Published on Wed Jun 05 2019

Combining crowd-sourcing and deep learning to explore the meso-scale organization of shallow convection

Stephan Rasp, Hauke Schulz, Sandrine Bony, Bjorn Stevens

Crowd-sourcing and deep learning can be combined to explore satellite imagery at scale. The focus is on the organization of shallow cumulus convection in the trade wind regions. Four subjective patterns of organization were defined: Sugar, Flower, Fish and Gravel.

0
0
0
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.

Tue Feb 18 2020
Computer Vision
Lake Ice Monitoring with Webcams and Crowd-Sourced Images
Lake ice is a strong climate indicator. The dynamics of freezing and thawing, and possible shifts of freezing patterns over time, can help in understanding the local and global climate. One way to acquire the spatio-temporal information about lake ice is to analyse webcam images.
0
0
0
Tue May 30 2017
Computer Vision
RSI-CB: A Large Scale Remote Sensing Image Classification Benchmark via Crowdsource Data
The remote sensing field is still lacking a large-scale benchmark compared to ImageNet and Place2. We propose a remote sensing image classification benchmark (RSI-CB) based on massive, scalable, and diverse crowdsource data. Ground objects in remote sensing images can be annotated effectively by points of interest.
0
0
0
Mon Mar 08 2021
Computer Vision
Data-driven Cloud Clustering via a Rotationally Invariant Autoencoder
0
0
0
Wed Jul 03 2019
Computer Vision
Using Deep Learning to Count Albatrosses from Space
A deep learning approach to automatically count Wandering Albatrosses in Very High Resolution (VHR) satellite imagery. Initial results achieve peak precision and recall values of approximately 80%. We conclude that the model accuracy falls within the range of human counters.
0
0
0
Wed Apr 11 2018
Machine Learning
Flexible and Scalable Deep Learning with MMLSpark
MMLSpark is an open source library that combines the Cognitive Toolkit with the distributed computing framework Apache Spark. It provides an end to end solution for the non-profit conservation organization, the Snow Leopard Trust.
0
0
0
Tue Nov 05 2019
Machine Learning
Cumulo: A Dataset for Learning Cloud Classes
One of the greatest sources of uncertainty in future climate projections comes from limitations in modelling clouds. A key first step is to accurately classify cloud types at high spatial and temporal resolution. We introduce Cumulo, a benchmark dataset for training and evaluating global cloud classification models.
0
0
0