Pub Date : 2022-09-23DOI: 10.1175/aies-d-22-0032.1
Boyin Huang, Xungang Yin, M. Menne, R. Vose, Huai-min Zhang
NOAAGlobalTemp is NOAA’s operational global surface temperature product, which has been widely used in the Earth’s climate assessment and monitoring. To improve the spatial interpolation of monthly land surface air temperatures (LSATs) in NOAAGlobalTemp from 1850 to 2020, a three-layer artificial neural network (ANN) system was designed. The ANN system was trained by repeatedly randomly selecting 90% of the LSATs from ERA5 (1950–2019) and validating with the remaining 10%. Validations show clear improvements of ANN over the original empirical orthogonal teleconnection (EOT) method: The global spatial correlation coefficient (SCC) increases from 65% to 80%, and the global root-mean-square-difference (RMSD) decreases from 0.99°C to 0.57°C during 1850–2020. The improvements of SCCs and RMSDs are larger in the Southern Hemisphere (SH) than in the Northern Hemisphere (NH), and are larger before the 1950s and where observations are sparse. The ANN system was finally fed in observed LSATs, and its output over the global land surface was compared with those from the EOT method. Comparisons demonstrate similar improvements by ANN over the EOT method: The global SCC increased from 78% to 89%, the global RMSD decreased from 0.93°C to 0.68°C, and the LSAT variability quantified by the monthly standard deviation (STD) increases from 1.16°C to 1.41°C during 1850–2020. While the SCC, RMSD, and STD at the monthly timescale have been improved, long-term trends remain largely unchanged because the low-frequency component of LSAT in ANN is identical to that in the EOT approach.
{"title":"Improvements to the Land Surface Air Temperature Reconstruction in NOAAGlobalTemp: An Artificial Neural Network Approach","authors":"Boyin Huang, Xungang Yin, M. Menne, R. Vose, Huai-min Zhang","doi":"10.1175/aies-d-22-0032.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0032.1","url":null,"abstract":"\u0000NOAAGlobalTemp is NOAA’s operational global surface temperature product, which has been widely used in the Earth’s climate assessment and monitoring. To improve the spatial interpolation of monthly land surface air temperatures (LSATs) in NOAAGlobalTemp from 1850 to 2020, a three-layer artificial neural network (ANN) system was designed. The ANN system was trained by repeatedly randomly selecting 90% of the LSATs from ERA5 (1950–2019) and validating with the remaining 10%. Validations show clear improvements of ANN over the original empirical orthogonal teleconnection (EOT) method: The global spatial correlation coefficient (SCC) increases from 65% to 80%, and the global root-mean-square-difference (RMSD) decreases from 0.99°C to 0.57°C during 1850–2020. The improvements of SCCs and RMSDs are larger in the Southern Hemisphere (SH) than in the Northern Hemisphere (NH), and are larger before the 1950s and where observations are sparse.\u0000The ANN system was finally fed in observed LSATs, and its output over the global land surface was compared with those from the EOT method. Comparisons demonstrate similar improvements by ANN over the EOT method: The global SCC increased from 78% to 89%, the global RMSD decreased from 0.93°C to 0.68°C, and the LSAT variability quantified by the monthly standard deviation (STD) increases from 1.16°C to 1.41°C during 1850–2020. While the SCC, RMSD, and STD at the monthly timescale have been improved, long-term trends remain largely unchanged because the low-frequency component of LSAT in ANN is identical to that in the EOT approach.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"17 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89107682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-06DOI: 10.1175/aies-d-22-0010.1
U. Mital, D. Dwivedi, Ilhan Özgen-Xian, J. B. Brown, C. Steefel
An accurate characterization of the water content of snowpack, or snow water equivalent (SWE), is necessary to quantify water availability and constrain hydrologic and land-surface models. Recently, airborne observations (e.g., lidar) have emerged as a promising method to accurately quantify SWE at high resolutions (scales of ∼100m and finer). However, the frequency of these observations is very low, typically once or twice per season in Rocky Mountains, Colorado. Here, we present a machine learning framework based on Random Forests to model temporally sparse lidar-derived SWE, enabling estimation of SWE at unmapped time points. We approximated the physical processes governing snow accumulation and melt as well as snow characteristics by obtaining fifteen different variables from gridded estimates of precipitation, temperature, surface reflectance, elevation, and canopy. Results showed that in the Rocky Mountains of Colorado, our framework is capable of modeling SWE with a higher accuracy when compared with estimates generated by the Snow Data Assimilation System (SNODAS). The mean value of the coefficient of determination (R2) using our approach was 0.57 and the root mean squared error (RMSE) was 13 cm, which was a significant improvement over SNODAS (mean R2 = 0.13, RMSE = 20 cm). We explored the relative importance of the input variables, and observed that at the spatial resolution of 800 m, meteorological variables are more important drivers of predictive accuracy than surface variables which characterize the properties of snow on the ground. This research provides a framework to expand the applicability of lidar-derived SWE to unmapped time points.
