Benefits and limits of season-ahead forecasts for hydropower production: a global analysis

2020 ◽  
Author(s):  
Jia Yi Ng ◽  
Donghoon Lee ◽  
Stefano Galelli ◽  
Paul Block
Keyword(s):  
Predictive Accuracy ◽  
Global Analysis ◽  
Principal Component ◽  
Seasonal Forecasts ◽  
Design Specifications ◽  
Reservoir Design ◽  
Hydropower Production ◽  
Flooding Season ◽  
Turbine Capacity ◽  
Effective Use

<p>Season-ahead hydro-climatological forecasts are a useful source of information for hydropower operators: at the onset of a flooding season, for example, predictive information on the timing and magnitude of the inflow volume can help operators schedule the release trajectory, decide on the amount of volume to store, and therefore maximize hydropower production. Intuitively, the forecast value varies not only with predictive accuracy, or skill, but also with the reservoir design specifications. Characterizing and explaining the relationship between skill, design specifications, and value is thus a necessary step towards a more informed and effective use of seasonal forecasts. To investigate the nature of this relationship, we modeled 1,593 hydropower reservoirs, for which we developed 3-month ahead monthly inflow forecasts—based on a principal component linear regression model. Our results show that more than half of the dams could benefit from forecasts, averaging a 6.56% annual increase in hydropower production. We also found that forecast value is largely controlled by reservoir design specifications; specifically, we found that reservoirs with small storage capacity (relative to inflow) and large inflow volumes (relative to turbine capacity) have better chances of benefitting from accurate forecasts. With this information, we classify and map each dam on the basis of its potential to increase hydropower production.</p>

scholarly journals The optimal number of partial least squares components in genomic selection for pork pH

2017 ◽  
Vol 47 (1) ◽  
Author(s):  
Fernanda Gomes da Silveira ◽  
Darlene Ana Souza Duarte ◽  
Lucas Monteiro Chaves ◽  
Fabyano Fonseca e Silva ◽  
Ivan Carvalho Filho ◽  
...  
Keyword(s):  
Least Squares ◽  
Genomic Selection ◽  
Multiple Regression ◽  
Partial Least Squares ◽  
Predictive Accuracy ◽  
Principal Component ◽  
Theoretical Background ◽  
Optimal Number ◽  
Number Of Components ◽  
Regression Techniques

ABSTRACT: The main application of genomic selection (GS) is the early identification of genetically superior animals for traits difficult-to-measure or lately evaluated, such as meat pH (measured after slaughter). Because the number of markers in GS is generally larger than the number of genotyped animals and these markers are highly correlated owing to linkage disequilibrium, statistical methods based on dimensionality reduction have been proposed. Among them, the partial least squares (PLS) technique stands out, because of its simplicity and high predictive accuracy. However, choosing the optimal number of components remains a relevant issue for PLS applications. Thus, we applied PLS (and principal component and traditional multiple regression) techniques to GS for pork pH traits (with pH measured at 45min and 24h after slaughter) and also identified the optimal number of PLS components based on the degree-of-freedom (DoF) and cross-validation (CV) methods. The PLS method out performs the principal component and traditional multiple regression techniques, enabling satisfactory predictions for pork pH traits using only genotypic data (low-density SNP panel). Furthermore, the SNP marker estimates from PLS revealed a relevant region on chromosome 4, which may affect these traits. The DoF and CV methods showed similar results for determining the optimal number of components in PLS analysis; thus, from the statistical viewpoint, the DoF method should be preferred because of its theoretical background (based on the "statistical information theory"), whereas CV is an empirical method based on computational effort.

scholarly journals PCA Forecast Averaging—Predicting Day-Ahead and Intraday Electricity Prices

Energies ◽  
2020 ◽  
Vol 13 (14) ◽  
pp. 3530
Author(s):  
Katarzyna Maciejowska ◽  
Bartosz Uniejewski ◽  
Tomasz Serafin
Keyword(s):  
Predictive Accuracy ◽  
Expert Knowledge ◽  
Predictive Ability ◽  
Principal Component ◽  
Absolute Error ◽  
Electricity Prices ◽  
Short Term ◽  
White Test ◽  
The Mean ◽  
Short Term Forecasting

