We develop an approach to identify whether recent technological advancements—such as the rise of commercial satellite-based macro estimates—can provide an alternative to government data. We measure ...the extent to which satellite estimates affect the value of a government macro announcement using its asset price impact. Our identification relies on cloud cover, which prevents satellites from observing economic activity at a few key hubs. Applying our approach, we find that some satellite estimates are now so effective that markets are no longer surprised by government announcements. Our results point to a future in which the resolution of macro uncertainty is smoother and governments have less control over macro information.
Stock trading, as a kind of high frequency trading, generally seeks profits in extremely short market changes. And effective stock price forecasting can help investors obtain higher returns. Based on ...the data set provided by Jane Street, this paper makes use of XGBoost model and LightGBM model to realize the prediction of stock price. Since the given training set has a large amount of data and includes abnormal data such as missing value, we first carry out feature engineering processing on the original data and take the mean value of the missing value, so as to obtain the preprocessed data that can be used in modeling.
The experimental results show that the combined model of XGBoost and LightGBM has better prediction performance than the single model and neural network.
Short term electricity load forecasting is one of the most important issue for all market participants. Short term electricity load is affected by natural and social factors, which makes load ...forecasting more difficult. To improve the forecasting accuracy, a new hybrid model based on improved empirical mode decomposition (IEMD), autoregressive integrated moving average (ARIMA) and wavelet neural network (WNN) optimized by fruit fly optimization algorithm (FOA) is proposed and compared with some other models. Simulation results illustrate that the proposed model performs well in electricity load forecasting than other comparison models.
•Advanced computational model aims at developing accurate solution techniques.•Electricity load is decomposed into regular components by improved EMD.•Different features associated with electricity load can be captured by the proposed model.•Hybrid model composed with different models performs well than singe model.
Accurate and timely spatial classification of crop types based on remote sensing data is important for both scientific and practical purposes. Spatially explicit crop-type information can be used to ...estimate crop areas for a variety of monitoring and decision-making applications such as crop insurance, land rental, supply-chain logistics, and financial market forecasting. However, there is no publically available spatially explicit in-season crop-type classification information for the U.S. Corn Belt (a landscape predominated by corn and soybean). Instead, researchers and decision-makers have to wait until four to six months after harvest to have such information from the previous year. The state-of-the-art research on crop-type classification has been shifted from relying on only spectral features of single static images to combining together spectral and time-series information. While Landsat data have a desirable spatial resolution for field-level crop-type classification, the ability to extract temporal phenology information based on Landsat data remains a challenge due to low temporal revisiting frequency and inevitable cloud contamination. To address this challenge and generate accurate, cost-effective, and in-season crop-type classification, this research uses the USDA's Common Land Units (CLUs) to aggregate spectral information for each field based on a time-series Landsat image data stack to largely overcome the cloud contamination issue while exploiting a machine learning model based on Deep Neural Network (DNN) and high-performance computing for intelligent and scalable computation of classification processes. Experiments were designed to evaluate what information is most useful for training the machine learning model for crop-type classification, and how various spatial and temporal factors affect the crop-type classification performance in order to derive timely crop type information. All experiments were conducted over Champaign County located in central Illinois, and a total of 1322 Landsat multi-temporal scenes including all the six optical spectral bands spanning from 2000 to 2015 were used. Computational experiments show the inclusion of temporal phenology information and evenly distributed spatial training samples in the study domain improves classification performance. The shortwave infrared bands show notably better performance than the widely used visible and near-infrared bands for classifying corn and soybean. In comparison with USDA's Crop Data Layer (CDL), this study found a relatively high Overall Accuracy (i.e. the number of the corrected classified fields divided by the number of the total fields) of 96% for classifying corn and soybean across all CLU fields in the Champaign County from 2000 to 2015. Furthermore, our approach achieved 95% Overall Accuracy by late July of the concurrent year for classifying corn and soybean. The findings suggest the methodology presented in this paper is promising for accurate, cost-effective, and in-season classification of field-level crop types, which may be scaled up to large geographic extents such as the U.S. Corn Belt.
•An in-season, field-level classification system for corn and soybean is presented.•Time series information of Landsat and the field boundary from CLU are used.•A case study has been demonstrated at a county in the US Corn Belt for 2000–2015.•Shortwave infrared bands provide most useful info for classifying corn and soybean.•95% classification accuracy can be achieved by late July of the concurrent year.
As a result of the analysis of the production and status of the fleet of flax harvesting machinery, negative problems with the machines of farms of different types were revealed. The extensive ...statistical material on the dynamics of changes in flax production indicators has been generalized. Conditional (reference) coefficients have been investigated and refined. The technological need for specialized flax harvesting equipment and its forecast for meeting Russia’s demand for flax fiber have been determined.
