Georgia Papacharalampous , Hristos Tyralis , Ilias G. Pechlivanidis , Salvatore Grimaldi , Elena Volpi
{"title":"大规模特征提取用于解释和预测全球尺度的水文气候时间序列可预测性","authors":"Georgia Papacharalampous , Hristos Tyralis , Ilias G. Pechlivanidis , Salvatore Grimaldi , Elena Volpi","doi":"10.1016/j.gsf.2022.101349","DOIUrl":null,"url":null,"abstract":"<div><p>Statistical analyses and descriptive characterizations are sometimes assumed to be offering information on time series forecastability. Despite the scientific interest suggested by such assumptions, the relationships between descriptive time series features (e.g., temporal dependence, entropy, seasonality, trend and linearity features) and actual time series forecastability (quantified by issuing and assessing forecasts for the past) are scarcely studied and quantified in the literature. In this work, we aim to fill in this gap by investigating such relationships, and the way that they can be exploited for understanding hydroclimatic forecastability and its patterns. To this end, we follow a systematic framework bringing together a variety of –mostly new for hydrology– concepts and methods, including 57 descriptive features and nine seasonal time series forecasting methods (i.e., one simple, five exponential smoothing, two state space and one automated autoregressive fractionally integrated moving average methods). We apply this framework to three global datasets originating from the larger Global Historical Climatology Network (GHCN) and Global Streamflow Indices and Metadata (GSIM) archives. As these datasets comprise over 13,000 monthly temperature, precipitation and river flow time series from several continents and hydroclimatic regimes, they allow us to provide trustable characterizations and interpretations of 12-month ahead hydroclimatic forecastability at the global scale. We first find that the exponential smoothing and state space methods for time series forecasting are rather equally efficient in identifying an upper limit of this forecastability in terms of Nash-Sutcliffe efficiency, while the simple method is shown to be mostly useful in identifying its lower limit. We then demonstrate that the assessed forecastability is strongly related to several descriptive features, including seasonality, entropy, (partial) autocorrelation, stability, (non)linearity, spikiness and heterogeneity features, among others. We further (i) show that, if such descriptive information is available for a monthly hydroclimatic time series, we can even foretell the quality of its future forecasts with a considerable degree of confidence, and (ii) rank the features according to their efficiency in explaining and foretelling forecastability. We believe that the obtained rankings are of key importance for understanding forecastability. Spatial forecastability patterns are also revealed through our experiments, with East Asia (Europe) being characterized by larger (smaller) monthly temperature time series forecastability and the Indian subcontinent (Australia) being characterized by larger (smaller) monthly precipitation time series forecastability, compared to other continental-scale regions, and less notable differences characterizing monthly river flow from continent to continent. A comprehensive interpretation of such patters through massive feature extraction and feature-based time series clustering is shown to be possible. Indeed, continental-scale regions characterized by different degrees of forecastability are also attributed to different clusters or mixtures of clusters (because of their essential differences in terms of descriptive features).</p></div>","PeriodicalId":12711,"journal":{"name":"Geoscience frontiers","volume":"13 3","pages":"Article 101349"},"PeriodicalIF":8.5000,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1674987122000020/pdfft?md5=d55f9255b411c9fc52af3417621dce76&pid=1-s2.0-S1674987122000020-main.pdf","citationCount":"8","resultStr":"{\"title\":\"Massive feature extraction for explaining and foretelling hydroclimatic time series forecastability at the global scale\",\"authors\":\"Georgia Papacharalampous , Hristos Tyralis , Ilias G. Pechlivanidis , Salvatore Grimaldi , Elena Volpi\",\"doi\":\"10.1016/j.gsf.2022.101349\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Statistical analyses and descriptive characterizations are sometimes assumed to be offering information on time series forecastability. Despite the scientific interest suggested by such assumptions, the relationships between descriptive time series features (e.g., temporal dependence, entropy, seasonality, trend and linearity features) and actual time series forecastability (quantified by issuing and assessing forecasts for the past) are scarcely studied and quantified in the literature. In this work, we aim to fill in this gap by investigating such relationships, and the way that they can be exploited for understanding hydroclimatic forecastability and its patterns. To this end, we follow a systematic framework bringing together a variety of –mostly new for hydrology– concepts and methods, including 57 descriptive features and nine seasonal time series forecasting methods (i.e., one simple, five exponential smoothing, two state space and one automated autoregressive fractionally integrated moving average methods). We apply this framework to three global datasets originating from the larger Global Historical Climatology Network (GHCN) and Global Streamflow Indices and Metadata (GSIM) archives. As these datasets comprise over 13,000 monthly temperature, precipitation and river flow time series from several continents and hydroclimatic regimes, they allow us to provide trustable characterizations and interpretations of 12-month ahead hydroclimatic forecastability at the global scale. We first find that the exponential smoothing and state space methods for time series forecasting are rather equally efficient in identifying an upper limit of this forecastability in terms of Nash-Sutcliffe efficiency, while the simple method is shown to be mostly useful in identifying its lower limit. We then demonstrate that the assessed forecastability is strongly related to several descriptive features, including seasonality, entropy, (partial) autocorrelation, stability, (non)linearity, spikiness and heterogeneity features, among others. We further (i) show that, if such descriptive