The objective of this work is to predict the spread of COVID-19 starting from observed data, using a forecast method inspired by probabilistic weather prediction systems operational today.
Results show that this method works well for China: on day 25 we could have predicted well the outcome for the next 35 days. The same method has been applied to Italy and South Korea, and forecasts for the forthcoming weeks are included in this work. For Italy, forecasts based on data collected up to today (24 March) indicate that number of observed cases could grow from the current value of 69,176, to between 101k-180k, with a 50% probability of being between 110k-135k. For South Korea, it suggests that the number of observed cases could grow from the current value of 9,018 (as of the 23rd of March), to values between 8,500 and 9,300, with a 50% probability of being between 8,700 and 8,900.
We conclude by suggesting that probabilistic disease prediction systems are possible and could be developed following key ideas and methods from weather forecasting. Having access to skilful daily updated forecasts could help taking better informed decisions on how to manage the spread of diseases such as COVID-19.
As the coronavirus disease 2019 (COVID-19) has shown profound effects on public health and the economy worldwide, it becomes crucial to assess the impact on the virus transmission and develop effective strategies to address the challenge. A new statistical model derived from the SIR epidemic model with functional parameters is proposed to understand the impact of weather and government interventions on the virus spread in the presence of asymptomatic infections among eight metropolitan areas in the United States. The model uses Bayesian inference with Gaussian process priors to study the funct…
Aggregated human judgment forecasts for COVID-19 targets of public health importance are accurate, often outperforming computational models. Our work shows aggregated human judgment forecasts for infectious agents are timely, accurate, and adaptable, and can be used as tool to aid public health decision making during outbreaks.
Correlation between weather and the transmission of SARS-CoV-2 may suggest its seasonality. Cointegration analysis can avoid spurious correlation among time series data. We examined the cointegration of virus transmission with daily temperature, dewpoint, and confounding factors of mobility measurements during the first year of the pandemic in the United States. We examined the cointegration of the effective reproductive rate, Rt, of the virus with the dewpoint at two meters, the temperature at two meters, Apple driving mobility, and Google workplace mobility measurements. We found that dewpoi…
In order to enable the transition towards renewable energy sources, probabilistic energy forecasting is of critical importance for incorporating volatile power sources such as solar energy into the electrical grid. Solar energy forecasting methods often aim to provide probabilistic predictions of solar irradiance. In particular, many hybrid approaches combine physical information from numerical weather prediction models with statistical methods. Even though the physical models can provide useful information at intra-day and day-ahead forecast horizons, ensemble weather forecasts from multiple …
In March 2020 the United Kingdom (UK) entered a nationwide lockdown period due to the Covid-19 pandemic. As a result, levels of nitrogen dioxide (NO2) in the atmosphere dropped. In this work, we use 550,134 NO2 data points from 237 stations in the UK to build a spatiotemporal Gaussian process capable of predicting NO2 levels across the entire UK. We integrate several covariate datasets to enhance the model's ability to capture the complex spatiotemporal dynamics of NO2. Our numerical analyses show that, within two weeks of a UK lockdown being imposed, UK NO2 levels dropped 36.8%. Further, we s…
We propose a detailed discrete-time model of COVID-19 epidemics coming in two flavours, mean-field and probabilistic. The main contribution lies in several extensions of the basic model that capture i) user mobility - distinguishing routing, i.e. change of residence, from commuting, i.e. daily mobility - and ii) contact tracing procedures. We confront this model to public data on daily hospitalizations, and discuss its application as well as underlying estimation procedures.
