RECORD
Combining crowd-sourcing and deep learning to explore the meso-scale organization of shallow convection
Atmospheric and Oceanic Physics · Submitted 5 Jun 2019
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Further, this study illustrates that crowd-sourcing and deep learning complement each other well for the exploration of image datasets.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Humans excel at detecting interesting patterns in images, for example those taken from satellites. This kind of anecdotal evidence can lead to the discovery of new phenomena. However, it is often difficult to gather enough data of subjective features for significant analysis. This paper presents an example of how two tools that have recently become accessible to a wide range of researchers, crowd-sourcing and deep learning, can be combined to explore satellite imagery at scale. In particular, the focus is on the organization of shallow cumulus convection in the trade wind regions. Shallow clouds play a large role in the Earth's radiation balance yet are poorly represented in climate models. For this project four subjective patterns of organization were defined: Sugar, Flower, Fish and Gravel. On cloud labeling days at two institutes, 67 scientists screened 10,000 satellite images on a crowd-sourcing platform and classified almost 50,000 mesoscale cloud clusters. This dataset is then used as a training dataset for deep learning algorithms that make it possible to automate the pattern detection and create global climatologies of the four patterns. Analysis of the geographical distribution and large-scale environmental conditions indicates that the four patterns have some overlap with established modes of organization, such as open and closed cellular convection, but also differ in important ways. The results and dataset from this project suggests promising research questions. Further, this study illustrates that crowd-sourcing and deep learning complement each other well for the exploration of image datasets.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Humans excel at detecting interesting patterns in images, for example those taken from satellites. | background 1.00 | 0.05 | 0.02 | asserted 1.00 |
| s1 | This kind of anecdotal evidence can lead to the discovery of new phenomena. | background 0.99 | 0.06 | 0.02 | hedged possibility 0.72 |
| s2 | However, it is often difficult to gather enough data of subjective features for significant analysis. | gap 0.79 | 0.06 | 0.02 | asserted 0.94 |
| s3 | This paper presents an example of how two tools that have recently become accessible to a wide range of researchers, crowd-sourcing and deep learning, can be combined to explore satellite imagery at scale. | contribution 1.00 | 0.69 | 0.08 | asserted 0.97 |
| s4 | In particular, the focus is on the organization of shallow cumulus convection in the trade wind regions. | contribution 0.79 | 0.27 | 0.03 | asserted 0.86 |
| s5 | Shallow clouds play a large role in the Earth's radiation balance yet are poorly represented in climate models. | background 0.96 | 0.05 | 0.02 | asserted 1.00 |
| s6 | For this project four subjective patterns of organization were defined: Sugar, Flower, Fish and Gravel. | method 0.88 | 0.92 | 0.02 | asserted 0.99 |
| s7 | On cloud labeling days at two institutes, 67 scientists screened 10,000 satellite images on a crowd-sourcing platform and classified almost 50,000 mesoscale cloud clusters. | method 0.98 | 0.94 | 0.04 | asserted 1.00 |
| s8 | This dataset is then used as a training dataset for deep learning algorithms that make it possible to automate the pattern detection and create global climatologies of the four patterns. | method 0.98 | 0.92 | 0.11 | asserted 0.99 |
| s9 | Analysis of the geographical distribution and large-scale environmental conditions indicates that the four patterns have some overlap with established modes of organization, such as open and closed cellular convection, but also differ in important ways. | result 0.71 | 0.91 | 0.21 | hedged possibility 0.95 |
| s10 | The results and dataset from this project suggests promising research questions. | future work 0.55 | 0.73 | 0.18 | hedged possibility 1.00 |
| s11 | Further, this study illustrates that crowd-sourcing and deep learning complement each other well for the exploration of image datasets. | interpretation 0.94 | 0.78 | 0.41 | asserted 0.99 |
What was examined, and what was not
- arXiv listing abstract v3
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Humans excel at detecting interesting patterns in images, for example those taken from satellites. This kind of anecdotal evidence can lead to the discovery of new phenomena. However, it is often difficult to gather enough data of subjective features for significant analysis. This paper presents an example of how two tools that have recently become accessible to a wide range of researchers, crowd-sourcing and deep learning, can be combined to explore satellite imagery at scale. In particular, the focus is on the organization of shallow cumulus convection in the trade wind regions. Shallow clouds play a large role in the Earth's radiation balance yet are poorly represented in climate models. For this project four subjective patterns of organization were defined: Sugar, Flower, Fish and Gravel. On cloud labeling days at two institutes, 67 scientists screened 10,000 satellite images on a crowd-sourcing platform and classified almost 50,000 mesoscale cloud clusters. This dataset is then used as a training dataset for deep learning algorithms that make it possible to automate the pattern detection and create global climatologies of the four patterns. Analysis of the geographical distribution and large-scale environmental conditions indicates that the four patterns have some overlap with established modes of organization, such as open and closed cellular convection, but also differ in important ways. The results and dataset from this project suggests promising research questions. Further, this study illustrates that crowd-sourcing and deep learning complement each other well for the exploration of image datasets.
Human review
How the literature uses it
3 arXiv papers cite this in 4 sentences
Papers citing it · 1 sentence without a confident label
Compares with it 1 paper
-
[ref] crowd-sourced human-level classifications of shallow trade clouds into four types: `sugar', `flower', `fish', `gravel'.
Cumulo: A Dataset for Learning Cloud Classes · Cloud Classification is key for modelling Climate Change · 0.88
Cites it as background 2 papers
-
In the last several years, a number of studies have sought to develop AI-based cloud classification by using supervised learning [ref] .
AICCA: AI-driven Cloud Classification Atlas · Introduction · 0.80
-
Additionally, there are datasets targeting specific applications of climate science, such as cloud cluster classification [ref] , storm classification [ref] , nowcasting [ref] , rain precipitation [ref] , tropical cyclone intensity prediction [ref] , global air quality metrics estimation [ref] , and stream flow forecasting with flash flood damage estimation [ref] .
ClimateBench-M: A Multi-Modal Climate Data Benchmark with a Simple Generative Method · Related Work · 0.97
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.