Browse

You are looking at 21 - 30 of 143 items for :

  • Artificial Intelligence for the Earth Systems x
  • Refine by Access: All Content x
Clear All
Shuang Yu
,
Indrasis Chakraborty
,
Gemma J. Anderson
,
Donald D. Lucas
,
Yannic Lops
, and
Daniel Galea

Abstract

Precipitation values produced by climate models are biased due to the parameterization of physical processes and limited spatial resolution. Current bias correction approaches usually focus on correcting lower-order statistics (mean, standard deviation), which make it difficult to capture precipitation extremes. However, accurate modeling of extremes is critical for policymaking to mitigate and adapt to the effects of climate change. We develop a deep learning framework, leveraging information from key dynamical variables impacting precipitation to also match higher-order statistics (skewness and kurtosis) for the entire precipitation distribution, including extremes. The deep learning framework consists of a two-part architecture: a U-Net convolutional network to capture the spatiotemporal distribution of precipitation and a fully connected network to capture the distribution of higher-order statistics. The joint network, termed UFNet, can simultaneously improve the spatial structure of the modeled precipitation and capture the distribution of extreme precipitation values. Using climate model simulation data and observations that are climatologically similar but not strictly paired, the UFNet identifies and corrects the climate model biases, significantly improving the estimation of daily precipitation as measured by a broad range of spatiotemporal statistics. In particular, UFNet significantly improves the underestimation of extreme precipitation values seen with current bias-correction methods. Our approach constitutes a generalized framework for correcting other climate model variables which improves the accuracy of the climate model predictions, while utilizing a simpler and more stable training process.

Open access
Israt Jahan
,
Diego Cerrai
, and
Marina Astitha

Abstract

Wind gusts are often associated with severe hazards and can cause structural and environmental damages, making gust prediction a crucial element of weather forecasting services. In this study, we explored the utilization of machine learning (ML) algorithms integrated with numerical weather prediction outputs from the Weather Research and Forecasting model (WRF), to align the estimation of wind gust potential with observed gusts. We have used two ML algorithms, namely Random Forest (RF), and Extreme Gradient Boosting (XGB), along with two statistical techniques: Generalized Linear Models with identity link function (GLM-Identity) and log link function (GLM-Log), to predict storm wind gusts for the NE USA. We used 61 simulated extratropical and tropical storms that occurred between 2005 and 2020, to develop and validate the ML and statistical models. To assess the ML model performance, we compared our results with post-processed gust potential from WRF. Our findings showed that ML models, especially XGB, performed significantly better than statistical models and WRF-UPP, and were able to better align predicted with observed gusts across all storms. The ML models faced challenges capturing the upper tail of the gust distribution, and the learning curves suggested that XGB was more effective than RF in generating better predictions with fewer storms.

Open access
Neelesh Rampal
,
Sanaa Hobeichi
,
Peter B. Gibson
,
Jorge Baño-Medina
,
Gab Abramowitz
,
Tom Beucler
,
Jose González-Abad
,
William Chapman
,
Paula Harder
, and
José Manuel Gutiérrez

Abstract

Despite the sophistication of global climate models (GCMs), their coarse spatial resolution limits their ability to resolve important aspects of climate variability and change at the local scale. Both dynamical and empirical methods are used for enhancing the resolution of climate projections through downscaling, each with distinct advantages and challenges. Dynamical downscaling is physics based but comes with a large computational cost, posing a barrier for downscaling an ensemble of GCMs large enough for reliable uncertainty quantification of climate risks. In contrast, empirical downscaling, which encompasses statistical and machine learning techniques, provides a computationally efficient alternative to downscaling GCMs. Empirical downscaling algorithms can be developed to emulate the behavior of dynamical models directly, or through frameworks such as perfect prognosis in which relationships are established between large-scale atmospheric conditions and local weather variables using observational data. However, the ability of empirical downscaling algorithms to apply their learned relationships out of distribution into future climates remains uncertain, as is their ability to represent certain types of extreme events. This review covers the growing potential of machine learning methods to address these challenges, offering a thorough exploration of the current applications and training strategies that can circumvent certain issues. Additionally, we propose an evaluation framework for machine learning algorithms specific to the problem of climate downscaling as needed to improve transparency and foster trust in climate projections.

Significance Statement

This review offers a significant contribution to our understanding of how machine learning can offer a transformative change in climate downscaling. It serves as a guide to navigate recent advances in machine learning and how these advances can be better aligned toward inherent challenges in climate downscaling. In this review, we provide an overview of these recent advances with a critical discussion of their advantages and limitations. We also discuss opportunities to refine existing machine learning methods alongside new approaches for the generation of large ensembles of high-resolution climate projections.

