In situ and remotely sensed observations have potential to facilitate data-driven predictive models for oceanography. A suite of machine learning models, including regression, decision tree and deep learning approaches were developed to estimate sea surface temperatures (SST). Training data consisted of satellite-derived SST and atmospheric data from The Weather Company. Models were evaluated in terms of accuracy and computational complexity. Predictive skill were assessed against observations and a state-of-the-art, physics-based model from the European Centre for Medium Weather Forecasting. Results demonstrated that by combining automated feature engineering with machine-learning approaches, accuracy comparable to existing state-of-the-art can be achieved. Models captured seasonal patterns in the data and qualitatively reproduce short-term variations driven by atmospheric forcing. Further, it demonstrated that machine-learning-based approaches can be used as transportable prediction tools for ocean variables -- the data-driven nature of the approach naturally integrates with automatic deployment frameworks, where model deployments are guided by data rather than user-parametrisation and expertise. The low computational cost of inference makes the approach particularly attractive for edge-based computing where predictive models could be deployed on low-power devices in the marine environment.
University of Corsica（科西嘉大学）；CNRS（法国国家科学研究中心）；University of Galatasaray（加拉塔萨雷大学）
In this paper, we propose to study four meteorological and seasonal time series coupled with a multi-layer perceptron (MLP) modeling. We chose to combine two transfer functions for the nodes of the hidden layer, and to use a temporal indicator (time index as input) in order to take into account the seasonal aspect of the studied time series. The results of the prediction concern two years of measurements and the learning step, eight independent years. We show that this methodology can improve the accuracy of meteorological data estimation compared to a classical MLP modelling with a homogenous…
University of Barcelona (UB)（巴塞罗那大学（UB））；Polytechnic University of Catalunya (UPC)（加泰罗尼亚理工大学（UPC））
This study assesses the influence of the forecast horizon on the forecasting performance of several machine learning techniques. We compare the fo recast accuracy of Support Vector Regression (SVR) to Neural Network (NN) models, using a linear model as a benchmark. We focus on international tourism demand to all seventeen regions of Spain. The SVR with a Gaussian radial basis function kernel outperforms the rest of the models for the longest forecast horizons. We also find that machine learning methods improve their forecasting accuracy with respect to linear models as forecast horizons increa…
CELESTE, Inria Saclay（法国国家信息与自动化研究所萨克雷研究中心，CELESTE）；School of Mathematics, University of Bristol（布里斯托大学数学学院）；EDF Lab（法国电力集团研究院）
In the context of smart grids and load balancing, daily peak load forecasting has become a critical activity for stakeholders of the energy industry. An understanding of peak magnitude and timing is paramount for the implementation of smart grid strategies such as peak shaving. The modelling approach proposed in this paper leverages high-resolution and low-resolution information to forecast daily peak demand size and timing. The resulting multi-resolution modelling framework can be adapted to different model classes. The key contributions of this paper are a) a general and formal introduction …
Energy Price Modelling: A Comparative Evaluation of four Generations of Forecasting Methods
Bucharest University of Economic Studies（布加勒斯特经济研究大学）；Humboldt University of Berlin（柏林洪堡大学）；California Institute of Technology（加州理工学院）；Institute for Economic Forecasting, Romanian Academy（罗马尼亚科学院经济预测研究所）
Geneva School of Business Administration, HES-SO University of Applied Sciences of Western Switzerland（日内瓦商学院，瑞士西部应用科学与艺术大学）；University of Geneva（日内瓦大学）
Traditional linear methods for forecasting multivariate time series are not able to satisfactorily model the non-linear dependencies that may exist in non-Gaussian series. We build on the theory of learning vector-valued functions in the reproducing kernel Hilbert space and develop a method for learning prediction functions that accommodate such non-linearities. The method not only learns the predictive function but also the matrix-valued kernel underlying the function search space directly from the data. Our approach is based on learning multiple matrix-valued kernels, each of those composed …
Stochastic Volatility Modelling with LSTM Networks: A Hybrid Approach for S&P 500 Index Volatility Forecasting
University of Warsaw（华沙大学）；Faculty of Economic Sciences（经济学院）；Department of Quantitative Finance and Machine Learning（金融与机器学习系）；Quantitative Finance Research Group（金融研究组）
University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）