Under the pressure of climate change, the demands for alternative green hydrogen (H 2 ) production methods have been on the rise to conform to the global trend of transition to a H 2 society. This ...article proposes a multirenewable-to-hydrogen production method to enhance the green H 2 production efficiency for renewable-dominated hydrogen fueling stations (HFSs). In this method, the aqueous electrolysis of native biomass can be powered by wind and solar generations based on electrochemical effects, and both electrolysis current and temperature are taken into account for facilitating on-site H 2 production and reducing the electricity consumption. Moreover, a capsule network based H 2 demand forecasting model is formulated to estimate the gas load for HFS by extracting the underlying spatial features and temporal dependencies of traffic flows in the transportation network. Furthermore, a hierarchical coordinated control strategy is developed to suppress high fluctuations in electrolysis current caused by volatility of wind and solar outputs based on model predictive control framework. Comparative studies validate the superior performance of the proposed methodology over the power-to-gas scheme on electrolysis efficiency and economic benefits.
The technological advancement in the communication and control infrastructure helps those smart households (SHs) that more actively participate in the incentive-based demand response (IBDR) programs. ...As the agent facilitating the SHs' participation in the IBDR program, load aggregators (LAs) need to comprehend the available SHs' demand response (DR) capacity before trading in the day-ahead market. However, there are few studies that forecast the available aggregated DR capacity from LAs' perspective. Therefore, this article proposes a forecasting model aiming to aid LAs forecast the available aggregated SHs' DR capacity in the day-ahead market. First, a home energy management system is implemented to perform optimal scheduling for SHs and to model the customers' responsive behavior in the IBDR program; second, a customer baseline load estimation method is applied to quantify the SHs' aggregated DR capacity during DR days; third, several features which may have significant impacts on the aggregated DR capacity are extracted and they are processed by principal component analysis; and finally, a support vector machine based forecasting model is proposed to forecast the aggregated SHs' DR capacity in the day-ahead market. The case study indicates that the proposed forecasting framework could provide good performance in terms of stability and accuracy.
Discrete grey model (DGM(1,1)) is considered to be superior to grey model (GM(1,1)) because it can completely simulate the pure exponential sequences. However, owing to practical data generation ...process is interfered by random factors, the superiority of DGM(1,1) model to GM(1,1) model cannot be widely and reliably validated in practical applications. Therefore, by utilizing the Monte-Carlo simulation method, groups of completely random sequences conforming to different distributions are randomly generated and the predictive capabilities of the two models are compared. In addition, the novel grey models of fractional order accumulation (FGM(1,1) and FDGM(1,1)) are introduced for further comparison. The results show that the predictive capabilities of the two models for random sequences conforming to normal distribution are nearly equivalent. However, the predictive capabilities of DGM(1,1) model for the other three kinds of random sequences are all superior to those of GM(1,1) model. The parameters change of completely random sequences influences the predictive capabilities of the two models. The parameters change of random sequences with exponential trend can influence the predictive capability of GM(1,1) model while has no significant influence on the predictive capability of DGM(1,1) model.
•The predictive capabilities of grey models are compared using Monte-Carlo simulation.•Random sequences conforming to different distributions are generated.•24,000 GM(1,1) models and DGM(1,1) models are separately established.•The conclusions can be used as the reference for model selection.
Distributed renewable energy, particularly photovoltaics (PV), has expanded rapidly over the past decade. Distributed PV is located behind the meter and is, thus, invisible to the retailers and the ...distribution system operator. This invisible generation, thus, injects additional uncertainty in the net load and makes it harder to forecast. This paper proposes a data-driven probabilistic net load forecasting method specifically designed to handle a high penetration of behind-the-meter (BtM) PV. The capacity of BtM PV is first estimated using a maximal information coefficient based correlation analysis and a grid search. The net load profile is then decomposed into three parts (PV output, actual load, and residual) which are forecast individually. Correlation analysis based on copula theory is conducted on the distributions and dependencies of the forecasting errors to generate a probabilistic net load forecast. Case studies based on ISO New England data demonstrate that the proposed method outperforms other approaches, particularly when the penetration of BtM PV is high.
Uncertainty modeling of renewable energy sources, load demand, electricity price, etc. create a high volume of data in smart grids. Accordingly, in this article, a precise forecasting method based on ...a deep learning concept with microclustering (MC) task is presented. The MC method is structured based on hybrid unsupervised and supervised clustering tasks by <inline-formula><tex-math notation="LaTeX">K</tex-math></inline-formula>-means and Gaussian support vector machine, respectively. In the proposed method, the input data sequence is clustered by the MC task, and then the forecasting process is employed. By applying the MC, input data in each hour are categorized into different groups, and a distinctive forecasting unit is allocated to each one. In this way, more clusters and forecasting networks are earmarked for the hours with higher fluctuation rates. The bi-directional long short-term memory (B-LSTM), which is one of the newest recurrent artificial neural networks, is proposed as the forecasting unit. The B-LSTM has bidirectional memory-feedforward and feedback loops-that helps us to investigate both previous and future hidden layers data. The optimal number of clusters in each hour is determined based on the Davies-Bouldin index. To evaluate the performance of the proposed method, in this study, three forecasting tasks including the wind speed, load demand, and electricity price are studied in different periods using the Ontario province, Canada, data set. The results are compared with other benchmarking methods to verify the robustness and effectiveness of the proposed method. In fact, the proposed method, which is equipped with the MC technique and B-LSTM networks, significantly promotes the forecasting results, especially in spike points.
PDF