The COVID-19 pandemic has placed forecasting models at the forefront of health policy making. Predictions of mortality and hospitalization help governments meet planning and resource allocation challenges. In this paper, we consider the weekly forecasting of the cumulative mortality due to COVID-19 at the national and state level in the U.S. Optimal decision-making requires a forecast of a probability distribution, rather than just a single point forecast. Interval forecasts are also important, as they can support decision making and provide situational awareness. We consider the case where pr…
Prediction of various weather quantities is mostly based on deterministic numerical weather forecasting models. Multiple runs of these models with different initial conditions result ensembles of forecasts which are applied for estimating the distribution of future weather quantities. However, the ensembles are usually under-dispersive and uncalibrated, so post-processing is required. In the present work Bayesian Model Averaging (BMA) is applied for calibrating ensembles of wind speed forecasts produced by the operational Limited Area Model Ensemble Prediction System of the Hungarian Meteorolo…
Agricultural food production and natural ecological systems depend on a range of seasonal climate indicators that describe seasonal patterns in climatological conditions. This paper proposes a probabilistic forecasting framework for predicting the end of the freeze-free season, or the time to a mean daily near-surface air temperature below 0 $^\circ$C (here referred to as hard freeze). The forecasting framework is based on the multi-model seasonal forecast ensemble provided by the Copernicus Climate Data Store and uses techniques from survival analysis for time-to-event data. The original mean…
After the onset of the recent COVID-19 pandemic, a number of studies reported on possible changes in electricity consumption trends. The overall theme of these reports was that ``electricity use has decreased during the pandemic, but the power grid is still reliable''---mostly due to reduced economic activity. In this paper we analyze electricity data upto end of May 2020, examining both electricity demand and variables that can indicate stress on the power grid, such as peak demand and demand ramp-rate. We limit this study to three states in the USA: New York, California, and Florida. The res…
Uncertainty in the prediction of future weather is commonly assessed through the use of forecast ensembles that employ a numerical weather prediction model in distinct variants. Statistical postprocessing can correct for biases in the numerical model and improves calibration. We propose a Bayesian version of the standard ensemble model output statistics (EMOS) postprocessing method, in which spatially varying bias coefficients are interpreted as realizations of Gaussian Markov random fields. Our Markovian EMOS (MEMOS) technique utilizes the recently developed stochastic partial differential eq…
To address the uncertainty in outputs of numerical weather prediction (NWP) models, ensembles of forecasts are used. To obtain such an ensemble of forecasts the NWP model is run multiple times, each time with different formulations and/or initial or boundary conditions. To correct for possible biases and dispersion errors in the ensemble, statistical postprocessing models are frequently employed. These statistical models yield full predictive probability distributions for a weather quantity of interest and thus allow for a more accurate assessment of forecast uncertainty. This paper proposes t…
We propose a method for post-processing an ensemble of multivariate forecasts in order to obtain a joint predictive distribution of weather. Our method utilizes existing univariate post-processing techniques, in this case ensemble Bayesian model averaging (BMA), to obtain estimated marginal distributions. However, implementing these methods individually offers no information regarding the joint distribution. To correct this, we propose the use of a Gaussian copula, which offers a simple procedure for recovering the dependence that is lost in the estimation of the ensemble BMA marginals. Our me…
We propose a fully probabilistic prediction model for spatially aggregated solar photovoltaic (PV) power production at an hourly time scale with lead times up to several days using weather forecasts from numerical weather prediction systems as covariates. After an appropriate logarithmic transformation of the power production, we develop a multivariate Gaussian prediction model under a Bayesian inference framework. The model incorporates the temporal error correlation yielding physically consistent forecast trajectories. Several formulations of the correlation structure are proposed and invest…
The novel Corona Virus COVID-19 arrived on Australian shores around 25 January 2020. This paper presents a novel method of dynamically modeling and forecasting the COVID-19 pandemic in Australia with a high degree of accuracy and in a timely manner using limited data; a valuable resource that can be used to guide government decision-making on societal restrictions on a daily and/or weekly basis. The "partially-observable stochastic process" used in this study predicts not only the future actual values with extremely low error, but also the percentage of unobserved COVID-19 cases in the populat…
Probabilistic AI models outperform numerical weather prediction models on record breaking heat extremes
Institute for Meteorology, Leipzig University（莱比锡大学气象研究所）；Center for Scalable Data Analytics and Artificial Intelligence, Leipzig University（莱比锡大学可扩展数据分析与人工智能中心）；Department of Mathematics and Statistics, University of Exeter（埃克塞特大学数学与统计系）