{"title":"Modeling Spatial Distribution of Snow Water Equivalent by Combining Meteorological and Satellite Data with Lidar Maps","authors":"U. Mital, D. Dwivedi, Ilhan Özgen-Xian, J. B. Brown, C. Steefel","doi":"10.1175/aies-d-22-0010.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0010.1","url":null,"abstract":"\u0000An accurate characterization of the water content of snowpack, or snow water equivalent (SWE), is necessary to quantify water availability and constrain hydrologic and land-surface models. Recently, airborne observations (e.g., lidar) have emerged as a promising method to accurately quantify SWE at high resolutions (scales of ∼100m and finer). However, the frequency of these observations is very low, typically once or twice per season in Rocky Mountains, Colorado. Here, we present a machine learning framework based on Random Forests to model temporally sparse lidar-derived SWE, enabling estimation of SWE at unmapped time points. We approximated the physical processes governing snow accumulation and melt as well as snow characteristics by obtaining fifteen different variables from gridded estimates of precipitation, temperature, surface reflectance, elevation, and canopy. Results showed that in the Rocky Mountains of Colorado, our framework is capable of modeling SWE with a higher accuracy when compared with estimates generated by the Snow Data Assimilation System (SNODAS). The mean value of the coefficient of determination (R2) using our approach was 0.57 and the root mean squared error (RMSE) was 13 cm, which was a significant improvement over SNODAS (mean R2 = 0.13, RMSE = 20 cm). We explored the relative importance of the input variables, and observed that at the spatial resolution of 800 m, meteorological variables are more important drivers of predictive accuracy than surface variables which characterize the properties of snow on the ground. This research provides a framework to expand the applicability of lidar-derived SWE to unmapped time points.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"43 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77165135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-31DOI: 10.1175/aies-d-21-0003.1
H. Cheung, Chang‐Hoi Ho, Minhee Chang
Tropical cyclone (TC) track forecasts derived from dynamical models inherit their errors. In this study, a neural network (NN) algorithm was proposed for postprocessing TC tracks predicted by the Global Ensemble Forecast System (GEFS) for lead times of 2, 4, 5, and 6 days over the western North Pacific. The hybrid NN is a combination of three NN classes: (1) convolutional NN that extracts spatial features from GEFS fields; (2) multilayer perceptron which processes TC positions predicted by GEFS; and (3) recurrent NN that handles information from previous time steps. A dataset of 204 TCs (6744 samples), which were formed from 1985 to 2019 (June through October) and survived for at least six days, was separated into various track patterns. TCs in each track pattern were distributed uniformly to validation and test dataset, in which each contained 10% TCs of the entire dataset, and the remaining 80% were allocated to the training dataset. Two NN architectures were developed, with and without a shortcut connection. Feature selection and hyperparameter tuning were performed to improve model performance. The results present that mean track error and dispersion could be reduced, particularly with the shortcut connection, which also corrected the systematic speed and direction bias of GEFS. Although a reduction in mean track error was not achieved by the NNs for every forecast lead time, improvement can be foreseen upon calibration for reducing overfitting, and the performance encourages further development in the present application.
