-density, dimensionality, homogeneity, are used to construct an input feature space, without adding any supervised/expert knowledge. The approach is very powerful and provides a comprehensive local information about density and homogeneity/fractality of spatially distributed point patterns.

A novel framework for spatio-temporal prediction of environmental data using deep learning.

As the role played by statistical and computational sciences in climate and environmental modelling and prediction becomes more important, Machine Learning researchers are becoming more aware of the relevance of their work to help tackle the climate crisis. Indeed, being universal nonlinear function approximation tools, Machine Learning algorithms are efficient in analysing and modelling spatially and temporally variable environmental data. While Deep Learning models have proved to be able to capture spatial, temporal, and spatio-temporal dependencies through their automatic feature representation learning, the problem of the interpolation of continuous spatio-temporal fields measured on a set of irregular points in space is still under-investigated. To fill this gap, we introduce here a framework for spatio-temporal prediction of climate and environmental data using deep learning. Specifically, we show how spatio-temporal processes can be decomposed in terms of a sum of products of temporally referenced basis functions, and of stochastic spatial coefficients which can be spatially modelled and mapped on a regular grid, allowing the reconstruction of the complete spatio-temporal signal. Applications on two case studies based on simulated and real-world data will show the effectiveness of the proposed framework in modelling coherent spatio-temporal fields.

Community detection analysis in wind speed-monitoring systems using mutual information-based complex network.

A mutual information-based weighted network representation of a wide wind speed-monitoring system in Switzerland was analyzed in order to detect communities. Two communities have been revealed, corresponding to two clusters of sensors situated, respectively, on the Alps and on the Jura-Plateau that define the two major climatic zones of Switzerland. The silhouette measure is used to evaluate the obtained communities and confirm the membership of each sensor to its cluster.

Fisher-Shannon Complexity Analysis of High-Frequency Urban Wind Speed Time Series.

One-hertz wind time series recorded at different levels (from 1.5-25.5 m) in an urban area are investigated by using the Fisher-Shannon (FS) analysis. FS analysis is a well-known method to gain insight into the complex behavior of nonlinear systems, by quantifying the order/disorder properties of time series. Our findings reveal that the FS complexity, defined as the product between the Fisher information measure and the Shannon entropy power, decreases with the height of the anemometer from the ground, suggesting a height-dependent variability in the order/disorder features of the high-frequency wind speed measured in urban layouts. Furthermore, the correlation between the FS complexity of wind speed and the daily variance of the ambient temperature shows a similar decrease with the height of the wind sensor. Such correlation is larger for the lower anemometers, indicating that ambient temperature is an important forcing of the wind speed variability in the vicinity of the ground.

Long-range fluctuations and multifractality in connectivity density time series of a wind speed monitoring network.

This paper studies the daily connectivity time series of a wind speed-monitoring network using multifractal detrended fluctuation analysis. It investigates the long-range fluctuation and multifractality in the residuals of the connectivity time series. Our findings reveal that the daily connectivity of the correlation-based network is persistent for any correlation threshold. Further, the multifractality degree is higher for larger absolute values of the correlation threshold.

Data-driven mapping of the potential mountain permafrost distribution.

Existing mountain permafrost distribution models generally offer a good overview of the potential extent of this phenomenon at a regional scale. They are however not always able to reproduce the high spatial discontinuity of permafrost at the micro-scale (scale of a specific landform; ten to several hundreds of meters). To overcome this lack, we tested an alternative modelling approach using three classification algorithms belonging to statistics and machine learning: Logistic regression, Support Vector Machines and Random forests. These supervised learning techniques infer a classification function from labelled training data (pixels of permafrost absence and presence) with the aim of predicting the permafrost occurrence where it is unknown. The research was carried out in a 588km2 area of the Western Swiss Alps. Permafrost evidences were mapped from ortho-image interpretation (rock glacier inventorying) and field data (mainly geoelectrical and thermal data). The relationship between selected permafrost evidences and permafrost controlling factors was computed with the mentioned techniques. Classification performances, assessed with AUROC, range between 0.81 for Logistic regression, 0.85 with Support Vector Machines and 0.88 with Random forests. The adopted machine learning algorithms have demonstrated to be efficient for permafrost distribution modelling thanks to consistent results compared to the field reality. The high resolution of the input dataset (10m) allows elaborating maps at the micro-scale with a modelled permafrost spatial distribution less optimistic than classic spatial models. Moreover, the probability output of adopted algorithms offers a more precise overview of the potential distribution of mountain permafrost than proposing simple indexes of the permafrost favorability. These encouraging results also open the way to new possibilities of permafrost data analysis and mapping.

Machine learning for toxicity characterization of organic chemical emissions using USEtox database: Learning the structure of the input space.

Toxicity characterization of chemical emissions in Life Cycle Assessment (LCA) is a complex task which usually proceeds via multimedia (fate, exposure and effect) models attached to models of dose-response relationships to assess the effects on target. Different models and approaches do exist, but all require a vast amount of data on the properties of the chemical compounds being assessed, which are hard to collect or hardly publicly available (especially for thousands of less common or newly developed chemicals), therefore hampering in practice the assessment in LCA. An example is USEtox, a consensual model for the characterization of human toxicity and freshwater ecotoxicity. This paper places itself in a line of research aiming at providing a methodology to reduce the number of input parameters necessary to run multimedia fate models, focusing in particular to the application of the USEtox toxicity model. By focusing on USEtox, in this paper two main goals are pursued: 1) performing an extensive exploratory analysis (using dimensionality reduction techniques) of the input space constituted by the substance-specific properties at the aim of detecting particular patterns in the data manifold and estimating the dimension of the subspace in which the data manifold actually lies; and 2) exploring the application of a set of linear models, based on partial least squares (PLS) regression, as well as a nonlinear model (general regression neural network--GRNN) in the seek for an automatic selection strategy of the most informative variables according to the modelled output (USEtox factor). After extensive analysis, the intrinsic dimension of the input manifold has been identified between three and four. The variables selected as most informative may vary according to the output modelled and the model used, but for the toxicity factors modelled in this paper the input variables selected as most informative are coherent with prior expectations based on scientific knowledge of toxicity factors modelling. Thus the outcomes of the analysis are promising for the future application of the approach to other portions of the model, affected by important data gaps, e.g., to the calculation of human health effect factors.

Indoor radon distribution in Switzerland: lognormality and Extreme Value Theory.

Analysis and modeling of statistical distributions of indoor radon concentration from data valorization to mapping and simulations are critical issues for real decision-making processes. The usual way to model indoor radon concentrations is to assume lognormal distributions of concentrations on a given territory. While these distributions usually model correctly the main body of the data density, they cannot model the extreme values, which are more important for risk assessment. In this paper, global and local indoor radon distributions are modeled using Extreme Value Theory (EVT). Emphasis is put on the tails of the distributions and their deviations from lognormality. The best fits of distributions to real data set density have been computed and goodness of fit with Root Mean Squared Error (RMSE) is evaluated. The results show that EVT performs better than lognormal pdf for real data sets characterized by high indoor radon concentrations.

Pattern detection in forensic case data using graph theory: application to heroin cutting agents.

Pattern recognition techniques can be very useful in forensic sciences to point out to relevant sets of events and potentially encourage an intelligence-led style of policing. In this study, these techniques have been applied to categorical data corresponding to cutting agents found in heroin seizures. An application of graph theoretic methods has been performed, in order to highlight the possible relationships between the location of seizures and co-occurrences of particular heroin cutting agents. An analysis of the co-occurrences to establish several main combinations has been done. Results illustrate the practical potential of mathematical models in forensic data analysis.