Weather forecasting is mostly based on the outputs of deterministic numerical weather forecasting models. Multiple runs of these models with different initial conditions result in forecast ensembles which is are used for estimating the distribution of future atmospheric variables. However, these ensembles are usually under-dispersive and uncalibrated, so post-processing is required. In the present work Bayesian Model Averaging (BMA) is applied for calibrating ensembles of temperature forecasts produced by the operational Limited Area Model Ensemble Prediction System of the Hungarian Meteorolog…
Capturing the uncertainty in probabilistic wind power forecasts is challenging, especially when uncertain input variables, such as the weather, play a role. Since ensemble weather predictions aim to capture the uncertainty in the weather system, they can be used to propagate this uncertainty through to subsequent wind power forecasting models. However, as weather ensemble systems are known to be biased and underdispersed, meteorologists post-process the ensembles. This post-processing can successfully correct the biases in the weather variables but has not been evaluated thoroughly in the cont…
Renewable energy sources provide a constantly increasing contribution to the total energy production worldwide. However, the power generation from these sources is highly variable due to their dependence on meteorological conditions. Accurate forecasts for the production at various temporal and spatial scales are thus needed for an efficiently operating electricity market. In this article - part 1 - we propose fully probabilistic prediction models for spatially aggregated wind power production at an hourly time scale with lead times up to several days using weather forecasts from numerical wea…
College of Engineering, Mathematics and Physical Sciences, University of Exeter（埃克塞特大学工程、数学与物理科学学院）；Met Office（英国气象局）；School of Computing Science, University of Glasgow（格拉斯哥大学计算科学学院）
Forecasting the weather is an increasingly data intensive exercise. Numerical Weather Prediction (NWP) models are becoming more complex, with higher resolutions, and there are increasing numbers of different models in operation. While the forecasting skill of NWP models continues to improve, the number and complexity of these models poses a new challenge for the operational meteorologist: how should the information from all available models, each with their own unique biases and limitations, be combined in order to provide stakeholders with well-calibrated probabilistic forecasts to use in dec…
Weather-Informed Probabilistic Forecasting and Scenario Generation in Power Systems
H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology（工业与系统工程系，佐治亚理工学院）；AI Institute for Advances in Optimization（优化前沿人工智能研究所）
In weather forecasting, nonhomogeneous regression is used to statistically postprocess forecast ensembles in order to obtain calibrated predictive distributions. For wind speed forecasts, the regression model is given by a truncated normal distribution where location and spread are derived from the ensemble. This paper proposes two alternative approaches which utilize the generalized extreme value (GEV) distribution. A direct alternative to the truncated normal regression is to apply a predictive distribution from the GEV family, while a regime switching approach based on the median of the for…
We compare probabilistic predictions of extreme temperature anomalies issued by two different forecast schemes. One is a dynamical physical weather model, the other a simple data model. We recall the concept of skill scores in order to assess the performance of these two different predictors. Although the result confirms the expectation that the (computationally expensive) weather model outperforms the simple data model, the performance of the latter is surprisingly good. More specifically, for some parameter range, it is even better than the uncalibrated weather model. Since probabilistic pre…
Coronavirus COVID-19 spreads through the population mostly based on social contact. To gauge the potential for widespread contagion, to cope with associated uncertainty and to inform its mitigation, more accurate and robust modelling is centrally important for policy making. We provide a flexible modelling approach that increases the accuracy with which insights can be made. We use this to analyse different scenarios relevant to the COVID-19 situation in the UK. We present a stochastic model that captures the inherently probabilistic nature of contagion between population members. The computat…
The evolution of the weather can be described by deterministic numerical weather forecasting models. Multiple runs of these models with different initial conditions and/or model physics result in forecast ensembles which are used for estimating the distribution of future atmospheric variables. However, these ensembles are usually under-dispersive and uncalibrated, so post-processing is required. In the present work we compare different versions of Bayesian Model Averaging (BMA) and Ensemble Model Output Statistics (EMOS) post-processing methods in order to calibrate 2m temperature and 10m wind…
A comparison of short-term probabilistic forecasts for the incidence of COVID-19 using mechanistic and statistical time series models
ETH Zurich（苏黎世联邦理工学院）；University of Bern（伯尔尼大学）；Imperial College London（伦敦帝国理工学院）；LMU Munich（慕尼黑大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）；National University of Singapore（新加坡国立大学）；National University Health System（国立大学医疗系统）；University of Copenhagen（哥本哈根大学）
NASA Jet Propulsion Lab（NASA喷气推进实验室）；UT Dallas（德克萨斯大学达拉斯分校）；Princeton University（普林斯顿大学）
As multiple adverse events in 2021 illustrated, virtually all aspects of our societal functioning -- from water and food security to energy supply to healthcare -- more than ever depend on the dynamics of environmental factors. Nevertheless, the social dimensions of weather and climate are noticeably less explored by the machine learning community, largely, due to the lack of reliable and easy access to use data. Here we present a unique not yet broadly available NASA's satellite dataset on aerosol optical depth (AOD), temperature and relative humidity and discuss the utility of these new data…