{"title":"Hybrid neural network models for postprocessing medium-range forecasts of tropical cyclone tracks over the western North Pacific","authors":"H. Cheung, Chang‐Hoi Ho, Minhee Chang","doi":"10.1175/aies-d-21-0003.1","DOIUrl":"https://doi.org/10.1175/aies-d-21-0003.1","url":null,"abstract":"\u0000Tropical cyclone (TC) track forecasts derived from dynamical models inherit their errors. In this study, a neural network (NN) algorithm was proposed for postprocessing TC tracks predicted by the Global Ensemble Forecast System (GEFS) for lead times of 2, 4, 5, and 6 days over the western North Pacific. The hybrid NN is a combination of three NN classes: (1) convolutional NN that extracts spatial features from GEFS fields; (2) multilayer perceptron which processes TC positions predicted by GEFS; and (3) recurrent NN that handles information from previous time steps. A dataset of 204 TCs (6744 samples), which were formed from 1985 to 2019 (June through October) and survived for at least six days, was separated into various track patterns. TCs in each track pattern were distributed uniformly to validation and test dataset, in which each contained 10% TCs of the entire dataset, and the remaining 80% were allocated to the training dataset. Two NN architectures were developed, with and without a shortcut connection. Feature selection and hyperparameter tuning were performed to improve model performance. The results present that mean track error and dispersion could be reduced, particularly with the shortcut connection, which also corrected the systematic speed and direction bias of GEFS. Although a reduction in mean track error was not achieved by the NNs for every forecast lead time, improvement can be foreseen upon calibration for reducing overfitting, and the performance encourages further development in the present application.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"44 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87320352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-29DOI: 10.1175/aies-d-22-0015.1
Bowen Li, S. Basu, S. Watson
As wind and solar power play increasingly important roles in the European energy system, unfavourable weather conditions, such as ‘Dunkelflaute’ (extended calm and cloudy periods), will pose ever greater challenges to transmission system operators. Thus, accurate identification and characterization of such events from open data streams (e.g., reanalysis, numerical weather prediction, and climate projection) are going to be crucial. In this study, we propose a two-step, unsupervised deep learning framework (named WISRnet) to automatically encode spatial patterns of wind speed and insolation, and subsequently, identify Dunkelflaute periods from the encoded patterns. Specifically, a deep convolutional neural network (CNN)-based autoencoder (AE) is first employed for feature extraction from the spatial patterns. These two-dimensional CNN-AE patterns encapsulate both amplitude and spatial information in a parsimonious way. In the second step of the WISRnet framework, a variant of the well-known k-means algorithm is used to divide the CNN-AE patterns in region-dependent meteorological clusters. For the validation of the WISRnet framework, aggregated wind and solar power production data from Belgium are used. Using a simple criterion from published literature, all the Dunkelflaute periods are directly identified from this six year-long dataset. Next, each of these periods is associated with a WISRnet-derived cluster. Interestingly, we find that the majority of these Dunkelflaute periods are part of only five clusters (out of twenty five). We show that in lieu of proprietary power production data, the WISRnet framework can identify Dunkelflaute periods from public-domain meteorological data. To further demonstrate the prowess of this framework, it is deployed to identify and characterize Dunkelflaute events in Denmark, Sweden, and the UK.