Accurately forecasting Arctic sea ice from subseasonal to seasonal scales has been a major scientific effort with fundamental challenges at play. In addition to physics-based earth system models, researchers have been applying multiple statistical and machine learning models for sea ice forecasting. Looking at the potential of data-driven sea ice forecasting, we propose an attention-based Long Short Term Memory (LSTM) ensemble method to predict monthly sea ice extent up to 1 month ahead. Using daily and monthly satellite retrieved sea ice data from NSIDC and atmospheric and oceanic variables f…
VanBerlo Consulting（范伯洛咨询公司）；The Corporation of the City of London（伦敦市公司）
This study describes an investigation into the modelling of citywide water consumption in London, Canada. Multiple modelling techniques were evaluated for the task of univariate time series forecasting with water consumption, including linear regression, Facebook's Prophet method, recurrent neural networks, and convolutional neural networks. Prophet was identified as the model of choice, having achieved a mean absolute percentage error of 2.51%, averaged across a 5-fold cross validation. Prophet was also found to have other advantages deemed valuable to water demand management stakeholders, in…
BBVA Data and Analytics（BBVA数据与分析公司）；Universitat de Barcelona（巴塞罗那大学）
Deep Learning is a consolidated, state-of-the-art Machine Learning tool to fit a function when provided with large data sets of examples. However, in regression tasks, the straightforward application of Deep Learning models provides a point estimate of the target. In addition, the model does not take into account the uncertainty of a prediction. This represents a great limitation for tasks where communicating an erroneous prediction carries a risk. In this paper we tackle a real-world problem of forecasting impending financial expenses and incomings of customers, while displaying predictable m…
An impact of climate change is the increase in frequency and intensity of extreme precipitation events. However, confidently predicting the likelihood of extreme precipitation at seasonal scales remains an outstanding challenge. Here, we present an approach to forecasting the quantiles of the maximum daily precipitation in each week up to six months ahead using the temporal fusion transformer (TFT) model. Through experiments in two regions, we compare TFT predictions with those of two baselines: climatology and a calibrated ECMWF SEAS5 ensemble forecast (S5). Our results show that, in terms of…
Indian Institute of Information Technology, Allahabad（印度阿拉哈巴德信息技术学院）
SARS-COV-19 is the most prominent issue which many countries face today. The frequent changes in infections, recovered and deaths represents the dynamic nature of this pandemic. It is very crucial to predict the spreading rate of this virus for accurate decision making against fighting with the situation of getting infected through the virus, tracking and controlling the virus transmission in the community. We develop a prediction model using statistical time series models such as SARIMA and FBProphet to monitor the daily active, recovered and death cases of COVID-19 accurately. Then with the …
University of New South Wales（新南威尔士大学）；Indian Institute of Technology Guwahati（印度理工学院古瓦哈提分校）
The COVID-19 pandemic continues to have major impact to health and medical infrastructure, economy, and agriculture. Prominent computational and mathematical models have been unreliable due to the complexity of the spread of infections. Moreover, lack of data collection and reporting makes modelling attempts difficult and unreliable. Hence, we need to re-look at the situation with reliable data sources and innovative forecasting models. Deep learning models such as recurrent neural networks are well suited for modelling spatiotemporal sequences. In this paper, we apply recurrent neural network…
This paper presents a time series forecasting framework which combines standard forecasting methods and a machine learning model. The inputs to the machine learning model are not lagged values or regular time series features, but instead forecasts produced by standard methods. The machine learning model can be either a convolutional neural network model or a recurrent neural network model. The intuition behind this approach is that forecasts of a time series are themselves good features characterizing the series, especially when the modelling purpose is forecasting. It can also be viewed as a …
Recurrent Neural Networks (RNNs) represent the de facto standard machine learning tool for sequence modelling, owing to their expressive power and memory. However, when dealing with large dimensional data, the corresponding exponential increase in the number of parameters imposes a computational bottleneck. The necessity to equip RNNs with the ability to deal with the curse of dimensionality, such as through the parameter compression ability inherent to tensors, has led to the development of the Tensor-Train RNN (TT-RNN). Despite achieving promising results in many applications, the full poten…