Open access
L. Raynaud
,
G. Faure
,
M. Puig
,
C. Dauvilliers
,
J-N Trosino
, and
P. Béjean

Abstract

Detection and tracking of Tropical Cyclones (TCs) in numerical weather prediction model outputs is essential for many applications, such as forecast guidance and real-time monitoring of events. While this task has been automated in the 90s with heuristic models, relying on a set of empirical rules and thresholds, the recent success of machine learning methods to detect objects in images opens new perspectives. This paper introduces and evaluates the capacity of a convolutional neural network based on the U-Net architecture to detect the TC wind structure, including maximum wind speed area and hurricane-force wind speed area, in the outputs of the convective-scale Arome model. A dataset of 400 Arome forecasts over the West Indies domain has been entirely hand labeled by experts, following a rigorous process to reduce heterogeneities. The U-Net performs well on a wide variety of TC intensities and shapes, with an average intersection-over-union metric around 0.8. Its performances however strongly depend on the TC strength, the detection of weak cyclones being more challenging since their structure is less well defined. The U-Net also significantly outperforms an operational heuristic detection model, with a significant gain for weak TCs, while running much faster. In a last part, the capacity of the U-Net to generalize on slightly different data is demonstrated in the context of a domain change and a resolution increase. In both cases, the pre-trained U-Net achieves similar performances as on the original dataset.

Open access
Fraser King
,
Claire Pettersen
,
Christopher G. Fletcher
, and
Andrew Geiss

Abstract

CloudSat’s Cloud Profiling Radar is a valuable tool for remotely monitoring high-latitude snowfall, but its ability to observe hydrometeor activity near the Earth’s surface is limited by a radar blind zone caused by ground-clutter contamination. This study presents the development of a deeply supervised U-Net-style convolutional neural network to predict cold season reflectivity profiles within the blind zone at two Arctic locations. The network learns to predict the presence and intensity of near-surface hydrometeors by coupling latent features encoded in blind zone-aloft clouds with additional context from collocated atmospheric state variables (i.e., temperature, specific humidity and wind speed). Results show that the U-Net predictions outperform traditional linear extrapolation methods, with low mean absolute error, a 38% higher Sørensen—Dice coefficient, and vertical reflectivity distributions 60% closer to observed values. The U-Net is also able to detect the presence of near surface cloud with a critical success index (CSI) of 72%, and cases of shallow cumuliform snowfall and virga with 18% higher CSI values compared to linear methods. A mechanistic interpretiability analysis highlights the fact that a combination of both the reflectivity information throughout the scene (most notably across cloud edges and at the 1.2 km blind zone threshold), along with atmospheric state variables near the tropopause, are the most significant contributors to model skill. This surface-trained generative inpainting technique has the potential to enhance current and future remote sensing precipitation missions by providing a better understanding of the nonlinear relationship between blind zone reflectivity values and the surrounding atmospheric state.

Open access
Philine Lou Bommer
,
Marlene Kretschmer
,
Anna Hedström
,
Dilyara Bareeva
, and
Marina M.-C. Höhne

Abstract

Explainable artificial intelligence (XAI) methods shed light on the predictions of machine learning algorithms. Several different approaches exist and have already been applied in climate science. However, usually missing ground truth explanations complicate their evaluation and comparison, subsequently impeding the choice of the XAI method. Therefore, in this work, we introduce XAI evaluation in the climate context and discuss different desired explanation properties, namely robustness, faithfulness, randomization, complexity, and localization. To this end, we chose previous work as a case study where the decade of annual-mean temperature maps is predicted. After training both a multi-layer perceptron (MLP) and a convolutional neural network (CNN), multiple XAI methods are applied and their skill scores in reference to a random uniform explanation are calculated for each property. Independent of the network, we find that XAI methods Integrated Gradients, layer-wise relevance propagation, and input times gradients exhibit considerable robustness, faithfulness, and complexity while sacrificing randomization performance. Sensitivity methods – gradient, SmoothGrad, NoiseGrad, and FusionGrad, match the robustness skill but sacrifice faithfulness and complexity for randomization skill. We find architecture-dependent performance differences regarding robustness, complexity and localization skills of different XAI methods, highlighting the necessity for research task-specific evaluation. Overall, our work offers an overview of different evaluation properties in the climate science context and shows how to compare and benchmark different explanation methods, assessing their suitability based on strengths and weaknesses, for the specific research problem at hand. By that, we aim to support climate researchers in the selection of a suitable XAI method.