{"title":"Automated Identification of ‘Dunkelflaute’ Events: A Convolutional Neural Network-Based Autoencoder Approach","authors":"Bowen Li, S. Basu, S. Watson","doi":"10.1175/aies-d-22-0015.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0015.1","url":null,"abstract":"\u0000As wind and solar power play increasingly important roles in the European energy system, unfavourable weather conditions, such as ‘Dunkelflaute’ (extended calm and cloudy periods), will pose ever greater challenges to transmission system operators. Thus, accurate identification and characterization of such events from open data streams (e.g., reanalysis, numerical weather prediction, and climate projection) are going to be crucial. In this study, we propose a two-step, unsupervised deep learning framework (named WISRnet) to automatically encode spatial patterns of wind speed and insolation, and subsequently, identify Dunkelflaute periods from the encoded patterns. Specifically, a deep convolutional neural network (CNN)-based autoencoder (AE) is first employed for feature extraction from the spatial patterns. These two-dimensional CNN-AE patterns encapsulate both amplitude and spatial information in a parsimonious way. In the second step of the WISRnet framework, a variant of the well-known k-means algorithm is used to divide the CNN-AE patterns in region-dependent meteorological clusters. For the validation of the WISRnet framework, aggregated wind and solar power production data from Belgium are used. Using a simple criterion from published literature, all the Dunkelflaute periods are directly identified from this six year-long dataset. Next, each of these periods is associated with a WISRnet-derived cluster. Interestingly, we find that the majority of these Dunkelflaute periods are part of only five clusters (out of twenty five). We show that in lieu of proprietary power production data, the WISRnet framework can identify Dunkelflaute periods from public-domain meteorological data. To further demonstrate the prowess of this framework, it is deployed to identify and characterize Dunkelflaute events in Denmark, Sweden, and the UK.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77990196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-26DOI: 10.1175/aies-d-22-0002.1
Qinqing Liu, Meijian Yang, Koushan Mohammadi, Dongjin Song, J. Bi, Guiling Wang
A major challenge for food security worldwide is the large inter-annual variability of crop yield, and climate change is expected to further exacerbate this volatility. Accurate prediction of the crop response to climate variability and change is critical for short-term management and long-term planning in multiple sectors. In this study, using maize in the U.S. Corn Belt as an example, we train and validate multiple machine learning (ML) models predicting crop yield based on meteorological variables and soil properties using the leaving-one-year-out approach, and compare their performance with that of a widely used process-based crop model (PBM). Our proposed Long Short-Term Memory model with attention (LSTMatt) outperforms other ML models (including other variations of LSTM developed in this study), and explains 73% of the spatiotemporal variance of the observed maize yield, in contrast to 16% explained by the regionally calibrated PBM; the magnitude of yield prediction errors in LSTMatt is about one-third of that in the PBM. When applied to the extreme drought year 2012 that has no counterpart in the training data, the LSTMatt performance drops but still shows advantage over the PBM. Findings from this study suggest a great potential for out-of-sample application of the 𝐿𝑆𝑇𝑀𝑎𝑡𝑡 model to predict crop yieldunder a changing climate.
{"title":"Machine Learning Crop Yield Models Based on Meteorological Features and Comparison with a Process-Based Model","authors":"Qinqing Liu, Meijian Yang, Koushan Mohammadi, Dongjin Song, J. Bi, Guiling Wang","doi":"10.1175/aies-d-22-0002.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0002.1","url":null,"abstract":"\u0000A major challenge for food security worldwide is the large inter-annual variability of crop yield, and climate change is expected to further exacerbate this volatility. Accurate prediction of the crop response to climate variability and change is critical for short-term management and long-term planning in multiple sectors. In this study, using maize in the U.S. Corn Belt as an example, we train and validate multiple machine learning (ML) models predicting crop yield based on meteorological variables and soil properties using the leaving-one-year-out approach, and compare their performance with that of a widely used process-based crop model (PBM). Our proposed Long Short-Term Memory model with attention (LSTMatt) outperforms other ML models (including other variations of LSTM developed in this study), and explains 73% of the spatiotemporal variance of the observed maize yield, in contrast to 16% explained by the regionally calibrated PBM; the magnitude of yield prediction errors in LSTMatt is about one-third of that in the PBM. When applied to the extreme drought year 2012 that has no counterpart in the training data, the LSTMatt performance drops but still shows advantage over the PBM. Findings from this study suggest a great potential for out-of-sample application of the 𝐿𝑆𝑇𝑀𝑎𝑡𝑡 model to predict crop yieldunder a changing climate.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"451 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79706635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-26DOI: 10.1175/aies-d-21-0001.1
C. White, A. Heidinger, S. Ackerman
Satellite imager estimates of cloud-top pressure (CTP) have many applications in both operations and in studying long-term variations in cloud properties. Recently, machine learning (ML) approaches have shown improvement upon physically-based algorithms. However, ML approaches, and especially neural networks, can suffer from a lack of interpretability making it difficult to understand what information is most useful for accurate predictions of cloud properties. We trained several neural networks to estimate CTP from the infrared channels of the Visible Infrared Imaging Radiometer Suite (VIIRS) and the Advanced Baseline Imager (ABI). The main focus of this work is assessing the relative importance of each instrument’s infrared channels in neural networks trained to estimate CTP. We use several ML explainability methods to offer different perspectives on feature importance. These methods show many differences in the relative feature importance depending on the exact method used, but most agree on a few points. Overall, the 8.4- and 8.6-μm channels appear to be the most useful for CTP estimation on ABI and VIIRS, respectively, with other native infrared window channels and the 13.3-μm channel playing a moderate role. Furthermore, we find that the neural networks learn relationships that may account for properties of clouds such as opacity and cloud-top phase that otherwise complicate the estimation of CTP.