MIT Operations Research Center（麻省理工学院运筹学研究中心）；MIT Laboratory for Financial Engineering（麻省理工学院金融工程实验室）；Machine Intelligence Technology, Alibaba Group（阿里巴巴集团机器智能技术部）
Seasonal time series Forecasting remains a challenging problem due to the long-term dependency from seasonality. In this paper, we propose a two-stage framework to forecast univariate seasonal time series. The first stage explicitly learns the long-range time series structure in a time window beyond the forecast horizon. By incorporating the learned long-range structure, the second stage can enhance the prediction accuracy in the forecast horizon. In both stages, we integrate the auto-regressive model with neural networks to capture both linear and non-linear characteristics in time series. Ou…
Providing long-range forecasts is a fundamental challenge in time series modeling, which is only compounded by the challenge of having to form such forecasts when a time series has never previously been observed. The latter challenge is the time series version of the cold-start problem seen in recommender systems which, to our knowledge, has not been addressed in previous work. A similar problem occurs when a long range forecast is required after only observing a small number of time points --- a warm start forecast. With these aims in mind, we focus on forecasting seasonal profiles---or basel…
Atos（源讯）；Flanders Research Institute for Agriculture, Fisheries and Food（法兰德斯农业、渔业和食品研究所）
This paper combines fisheries dependent data and environmental data to be used in a machine learning pipeline to predict the spatio-temporal abundance of two species (plaice and sole) commonly caught by the Belgian fishery in the North Sea. By combining fisheries related features with environmental data, sea bottom temperature derived from remote sensing, a higher accuracy can be achieved. In a forecast setting, the predictive accuracy is further improved by predicting, using a recurrent deep neural network, the sea bottom temperature up to four days in advance instead of relying on the last p…
Applied AI Center（应用人工智能中心）；Skolkovo Institute of Science and Technology（斯科尔科沃科学技术学院）；Shirshov Institute of Oceanology（希尔绍夫海洋研究所）；Moscow Institute of Physics and Technology（莫斯科物理技术学院）；Gazprom Neft（俄罗斯天然气工业石油公司）
Global warming made the Arctic available for marine operations and created demand for reliable operational sea ice forecasts to make them safe. While ocean-ice numerical models are highly computationally intensive, relatively lightweight ML-based methods may be more efficient in this task. Many works have exploited different deep learning models alongside classical approaches for predicting sea ice concentration in the Arctic. However, only a few focus on daily operational forecasts and consider the real-time availability of data they need for operation. In this work, we aim to close this gap …
Yield forecast is essential to agriculture stakeholders and can be obtained with the use of machine learning models and data coming from multiple sources. Most solutions for yield forecast rely on NDVI (Normalized Difference Vegetation Index) data, which is time-consuming to be acquired and processed. To bring scalability for yield forecast, in the present paper we describe a system that incorporates satellite-derived precipitation and soil properties datasets, seasonal climate forecasting data from physical models and other sources to produce a pre-season prediction of soybean/maize yield---w…
Generating forecasts for time series with multiple seasonal cycles is an important use-case for many industries nowadays. Accounting for the multi-seasonal patterns becomes necessary to generate more accurate and meaningful forecasts in these contexts. In this paper, we propose Long Short-Term Memory Multi-Seasonal Net (LSTM-MSNet), a decomposition based, unified prediction framework to forecast time series with multiple seasonal patterns. The current state of the art in this space are typically univariate methods, in which the model parameters of each time series are estimated independently. …
Seoul National University（首尔大学）；Korea Aerospace University（韩国航空大学）；Korea Advanced Institute of Science and Technology（韩国科学技术院）
Multiple seasonal patterns play a key role in time series forecasting, especially for business time series where seasonal effects are often dramatic. Previous approaches including Fourier decomposition, exponential smoothing, and seasonal autoregressive integrated moving average (SARIMA) models do not reflect the distinct characteristics of each period in seasonal patterns. We propose a mixed hierarchical seasonality (MHS) model. Intermediate parameters for each seasonal period are first estimated, and a mixture of intermediate parameters is taken. This results in a model that automatically le…
We show that probabilistic weather forecasts of site specific temperatures can be dramatically improved by using seasonally varying rather than constant calibration parameters.