Open access
Marius Appel

Abstract

The abundance of gaps in satellite image time series often complicates the application of deep learning models such as convolutional neural networks for spatiotemporal modeling. Based on previous work in computer vision on image inpainting, this paper shows how three-dimensional spatiotemporal partial convolutions can be used as layers in neural networks to fill gaps in satellite image time series. To evaluate the approach, we apply a U-Net-like model on incomplete image time series of quasi-global carbon monoxide observations from the Sentinel-5 Precursor (Sentinel-5P) satellite. Prediction errors were comparable to two considered statistical approaches while computation times for predictions were up to three orders of magnitude faster, making the approach applicable to process large amounts of satellite data. Partial convolutions can be added as layers to other types of neural networks, making it relatively easy to integrate with existing deep learning models. However, the approach does not provide prediction uncertainties and further research is needed to understand and improve model transferability. The implementation of spatiotemporal partial convolutions and the U-Net-like model is available as open-source software.

Significance Statement

Gaps in satellite-based measurements of atmospheric variables can make the application of complex analysis methods such as deep learning approaches difficult. The purpose of this study is to present and evaluate a purely data-driven method to fill incomplete satellite image time series. The application on atmospheric carbon monoxide data suggests that the method can achieve prediction errors comparable to other approaches with much lower computation times. Results highlight that the method is promising for larger datasets but also that care must be taken to avoid extrapolation. Future studies may integrate the approach into more complex deep learning models for understanding spatiotemporal dynamics from incomplete data.

Open access
Randy J. Chase
,
Amy McGovern
,
Cameron R. Homeyer
,
Peter J. Marinescu
, and
Corey K. Potvin

Abstract

The quantification of storm updrafts remains unavailable for operational forecasting despite their inherent importance to convection and its associated severe weather hazards. Updraft proxies, like overshooting top area from satellite images, have been linked to severe weather hazards but only relate to a limited portion of the total storm updraft. This study investigates if a machine learning model, namely, U-Nets, can skillfully retrieve maximum vertical velocity and its areal extent from three-dimensional gridded radar reflectivity alone. The machine learning model is trained using simulated radar reflectivity and vertical velocity from the National Severe Storm Laboratory’s convection permitting Warn-on-Forecast System (WoFS). A parametric regression technique using the sinh–arcsinh–normal distribution is adapted to run with U-Nets, allowing for both deterministic and probabilistic predictions of maximum vertical velocity. The best models after hyperparameter search provided less than 50% root mean squared error, a coefficient of determination greater than 0.65, and an intersection over union (IoU) of more than 0.45 on the independent test set composed of WoFS data. Beyond the WoFS analysis, a case study was conducted using real radar data and corresponding dual-Doppler analyses of vertical velocity within a supercell. The U-Net consistently underestimates the dual-Doppler updraft speed estimates by 50%. Meanwhile, the area of the 5 and 10 m s−1 updraft cores shows an IoU of 0.25. While the above statistics are not exceptional, the machine learning model enables quick distillation of 3D radar data that is related to the maximum vertical velocity, which could be useful in assessing a storm’s severe potential.

Significance Statement

All convective storm hazards (tornadoes, hail, heavy rain, straight line winds) can be related to a storm’s updraft. Yet, there is no direct measurement of updraft speed or area available for forecasters to make their warning decisions from. This paper addresses the lack of observational data by providing a machine learning solution that skillfully estimates the maximum updraft speed within storms from only the radar reflectivity 3D structure. After further vetting the machine learning solutions on additional real-world examples, the estimated storm updrafts will hopefully provide forecasters with an added tool to help diagnose a storm’s hazard potential more accurately.

Open access
Junsu Kim
,
Yeon-Hee Kim
,
Hyejeong Bok
,
Sungbin Jang
,
Eunju Cho
, and
Seungbum Kim

Abstract

We developed an advanced postprocessing model for precipitation forecasting using a microgenetic algorithm (MGA). The algorithm determines the optimal combination of three general circulation models: the Korean Integrated Model, the Unified Model, and the Integrated Forecast System model. To measure model accuracy, including the critical success index (CSI), probability of detection (POD), and frequency bias index, the MGA calculates optimal weights for individual models based on a fitness function that considers various indices. Our optimized multimodel yielded up to 13% and 10% improvement in CSI and POD performance compared to each individual model, respectively. Notably, when applied to an operational definition that considers precipitation thresholds from three models and averages the precipitation amount from the satisfactory models, our optimized multimodel outperformed the current operational model used by the Korea Meteorological Administration by up to 1.0% and 6.8% in terms of CSI and false alarm ratio performance, respectively. This study highlights the effectiveness of a weighted combination of global models to enhance the forecasting accuracy for regional precipitation. By utilizing the MGA for the fine-tuning of model weights, we achieved superior precipitation prediction compared to that of individual models and existing standard postprocessing operations. This approach can significantly improve the accuracy of precipitation forecasts.

Significance Statement

We developed an optimized multimodel for predicting precipitation occurrence using advanced techniques. By integrating various weather models with their optimized weights, our approach outperforms the method of using an arithmetic average of all models. This study underscores the potential to enhance regional precipitation forecasts, thereby facilitating more precise weather predictions for the public.

Open access
Free access