{"title":"Probing the Explainability of Neural Network Cloud-Top Pressure Models for LEO and GEO Imagers","authors":"C. White, A. Heidinger, S. Ackerman","doi":"10.1175/aies-d-21-0001.1","DOIUrl":"https://doi.org/10.1175/aies-d-21-0001.1","url":null,"abstract":"\u0000Satellite imager estimates of cloud-top pressure (CTP) have many applications in both operations and in studying long-term variations in cloud properties. Recently, machine learning (ML) approaches have shown improvement upon physically-based algorithms. However, ML approaches, and especially neural networks, can suffer from a lack of interpretability making it difficult to understand what information is most useful for accurate predictions of cloud properties. We trained several neural networks to estimate CTP from the infrared channels of the Visible Infrared Imaging Radiometer Suite (VIIRS) and the Advanced Baseline Imager (ABI). The main focus of this work is assessing the relative importance of each instrument’s infrared channels in neural networks trained to estimate CTP. We use several ML explainability methods to offer different perspectives on feature importance. These methods show many differences in the relative feature importance depending on the exact method used, but most agree on a few points. Overall, the 8.4- and 8.6-μm channels appear to be the most useful for CTP estimation on ABI and VIIRS, respectively, with other native infrared window channels and the 13.3-μm channel playing a moderate role. Furthermore, we find that the neural networks learn relationships that may account for properties of clouds such as opacity and cloud-top phase that otherwise complicate the estimation of CTP.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"7 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73796852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-26DOI: 10.1175/aies-d-22-0005.1
G. Petty
A simple yet flexible and robust algorithm is described for fully partitioning an arbitrary dataset into compact, non-overlapping groups or classes, sorted by size, based entirely on a pairwise similarity matrix and a user-specified similarity threshold. Unlike many clustering algorithms, there is no assumption that natural clusters exist in the dataset, though clusters, when present, may be preferentially assigned to one or more classes. The method also does not require data objects to be compared within any coordinate system but rather permits the user to define pairwise similarity using almost any conceivable criterion. The method therefore lends itself to certain geoscientific applications for which conventional clustering methods are unsuited, including two non-trivial and distinctly different datasets presented as examples. In addition to identifying large classes containing numerous similar dataset members, it is also well-suited for isolating rare or anomalous members of a dataset. The method is inductive, in that prototypes identified in representative subset of a larger dataset can be used to classify the remainder.