Recently, the development in combining point forecasts of electricity prices obtained with different length of calibration windows have provided an extremely efficient and simple tool for improving predictive accuracy. However, the proposed methods are strongly dependent on expert knowledge and may not be directly transferred from one to another model or market. Hence, we consider a novel extension and propose to use principal component analysis (PCA) to automate the procedure of averaging over a rich pool of predictions. We apply PCA to a panel of over 650 point forecasts obtained for different calibration windows length. The robustness of the approach is evaluated with three different forecasting tasks, i.e., forecasting day-ahead prices, forecasting intraday ID3 prices one day in advance, and finally very short term forecasting of ID3 prices (i.e., six hours before delivery). The empirical results are compared using the Mean Absolute Error measure and Giacomini and White test for conditional predictive ability (CPA). The results indicate that PCA averaging not only yields significantly more accurate forecasts than individual predictions but also outperforms other forecast averaging schemes.

scholarly journals Identifying candidate Aspergillus pathogenicity factors by annotation frequency

2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Kayla K. Pennerman ◽  
Guohua Yin ◽  
Anthony E. Glenn ◽  
Joan W. Bennett
Keyword(s):  
Gc Content ◽  
Sugar Metabolism ◽  
Principal Component ◽  
Amino Sugar ◽  
Human Immune System ◽  
Protein Coding ◽  
Functional Annotations ◽  
Pathogenicity Factors ◽  
Genes Encoding ◽  
Effective Use

Abstract Background Members of the genus Aspergillus display a variety of lifestyles, ranging from saprobic to pathogenic on plants and/or animals. Increased genome sequencing of economically important members of the genus permits effective use of “-omics” comparisons between closely related species and strains to identify candidate genes that may contribute to phenotypes of interest, especially relating to pathogenicity. Protein-coding genes were predicted from 216 genomes of 12 Aspergillus species, and the frequencies of various structural aspects (exon count and length, intron count and length, GC content, and codon usage) and functional annotations (InterPro, Gene Ontology, and Kyoto Encyclopedia of Genes and Genomes terms) were compared. Results Using principal component analyses, the three sets of functional annotations for each strain were clustered by species. The species clusters appeared to separate by pathogenicity on plants along the first dimensions, which accounted for over 20% of the variance. More annotations for genes encoding pectinases and secondary metabolite biosynthetic enzymes were assigned to phytopathogenic strains from species such as Aspergillus flavus. In contrast, Aspergillus fumigatus strains, which are pathogenic to animals but not plants, were assigned relatively more terms related to phosphate transferases, and carbohydrate and amino-sugar metabolism. Analyses of publicly available RNA-Seq data indicated that one A. fumigatus protein among 17 amino-sugar processing candidates, a hexokinase, was up-regulated during co-culturing with human immune system cells. Conclusion Genes encoding hexokinases and other proteins of interest may be subject to future manipulations to further refine understanding of Aspergillus pathogenicity factors.

Applied-Information Technology in Power System with Short-Term Load Forecasting Based on SPSS and BP Neural Network

2014 ◽  
Vol 1022 ◽  
pp. 241-244 ◽  
Author(s):  
Jian Ping Chen ◽  
Chang Hao Xia ◽  
Zhi Peng Tian
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Predictive Accuracy ◽  
Load Forecasting ◽  
Influence Factors ◽  
Principal Component ◽  
Weather Data ◽  
Power Load ◽  
Bp Neural Network Model ◽  
Bp Model

In the study of power load forecasting, the factors influencing power load have data redundancy and data nonlinearity. The traditional load forecasting methods can’t eliminate redundant or nonlinear law between data, which result in reduced accuracy. In order to improve the predictive accuracy of power load, a prediction model based on BP neural network and SPSS (SPSS-BP) is established. The paper first analyzes the correlation and principal component of influence factors of electric power load, which eliminates the redundancy between various factors, accelerates the speed of BP neural network forecasting and improves predictive accuracy; then model the processed data and forecast through the BP neural network model. One-month weather data and load data of Yichang city have been confirmatory tested and analyzed through application of SPSS-BP model. The results show that SPSS-BP model significantly improves the accuracy, verify the feasibility and effectiveness of the model.

scholarly journals Climate Change Perception and Uptake of Climate-Smart Agriculture in Rice Production in Ebonyi State, Nigeria

