Applying machine learning methods to detect convection using
GOES-16 ABI data

Lee, Yoonjin; Kummerow, Christian D.; Ebert‐Uphoff, Imme

doi:10.5194/amt-2020-420

Cited by 8 publications

(12 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Methods for explaining DNNs have also been applied outside of medical imaging, for example, in earth sciences. Ebert-Uphoff and Hilburn [43] and Lee et al [109] predict various meteorological values, such as convection, or MRMS radar, from satellite imagery, and the latter prediction is then attributed to the individual pixels. An example is shown in Fig.…”

Section: B From Explanations To Novel Scientific Insightsmentioning

confidence: 99%

Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications

Montavon²,

et al. 2021

View full text Add to dashboard Cite

show abstract

Section: B From Explanations To Novel Scientific Insightsmentioning

confidence: 99%

Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications

Montavon²,

et al. 2021

View full text Add to dashboard Cite

show abstract

“…An example of Strategy 2 is to use ground-based radar (only available in some locations) to generate convection labels for GOES satellite imagery (Y. Lee et al, 2021), or to use CloudSat data (only available intermittently) to generate cloud type labels for Himawari-8 satellite imagery (C. . Similarly, (Zantedeschi et al, 2019) used a semi-supervised learning approach to leverage a small number of classified satellite images for creating a much larger labeled dataset to cloud types.…”

Section: Cloud Detection and Classificationmentioning

confidence: 99%

Machine Learning for Clouds and Climate (Invited Chapter for the AGU Geophysical Monograph Series "Clouds and Climate")

Beucler¹,

Ebert‐Uphoff²,

Rasp³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Key Points: * Machine learning (ML) helps model the interaction between clouds and climate using large datasets. * We review physics-guided/explainable ML applied to cloud-related processes in the climate system. * We also provide a guide to scientists who would like to get started with ML. Abstract: Machine learning (ML) algorithms are powerful tools to build models of clouds and climate that are more faithful to the rapidly-increasing volumes of Earth system data than commonly-used semiempirical models. Here, we review ML tools, including interpretable and physics-guided ML, and outline how they can be applied to cloud-related processes in the climate system, including radiation, microphysics, convection, and cloud detection , classification, emulation, and uncertainty quantification. We additionally provide a short guide to get started with ML and survey the frontiers of ML for clouds and climate .

show abstract

“…Training in discrete phases: [25] seeks to identify convection from satellite imagery and uses two loss function sequentially to train the model. The overall motivation for this type of approach is that the network first seeks to achieve an overall objective, then, after hopefully reaching the neighborhood of the desired model, it is fine tuned with the second loss function that additionally includes a secondary objective.…”

Section: Adaptive Loss Functionsmentioning

confidence: 99%

“…The overall motivation for this type of approach is that the network first seeks to achieve an overall objective, then, after hopefully reaching the neighborhood of the desired model, it is fine tuned with the second loss function that additionally includes a secondary objective. For example, in [25] the model is first trained with MSE as the loss function, which penalizes both misses and false alarms, for a fixed number of epochs. The number of epochs is chosen (through trial) large enough to ensure the model has converged to a plateau.…”

Section: Adaptive Loss Functionsmentioning

confidence: 99%

“…The number of epochs is chosen (through trial) large enough to ensure the model has converged to a plateau. After this initial training the model is trained further, using a loss function that consists of MSE plus an additional term that adds an extra penalty specifically when the model prediction misses convection (but not for false alarms), since for the application in [25] we care more about preventing misses than false alarms:…”

Section: Adaptive Loss Functionsmentioning

confidence: 99%

See 1 more Smart Citation

CIRA Guide to Custom Loss Functions for Neural Networks in Environmental Sciences -- Version 1

Ebert‐Uphoff¹,

Lagerquist²,

Hilburn³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Neural networks are increasingly used in environmental science applications. Furthermore, neural network models are trained by minimizing a loss function, and it is crucial to choose the loss function very carefully for environmental science applications, as it determines what exactly is being optimized. Standard loss functions do not cover all the needs of the environmental sciences, which makes it important for scientists to be able to develop their own custom loss functions so that they can implement many of the classic performance measures already developed in environmental science, including measures developed for spatial model verification. However, there are very few resources available that cover the basics of custom loss function development comprehensively, and to the best of our knowledge none that focus on the needs of environmental scientists. This document seeks to fill this gap by providing a guide on how to write custom loss functions targeted toward environmental science applications. Topics include the basics of writing custom loss functions, common pitfalls, functions to use in loss functions, examples such as fractions skill score as loss function, how to incorporate physical constraints, discrete and soft discretization, and concepts such as focal, robust, and adaptive loss. While examples are currently provided in this guide for Python with Keras and the TensorFlow backend, the basic concepts also apply to other environments, such as Python with PyTorch. Similarly, while the sample loss functions provided here are from meteorology, these are just examples of how to create custom loss functions. Other fields in the environmental sciences have very similar needs for custom loss functions, e.g., for evaluating spatial forecasts effectively, and the concepts discussed here can be applied there as well. All code samples are provided in a GitHub repository.

show abstract

Applying machine learning methods to detect convection using GOES-16 ABI data

Cited by 8 publications

References 17 publications

Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications

Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications

Machine Learning for Clouds and Climate (Invited Chapter for the AGU Geophysical Monograph Series "Clouds and Climate")

CIRA Guide to Custom Loss Functions for Neural Networks in Environmental Sciences -- Version 1

Contact Info

Product

Resources

About