{"title":"The Pairwise Similarity Partitioning algorithm: a method for unsupervised partitioning of geoscientific and other datasets using arbitrary similarity metrics","authors":"G. Petty","doi":"10.1175/aies-d-22-0005.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0005.1","url":null,"abstract":"\u0000A simple yet flexible and robust algorithm is described for fully partitioning an arbitrary dataset into compact, non-overlapping groups or classes, sorted by size, based entirely on a pairwise similarity matrix and a user-specified similarity threshold. Unlike many clustering algorithms, there is no assumption that natural clusters exist in the dataset, though clusters, when present, may be preferentially assigned to one or more classes. The method also does not require data objects to be compared within any coordinate system but rather permits the user to define pairwise similarity using almost any conceivable criterion. The method therefore lends itself to certain geoscientific applications for which conventional clustering methods are unsuited, including two non-trivial and distinctly different datasets presented as examples. In addition to identifying large classes containing numerous similar dataset members, it is also well-suited for isolating rare or anomalous members of a dataset. The method is inductive, in that prototypes identified in representative subset of a larger dataset can be used to classify the remainder.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"25 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85911109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-03DOI: 10.1175/aies-d-22-0020.1
M. Rempel, P. Schaumann, R. Hess, V. Schmidt, U. Blahak
A wealth of forecasting models is available for operational weather forecasting. Their strengths often depend on the lead time considered, which generates the need for a seamless combination of different forecast methods. The combined and continuous products are made in order to retain or even enhance the forecast quality of the individual forecasts and to extend the lead time to potentially hazardous weather events. In this study, we further improve an artificial neural network based combination model that was recently proposed in a previous paper. This model combines two initial precipitation ensemble forecasts and produces exceedance probabilities for a set of thresholds for hourly precipitation amounts. Both initial forecasts perform differently well for different lead times, whereas the combined forecast is calibrated and outperforms both initial forecasts with respect to various validation scores and for all considered lead times (+1h to +6h). Moreover, the robustness of the combination model is tested by applying it to a new dataset and by evaluating the spatial and temporal consistency of its forecasts. The changes proposed further improve the forecast quality and make it more useful for practical applications. Temporal consistency of the combined product is evaluated using a flip-flop index. It is shown that the combination provides a higher persistence with decreasing lead times compared to both input systems.
{"title":"Adaptive Blending of Probabilistic Precipitation Forecasts with Emphasis on Calibration and Temporal Forecast Consistency","authors":"M. Rempel, P. Schaumann, R. Hess, V. Schmidt, U. Blahak","doi":"10.1175/aies-d-22-0020.1","DOIUrl":"https://doi.org/10.1175/aies-d-22-0020.1","url":null,"abstract":"\u0000A wealth of forecasting models is available for operational weather forecasting. Their strengths often depend on the lead time considered, which generates the need for a seamless combination of different forecast methods. The combined and continuous products are made in order to retain or even enhance the forecast quality of the individual forecasts and to extend the lead time to potentially hazardous weather events. In this study, we further improve an artificial neural network based combination model that was recently proposed in a previous paper. This model combines two initial precipitation ensemble forecasts and produces exceedance probabilities for a set of thresholds for hourly precipitation amounts. Both initial forecasts perform differently well for different lead times, whereas the combined forecast is calibrated and outperforms both initial forecasts with respect to various validation scores and for all considered lead times (+1h to +6h). Moreover, the robustness of the combination model is tested by applying it to a new dataset and by evaluating the spatial and temporal consistency of its forecasts. The changes proposed further improve the forecast quality and make it more useful for practical applications. Temporal consistency of the combined product is evaluated using a flip-flop index. It is shown that the combination provides a higher persistence with decreasing lead times compared to both input systems.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87629003","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-02DOI: 10.1175/aies-d-21-0011.1
Na-Yeon Shin, Y. Ham, Jeong-Hwan Kim, M. Cho, J. Kug
Many deep learning technologies have been applied to the Earth sciences. Nonetheless, the difficulty in interpreting deep learning results still prevents their applications to studies on climate dynamics. Here, we applied a convolutional neural network to understand El Niño–Southern Oscillation (ENSO) dynamics from long-term climate model simulations. The deep learning algorithm successfully predicted ENSO events with a high correlation skill (∼0.82) for a 9-month lead. For interpreting deep learning results beyond the prediction, we present a “contribution map” to estimate how much the grid box and variable contribute to the output and “contribution sensitivity” to estimate how much the output variable is changed to the small perturbation of the input variables. The contribution map and sensitivity are calculated by modifying the input variables to the pre-trained deep learning, which is quite similar to the occlusion sensitivity. Based on the two methods, we identified three precursors of ENSO and investigated their physical processes with El Niño and La Niña development. In particular, it is suggested here that the roles of each precursor are asymmetric between El Niño and La Niña. Our results suggest that the contribution map and sensitivity are simple approaches but can be a powerful tool in understanding ENSO dynamics and they might be also applied to other climate phenomena.