Observational time series data often exhibit both cyclic temporal trends and autocorrelation and may also depend on covariates. As such, there is a need for flexible regression models that are able to capture these trends and model any residual autocorrelation simultaneously. Modelling the autocorrelation in the residuals leads to more realistic forecasts than an assumption of independence. In this paper we propose a method which combines spline-based semi-parametric regression modelling with the modelling of auto-regressive errors. The method is applied to a simulated data set in order to sho…
Seasonal climate forecasts are being used increasingly across a range of application sectors. A recent UK governmental report asked: How good are seasonal climate forecasts on a scale of 1-5 (where 5 is very good), and how good can we expect them to be in 30 years time? Seasonal climate forecasts are made from ensembles of integrations of numerical models of climate. We argue that goodness should be assessed primarily in terms of the probabilistic reliability of these ensemble-based forecasts and that a 5 should be reserved for systems which are not only reliable overall, but where, in particu…
The paper describes the existing operational sea state forecast system of NIMH- BAS for sea state in the Black Sea and our current progress on the implementation of an additional component for the forecasts of wind waves in the Bulgarian coastal zone. Wind Waves and especially the extreme ones, occurring during severe storms are a major hazard for the coastal zone, causing significant damages to the infrastructure, threat for the human lives and also causing significant damages to the protected areas around the coast. The numerical model WAVEWATCH III is in use for wind waves forecasts for the…
We study the response of the Lagrangian sea ice model neXtSIM to the uncertainty in the sea surface wind and sea ice cohesion. The ice mechanics in neXtSIM is based on a brittle-like rheological framework. The study considers short-term ensemble forecasts of the Arctic sea ice from January to April 2008. Ensembles are generated by perturbing the wind inputs and ice cohesion field both separately and jointly. The resulting uncertainty in the probabilistic forecasts is evaluated statistically based on the analysis of Lagrangian sea ice trajectories as sampled by virtual drifters seeded in the mo…
We evaluate the performance of two 44 year ensemble seasonal hindcast time series for the Nino3 index produced as part of the DEMETER project. We show that the ensemble mean carries useful information out to six months. The ensemble spread, however, only carries useful information out to four months in one of the models, and two months in the other.
We derive a simple algebraic form of the nonlinear wavenumber correction of surface gravity waves in deep water, based on temporal measurements of the water surface and the spatial Zakharov equation. This allows us to formulate an improvement over linear deterministic wave forecasting with no additional computational cost. Our new formulation is used to forecast both synthetically generated as well as experimentally measured seas, and shows marked improvements over the linear theory.
We propose a nonlinear ocean forecasting technique based on a combination of genetic algorithms and empirical orthogonal function (EOF) analysis. The method is used to forecast the space-time variability of the sea surface temperature (SST) in the Alboran Sea. The genetic algorithm finds the equations that best describe the behaviour of the different temporal amplitude functions in the EOF decomposition and, therefore, enables global forecasting of the future time-variability.
This paper briefly describes the existing operational system for wind waves forecasting in the Black Sea. It is a system of coupled atmospheric and wave numerical models aiming at a detailed and accurate sea state forecast on an operational level. The system was created at the National Institute of Meteorology and Hydrology Bulgarian Academy of Sciences (NIMH-BAS) in collaboration with the Meteorological Office of France - Meteo-France. The present work introduces the use of wave models at NIMH-BAS and shows the model results, as well as an intercomparison. The numerical wave models VAG, WAVEW…
We assess the skill and reliability of forecasts of winter and summer temperature, wind speed and irradiance over China, using the GloSea5 seasonal forecast system. Skill in such forecasts is important for the future development of seasonal climate services for the energy sector, allowing better estimates of forthcoming demand and renewable electricity supply. We find that although overall the skill from the direct model output is patchy, some high-skill regions of interest to the energy sector can be identified. In particular, winter mean wind speed is skilfully forecast around the coast of t…
The accumulated remote sensing data of altimeters and scatterometers have provided a new opportunity to forecast the ocean states and improve the knowledge in ocean/atmosphere exchanges. Few previous studies have focused on sea level anomaly (SLA) multi-step forecasting by multivariate deep learning for different modalities. For this paper, a novel multimodal fusion approach named MMFnet is used for SLA multi-step forecasting in South China Sea (SCS). First, a grid forecasting network is trained by an improved Convolutional Long Short-Term Memory (ConvLSTM) network on daily multiple remote sen…
Statistical postprocessing is routinely applied to correct systematic errors of numerical weather prediction models (NWP) and to automatically produce calibrated local forecasts for end-users. Postprocessing is particularly relevant in complex terrain, where even state-of-the-art high-resolution NWP systems cannot resolve many of the small-scale processes shaping local weather conditions. In addition, statistical postprocessing can also be used to combine forecasts from multiple NWP systems. Here we assess an ensemble model output statistics (EMOS) approach to produce seamless temperature fore…