Hospital-acquired infections of communicable viral diseases (CVDs) are posing a tremendous challenge to healthcare workers globally. Healthcare personnel (HCP) is facing a consistent risk of hospital-acquired infections, and subsequently higher rates of morbidity and mortality. We proposed a domain knowledge-driven infection risk model to quantify the individual HCP and the population-level healthcare facility risks. For individual-level risk estimation, a time-variant infection risk model is proposed to capture the transmission dynamics of CVDs. At the population-level, the infection risk is …
We introduce a new probabilistic model to estimate the real spread of the novel SARS-CoV-2 virus along regions or countries. Our model simulates the behavior of each individual in a population according to a probabilistic model through an inverse problem; we estimate the real number of recovered and infected people using mortality records. In addition, the model is dynamic in the sense that it takes into account the policy measures introduced when we solve the inverse problem. The results obtained in Spain have particular practical relevance: the number of infected individuals can be $17$ time…
The outbreak of Coronavirus Disease 2019 (COVID-19) is an ongoing pandemic affecting over 200 countries and regions. Inference about the transmission dynamics of COVID-19 can provide important insights into the speed of disease spread and the effects of mitigation policies. We develop a novel Bayesian approach to such inference based on a probabilistic compartmental model using data of daily confirmed COVID-19 cases. In particular, we consider a probabilistic extension of the classical susceptible-infectious-recovered model, which takes into account undocumented infections and allows the epide…
Achieving Skilled and Reliable Daily Probabilistic Forecasts of Wind Power at Subseasonal-to-Seasonal Timescales over France
Atos Inno’Lab TS Bezons（阿托斯创新实验室TS贝宗）；EDF R&D Lab（EDF研发实验室）；Laboratoire des Sciences du Climat & de l’Environnement（气候与环境科学实验室）；CEA（法国国家科学研究中心）；CNRS（法国国家科学研究中心）；UVSQ（法国大学巴黎-萨克雷）；Université Paris-Saclay（巴黎-萨克雷大学）；Laboratoire de Mathématiques d’Orsay（奥赛数学实验室）
We consider the problem of short- and medium-term electricity load forecasting by using past loads and daily weather forecast information. Conventionally, many researchers have directly applied regression analysis. However, interpreting the effect of weather on these loads is difficult with the existing methods. In this study, we build a statistical model that resolves this interpretation issue. A varying coefficient model with basis expansion is used to capture the nonlinear structure of the weather effect. This approach results in an interpretable model when the regression coefficients are n…
A novel coronavirus disease has emerged (later named COVID-19) and caused the world to enter a new reality, with many direct and indirect factors influencing it. Some are human-controllable (e.g. interventional policies, mobility and the vaccine); some are not (e.g. the weather). We have sought to test how a change in these human-controllable factors might influence two measures: the number of daily cases against economic impact. If applied at the right level and with up-to-date data to measure, policymakers would be able to make targeted interventions and measure their cost. This study aims t…
The need to forecast COVID-19 related variables continues to be pressing as the epidemic unfolds. Different efforts have been made, with compartmental models in epidemiology and statistical models such as AutoRegressive Integrated Moving Average (ARIMA), Exponential Smoothing (ETS) or computing intelligence models. These efforts have proved useful in some instances by allowing decision makers to distinguish different scenarios during the emergency, but their accuracy has been disappointing, forecasts ignore uncertainties and less attention is given to local areas. In this study, we propose a s…
Royal Netherlands Meteorological Institute (KNMI)（荷兰皇家气象研究所（KNMI））；Utrecht University（乌得勒支大学）
Current statistical post-processing methods for probabilistic weather forecasting are not capable of using full spatial patterns from the numerical weather prediction (NWP) model. In this paper we incorporate spatial wind speed information by using convolutional neural networks (CNNs) and obtain probabilistic wind speed forecasts in the Netherlands for 48 hours ahead, based on KNMI's deterministic Harmonie-Arome NWP model. The probabilistic forecasts from the CNNs are shown to have higher Brier skill scores for medium to higher wind speeds, as well as a better continuous ranked probability sco…
The ongoing COVID-19 pandemic calls for a multi-faceted public health response comprising complementary interventions to control the spread of the disease while vaccines and therapies are developed. Many of these interventions need to be informed by epidemic risk predictions given available data, including symptoms, contact patterns, and environmental factors. Here we propose a novel probabilistic formalism based on Individual-Level Models (ILMs) that offers rigorous formulas for the probability of infection of individuals, which can be parameterised via Maximum Likelihood Estimation (MLE) app…
The first cases of COVID-19 in France were detected on January 24, 2020. The number of screening tests carried out and the methodology used to target the patients tested do not allow for a direct computation of the real number of cases and the mortality rate.In this report, we develop a 'mechanistic-statistical' approach coupling a SIR ODE model describing the unobserved epidemiological dynamics, a probabilistic model describing the data acquisition process and a statistical inference method. The objective of this model is not to make forecasts but to estimate the real number of people infecte…
