IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium 2018
DOI: 10.1109/igarss.2018.8517346
|View full text |Cite
|
Sign up to set email alerts
|

Earth Science Deep Learning: Applications and Lessons Learned

Abstract: Deep learning has revolutionized computer vision and natural language processing with various algorithms scaled using high-performance computing. At the NASA Marshall Space Flight Center (MSFC), the Data Science and Informatics Group (DSIG) has been using deep learning for a variety of Earth science applications. This paper provides examples of the applications and also addresses some of the challenges that were encountered.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
4
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
4
1
1

Relationship

0
6

Authors

Journals

citations
Cited by 7 publications
(4 citation statements)
references
References 9 publications
0
4
0
Order By: Relevance
“…Using a convolutional neural network optimized by parameters has turned out to be a promising prediction method due to the higher accuracy rates. The CNN specified in Maskey et al [20] uses a training data set consisting of previous instances of hailstorms, along with their respective Next Generation Weather Radar (NEXRAD) images. The CNN classified the images where hail was present.…”
Section: Cnn Models Using Image Processing For Hailstorm Predictionmentioning
confidence: 99%
See 1 more Smart Citation
“…Using a convolutional neural network optimized by parameters has turned out to be a promising prediction method due to the higher accuracy rates. The CNN specified in Maskey et al [20] uses a training data set consisting of previous instances of hailstorms, along with their respective Next Generation Weather Radar (NEXRAD) images. The CNN classified the images where hail was present.…”
Section: Cnn Models Using Image Processing For Hailstorm Predictionmentioning
confidence: 99%
“…It was also pointed out that most of the hailstorm prediction techniques require efficient preprocessing of the data, which can be complicated. Hence, Maskey et al [20] utilized a CNN optimized by parameters that has high accuracy compared to the existing CNN models.…”
Section: Cnn Models Using Image Processing For Hailstorm Predictionmentioning
confidence: 99%
“…Rolnick et al [30] outline the wide range of machine learning applications to climate action, from enhancing efficiency in transport and infrastructure, to advancing the energy transition by improving renewable energy technologies. Other examples include using ML models for more accurate weather and climate forecasts [20] and applying deep learning to improve climate models [29] or advance earth science more broadly [24]. Meanwhile, the number of companies using AI to offer 'climate services' has surged for example through monitoring environmental risks (eg Ecometrica [16]), predicting extreme weather events (eg Jupiter [21]), or providing data to assess general climate risks (eg Acclimatise [4]).…”
Section: Ai For Climate Change and Food Securitymentioning
confidence: 99%
“…These satellites capture large volumes of images and are used for various purposes. Processing and analysis of these images are useful for many applications such as the prediction of landslides, forest fires, rescue operations on post-disaster, post-disaster damage assessment, land use and land cover (LULC) classification, and many more [3]- [9]. With the advancement in space technology small satellites such as CubeSats, nanosatellites, and miniature satellites are launched which are less costly, less power consumable, and easy to manufacture with less weight and less time.…”
Section: Introductionmentioning
confidence: 99%