Atmosphere ◽  
2021 ◽  
Vol 12 (11) ◽  
pp. 1503
Author(s):  
Robert Ugochukwu Onyeneke ◽  
Mark Umunna Amadi ◽  
Chukwudi Loveday Njoku ◽  
Emeka Emmanuel Osuji
Keyword(s):  
Climate Change ◽  
Principal Component ◽  
Rice Production ◽  
Climate Risks ◽  
Rice Farmers ◽  
Change Perception ◽  
Climate Change Perception ◽  
Smart Agriculture ◽  
Effective Use ◽  
Climate Events

Rice production in Nigeria is vulnerable to climate risks and rice farmers over time have experienced the risks and their respective impacts on rice farming. Rice farmers have also responded to perceived climate risks with strategies believed to be climate-smart. Farmers’ perception of climate risks is an important first step of determining any action to be taken to counteract the negative effects of climate change on agriculture. Studies on the link between perceived climate risks and farmers’ response strategies are increasing. However, there are limited studies on the determinants of rice farmers’ perception of climate events. The paper therefore examined climate change perception and uptake of climate-smart agriculture in rice production in Ebonyi State, Nigeria using cross-sectional data from 347 rice farmers in an important rice-producing area in Nigeria. Principal component analysis, multivariate probit regression model and descriptive statistics were adopted for data analysis. Perceived climate events include increased rainfall intensity, prolonged dry seasons, frequent floods, rising temperature, severe windstorms, unpredictable rainfall pattern and distribution, late onset rain, and early cessation of rain. Farmers’ socioeconomic, farm and institutional characteristics influenced their perception of climate change. Additionally, rice farmers used a variety of climate-smart practices and technologies to respond to the perceived climate events. Such climate-smart practices include planting improved rice varieties, insurance, planting different crops, livelihood diversification, soil and water conservation techniques, adjusting planting and harvesting dates, irrigation, reliance on climate information and forecasts, planting on the nursery, appropriate application of fertilizer and efficient and effective use of pesticides. These climate-smart agricultural measures were further delineated into five broad packages using principal component analysis. These packages include crop and land management practices, climate-based services and irrigation, livelihood diversification and soil fertility management, efficient and effective use of pesticide and planting on the nursery. High fertilizer costs, lack of access to inputs, insufficient land, insufficient capital, pests and diseases, floods, scorching sun, high labour cost, insufficient climate information, and poor extension services were the barriers to uptake of climate-smart agriculture in rice production. Rice farmers should be supported to implement climate-smart agriculture in rice production in order to achieve the objectives of increased rice productivity and income, food security, climate resilience and mitigation.

Application of Statistical Models to the Prediction of Seasonal Rainfall Anomalies over the Sahel

2014 ◽  
Vol 53 (3) ◽  
pp. 614-636 ◽  
Author(s):  
Hamada S. Badr ◽  
Benjamin F. Zaitchik ◽  
Seth D. Guikema
Keyword(s):  
Statistical Models ◽  
Large Scale ◽  
Predictive Accuracy ◽  
Learning Algorithm ◽  
Surface Air Temperature ◽  
Principal Component ◽  
Seasonal Precipitation ◽  
Precipitation Prediction ◽  
Rainfall Anomalies ◽  
Sahel Region

AbstractRainfall in the Sahel region of Africa is prone to large interannual variability, and it has exhibited a recent multidecadal drying trend. The well-documented social impacts of this variability have motivated numerous efforts at seasonal precipitation prediction, many of which employ statistical techniques that forecast Sahelian precipitation as a function of large-scale indices of surface air temperature (SAT) anomalies, sea surface temperature (SST), surface pressure, and other variables. These statistical models have demonstrated some skill, but nearly all have adopted conventional statistical modeling techniques—most commonly generalized linear models—to associate predictor fields with precipitation anomalies. Here, the results of an artificial neural network (ANN) machine-learning algorithm applied to predict summertime (July–September) Sahel rainfall anomalies using indices of springtime (April–June) SST and SAT anomalies for the period 1900–2011 are presented. Principal component analysis was used to remove multicollinearity between predictor variables. Predictive accuracy was assessed using repeated k-fold random holdout and leave-one-out cross-validation methods. It was found that the ANN achieved predictive accuracy superior to that of eight alternative statistical methods tested in this study, and it was also superior to that of previously published predictive models of summertime Sahel precipitation. Analysis of partial dependence plots indicates that ANN skill is derived primarily from the ability to capture nonlinear influences that multiple major modes of large-scale variability have on Sahelian precipitation. These results point to the value of ANN techniques for seasonal precipitation prediction in the Sahel.

Sign in / Sign up

Export Citation Format

Share Document