{"title":"Application of deep learning to understanding ENSO dynamics","authors":"Na-Yeon Shin, Y. Ham, Jeong-Hwan Kim, M. Cho, J. Kug","doi":"10.1175/aies-d-21-0011.1","DOIUrl":"https://doi.org/10.1175/aies-d-21-0011.1","url":null,"abstract":"\u0000Many deep learning technologies have been applied to the Earth sciences. Nonetheless, the difficulty in interpreting deep learning results still prevents their applications to studies on climate dynamics. Here, we applied a convolutional neural network to understand El Niño–Southern Oscillation (ENSO) dynamics from long-term climate model simulations. The deep learning algorithm successfully predicted ENSO events with a high correlation skill (∼0.82) for a 9-month lead. For interpreting deep learning results beyond the prediction, we present a “contribution map” to estimate how much the grid box and variable contribute to the output and “contribution sensitivity” to estimate how much the output variable is changed to the small perturbation of the input variables. The contribution map and sensitivity are calculated by modifying the input variables to the pre-trained deep learning, which is quite similar to the occlusion sensitivity. Based on the two methods, we identified three precursors of ENSO and investigated their physical processes with El Niño and La Niña development. In particular, it is suggested here that the roles of each precursor are asymmetric between El Niño and La Niña. Our results suggest that the contribution map and sensitivity are simple approaches but can be a powerful tool in understanding ENSO dynamics and they might be also applied to other climate phenomena.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"122 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91454379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-25DOI: 10.1175/aies-d-21-0007.1
A. Black, D. Monselesan, J. Risbey, B. Sloyan, C. Chapman, A. Hannachi, D. Richardson, D. Squire, C. Tozer, Nikolay Trendafilov
The ability to find and recognize patterns in high-dimensional geophysical data is fundamental to climate science and critical for meaningful interpretation of weather and climate processes. Archetypal analysis (AA) is one technique that has recently gained traction in the geophysical science community for its ability to find patterns based on extreme conditions. While traditional empirical orthogonal function (EOF) analysis can reveal patterns based on data covariance, AA seeks patterns from the points located at the edges of the data distribution. The utility of any objective pattern method depends on the properties of the data to which it is applied and the choices made in implementing the method. Given the relative novelty of the application of AA in geophysics it is important to develop experience in applying the method. We provide an assessment of the method, implementation, sensitivity, and interpretation of AA with respect to geophysical data. As an example for demonstration, we apply AA to a 39-year sea surface temperature (SST) reanalysis data set. We show that the decisions made to implement AA can significantly affect the interpretation of results, but also, in the case of SST, that the analysis is exceptionally robust under both spatial and temporal coarse-graining.
{"title":"Archetypal Analysis of Geophysical Data illustrated by Sea Surface Temperature","authors":"A. Black, D. Monselesan, J. Risbey, B. Sloyan, C. Chapman, A. Hannachi, D. Richardson, D. Squire, C. Tozer, Nikolay Trendafilov","doi":"10.1175/aies-d-21-0007.1","DOIUrl":"https://doi.org/10.1175/aies-d-21-0007.1","url":null,"abstract":"\u0000The ability to find and recognize patterns in high-dimensional geophysical data is fundamental to climate science and critical for meaningful interpretation of weather and climate processes. Archetypal analysis (AA) is one technique that has recently gained traction in the geophysical science community for its ability to find patterns based on extreme conditions. While traditional empirical orthogonal function (EOF) analysis can reveal patterns based on data covariance, AA seeks patterns from the points located at the edges of the data distribution. The utility of any objective pattern method depends on the properties of the data to which it is applied and the choices made in implementing the method. Given the relative novelty of the application of AA in geophysics it is important to develop experience in applying the method. We provide an assessment of the method, implementation, sensitivity, and interpretation of AA with respect to geophysical data. As an example for demonstration, we apply AA to a 39-year sea surface temperature (SST) reanalysis data set. We show that the decisions made to implement AA can significantly affect the interpretation of results, but also, in the case of SST, that the analysis is exceptionally robust under both spatial and temporal coarse-graining.","PeriodicalId":94369,"journal":{"name":"Artificial intelligence for the earth systems","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86750173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：