information is available for a monthly hydroclimatic time series, we can even foretell the quality of its future forecasts with a considerable degree of confidence, and (ii) rank the features according to their efficiency in explaining and foretelling forecastability. We believe that the obtained rankings are of key importance for understanding forecastability. Spatial forecastability patterns are also revealed through our experiments, with East Asia (Europe) being characterized by larger (smaller) monthly temperature time series forecastability and the Indian subcontinent (Australia) being characterized by larger (smaller) monthly precipitation time series forecastability, compared to other continental-scale regions, and less notable differences characterizing monthly river flow from continent to continent. A comprehensive interpretation of such patters through massive feature extraction and feature-based time series clustering is shown to be possible. Indeed, continental-scale regions characterized by different degrees of forecastability are also attributed to different clusters or mixtures of clusters (because of their essential differences in terms of descriptive features).</p></div>\",\"PeriodicalId\":12711,\"journal\":{\"name\":\"Geoscience frontiers\",\"volume\":\"13 3\",\"pages\":\"Article 101349\"},\"PeriodicalIF\":8.5000,\"publicationDate\":\"2022-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S1674987122000020/pdfft?md5=d55f9255b411c9fc52af3417621dce76&pid=1-s2.0-S1674987122000020-main.pdf\",\"citationCount\":\"8\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Geoscience frontiers\",\"FirstCategoryId\":\"1089\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1674987122000020\",\"RegionNum\":1,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"GEOSCIENCES, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Geoscience frontiers","FirstCategoryId":"1089","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1674987122000020","RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GEOSCIENCES, MULTIDISCIPLINARY","Score":null,"Total":0}
Massive feature extraction for explaining and foretelling hydroclimatic time series forecastability at the global scale
Statistical analyses and descriptive characterizations are sometimes assumed to be offering information on time series forecastability. Despite the scientific interest suggested by such assumptions, the relationships between descriptive time series features (e.g., temporal dependence, entropy, seasonality, trend and linearity features) and actual time series forecastability (quantified by issuing and assessing forecasts for the past) are scarcely studied and quantified in the literature. In this work, we aim to fill in this gap by investigating such relationships, and the way that they can be exploited for understanding hydroclimatic forecastability and its patterns. To this end, we follow a systematic framework bringing together a variety of –mostly new for hydrology– concepts and methods, including 57 descriptive features and nine seasonal time series forecasting methods (i.e., one simple, five exponential smoothing, two state space and one automated autoregressive fractionally integrated moving average methods). We apply this framework to three global datasets originating from the larger Global Historical Climatology Network (GHCN) and Global Streamflow Indices and Metadata (GSIM) archives. As these datasets comprise over 13,000 monthly temperature, precipitation and river flow time series from several continents and hydroclimatic regimes, they allow us to provide trustable characterizations and interpretations of 12-month ahead hydroclimatic forecastability at the global scale. We first find that the exponential smoothing and state space methods for time series forecasting are rather equally efficient in identifying an upper limit of this forecastability in terms of Nash-Sutcliffe efficiency, while the simple method is shown to be mostly useful in identifying its lower limit. We then demonstrate that the assessed forecastability is strongly related to several descriptive features, including seasonality, entropy, (partial) autocorrelation, stability, (non)linearity, spikiness and heterogeneity features, among others. We further (i) show that, if such descriptive information is available for a monthly hydroclimatic time series, we can even foretell the quality of its future forecasts with a considerable degree of confidence, and (ii) rank the features according to their efficiency in explaining and foretelling forecastability. We believe that the obtained rankings are of key importance for understanding forecastability. Spatial forecastability patterns are also revealed through our experiments, with East Asia (Europe) being characterized by larger (smaller) monthly temperature time series forecastability and the Indian subcontinent (Australia) being characterized by larger (smaller) monthly precipitation time series forecastability, compared to other continental-scale regions, and less notable differences characterizing monthly river flow from continent to continent. A comprehensive interpretation of such patters through massive feature extraction and feature-based time series clustering is shown to be possible. Indeed, continental-scale regions characterized by different degrees of forecastability are also attributed to different clusters or mixtures of clusters (because of their essential differences in terms of descriptive features).
Geoscience frontiersEarth and Planetary Sciences-General Earth and Planetary Sciences
CiteScore
17.80
自引率
3.40%
发文量
147
审稿时长
35 days
期刊介绍:
Geoscience Frontiers (GSF) is the Journal of China University of Geosciences (Beijing) and Peking University. It publishes peer-reviewed research articles and reviews in interdisciplinary fields of Earth and Planetary Sciences. GSF covers various research areas including petrology and geochemistry, lithospheric architecture and mantle dynamics, global tectonics, economic geology and fuel exploration, geophysics, stratigraphy and paleontology, environmental and engineering geology, astrogeology, and the nexus of resources-energy-emissions-climate under Sustainable Development Goals. The journal aims to bridge innovative, provocative, and challenging concepts and models in these fields, providing insights on correlations and evolution.